basic.py 166 KB
Newer Older
wxchan's avatar
wxchan committed
1
# coding: utf-8
2
"""Wrapper for C API of LightGBM."""
3
import abc
wxchan's avatar
wxchan committed
4
import ctypes
5
import json
wxchan's avatar
wxchan committed
6
import warnings
7
from collections import OrderedDict
8
from copy import deepcopy
9
from functools import wraps
10
11
12
from os import SEEK_END
from os.path import getsize
from pathlib import Path
13
from tempfile import NamedTemporaryFile
14
from typing import Any, Callable, Dict, Iterable, List, Optional, Set, Tuple, Union
wxchan's avatar
wxchan committed
15
16
17
18

import numpy as np
import scipy.sparse

19
from .compat import PANDAS_INSTALLED, concat, dt_DataTable, pd_CategoricalDtype, pd_DataFrame, pd_Series
wxchan's avatar
wxchan committed
20
21
from .libpath import find_lib_path

22
23
24
ZERO_THRESHOLD = 1e-35


25
def _get_sample_count(total_nrow: int, params: str) -> int:
26
27
28
29
30
31
32
33
    sample_cnt = ctypes.c_int(0)
    _safe_call(_LIB.LGBM_GetSampleCount(
        ctypes.c_int32(total_nrow),
        c_str(params),
        ctypes.byref(sample_cnt),
    ))
    return sample_cnt.value

wxchan's avatar
wxchan committed
34

35
class _DummyLogger:
36
    def info(self, msg: str) -> None:
37
38
        print(msg)

39
    def warning(self, msg: str) -> None:
40
41
42
        warnings.warn(msg, stacklevel=3)


43
44
45
_LOGGER: Any = _DummyLogger()
_INFO_METHOD_NAME = "info"
_WARNING_METHOD_NAME = "warning"
46
47


48
49
50
def register_logger(
    logger: Any, info_method_name: str = "info", warning_method_name: str = "warning"
) -> None:
51
52
53
54
    """Register custom logger.

    Parameters
    ----------
55
    logger : Any
56
        Custom logger.
57
58
59
60
    info_method_name : str, optional (default="info")
        Method used to log info messages.
    warning_method_name : str, optional (default="warning")
        Method used to log warning messages.
61
    """
62
63
64
65
66
67
68
69
70
    def _has_method(logger: Any, method_name: str) -> bool:
        return callable(getattr(logger, method_name, None))

    if not _has_method(logger, info_method_name) or not _has_method(logger, warning_method_name):
        raise TypeError(
            f"Logger must provide '{info_method_name}' and '{warning_method_name}' method"
        )

    global _LOGGER, _INFO_METHOD_NAME, _WARNING_METHOD_NAME
71
    _LOGGER = logger
72
73
    _INFO_METHOD_NAME = info_method_name
    _WARNING_METHOD_NAME = warning_method_name
74
75


76
def _normalize_native_string(func: Callable[[str], None]) -> Callable[[str], None]:
77
    """Join log messages from native library which come by chunks."""
78
    msg_normalized: List[str] = []
79
80

    @wraps(func)
81
    def wrapper(msg: str) -> None:
82
83
84
85
86
87
88
89
90
91
92
        nonlocal msg_normalized
        if msg.strip() == '':
            msg = ''.join(msg_normalized)
            msg_normalized = []
            return func(msg)
        else:
            msg_normalized.append(msg)

    return wrapper


93
def _log_info(msg: str) -> None:
94
    getattr(_LOGGER, _INFO_METHOD_NAME)(msg)
95
96


97
def _log_warning(msg: str) -> None:
98
    getattr(_LOGGER, _WARNING_METHOD_NAME)(msg)
99
100
101


@_normalize_native_string
102
def _log_native(msg: str) -> None:
103
    getattr(_LOGGER, _INFO_METHOD_NAME)(msg)
104
105


106
def _log_callback(msg: bytes) -> None:
107
    """Redirect logs from native library into Python."""
108
    _log_native(str(msg.decode('utf-8')))
109
110


111
def _load_lib() -> Optional[ctypes.CDLL]:
112
    """Load LightGBM library."""
wxchan's avatar
wxchan committed
113
114
    lib_path = find_lib_path()
    if len(lib_path) == 0:
115
        return None
wxchan's avatar
wxchan committed
116
117
    lib = ctypes.cdll.LoadLibrary(lib_path[0])
    lib.LGBM_GetLastError.restype = ctypes.c_char_p
118
119
120
    callback = ctypes.CFUNCTYPE(None, ctypes.c_char_p)
    lib.callback = callback(_log_callback)
    if lib.LGBM_RegisterLogCallback(lib.callback) != 0:
121
        raise LightGBMError(lib.LGBM_GetLastError().decode('utf-8'))
wxchan's avatar
wxchan committed
122
123
    return lib

wxchan's avatar
wxchan committed
124

wxchan's avatar
wxchan committed
125
126
_LIB = _load_lib()

wxchan's avatar
wxchan committed
127

128
NUMERIC_TYPES = (int, float, bool)
129
_ArrayLike = Union[List, np.ndarray, pd_Series]
130
131


132
def _safe_call(ret: int) -> None:
133
134
    """Check the return value from C API call.

wxchan's avatar
wxchan committed
135
136
137
    Parameters
    ----------
    ret : int
138
        The return value from C API calls.
wxchan's avatar
wxchan committed
139
140
    """
    if ret != 0:
141
        raise LightGBMError(_LIB.LGBM_GetLastError().decode('utf-8'))
wxchan's avatar
wxchan committed
142

wxchan's avatar
wxchan committed
143

144
def is_numeric(obj: Any) -> bool:
145
    """Check whether object is a number or not, include numpy number, etc."""
wxchan's avatar
wxchan committed
146
147
148
    try:
        float(obj)
        return True
wxchan's avatar
wxchan committed
149
150
151
    except (TypeError, ValueError):
        # TypeError: obj is not a string or a number
        # ValueError: invalid literal
wxchan's avatar
wxchan committed
152
153
        return False

wxchan's avatar
wxchan committed
154

155
def is_numpy_1d_array(data: Any) -> bool:
156
    """Check whether data is a numpy 1-D array."""
157
    return isinstance(data, np.ndarray) and len(data.shape) == 1
wxchan's avatar
wxchan committed
158

wxchan's avatar
wxchan committed
159

160
def is_numpy_column_array(data: Any) -> bool:
161
162
163
164
165
166
167
    """Check whether data is a column numpy array."""
    if not isinstance(data, np.ndarray):
        return False
    shape = data.shape
    return len(shape) == 2 and shape[1] == 1


168
169
def cast_numpy_array_to_dtype(array, dtype):
    """Cast numpy array to given dtype."""
170
171
172
173
174
    if array.dtype == dtype:
        return array
    return array.astype(dtype=dtype, copy=False)


175
def is_1d_list(data: Any) -> bool:
176
177
    """Check whether data is a 1-D list."""
    return isinstance(data, list) and (not data or is_numeric(data[0]))
wxchan's avatar
wxchan committed
178

wxchan's avatar
wxchan committed
179

180
181
182
183
184
185
186
187
188
189
def _is_1d_collection(data: Any) -> bool:
    """Check whether data is a 1-D collection."""
    return (
        is_numpy_1d_array(data)
        or is_numpy_column_array(data)
        or is_1d_list(data)
        or isinstance(data, pd_Series)
    )


190
def list_to_1d_numpy(data, dtype=np.float32, name='list'):
191
    """Convert data to numpy 1-D array."""
wxchan's avatar
wxchan committed
192
    if is_numpy_1d_array(data):
193
        return cast_numpy_array_to_dtype(data, dtype)
194
195
196
    elif is_numpy_column_array(data):
        _log_warning('Converting column-vector to 1d array')
        array = data.ravel()
197
        return cast_numpy_array_to_dtype(array, dtype)
wxchan's avatar
wxchan committed
198
199
    elif is_1d_list(data):
        return np.array(data, dtype=dtype, copy=False)
200
    elif isinstance(data, pd_Series):
201
        _check_for_bad_pandas_dtypes(data.to_frame().dtypes)
202
        return np.array(data, dtype=dtype, copy=False)  # SparseArray should be supported as well
wxchan's avatar
wxchan committed
203
    else:
204
205
        raise TypeError(f"Wrong type({type(data).__name__}) for {name}.\n"
                        "It should be list, numpy 1-D array or pandas Series")
wxchan's avatar
wxchan committed
206

wxchan's avatar
wxchan committed
207

208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
def _is_numpy_2d_array(data: Any) -> bool:
    """Check whether data is a numpy 2-D array."""
    return isinstance(data, np.ndarray) and len(data.shape) == 2 and data.shape[1] > 1


def _is_2d_list(data: Any) -> bool:
    """Check whether data is a 2-D list."""
    return isinstance(data, list) and len(data) > 0 and is_1d_list(data[0])


def _is_2d_collection(data: Any) -> bool:
    """Check whether data is a 2-D collection."""
    return (
        _is_numpy_2d_array(data)
        or _is_2d_list(data)
        or isinstance(data, pd_DataFrame)
    )


def _data_to_2d_numpy(data: Any, dtype: type = np.float32, name: str = 'list') -> np.ndarray:
    """Convert data to numpy 2-D array."""
    if _is_numpy_2d_array(data):
        return cast_numpy_array_to_dtype(data, dtype)
    if _is_2d_list(data):
        return np.array(data, dtype=dtype)
    if isinstance(data, pd_DataFrame):
234
        _check_for_bad_pandas_dtypes(data.dtypes)
235
236
237
238
239
        return cast_numpy_array_to_dtype(data.values, dtype)
    raise TypeError(f"Wrong type({type(data).__name__}) for {name}.\n"
                    "It should be list of lists, numpy 2-D array or pandas DataFrame")


wxchan's avatar
wxchan committed
240
def cfloat32_array_to_numpy(cptr, length):
241
    """Convert a ctypes float pointer array to a numpy array."""
wxchan's avatar
wxchan committed
242
    if isinstance(cptr, ctypes.POINTER(ctypes.c_float)):
243
        return np.ctypeslib.as_array(cptr, shape=(length,)).copy()
wxchan's avatar
wxchan committed
244
    else:
245
        raise RuntimeError('Expected float pointer')
wxchan's avatar
wxchan committed
246

Guolin Ke's avatar
Guolin Ke committed
247

Guolin Ke's avatar
Guolin Ke committed
248
def cfloat64_array_to_numpy(cptr, length):
249
    """Convert a ctypes double pointer array to a numpy array."""
Guolin Ke's avatar
Guolin Ke committed
250
    if isinstance(cptr, ctypes.POINTER(ctypes.c_double)):
251
        return np.ctypeslib.as_array(cptr, shape=(length,)).copy()
Guolin Ke's avatar
Guolin Ke committed
252
253
254
    else:
        raise RuntimeError('Expected double pointer')

wxchan's avatar
wxchan committed
255

wxchan's avatar
wxchan committed
256
def cint32_array_to_numpy(cptr, length):
257
    """Convert a ctypes int pointer array to a numpy array."""
wxchan's avatar
wxchan committed
258
    if isinstance(cptr, ctypes.POINTER(ctypes.c_int32)):
259
        return np.ctypeslib.as_array(cptr, shape=(length,)).copy()
wxchan's avatar
wxchan committed
260
    else:
261
262
263
264
265
266
        raise RuntimeError('Expected int32 pointer')


def cint64_array_to_numpy(cptr, length):
    """Convert a ctypes int pointer array to a numpy array."""
    if isinstance(cptr, ctypes.POINTER(ctypes.c_int64)):
267
        return np.ctypeslib.as_array(cptr, shape=(length,)).copy()
268
269
    else:
        raise RuntimeError('Expected int64 pointer')
wxchan's avatar
wxchan committed
270

wxchan's avatar
wxchan committed
271

wxchan's avatar
wxchan committed
272
def c_str(string):
273
    """Convert a Python string to C string."""
wxchan's avatar
wxchan committed
274
275
    return ctypes.c_char_p(string.encode('utf-8'))

wxchan's avatar
wxchan committed
276

wxchan's avatar
wxchan committed
277
def c_array(ctype, values):
278
    """Convert a Python array to C array."""
wxchan's avatar
wxchan committed
279
280
    return (ctype * len(values))(*values)

wxchan's avatar
wxchan committed
281

282
def json_default_with_numpy(obj: Any) -> Any:
283
284
285
286
287
288
289
290
291
    """Convert numpy classes to JSON serializable objects."""
    if isinstance(obj, (np.integer, np.floating, np.bool_)):
        return obj.item()
    elif isinstance(obj, np.ndarray):
        return obj.tolist()
    else:
        return obj


292
def param_dict_to_str(data: Optional[Dict[str, Any]]) -> str:
293
    """Convert Python dictionary to string, which is passed to C API."""
294
    if data is None or not data:
wxchan's avatar
wxchan committed
295
296
297
        return ""
    pairs = []
    for key, val in data.items():
298
        if isinstance(val, (list, tuple, set)) or is_numpy_1d_array(val):
299
300
            def to_string(x):
                if isinstance(x, list):
301
                    return f"[{','.join(map(str, x))}]"
302
303
                else:
                    return str(x)
304
            pairs.append(f"{key}={','.join(map(to_string, val))}")
305
        elif isinstance(val, (str, Path, NUMERIC_TYPES)) or is_numeric(val):
306
            pairs.append(f"{key}={val}")
307
        elif val is not None:
308
            raise TypeError(f'Unknown type of parameter:{key}, got:{type(val).__name__}')
wxchan's avatar
wxchan committed
309
    return ' '.join(pairs)
310

wxchan's avatar
wxchan committed
311

312
class _TempFile:
313
314
    """Proxy class to workaround errors on Windows."""

315
316
317
    def __enter__(self):
        with NamedTemporaryFile(prefix="lightgbm_tmp_", delete=True) as f:
            self.name = f.name
318
            self.path = Path(self.name)
319
        return self
wxchan's avatar
wxchan committed
320

321
    def __exit__(self, exc_type, exc_val, exc_tb):
322
323
        if self.path.is_file():
            self.path.unlink()
324

wxchan's avatar
wxchan committed
325

326
class LightGBMError(Exception):
327
328
    """Error thrown by LightGBM."""

329
330
331
    pass


332
333
334
335
336
337
338
339
# DeprecationWarning is not shown by default, so let's create our own with higher level
class LGBMDeprecationWarning(UserWarning):
    """Custom deprecation warning."""

    pass


class _ConfigAliases:
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
    # lazy evaluation to allow import without dynamic library, e.g., for docs generation
    aliases = None

    @staticmethod
    def _get_all_param_aliases() -> Dict[str, Set[str]]:
        buffer_len = 1 << 20
        tmp_out_len = ctypes.c_int64(0)
        string_buffer = ctypes.create_string_buffer(buffer_len)
        ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
        _safe_call(_LIB.LGBM_DumpParamAliases(
            ctypes.c_int64(buffer_len),
            ctypes.byref(tmp_out_len),
            ptr_string_buffer))
        actual_len = tmp_out_len.value
        # if buffer length is not long enough, re-allocate a buffer
        if actual_len > buffer_len:
            string_buffer = ctypes.create_string_buffer(actual_len)
            ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
            _safe_call(_LIB.LGBM_DumpParamAliases(
                ctypes.c_int64(actual_len),
                ctypes.byref(tmp_out_len),
                ptr_string_buffer))
        aliases = json.loads(
            string_buffer.value.decode('utf-8'),
            object_hook=lambda obj: {k: set(v) | {k} for k, v in obj.items()}
        )
        return aliases
367
368

    @classmethod
369
370
371
    def get(cls, *args) -> Set[str]:
        if cls.aliases is None:
            cls.aliases = cls._get_all_param_aliases()
372
373
        ret = set()
        for i in args:
374
            ret |= cls.aliases.get(i, {i})
375
376
        return ret

377
    @classmethod
378
379
380
    def get_by_alias(cls, *args) -> Set[str]:
        if cls.aliases is None:
            cls.aliases = cls._get_all_param_aliases()
381
382
383
384
385
386
387
388
        ret = set(args)
        for arg in args:
            for aliases in cls.aliases.values():
                if arg in aliases:
                    ret |= aliases
                    break
        return ret

389

390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
def _choose_param_value(main_param_name: str, params: Dict[str, Any], default_value: Any) -> Dict[str, Any]:
    """Get a single parameter value, accounting for aliases.

    Parameters
    ----------
    main_param_name : str
        Name of the main parameter to get a value for. One of the keys of ``_ConfigAliases``.
    params : dict
        Dictionary of LightGBM parameters.
    default_value : Any
        Default value to use for the parameter, if none is found in ``params``.

    Returns
    -------
    params : dict
        A ``params`` dict with exactly one value for ``main_param_name``, and all aliases ``main_param_name`` removed.
        If both ``main_param_name`` and one or more aliases for it are found, the value of ``main_param_name`` will be preferred.
    """
    # avoid side effects on passed-in parameters
    params = deepcopy(params)

411
412
413
    aliases = _ConfigAliases.get(main_param_name) - {main_param_name}

    # if main_param_name was provided, keep that value and remove all aliases
414
    if main_param_name in params.keys():
415
416
417
        for param in aliases:
            params.pop(param, None)
        return params
418

419
420
421
422
423
    # if main param name was not found, search for an alias
    for param in aliases:
        if param in params.keys():
            params[main_param_name] = params[param]
            break
424

425
426
427
428
429
430
431
    if main_param_name in params.keys():
        for param in aliases:
            params.pop(param, None)
        return params

    # neither of main_param_name, aliases were found
    params[main_param_name] = default_value
432
433
434
435

    return params


436
437
MAX_INT32 = (1 << 31) - 1

438
"""Macro definition of data type in C API of LightGBM"""
wxchan's avatar
wxchan committed
439
440
441
442
C_API_DTYPE_FLOAT32 = 0
C_API_DTYPE_FLOAT64 = 1
C_API_DTYPE_INT32 = 2
C_API_DTYPE_INT64 = 3
Guolin Ke's avatar
Guolin Ke committed
443

444
"""Matrix is row major in Python"""
wxchan's avatar
wxchan committed
445
446
C_API_IS_ROW_MAJOR = 1

447
"""Macro definition of prediction type in C API of LightGBM"""
wxchan's avatar
wxchan committed
448
449
450
C_API_PREDICT_NORMAL = 0
C_API_PREDICT_RAW_SCORE = 1
C_API_PREDICT_LEAF_INDEX = 2
451
C_API_PREDICT_CONTRIB = 3
wxchan's avatar
wxchan committed
452

453
454
455
456
"""Macro definition of sparse matrix type"""
C_API_MATRIX_TYPE_CSR = 0
C_API_MATRIX_TYPE_CSC = 1

457
458
459
460
"""Macro definition of feature importance type"""
C_API_FEATURE_IMPORTANCE_SPLIT = 0
C_API_FEATURE_IMPORTANCE_GAIN = 1

461
"""Data type of data field"""
wxchan's avatar
wxchan committed
462
463
FIELD_TYPE_MAPPER = {"label": C_API_DTYPE_FLOAT32,
                     "weight": C_API_DTYPE_FLOAT32,
Guolin Ke's avatar
Guolin Ke committed
464
                     "init_score": C_API_DTYPE_FLOAT64,
465
                     "group": C_API_DTYPE_INT32}
wxchan's avatar
wxchan committed
466

467
468
469
470
"""String name to int feature importance type mapper"""
FEATURE_IMPORTANCE_TYPE_MAPPER = {"split": C_API_FEATURE_IMPORTANCE_SPLIT,
                                  "gain": C_API_FEATURE_IMPORTANCE_GAIN}

wxchan's avatar
wxchan committed
471

472
def convert_from_sliced_object(data):
473
    """Fix the memory of multi-dimensional sliced object."""
474
    if isinstance(data, np.ndarray) and isinstance(data.base, np.ndarray):
475
        if not data.flags.c_contiguous:
476
477
            _log_warning("Usage of np.ndarray subset (sliced data) is not recommended "
                         "due to it will double the peak memory cost in LightGBM.")
478
479
480
481
            return np.copy(data)
    return data


wxchan's avatar
wxchan committed
482
def c_float_array(data):
483
    """Get pointer of float numpy array / list."""
wxchan's avatar
wxchan committed
484
485
486
    if is_1d_list(data):
        data = np.array(data, copy=False)
    if is_numpy_1d_array(data):
487
488
        data = convert_from_sliced_object(data)
        assert data.flags.c_contiguous
wxchan's avatar
wxchan committed
489
490
491
492
493
494
495
        if data.dtype == np.float32:
            ptr_data = data.ctypes.data_as(ctypes.POINTER(ctypes.c_float))
            type_data = C_API_DTYPE_FLOAT32
        elif data.dtype == np.float64:
            ptr_data = data.ctypes.data_as(ctypes.POINTER(ctypes.c_double))
            type_data = C_API_DTYPE_FLOAT64
        else:
496
            raise TypeError(f"Expected np.float32 or np.float64, met type({data.dtype})")
wxchan's avatar
wxchan committed
497
    else:
498
        raise TypeError(f"Unknown type({type(data).__name__})")
499
    return (ptr_data, type_data, data)  # return `data` to avoid the temporary copy is freed
wxchan's avatar
wxchan committed
500

wxchan's avatar
wxchan committed
501

wxchan's avatar
wxchan committed
502
def c_int_array(data):
503
    """Get pointer of int numpy array / list."""
wxchan's avatar
wxchan committed
504
505
506
    if is_1d_list(data):
        data = np.array(data, copy=False)
    if is_numpy_1d_array(data):
507
508
        data = convert_from_sliced_object(data)
        assert data.flags.c_contiguous
wxchan's avatar
wxchan committed
509
510
511
512
513
514
515
        if data.dtype == np.int32:
            ptr_data = data.ctypes.data_as(ctypes.POINTER(ctypes.c_int32))
            type_data = C_API_DTYPE_INT32
        elif data.dtype == np.int64:
            ptr_data = data.ctypes.data_as(ctypes.POINTER(ctypes.c_int64))
            type_data = C_API_DTYPE_INT64
        else:
516
            raise TypeError(f"Expected np.int32 or np.int64, met type({data.dtype})")
wxchan's avatar
wxchan committed
517
    else:
518
        raise TypeError(f"Unknown type({type(data).__name__})")
519
    return (ptr_data, type_data, data)  # return `data` to avoid the temporary copy is freed
wxchan's avatar
wxchan committed
520

wxchan's avatar
wxchan committed
521

522
def _check_for_bad_pandas_dtypes(pandas_dtypes_series):
523
524
525
526
527
528
529
530
    float128 = getattr(np, 'float128', type(None))

    def is_allowed_numpy_dtype(dtype):
        return (
            issubclass(dtype, (np.integer, np.floating, np.bool_))
            and not issubclass(dtype, (np.timedelta64, float128))
        )

531
532
533
534
535
536
537
538
    bad_pandas_dtypes = [
        f'{column_name}: {pandas_dtype}'
        for column_name, pandas_dtype in pandas_dtypes_series.iteritems()
        if not is_allowed_numpy_dtype(pandas_dtype.type)
    ]
    if bad_pandas_dtypes:
        raise ValueError('pandas dtypes must be int, float or bool.\n'
                         f'Fields with bad pandas dtypes: {", ".join(bad_pandas_dtypes)}')
539
540


541
def _data_from_pandas(data, feature_name, categorical_feature, pandas_categorical):
542
    if isinstance(data, pd_DataFrame):
543
544
        if len(data.shape) != 2 or data.shape[0] < 1:
            raise ValueError('Input data must be 2 dimensional and non empty.')
545
        if feature_name == 'auto' or feature_name is None:
546
            data = data.rename(columns=str, copy=False)
547
        cat_cols = [col for col, dtype in zip(data.columns, data.dtypes) if isinstance(dtype, pd_CategoricalDtype)]
548
        cat_cols_not_ordered = [col for col in cat_cols if not data[col].cat.ordered]
549
550
551
552
553
        if pandas_categorical is None:  # train dataset
            pandas_categorical = [list(data[col].cat.categories) for col in cat_cols]
        else:
            if len(cat_cols) != len(pandas_categorical):
                raise ValueError('train and valid dataset categorical_feature do not match.')
554
            for col, category in zip(cat_cols, pandas_categorical):
555
556
                if list(data[col].cat.categories) != list(category):
                    data[col] = data[col].cat.set_categories(category)
557
        if len(cat_cols):  # cat_cols is list
558
            data = data.copy(deep=False)  # not alter origin DataFrame
559
            data[cat_cols] = data[cat_cols].apply(lambda x: x.cat.codes).replace({-1: np.nan})
560
561
562
        if categorical_feature is not None:
            if feature_name is None:
                feature_name = list(data.columns)
563
            if categorical_feature == 'auto':  # use cat cols from DataFrame
564
                categorical_feature = cat_cols_not_ordered
565
566
            else:  # use cat cols specified by user
                categorical_feature = list(categorical_feature)
567
568
        if feature_name == 'auto':
            feature_name = list(data.columns)
569
        _check_for_bad_pandas_dtypes(data.dtypes)
570
571
572
573
        df_dtypes = [dtype.type for dtype in data.dtypes]
        df_dtypes.append(np.float32)  # so that the target dtype considers floats
        target_dtype = np.find_common_type(df_dtypes, [])
        data = data.astype(target_dtype, copy=False).values
574
575
576
577
578
579
    else:
        if feature_name == 'auto':
            feature_name = None
        if categorical_feature == 'auto':
            categorical_feature = None
    return data, feature_name, categorical_feature, pandas_categorical
580
581
582


def _label_from_pandas(label):
583
    if isinstance(label, pd_DataFrame):
584
585
        if len(label.columns) > 1:
            raise ValueError('DataFrame for label cannot have multiple columns')
586
        _check_for_bad_pandas_dtypes(label.dtypes)
587
        label = np.ravel(label.values.astype(np.float32, copy=False))
588
589
590
    return label


591
def _dump_pandas_categorical(pandas_categorical, file_name=None):
592
593
    categorical_json = json.dumps(pandas_categorical, default=json_default_with_numpy)
    pandas_str = f'\npandas_categorical:{categorical_json}\n'
594
595
596
597
598
599
600
    if file_name is not None:
        with open(file_name, 'a') as f:
            f.write(pandas_str)
    return pandas_str


def _load_pandas_categorical(file_name=None, model_str=None):
601
602
    pandas_key = 'pandas_categorical:'
    offset = -len(pandas_key)
603
    if file_name is not None:
604
        max_offset = -getsize(file_name)
605
606
607
608
        with open(file_name, 'rb') as f:
            while True:
                if offset < max_offset:
                    offset = max_offset
609
                f.seek(offset, SEEK_END)
610
611
612
613
                lines = f.readlines()
                if len(lines) >= 2:
                    break
                offset *= 2
614
        last_line = lines[-1].decode('utf-8').strip()
615
        if not last_line.startswith(pandas_key):
616
            last_line = lines[-2].decode('utf-8').strip()
617
    elif model_str is not None:
618
619
620
621
622
623
        idx = model_str.rfind('\n', 0, offset)
        last_line = model_str[idx:].strip()
    if last_line.startswith(pandas_key):
        return json.loads(last_line[len(pandas_key):])
    else:
        return None
624
625


626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
class Sequence(abc.ABC):
    """
    Generic data access interface.

    Object should support the following operations:

    .. code-block::

        # Get total row number.
        >>> len(seq)
        # Random access by row index. Used for data sampling.
        >>> seq[10]
        # Range data access. Used to read data in batch when constructing Dataset.
        >>> seq[0:100]
        # Optionally specify batch_size to control range data read size.
        >>> seq.batch_size

    - With random access, **data sampling does not need to go through all data**.
    - With range data access, there's **no need to read all data into memory thus reduce memory usage**.

646
647
    .. versionadded:: 3.3.0

648
649
650
651
652
653
654
655
656
    Attributes
    ----------
    batch_size : int
        Default size of a batch.
    """

    batch_size = 4096  # Defaults to read 4K rows in each batch.

    @abc.abstractmethod
657
    def __getitem__(self, idx: Union[int, slice, List[int]]) -> np.ndarray:
658
659
660
661
662
663
664
        """Return data for given row index.

        A basic implementation should look like this:

        .. code-block:: python

            if isinstance(idx, numbers.Integral):
665
                return self._get_one_line(idx)
666
            elif isinstance(idx, slice):
667
668
                return np.stack([self._get_one_line(i) for i in range(idx.start, idx.stop)])
            elif isinstance(idx, list):
669
                # Only required if using ``Dataset.subset()``.
670
                return np.array([self._get_one_line(i) for i in idx])
671
            else:
672
                raise TypeError(f"Sequence index must be integer, slice or list, got {type(idx).__name__}")
673
674
675

        Parameters
        ----------
676
        idx : int, slice[int], list[int]
677
678
679
680
            Item index.

        Returns
        -------
681
        result : numpy 1-D array or numpy 2-D array
682
            1-D array if idx is int, 2-D array if idx is slice or list.
683
684
685
686
687
688
689
690
691
        """
        raise NotImplementedError("Sub-classes of lightgbm.Sequence must implement __getitem__()")

    @abc.abstractmethod
    def __len__(self) -> int:
        """Return row count of this sequence."""
        raise NotImplementedError("Sub-classes of lightgbm.Sequence must implement __len__()")


692
class _InnerPredictor:
693
694
695
696
697
    """_InnerPredictor of LightGBM.

    Not exposed to user.
    Used only for prediction, usually used for continued training.

Nikita Titov's avatar
Nikita Titov committed
698
699
700
    .. note::

        Can be converted from Booster, but cannot be converted to Booster.
Guolin Ke's avatar
Guolin Ke committed
701
    """
702

703
    def __init__(self, model_file=None, booster_handle=None, pred_parameter=None):
704
        """Initialize the _InnerPredictor.
wxchan's avatar
wxchan committed
705
706
707

        Parameters
        ----------
708
        model_file : str, pathlib.Path or None, optional (default=None)
wxchan's avatar
wxchan committed
709
            Path to the model file.
710
711
712
        booster_handle : object or None, optional (default=None)
            Handle of Booster.
        pred_parameter: dict or None, optional (default=None)
713
            Other parameters for the prediction.
wxchan's avatar
wxchan committed
714
715
716
717
718
        """
        self.handle = ctypes.c_void_p()
        self.__is_manage_handle = True
        if model_file is not None:
            """Prediction task"""
Guolin Ke's avatar
Guolin Ke committed
719
            out_num_iterations = ctypes.c_int(0)
wxchan's avatar
wxchan committed
720
            _safe_call(_LIB.LGBM_BoosterCreateFromModelfile(
721
                c_str(str(model_file)),
wxchan's avatar
wxchan committed
722
723
                ctypes.byref(out_num_iterations),
                ctypes.byref(self.handle)))
Guolin Ke's avatar
Guolin Ke committed
724
            out_num_class = ctypes.c_int(0)
wxchan's avatar
wxchan committed
725
726
727
728
            _safe_call(_LIB.LGBM_BoosterGetNumClasses(
                self.handle,
                ctypes.byref(out_num_class)))
            self.num_class = out_num_class.value
729
            self.num_total_iteration = out_num_iterations.value
730
            self.pandas_categorical = _load_pandas_categorical(file_name=model_file)
wxchan's avatar
wxchan committed
731
        elif booster_handle is not None:
Guolin Ke's avatar
Guolin Ke committed
732
            self.__is_manage_handle = False
wxchan's avatar
wxchan committed
733
            self.handle = booster_handle
Guolin Ke's avatar
Guolin Ke committed
734
            out_num_class = ctypes.c_int(0)
wxchan's avatar
wxchan committed
735
736
737
738
            _safe_call(_LIB.LGBM_BoosterGetNumClasses(
                self.handle,
                ctypes.byref(out_num_class)))
            self.num_class = out_num_class.value
739
            self.num_total_iteration = self.current_iteration()
740
            self.pandas_categorical = None
wxchan's avatar
wxchan committed
741
        else:
742
            raise TypeError('Need model_file or booster_handle to create a predictor')
wxchan's avatar
wxchan committed
743

744
745
        pred_parameter = {} if pred_parameter is None else pred_parameter
        self.pred_parameter = param_dict_to_str(pred_parameter)
cbecker's avatar
cbecker committed
746

747
    def __del__(self) -> None:
748
749
750
751
752
        try:
            if self.__is_manage_handle:
                _safe_call(_LIB.LGBM_BoosterFree(self.handle))
        except AttributeError:
            pass
wxchan's avatar
wxchan committed
753

754
755
756
757
758
    def __getstate__(self):
        this = self.__dict__.copy()
        this.pop('handle', None)
        return this

759
760
761
762
763
764
765
766
767
768
769
    def predict(
        self,
        data,
        start_iteration: int = 0,
        num_iteration: int = -1,
        raw_score: bool = False,
        pred_leaf: bool = False,
        pred_contrib: bool = False,
        data_has_header: bool = False,
        validate_features: bool = False
    ):
770
        """Predict logic.
wxchan's avatar
wxchan committed
771
772
773

        Parameters
        ----------
774
        data : str, pathlib.Path, numpy array, pandas DataFrame, H2O DataTable's Frame or scipy.sparse
775
            Data source for prediction.
776
            If str or pathlib.Path, it represents the path to a text file (CSV, TSV, or LibSVM).
777
778
        start_iteration : int, optional (default=0)
            Start index of the iteration to predict.
779
780
781
782
783
784
785
786
787
788
789
        num_iteration : int, optional (default=-1)
            Iteration used for prediction.
        raw_score : bool, optional (default=False)
            Whether to predict raw scores.
        pred_leaf : bool, optional (default=False)
            Whether to predict leaf index.
        pred_contrib : bool, optional (default=False)
            Whether to predict feature contributions.
        data_has_header : bool, optional (default=False)
            Whether data has header.
            Used only for txt data.
790
791
792
        validate_features : bool, optional (default=False)
            If True, ensure that the features used to predict match the ones used to train.
            Used only if data is pandas DataFrame.
wxchan's avatar
wxchan committed
793
794
795

        Returns
        -------
796
        result : numpy array, scipy.sparse or list of scipy.sparse
797
            Prediction result.
798
            Can be sparse or a list of sparse objects (each element represents predictions for one class) for feature contributions (when ``pred_contrib=True``).
wxchan's avatar
wxchan committed
799
        """
wxchan's avatar
wxchan committed
800
        if isinstance(data, Dataset):
801
            raise TypeError("Cannot use Dataset instance for prediction, please use raw data instead")
802
803
804
805
806
807
808
809
810
811
812
        elif isinstance(data, pd_DataFrame) and validate_features:
            data_names = [str(x) for x in data.columns]
            ptr_names = (ctypes.c_char_p * len(data_names))()
            ptr_names[:] = [x.encode('utf-8') for x in data_names]
            _safe_call(
                _LIB.LGBM_BoosterValidateFeatureNames(
                    self.handle,
                    ptr_names,
                    ctypes.c_int(len(data_names)),
                )
            )
813
        data = _data_from_pandas(data, None, None, self.pandas_categorical)[0]
wxchan's avatar
wxchan committed
814
815
816
817
818
        predict_type = C_API_PREDICT_NORMAL
        if raw_score:
            predict_type = C_API_PREDICT_RAW_SCORE
        if pred_leaf:
            predict_type = C_API_PREDICT_LEAF_INDEX
819
820
        if pred_contrib:
            predict_type = C_API_PREDICT_CONTRIB
wxchan's avatar
wxchan committed
821
        int_data_has_header = 1 if data_has_header else 0
cbecker's avatar
cbecker committed
822

823
        if isinstance(data, (str, Path)):
824
            with _TempFile() as f:
wxchan's avatar
wxchan committed
825
826
                _safe_call(_LIB.LGBM_BoosterPredictForFile(
                    self.handle,
827
                    c_str(str(data)),
Guolin Ke's avatar
Guolin Ke committed
828
829
                    ctypes.c_int(int_data_has_header),
                    ctypes.c_int(predict_type),
830
                    ctypes.c_int(start_iteration),
Guolin Ke's avatar
Guolin Ke committed
831
                    ctypes.c_int(num_iteration),
832
                    c_str(self.pred_parameter),
wxchan's avatar
wxchan committed
833
                    c_str(f.name)))
834
835
                preds = np.loadtxt(f.name, dtype=np.float64)
                nrow = preds.shape[0]
wxchan's avatar
wxchan committed
836
        elif isinstance(data, scipy.sparse.csr_matrix):
837
            preds, nrow = self.__pred_for_csr(data, start_iteration, num_iteration, predict_type)
Guolin Ke's avatar
Guolin Ke committed
838
        elif isinstance(data, scipy.sparse.csc_matrix):
839
            preds, nrow = self.__pred_for_csc(data, start_iteration, num_iteration, predict_type)
wxchan's avatar
wxchan committed
840
        elif isinstance(data, np.ndarray):
841
            preds, nrow = self.__pred_for_np2d(data, start_iteration, num_iteration, predict_type)
842
843
844
        elif isinstance(data, list):
            try:
                data = np.array(data)
845
            except BaseException:
846
                raise ValueError('Cannot convert data list to numpy array.')
847
            preds, nrow = self.__pred_for_np2d(data, start_iteration, num_iteration, predict_type)
848
        elif isinstance(data, dt_DataTable):
849
            preds, nrow = self.__pred_for_np2d(data.to_numpy(), start_iteration, num_iteration, predict_type)
wxchan's avatar
wxchan committed
850
851
        else:
            try:
852
                _log_warning('Converting data to scipy sparse matrix.')
wxchan's avatar
wxchan committed
853
                csr = scipy.sparse.csr_matrix(data)
854
            except BaseException:
855
                raise TypeError(f'Cannot predict data for type {type(data).__name__}')
856
            preds, nrow = self.__pred_for_csr(csr, start_iteration, num_iteration, predict_type)
wxchan's avatar
wxchan committed
857
858
        if pred_leaf:
            preds = preds.astype(np.int32)
859
        is_sparse = scipy.sparse.issparse(preds) or isinstance(preds, list)
860
        if not is_sparse and preds.size != nrow:
wxchan's avatar
wxchan committed
861
            if preds.size % nrow == 0:
862
                preds = preds.reshape(nrow, -1)
wxchan's avatar
wxchan committed
863
            else:
864
                raise ValueError(f'Length of predict result ({preds.size}) cannot be divide nrow ({nrow})')
wxchan's avatar
wxchan committed
865
866
        return preds

867
    def __get_num_preds(self, start_iteration, num_iteration, nrow, predict_type):
868
        """Get size of prediction result."""
869
        if nrow > MAX_INT32:
870
            raise LightGBMError('LightGBM cannot perform prediction for data '
871
                                f'with number of rows greater than MAX_INT32 ({MAX_INT32}).\n'
872
                                'You can split your data into chunks '
873
                                'and then concatenate predictions for them')
Guolin Ke's avatar
Guolin Ke committed
874
875
876
        n_preds = ctypes.c_int64(0)
        _safe_call(_LIB.LGBM_BoosterCalcNumPredict(
            self.handle,
Guolin Ke's avatar
Guolin Ke committed
877
878
            ctypes.c_int(nrow),
            ctypes.c_int(predict_type),
879
            ctypes.c_int(start_iteration),
Guolin Ke's avatar
Guolin Ke committed
880
            ctypes.c_int(num_iteration),
Guolin Ke's avatar
Guolin Ke committed
881
882
            ctypes.byref(n_preds)))
        return n_preds.value
wxchan's avatar
wxchan committed
883

884
    def __pred_for_np2d(self, mat, start_iteration, num_iteration, predict_type):
885
        """Predict for a 2-D numpy matrix."""
wxchan's avatar
wxchan committed
886
        if len(mat.shape) != 2:
887
            raise ValueError('Input numpy.ndarray or list must be 2 dimensional')
wxchan's avatar
wxchan committed
888

889
        def inner_predict(mat, start_iteration, num_iteration, predict_type, preds=None):
890
891
            if mat.dtype == np.float32 or mat.dtype == np.float64:
                data = np.array(mat.reshape(mat.size), dtype=mat.dtype, copy=False)
892
            else:  # change non-float data to float data, need to copy
893
894
                data = np.array(mat.reshape(mat.size), dtype=np.float32)
            ptr_data, type_ptr_data, _ = c_float_array(data)
895
            n_preds = self.__get_num_preds(start_iteration, num_iteration, mat.shape[0], predict_type)
896
            if preds is None:
897
                preds = np.empty(n_preds, dtype=np.float64)
898
899
900
901
902
903
904
            elif len(preds.shape) != 1 or len(preds) != n_preds:
                raise ValueError("Wrong length of pre-allocated predict array")
            out_num_preds = ctypes.c_int64(0)
            _safe_call(_LIB.LGBM_BoosterPredictForMat(
                self.handle,
                ptr_data,
                ctypes.c_int(type_ptr_data),
905
906
                ctypes.c_int32(mat.shape[0]),
                ctypes.c_int32(mat.shape[1]),
907
908
                ctypes.c_int(C_API_IS_ROW_MAJOR),
                ctypes.c_int(predict_type),
909
                ctypes.c_int(start_iteration),
910
911
912
913
914
915
916
917
918
919
920
921
                ctypes.c_int(num_iteration),
                c_str(self.pred_parameter),
                ctypes.byref(out_num_preds),
                preds.ctypes.data_as(ctypes.POINTER(ctypes.c_double))))
            if n_preds != out_num_preds.value:
                raise ValueError("Wrong length for predict results")
            return preds, mat.shape[0]

        nrow = mat.shape[0]
        if nrow > MAX_INT32:
            sections = np.arange(start=MAX_INT32, stop=nrow, step=MAX_INT32)
            # __get_num_preds() cannot work with nrow > MAX_INT32, so calculate overall number of predictions piecemeal
922
            n_preds = [self.__get_num_preds(start_iteration, num_iteration, i, predict_type) for i in np.diff([0] + list(sections) + [nrow])]
923
            n_preds_sections = np.array([0] + n_preds, dtype=np.intp).cumsum()
924
            preds = np.empty(sum(n_preds), dtype=np.float64)
925
926
            for chunk, (start_idx_pred, end_idx_pred) in zip(np.array_split(mat, sections),
                                                             zip(n_preds_sections, n_preds_sections[1:])):
927
                # avoid memory consumption by arrays concatenation operations
928
                inner_predict(chunk, start_iteration, num_iteration, predict_type, preds[start_idx_pred:end_idx_pred])
929
            return preds, nrow
wxchan's avatar
wxchan committed
930
        else:
931
            return inner_predict(mat, start_iteration, num_iteration, predict_type)
wxchan's avatar
wxchan committed
932

933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
    def __create_sparse_native(self, cs, out_shape, out_ptr_indptr, out_ptr_indices, out_ptr_data,
                               indptr_type, data_type, is_csr=True):
        # create numpy array from output arrays
        data_indices_len = out_shape[0]
        indptr_len = out_shape[1]
        if indptr_type == C_API_DTYPE_INT32:
            out_indptr = cint32_array_to_numpy(out_ptr_indptr, indptr_len)
        elif indptr_type == C_API_DTYPE_INT64:
            out_indptr = cint64_array_to_numpy(out_ptr_indptr, indptr_len)
        else:
            raise TypeError("Expected int32 or int64 type for indptr")
        if data_type == C_API_DTYPE_FLOAT32:
            out_data = cfloat32_array_to_numpy(out_ptr_data, data_indices_len)
        elif data_type == C_API_DTYPE_FLOAT64:
            out_data = cfloat64_array_to_numpy(out_ptr_data, data_indices_len)
        else:
            raise TypeError("Expected float32 or float64 type for data")
        out_indices = cint32_array_to_numpy(out_ptr_indices, data_indices_len)
        # break up indptr based on number of rows (note more than one matrix in multiclass case)
        per_class_indptr_shape = cs.indptr.shape[0]
        # for CSC there is extra column added
        if not is_csr:
            per_class_indptr_shape += 1
        out_indptr_arrays = np.split(out_indptr, out_indptr.shape[0] / per_class_indptr_shape)
        # reformat output into a csr or csc matrix or list of csr or csc matrices
        cs_output_matrices = []
        offset = 0
        for cs_indptr in out_indptr_arrays:
            matrix_indptr_len = cs_indptr[cs_indptr.shape[0] - 1]
            cs_indices = out_indices[offset + cs_indptr[0]:offset + matrix_indptr_len]
            cs_data = out_data[offset + cs_indptr[0]:offset + matrix_indptr_len]
            offset += matrix_indptr_len
            # same shape as input csr or csc matrix except extra column for expected value
            cs_shape = [cs.shape[0], cs.shape[1] + 1]
            # note: make sure we copy data as it will be deallocated next
            if is_csr:
                cs_output_matrices.append(scipy.sparse.csr_matrix((cs_data, cs_indices, cs_indptr), cs_shape))
            else:
                cs_output_matrices.append(scipy.sparse.csc_matrix((cs_data, cs_indices, cs_indptr), cs_shape))
        # free the temporary native indptr, indices, and data
        _safe_call(_LIB.LGBM_BoosterFreePredictSparse(out_ptr_indptr, out_ptr_indices, out_ptr_data,
                                                      ctypes.c_int(indptr_type), ctypes.c_int(data_type)))
        if len(cs_output_matrices) == 1:
            return cs_output_matrices[0]
        return cs_output_matrices

979
    def __pred_for_csr(self, csr, start_iteration, num_iteration, predict_type):
980
        """Predict for a CSR data."""
981
        def inner_predict(csr, start_iteration, num_iteration, predict_type, preds=None):
982
            nrow = len(csr.indptr) - 1
983
            n_preds = self.__get_num_preds(start_iteration, num_iteration, nrow, predict_type)
984
            if preds is None:
985
                preds = np.empty(n_preds, dtype=np.float64)
986
987
988
989
990
991
992
            elif len(preds.shape) != 1 or len(preds) != n_preds:
                raise ValueError("Wrong length of pre-allocated predict array")
            out_num_preds = ctypes.c_int64(0)

            ptr_indptr, type_ptr_indptr, __ = c_int_array(csr.indptr)
            ptr_data, type_ptr_data, _ = c_float_array(csr.data)

993
            assert csr.shape[1] <= MAX_INT32
994
            csr_indices = csr.indices.astype(np.int32, copy=False)
995

996
997
998
            _safe_call(_LIB.LGBM_BoosterPredictForCSR(
                self.handle,
                ptr_indptr,
999
                ctypes.c_int(type_ptr_indptr),
1000
                csr_indices.ctypes.data_as(ctypes.POINTER(ctypes.c_int32)),
1001
1002
1003
1004
1005
1006
                ptr_data,
                ctypes.c_int(type_ptr_data),
                ctypes.c_int64(len(csr.indptr)),
                ctypes.c_int64(len(csr.data)),
                ctypes.c_int64(csr.shape[1]),
                ctypes.c_int(predict_type),
1007
                ctypes.c_int(start_iteration),
1008
1009
1010
1011
1012
1013
1014
                ctypes.c_int(num_iteration),
                c_str(self.pred_parameter),
                ctypes.byref(out_num_preds),
                preds.ctypes.data_as(ctypes.POINTER(ctypes.c_double))))
            if n_preds != out_num_preds.value:
                raise ValueError("Wrong length for predict results")
            return preds, nrow
wxchan's avatar
wxchan committed
1015

1016
        def inner_predict_sparse(csr, start_iteration, num_iteration, predict_type):
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
            ptr_indptr, type_ptr_indptr, __ = c_int_array(csr.indptr)
            ptr_data, type_ptr_data, _ = c_float_array(csr.data)
            csr_indices = csr.indices.astype(np.int32, copy=False)
            matrix_type = C_API_MATRIX_TYPE_CSR
            if type_ptr_indptr == C_API_DTYPE_INT32:
                out_ptr_indptr = ctypes.POINTER(ctypes.c_int32)()
            else:
                out_ptr_indptr = ctypes.POINTER(ctypes.c_int64)()
            out_ptr_indices = ctypes.POINTER(ctypes.c_int32)()
            if type_ptr_data == C_API_DTYPE_FLOAT32:
                out_ptr_data = ctypes.POINTER(ctypes.c_float)()
            else:
                out_ptr_data = ctypes.POINTER(ctypes.c_double)()
1030
            out_shape = np.empty(2, dtype=np.int64)
1031
1032
1033
            _safe_call(_LIB.LGBM_BoosterPredictSparseOutput(
                self.handle,
                ptr_indptr,
1034
                ctypes.c_int(type_ptr_indptr),
1035
1036
1037
1038
1039
1040
1041
                csr_indices.ctypes.data_as(ctypes.POINTER(ctypes.c_int32)),
                ptr_data,
                ctypes.c_int(type_ptr_data),
                ctypes.c_int64(len(csr.indptr)),
                ctypes.c_int64(len(csr.data)),
                ctypes.c_int64(csr.shape[1]),
                ctypes.c_int(predict_type),
1042
                ctypes.c_int(start_iteration),
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
                ctypes.c_int(num_iteration),
                c_str(self.pred_parameter),
                ctypes.c_int(matrix_type),
                out_shape.ctypes.data_as(ctypes.POINTER(ctypes.c_int64)),
                ctypes.byref(out_ptr_indptr),
                ctypes.byref(out_ptr_indices),
                ctypes.byref(out_ptr_data)))
            matrices = self.__create_sparse_native(csr, out_shape, out_ptr_indptr, out_ptr_indices, out_ptr_data,
                                                   type_ptr_indptr, type_ptr_data, is_csr=True)
            nrow = len(csr.indptr) - 1
            return matrices, nrow

        if predict_type == C_API_PREDICT_CONTRIB:
1056
            return inner_predict_sparse(csr, start_iteration, num_iteration, predict_type)
1057
1058
1059
1060
        nrow = len(csr.indptr) - 1
        if nrow > MAX_INT32:
            sections = [0] + list(np.arange(start=MAX_INT32, stop=nrow, step=MAX_INT32)) + [nrow]
            # __get_num_preds() cannot work with nrow > MAX_INT32, so calculate overall number of predictions piecemeal
1061
            n_preds = [self.__get_num_preds(start_iteration, num_iteration, i, predict_type) for i in np.diff(sections)]
1062
            n_preds_sections = np.array([0] + n_preds, dtype=np.intp).cumsum()
1063
            preds = np.empty(sum(n_preds), dtype=np.float64)
1064
1065
            for (start_idx, end_idx), (start_idx_pred, end_idx_pred) in zip(zip(sections, sections[1:]),
                                                                            zip(n_preds_sections, n_preds_sections[1:])):
1066
                # avoid memory consumption by arrays concatenation operations
1067
                inner_predict(csr[start_idx:end_idx], start_iteration, num_iteration, predict_type, preds[start_idx_pred:end_idx_pred])
1068
1069
            return preds, nrow
        else:
1070
            return inner_predict(csr, start_iteration, num_iteration, predict_type)
Guolin Ke's avatar
Guolin Ke committed
1071

1072
    def __pred_for_csc(self, csc, start_iteration, num_iteration, predict_type):
1073
        """Predict for a CSC data."""
1074
        def inner_predict_sparse(csc, start_iteration, num_iteration, predict_type):
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
            ptr_indptr, type_ptr_indptr, __ = c_int_array(csc.indptr)
            ptr_data, type_ptr_data, _ = c_float_array(csc.data)
            csc_indices = csc.indices.astype(np.int32, copy=False)
            matrix_type = C_API_MATRIX_TYPE_CSC
            if type_ptr_indptr == C_API_DTYPE_INT32:
                out_ptr_indptr = ctypes.POINTER(ctypes.c_int32)()
            else:
                out_ptr_indptr = ctypes.POINTER(ctypes.c_int64)()
            out_ptr_indices = ctypes.POINTER(ctypes.c_int32)()
            if type_ptr_data == C_API_DTYPE_FLOAT32:
                out_ptr_data = ctypes.POINTER(ctypes.c_float)()
            else:
                out_ptr_data = ctypes.POINTER(ctypes.c_double)()
1088
            out_shape = np.empty(2, dtype=np.int64)
1089
1090
1091
            _safe_call(_LIB.LGBM_BoosterPredictSparseOutput(
                self.handle,
                ptr_indptr,
1092
                ctypes.c_int(type_ptr_indptr),
1093
1094
1095
1096
1097
1098
1099
                csc_indices.ctypes.data_as(ctypes.POINTER(ctypes.c_int32)),
                ptr_data,
                ctypes.c_int(type_ptr_data),
                ctypes.c_int64(len(csc.indptr)),
                ctypes.c_int64(len(csc.data)),
                ctypes.c_int64(csc.shape[0]),
                ctypes.c_int(predict_type),
1100
                ctypes.c_int(start_iteration),
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
                ctypes.c_int(num_iteration),
                c_str(self.pred_parameter),
                ctypes.c_int(matrix_type),
                out_shape.ctypes.data_as(ctypes.POINTER(ctypes.c_int64)),
                ctypes.byref(out_ptr_indptr),
                ctypes.byref(out_ptr_indices),
                ctypes.byref(out_ptr_data)))
            matrices = self.__create_sparse_native(csc, out_shape, out_ptr_indptr, out_ptr_indices, out_ptr_data,
                                                   type_ptr_indptr, type_ptr_data, is_csr=False)
            nrow = csc.shape[0]
            return matrices, nrow

Guolin Ke's avatar
Guolin Ke committed
1113
        nrow = csc.shape[0]
1114
        if nrow > MAX_INT32:
1115
            return self.__pred_for_csr(csc.tocsr(), start_iteration, num_iteration, predict_type)
1116
        if predict_type == C_API_PREDICT_CONTRIB:
1117
1118
            return inner_predict_sparse(csc, start_iteration, num_iteration, predict_type)
        n_preds = self.__get_num_preds(start_iteration, num_iteration, nrow, predict_type)
1119
        preds = np.empty(n_preds, dtype=np.float64)
Guolin Ke's avatar
Guolin Ke committed
1120
1121
        out_num_preds = ctypes.c_int64(0)

1122
1123
        ptr_indptr, type_ptr_indptr, __ = c_int_array(csc.indptr)
        ptr_data, type_ptr_data, _ = c_float_array(csc.data)
Guolin Ke's avatar
Guolin Ke committed
1124

1125
        assert csc.shape[0] <= MAX_INT32
1126
        csc_indices = csc.indices.astype(np.int32, copy=False)
1127

Guolin Ke's avatar
Guolin Ke committed
1128
1129
1130
        _safe_call(_LIB.LGBM_BoosterPredictForCSC(
            self.handle,
            ptr_indptr,
1131
            ctypes.c_int(type_ptr_indptr),
1132
            csc_indices.ctypes.data_as(ctypes.POINTER(ctypes.c_int32)),
Guolin Ke's avatar
Guolin Ke committed
1133
            ptr_data,
Guolin Ke's avatar
Guolin Ke committed
1134
1135
1136
1137
1138
            ctypes.c_int(type_ptr_data),
            ctypes.c_int64(len(csc.indptr)),
            ctypes.c_int64(len(csc.data)),
            ctypes.c_int64(csc.shape[0]),
            ctypes.c_int(predict_type),
1139
            ctypes.c_int(start_iteration),
Guolin Ke's avatar
Guolin Ke committed
1140
            ctypes.c_int(num_iteration),
1141
            c_str(self.pred_parameter),
Guolin Ke's avatar
Guolin Ke committed
1142
            ctypes.byref(out_num_preds),
wxchan's avatar
wxchan committed
1143
            preds.ctypes.data_as(ctypes.POINTER(ctypes.c_double))))
wxchan's avatar
wxchan committed
1144
        if n_preds != out_num_preds.value:
1145
            raise ValueError("Wrong length for predict results")
wxchan's avatar
wxchan committed
1146
1147
        return preds, nrow

1148
    def current_iteration(self) -> int:
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
        """Get the index of the current iteration.

        Returns
        -------
        cur_iter : int
            The index of the current iteration.
        """
        out_cur_iter = ctypes.c_int(0)
        _safe_call(_LIB.LGBM_BoosterGetCurrentIteration(
            self.handle,
            ctypes.byref(out_cur_iter)))
        return out_cur_iter.value

wxchan's avatar
wxchan committed
1162

1163
class Dataset:
wxchan's avatar
wxchan committed
1164
    """Dataset in LightGBM."""
1165

1166
    def __init__(self, data, label=None, reference=None,
1167
                 weight=None, group=None, init_score=None,
1168
                 feature_name='auto', categorical_feature='auto', params=None,
wxchan's avatar
wxchan committed
1169
                 free_raw_data=True):
1170
        """Initialize Dataset.
1171

wxchan's avatar
wxchan committed
1172
1173
        Parameters
        ----------
1174
        data : str, pathlib.Path, numpy array, pandas DataFrame, H2O DataTable's Frame, scipy.sparse, Sequence, list of Sequence or list of numpy array
wxchan's avatar
wxchan committed
1175
            Data source of Dataset.
1176
            If str or pathlib.Path, it represents the path to a text file (CSV, TSV, or LibSVM) or a LightGBM Dataset binary file.
1177
        label : list, numpy 1-D array, pandas Series / one-column DataFrame or None, optional (default=None)
1178
1179
1180
            Label of the data.
        reference : Dataset or None, optional (default=None)
            If this is Dataset for validation, training data should be used as reference.
1181
        weight : list, numpy 1-D array, pandas Series or None, optional (default=None)
1182
            Weight for each instance. Weights should be non-negative.
1183
        group : list, numpy 1-D array, pandas Series or None, optional (default=None)
1184
1185
1186
            Group/query data.
            Only used in the learning-to-rank task.
            sum(group) = n_samples.
1187
1188
            For example, if you have a 100-document dataset with ``group = [10, 20, 40, 10, 10, 10]``, that means that you have 6 groups,
            where the first 10 records are in the first group, records 11-30 are in the second group, records 31-70 are in the third group, etc.
1189
        init_score : list, list of lists (for multi-class task), numpy array, pandas Series, pandas DataFrame (for multi-class task), or None, optional (default=None)
1190
            Init score for Dataset.
1191
        feature_name : list of str, or 'auto', optional (default="auto")
1192
1193
            Feature names.
            If 'auto' and data is pandas DataFrame, data columns names are used.
1194
        categorical_feature : list of str or int, or 'auto', optional (default="auto")
1195
1196
            Categorical features.
            If list of int, interpreted as indices.
1197
            If list of str, interpreted as feature names (need to specify ``feature_name`` as well).
1198
            If 'auto' and data is pandas DataFrame, pandas unordered categorical columns are used.
1199
            All values in categorical features will be cast to int32 and thus should be less than int32 max value (2147483647).
1200
            Large values could be memory consuming. Consider using consecutive integers starting from zero.
1201
            All negative values in categorical features will be treated as missing values.
1202
            The output cannot be monotonically constrained with respect to a categorical feature.
1203
            Floating point numbers in categorical features will be rounded towards 0.
Nikita Titov's avatar
Nikita Titov committed
1204
        params : dict or None, optional (default=None)
1205
            Other parameters for Dataset.
Nikita Titov's avatar
Nikita Titov committed
1206
        free_raw_data : bool, optional (default=True)
1207
            If True, raw data is freed after constructing inner Dataset.
wxchan's avatar
wxchan committed
1208
        """
wxchan's avatar
wxchan committed
1209
1210
1211
1212
1213
1214
        self.handle = None
        self.data = data
        self.label = label
        self.reference = reference
        self.weight = weight
        self.group = group
1215
        self.init_score = init_score
wxchan's avatar
wxchan committed
1216
        self.feature_name = feature_name
1217
        self.categorical_feature = categorical_feature
1218
        self.params = deepcopy(params)
wxchan's avatar
wxchan committed
1219
1220
        self.free_raw_data = free_raw_data
        self.used_indices = None
1221
        self.need_slice = True
wxchan's avatar
wxchan committed
1222
        self._predictor = None
1223
        self.pandas_categorical = None
1224
        self.params_back_up = None
1225
1226
        self.feature_penalty = None
        self.monotone_constraints = None
1227
        self.version = 0
1228
        self._start_row = 0  # Used when pushing rows one by one.
wxchan's avatar
wxchan committed
1229

1230
    def __del__(self) -> None:
1231
1232
1233
1234
        try:
            self._free_handle()
        except AttributeError:
            pass
1235

1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
    def _create_sample_indices(self, total_nrow: int) -> np.ndarray:
        """Get an array of randomly chosen indices from this ``Dataset``.

        Indices are sampled without replacement.

        Parameters
        ----------
        total_nrow : int
            Total number of rows to sample from.
            If this value is greater than the value of parameter ``bin_construct_sample_cnt``, only ``bin_construct_sample_cnt`` indices will be used.
            If Dataset has multiple input data, this should be the sum of rows of every file.

        Returns
        -------
        indices : numpy array
            Indices for sampled data.
        """
        param_str = param_dict_to_str(self.get_params())
        sample_cnt = _get_sample_count(total_nrow, param_str)
        indices = np.empty(sample_cnt, dtype=np.int32)
        ptr_data, _, _ = c_int_array(indices)
        actual_sample_cnt = ctypes.c_int32(0)

        _safe_call(_LIB.LGBM_SampleIndices(
            ctypes.c_int32(total_nrow),
            c_str(param_str),
            ptr_data,
            ctypes.byref(actual_sample_cnt),
        ))
1265
1266
        assert sample_cnt == actual_sample_cnt.value
        return indices
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301

    def _init_from_ref_dataset(self, total_nrow: int, ref_dataset: 'Dataset') -> 'Dataset':
        """Create dataset from a reference dataset.

        Parameters
        ----------
        total_nrow : int
            Number of rows expected to add to dataset.
        ref_dataset : Dataset
            Reference dataset to extract meta from.

        Returns
        -------
        self : Dataset
            Constructed Dataset object.
        """
        self.handle = ctypes.c_void_p()
        _safe_call(_LIB.LGBM_DatasetCreateByReference(
            ref_dataset,
            ctypes.c_int64(total_nrow),
            ctypes.byref(self.handle),
        ))
        return self

    def _init_from_sample(
        self,
        sample_data: List[np.ndarray],
        sample_indices: List[np.ndarray],
        sample_cnt: int,
        total_nrow: int,
    ) -> "Dataset":
        """Create Dataset from sampled data structures.

        Parameters
        ----------
1302
        sample_data : list of numpy array
1303
            Sample data for each column.
1304
        sample_indices : list of numpy array
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
            Sample data row index for each column.
        sample_cnt : int
            Number of samples.
        total_nrow : int
            Total number of rows for all input files.

        Returns
        -------
        self : Dataset
            Constructed Dataset object.
        """
        ncol = len(sample_indices)
        assert len(sample_data) == ncol, "#sample data column != #column indices"

        for i in range(ncol):
            if sample_data[i].dtype != np.double:
                raise ValueError(f"sample_data[{i}] type {sample_data[i].dtype} is not double")
            if sample_indices[i].dtype != np.int32:
                raise ValueError(f"sample_indices[{i}] type {sample_indices[i].dtype} is not int32")

        # c type: double**
        # each double* element points to start of each column of sample data.
        sample_col_ptr = (ctypes.POINTER(ctypes.c_double) * ncol)()
        # c type int**
        # each int* points to start of indices for each column
        indices_col_ptr = (ctypes.POINTER(ctypes.c_int32) * ncol)()
        for i in range(ncol):
            sample_col_ptr[i] = c_float_array(sample_data[i])[0]
            indices_col_ptr[i] = c_int_array(sample_indices[i])[0]

        num_per_col = np.array([len(d) for d in sample_indices], dtype=np.int32)
        num_per_col_ptr, _, _ = c_int_array(num_per_col)

        self.handle = ctypes.c_void_p()
        params_str = param_dict_to_str(self.get_params())
        _safe_call(_LIB.LGBM_DatasetCreateFromSampledColumn(
            ctypes.cast(sample_col_ptr, ctypes.POINTER(ctypes.POINTER(ctypes.c_double))),
            ctypes.cast(indices_col_ptr, ctypes.POINTER(ctypes.POINTER(ctypes.c_int32))),
            ctypes.c_int32(ncol),
            num_per_col_ptr,
            ctypes.c_int32(sample_cnt),
            ctypes.c_int32(total_nrow),
            c_str(params_str),
            ctypes.byref(self.handle),
        ))
        return self

    def _push_rows(self, data: np.ndarray) -> 'Dataset':
        """Add rows to Dataset.

        Parameters
        ----------
        data : numpy 1-D array
            New data to add to the Dataset.

        Returns
        -------
        self : Dataset
            Dataset object.
        """
        nrow, ncol = data.shape
        data = data.reshape(data.size)
        data_ptr, data_type, _ = c_float_array(data)

        _safe_call(_LIB.LGBM_DatasetPushRows(
            self.handle,
            data_ptr,
            data_type,
            ctypes.c_int32(nrow),
            ctypes.c_int32(ncol),
            ctypes.c_int32(self._start_row),
        ))
        self._start_row += nrow
        return self

1380
    def get_params(self) -> Dict[str, Any]:
1381
1382
1383
1384
        """Get the used parameters in the Dataset.

        Returns
        -------
1385
        params : dict
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
            The used parameters in this Dataset object.
        """
        if self.params is not None:
            # no min_data, nthreads and verbose in this function
            dataset_params = _ConfigAliases.get("bin_construct_sample_cnt",
                                                "categorical_feature",
                                                "data_random_seed",
                                                "enable_bundle",
                                                "feature_pre_filter",
                                                "forcedbins_filename",
                                                "group_column",
                                                "header",
                                                "ignore_column",
                                                "is_enable_sparse",
                                                "label_column",
1401
                                                "linear_tree",
1402
1403
1404
1405
                                                "max_bin",
                                                "max_bin_by_feature",
                                                "min_data_in_bin",
                                                "pre_partition",
Nikita Titov's avatar
Nikita Titov committed
1406
                                                "precise_float_parser",
1407
1408
1409
1410
1411
                                                "two_round",
                                                "use_missing",
                                                "weight_column",
                                                "zero_as_missing")
            return {k: v for k, v in self.params.items() if k in dataset_params}
1412
1413
        else:
            return {}
1414

1415
    def _free_handle(self) -> "Dataset":
1416
        if self.handle is not None:
1417
            _safe_call(_LIB.LGBM_DatasetFree(self.handle))
1418
            self.handle = None
Guolin Ke's avatar
Guolin Ke committed
1419
1420
1421
        self.need_slice = True
        if self.used_indices is not None:
            self.data = None
Nikita Titov's avatar
Nikita Titov committed
1422
        return self
wxchan's avatar
wxchan committed
1423

Guolin Ke's avatar
Guolin Ke committed
1424
1425
    def _set_init_score_by_predictor(self, predictor, data, used_indices=None):
        data_has_header = False
1426
        if isinstance(data, (str, Path)):
Guolin Ke's avatar
Guolin Ke committed
1427
            # check data has header or not
1428
            data_has_header = any(self.params.get(alias, False) for alias in _ConfigAliases.get("header"))
Guolin Ke's avatar
Guolin Ke committed
1429
        num_data = self.num_data()
1430
1431
1432
        if predictor is not None:
            init_score = predictor.predict(data,
                                           raw_score=True,
1433
1434
                                           data_has_header=data_has_header)
            init_score = init_score.ravel()
1435
1436
            if used_indices is not None:
                assert not self.need_slice
1437
                if isinstance(data, (str, Path)):
1438
                    sub_init_score = np.empty(num_data * predictor.num_class, dtype=np.float64)
1439
                    assert num_data == len(used_indices)
1440
1441
                    for i in range(len(used_indices)):
                        for j in range(predictor.num_class):
1442
1443
1444
1445
                            sub_init_score[i * predictor.num_class + j] = init_score[used_indices[i] * predictor.num_class + j]
                    init_score = sub_init_score
            if predictor.num_class > 1:
                # need to regroup init_score
1446
                new_init_score = np.empty(init_score.size, dtype=np.float64)
1447
1448
                for i in range(num_data):
                    for j in range(predictor.num_class):
1449
1450
1451
                        new_init_score[j * num_data + i] = init_score[i * predictor.num_class + j]
                init_score = new_init_score
        elif self.init_score is not None:
1452
            init_score = np.zeros(self.init_score.shape, dtype=np.float64)
1453
1454
        else:
            return self
Guolin Ke's avatar
Guolin Ke committed
1455
1456
        self.set_init_score(init_score)

1457
    def _lazy_init(self, data, label=None, reference=None,
1458
                   weight=None, group=None, init_score=None, predictor=None,
1459
                   feature_name='auto', categorical_feature='auto', params=None):
wxchan's avatar
wxchan committed
1460
1461
        if data is None:
            self.handle = None
Nikita Titov's avatar
Nikita Titov committed
1462
            return self
Guolin Ke's avatar
Guolin Ke committed
1463
1464
1465
        if reference is not None:
            self.pandas_categorical = reference.pandas_categorical
            categorical_feature = reference.categorical_feature
1466
1467
1468
1469
        data, feature_name, categorical_feature, self.pandas_categorical = _data_from_pandas(data,
                                                                                             feature_name,
                                                                                             categorical_feature,
                                                                                             self.pandas_categorical)
wxchan's avatar
wxchan committed
1470
        label = _label_from_pandas(label)
Guolin Ke's avatar
Guolin Ke committed
1471

1472
        # process for args
wxchan's avatar
wxchan committed
1473
        params = {} if params is None else params
1474
1475
1476
        args_names = (getattr(self.__class__, '_lazy_init')
                      .__code__
                      .co_varnames[:getattr(self.__class__, '_lazy_init').__code__.co_argcount])
1477
        for key in params.keys():
1478
            if key in args_names:
1479
1480
                _log_warning(f'{key} keyword has been found in `params` and will be ignored.\n'
                             f'Please use {key} argument of the Dataset constructor to pass this parameter.')
1481
        # get categorical features
1482
1483
1484
1485
1486
1487
        if categorical_feature is not None:
            categorical_indices = set()
            feature_dict = {}
            if feature_name is not None:
                feature_dict = {name: i for i, name in enumerate(feature_name)}
            for name in categorical_feature:
1488
                if isinstance(name, str) and name in feature_dict:
1489
                    categorical_indices.add(feature_dict[name])
1490
                elif isinstance(name, int):
1491
1492
                    categorical_indices.add(name)
                else:
1493
                    raise TypeError(f"Wrong type({type(name).__name__}) or unknown name({name}) in categorical_feature")
1494
            if categorical_indices:
1495
1496
                for cat_alias in _ConfigAliases.get("categorical_feature"):
                    if cat_alias in params:
1497
1498
1499
                        # If the params[cat_alias] is equal to categorical_indices, do not report the warning.
                        if not(isinstance(params[cat_alias], list) and set(params[cat_alias]) == categorical_indices):
                            _log_warning(f'{cat_alias} in param dict is overridden.')
1500
                        params.pop(cat_alias, None)
1501
                params['categorical_column'] = sorted(categorical_indices)
1502

wxchan's avatar
wxchan committed
1503
        params_str = param_dict_to_str(params)
1504
        self.params = params
1505
        # process for reference dataset
wxchan's avatar
wxchan committed
1506
        ref_dataset = None
wxchan's avatar
wxchan committed
1507
        if isinstance(reference, Dataset):
1508
            ref_dataset = reference.construct().handle
wxchan's avatar
wxchan committed
1509
1510
        elif reference is not None:
            raise TypeError('Reference dataset should be None or dataset instance')
1511
        # start construct data
1512
        if isinstance(data, (str, Path)):
wxchan's avatar
wxchan committed
1513
1514
            self.handle = ctypes.c_void_p()
            _safe_call(_LIB.LGBM_DatasetCreateFromFile(
1515
                c_str(str(data)),
wxchan's avatar
wxchan committed
1516
1517
1518
1519
1520
                c_str(params_str),
                ref_dataset,
                ctypes.byref(self.handle)))
        elif isinstance(data, scipy.sparse.csr_matrix):
            self.__init_from_csr(data, params_str, ref_dataset)
Guolin Ke's avatar
Guolin Ke committed
1521
1522
        elif isinstance(data, scipy.sparse.csc_matrix):
            self.__init_from_csc(data, params_str, ref_dataset)
wxchan's avatar
wxchan committed
1523
1524
        elif isinstance(data, np.ndarray):
            self.__init_from_np2d(data, params_str, ref_dataset)
1525
1526
1527
1528
1529
1530
1531
1532
1533
        elif isinstance(data, list) and len(data) > 0:
            if all(isinstance(x, np.ndarray) for x in data):
                self.__init_from_list_np2d(data, params_str, ref_dataset)
            elif all(isinstance(x, Sequence) for x in data):
                self.__init_from_seqs(data, ref_dataset)
            else:
                raise TypeError('Data list can only be of ndarray or Sequence')
        elif isinstance(data, Sequence):
            self.__init_from_seqs([data], ref_dataset)
1534
        elif isinstance(data, dt_DataTable):
1535
            self.__init_from_np2d(data.to_numpy(), params_str, ref_dataset)
wxchan's avatar
wxchan committed
1536
1537
1538
1539
        else:
            try:
                csr = scipy.sparse.csr_matrix(data)
                self.__init_from_csr(csr, params_str, ref_dataset)
1540
            except BaseException:
1541
                raise TypeError(f'Cannot initialize Dataset from {type(data).__name__}')
wxchan's avatar
wxchan committed
1542
1543
1544
        if label is not None:
            self.set_label(label)
        if self.get_label() is None:
1545
            raise ValueError("Label should not be None")
wxchan's avatar
wxchan committed
1546
1547
1548
1549
        if weight is not None:
            self.set_weight(weight)
        if group is not None:
            self.set_group(group)
1550
1551
        if isinstance(predictor, _InnerPredictor):
            if self._predictor is None and init_score is not None:
1552
                _log_warning("The init_score will be overridden by the prediction of init_model.")
Guolin Ke's avatar
Guolin Ke committed
1553
            self._set_init_score_by_predictor(predictor, data)
1554
1555
        elif init_score is not None:
            self.set_init_score(init_score)
Guolin Ke's avatar
Guolin Ke committed
1556
        elif predictor is not None:
1557
            raise TypeError(f'Wrong predictor type {type(predictor).__name__}')
Guolin Ke's avatar
Guolin Ke committed
1558
        # set feature names
Nikita Titov's avatar
Nikita Titov committed
1559
        return self.set_feature_name(feature_name)
wxchan's avatar
wxchan committed
1560

1561
1562
    @staticmethod
    def _yield_row_from_seqlist(seqs: List[Sequence], indices: Iterable[int]):
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
        offset = 0
        seq_id = 0
        seq = seqs[seq_id]
        for row_id in indices:
            assert row_id >= offset, "sample indices are expected to be monotonic"
            while row_id >= offset + len(seq):
                offset += len(seq)
                seq_id += 1
                seq = seqs[seq_id]
            id_in_seq = row_id - offset
            row = seq[id_in_seq]
            yield row if row.flags['OWNDATA'] else row.copy()

    def __sample(self, seqs: List[Sequence], total_nrow: int) -> Tuple[List[np.ndarray], List[np.ndarray]]:
        """Sample data from seqs.

        Mimics behavior in c_api.cpp:LGBM_DatasetCreateFromMats()

        Returns
        -------
            sampled_rows, sampled_row_indices
        """
        indices = self._create_sample_indices(total_nrow)

        # Select sampled rows, transpose to column order.
1588
        sampled = np.array([row for row in self._yield_row_from_seqlist(seqs, indices)])
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
        sampled = sampled.T

        filtered = []
        filtered_idx = []
        sampled_row_range = np.arange(len(indices), dtype=np.int32)
        for col in sampled:
            col_predicate = (np.abs(col) > ZERO_THRESHOLD) | np.isnan(col)
            filtered_col = col[col_predicate]
            filtered_row_idx = sampled_row_range[col_predicate]

            filtered.append(filtered_col)
            filtered_idx.append(filtered_row_idx)

        return filtered, filtered_idx

    def __init_from_seqs(self, seqs: List[Sequence], ref_dataset: Optional['Dataset'] = None):
        """
        Initialize data from list of Sequence objects.

        Sequence: Generic Data Access Object
            Supports random access and access by batch if properly defined by user

        Data scheme uniformity are trusted, not checked
        """
        total_nrow = sum(len(seq) for seq in seqs)

        # create validation dataset from ref_dataset
        if ref_dataset is not None:
            self._init_from_ref_dataset(total_nrow, ref_dataset)
        else:
            param_str = param_dict_to_str(self.get_params())
            sample_cnt = _get_sample_count(total_nrow, param_str)

            sample_data, col_indices = self.__sample(seqs, total_nrow)
            self._init_from_sample(sample_data, col_indices, sample_cnt, total_nrow)

        for seq in seqs:
            nrow = len(seq)
            batch_size = getattr(seq, 'batch_size', None) or Sequence.batch_size
            for start in range(0, nrow, batch_size):
                end = min(start + batch_size, nrow)
                self._push_rows(seq[start:end])
        return self

wxchan's avatar
wxchan committed
1633
    def __init_from_np2d(self, mat, params_str, ref_dataset):
1634
        """Initialize data from a 2-D numpy matrix."""
wxchan's avatar
wxchan committed
1635
1636
1637
1638
1639
1640
        if len(mat.shape) != 2:
            raise ValueError('Input numpy.ndarray must be 2 dimensional')

        self.handle = ctypes.c_void_p()
        if mat.dtype == np.float32 or mat.dtype == np.float64:
            data = np.array(mat.reshape(mat.size), dtype=mat.dtype, copy=False)
1641
        else:  # change non-float data to float data, need to copy
wxchan's avatar
wxchan committed
1642
1643
            data = np.array(mat.reshape(mat.size), dtype=np.float32)

1644
        ptr_data, type_ptr_data, _ = c_float_array(data)
wxchan's avatar
wxchan committed
1645
1646
        _safe_call(_LIB.LGBM_DatasetCreateFromMat(
            ptr_data,
Guolin Ke's avatar
Guolin Ke committed
1647
            ctypes.c_int(type_ptr_data),
1648
1649
            ctypes.c_int32(mat.shape[0]),
            ctypes.c_int32(mat.shape[1]),
Guolin Ke's avatar
Guolin Ke committed
1650
            ctypes.c_int(C_API_IS_ROW_MAJOR),
wxchan's avatar
wxchan committed
1651
1652
1653
            c_str(params_str),
            ref_dataset,
            ctypes.byref(self.handle)))
Nikita Titov's avatar
Nikita Titov committed
1654
        return self
wxchan's avatar
wxchan committed
1655

1656
    def __init_from_list_np2d(self, mats, params_str, ref_dataset):
1657
        """Initialize data from a list of 2-D numpy matrices."""
1658
        ncol = mats[0].shape[1]
1659
        nrow = np.empty((len(mats),), np.int32)
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
        if mats[0].dtype == np.float64:
            ptr_data = (ctypes.POINTER(ctypes.c_double) * len(mats))()
        else:
            ptr_data = (ctypes.POINTER(ctypes.c_float) * len(mats))()

        holders = []
        type_ptr_data = None

        for i, mat in enumerate(mats):
            if len(mat.shape) != 2:
                raise ValueError('Input numpy.ndarray must be 2 dimensional')

            if mat.shape[1] != ncol:
                raise ValueError('Input arrays must have same number of columns')

            nrow[i] = mat.shape[0]

            if mat.dtype == np.float32 or mat.dtype == np.float64:
                mats[i] = np.array(mat.reshape(mat.size), dtype=mat.dtype, copy=False)
1679
            else:  # change non-float data to float data, need to copy
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
                mats[i] = np.array(mat.reshape(mat.size), dtype=np.float32)

            chunk_ptr_data, chunk_type_ptr_data, holder = c_float_array(mats[i])
            if type_ptr_data is not None and chunk_type_ptr_data != type_ptr_data:
                raise ValueError('Input chunks must have same type')
            ptr_data[i] = chunk_ptr_data
            type_ptr_data = chunk_type_ptr_data
            holders.append(holder)

        self.handle = ctypes.c_void_p()
        _safe_call(_LIB.LGBM_DatasetCreateFromMats(
1691
            ctypes.c_int32(len(mats)),
1692
1693
1694
            ctypes.cast(ptr_data, ctypes.POINTER(ctypes.POINTER(ctypes.c_double))),
            ctypes.c_int(type_ptr_data),
            nrow.ctypes.data_as(ctypes.POINTER(ctypes.c_int32)),
1695
            ctypes.c_int32(ncol),
1696
1697
1698
1699
            ctypes.c_int(C_API_IS_ROW_MAJOR),
            c_str(params_str),
            ref_dataset,
            ctypes.byref(self.handle)))
Nikita Titov's avatar
Nikita Titov committed
1700
        return self
1701

wxchan's avatar
wxchan committed
1702
    def __init_from_csr(self, csr, params_str, ref_dataset):
1703
        """Initialize data from a CSR matrix."""
wxchan's avatar
wxchan committed
1704
        if len(csr.indices) != len(csr.data):
1705
            raise ValueError(f'Length mismatch: {len(csr.indices)} vs {len(csr.data)}')
wxchan's avatar
wxchan committed
1706
1707
        self.handle = ctypes.c_void_p()

1708
1709
        ptr_indptr, type_ptr_indptr, __ = c_int_array(csr.indptr)
        ptr_data, type_ptr_data, _ = c_float_array(csr.data)
wxchan's avatar
wxchan committed
1710

1711
        assert csr.shape[1] <= MAX_INT32
1712
        csr_indices = csr.indices.astype(np.int32, copy=False)
1713

wxchan's avatar
wxchan committed
1714
1715
        _safe_call(_LIB.LGBM_DatasetCreateFromCSR(
            ptr_indptr,
Guolin Ke's avatar
Guolin Ke committed
1716
            ctypes.c_int(type_ptr_indptr),
1717
            csr_indices.ctypes.data_as(ctypes.POINTER(ctypes.c_int32)),
wxchan's avatar
wxchan committed
1718
            ptr_data,
Guolin Ke's avatar
Guolin Ke committed
1719
1720
1721
1722
            ctypes.c_int(type_ptr_data),
            ctypes.c_int64(len(csr.indptr)),
            ctypes.c_int64(len(csr.data)),
            ctypes.c_int64(csr.shape[1]),
wxchan's avatar
wxchan committed
1723
1724
1725
            c_str(params_str),
            ref_dataset,
            ctypes.byref(self.handle)))
Nikita Titov's avatar
Nikita Titov committed
1726
        return self
wxchan's avatar
wxchan committed
1727

Guolin Ke's avatar
Guolin Ke committed
1728
    def __init_from_csc(self, csc, params_str, ref_dataset):
1729
        """Initialize data from a CSC matrix."""
Guolin Ke's avatar
Guolin Ke committed
1730
        if len(csc.indices) != len(csc.data):
1731
            raise ValueError(f'Length mismatch: {len(csc.indices)} vs {len(csc.data)}')
Guolin Ke's avatar
Guolin Ke committed
1732
1733
        self.handle = ctypes.c_void_p()

1734
1735
        ptr_indptr, type_ptr_indptr, __ = c_int_array(csc.indptr)
        ptr_data, type_ptr_data, _ = c_float_array(csc.data)
Guolin Ke's avatar
Guolin Ke committed
1736

1737
        assert csc.shape[0] <= MAX_INT32
1738
        csc_indices = csc.indices.astype(np.int32, copy=False)
1739

Guolin Ke's avatar
Guolin Ke committed
1740
1741
        _safe_call(_LIB.LGBM_DatasetCreateFromCSC(
            ptr_indptr,
Guolin Ke's avatar
Guolin Ke committed
1742
            ctypes.c_int(type_ptr_indptr),
1743
            csc_indices.ctypes.data_as(ctypes.POINTER(ctypes.c_int32)),
Guolin Ke's avatar
Guolin Ke committed
1744
            ptr_data,
Guolin Ke's avatar
Guolin Ke committed
1745
1746
1747
1748
            ctypes.c_int(type_ptr_data),
            ctypes.c_int64(len(csc.indptr)),
            ctypes.c_int64(len(csc.data)),
            ctypes.c_int64(csc.shape[0]),
Guolin Ke's avatar
Guolin Ke committed
1749
1750
1751
            c_str(params_str),
            ref_dataset,
            ctypes.byref(self.handle)))
Nikita Titov's avatar
Nikita Titov committed
1752
        return self
Guolin Ke's avatar
Guolin Ke committed
1753

1754
    @staticmethod
1755
1756
1757
1758
1759
1760
    def _compare_params_for_warning(
        params: Optional[Dict[str, Any]],
        other_params: Optional[Dict[str, Any]],
        ignore_keys: Set[str]
    ) -> bool:
        """Compare two dictionaries with params ignoring some keys.
1761

1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
        It is only for the warning purpose.

        Parameters
        ----------
        params : dict or None
            One dictionary with parameters to compare.
        other_params : dict or None
            Another dictionary with parameters to compare.
        ignore_keys : set
            Keys that should be ignored during comparing two dictionaries.
1772
1773
1774

        Returns
        -------
1775
1776
        compare_result : bool
          Returns whether two dictionaries with params are equal.
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
        """
        if params is None:
            params = {}
        if other_params is None:
            other_params = {}
        for k in other_params:
            if k not in ignore_keys:
                if k not in params or params[k] != other_params[k]:
                    return False
        for k in params:
            if k not in ignore_keys:
                if k not in other_params or params[k] != other_params[k]:
                    return False
        return True

1792
    def construct(self) -> "Dataset":
1793
1794
1795
1796
1797
        """Lazy init.

        Returns
        -------
        self : Dataset
Nikita Titov's avatar
Nikita Titov committed
1798
            Constructed Dataset object.
1799
        """
1800
        if self.handle is None:
wxchan's avatar
wxchan committed
1801
            if self.reference is not None:
1802
                reference_params = self.reference.get_params()
1803
1804
                params = self.get_params()
                if params != reference_params:
1805
1806
1807
1808
1809
                    if not self._compare_params_for_warning(
                        params=params,
                        other_params=reference_params,
                        ignore_keys=_ConfigAliases.get("categorical_feature")
                    ):
1810
                        _log_warning('Overriding the parameters from Reference Dataset.')
1811
                    self._update_params(reference_params)
wxchan's avatar
wxchan committed
1812
                if self.used_indices is None:
1813
                    # create valid
1814
                    self._lazy_init(self.data, label=self.label, reference=self.reference,
1815
1816
                                    weight=self.weight, group=self.group,
                                    init_score=self.init_score, predictor=self._predictor,
1817
                                    feature_name=self.feature_name, params=self.params)
wxchan's avatar
wxchan committed
1818
                else:
1819
                    # construct subset
wxchan's avatar
wxchan committed
1820
                    used_indices = list_to_1d_numpy(self.used_indices, np.int32, name='used_indices')
1821
                    assert used_indices.flags.c_contiguous
Guolin Ke's avatar
Guolin Ke committed
1822
                    if self.reference.group is not None:
1823
                        group_info = np.array(self.reference.group).astype(np.int32, copy=False)
1824
                        _, self.group = np.unique(np.repeat(range(len(group_info)), repeats=group_info)[self.used_indices],
1825
                                                  return_counts=True)
1826
                    self.handle = ctypes.c_void_p()
wxchan's avatar
wxchan committed
1827
1828
                    params_str = param_dict_to_str(self.params)
                    _safe_call(_LIB.LGBM_DatasetGetSubset(
1829
                        self.reference.construct().handle,
wxchan's avatar
wxchan committed
1830
                        used_indices.ctypes.data_as(ctypes.POINTER(ctypes.c_int32)),
1831
                        ctypes.c_int32(used_indices.shape[0]),
wxchan's avatar
wxchan committed
1832
1833
                        c_str(params_str),
                        ctypes.byref(self.handle)))
Guolin Ke's avatar
Guolin Ke committed
1834
1835
                    if not self.free_raw_data:
                        self.get_data()
Guolin Ke's avatar
Guolin Ke committed
1836
1837
                    if self.group is not None:
                        self.set_group(self.group)
wxchan's avatar
wxchan committed
1838
1839
                    if self.get_label() is None:
                        raise ValueError("Label should not be None.")
Guolin Ke's avatar
Guolin Ke committed
1840
1841
1842
                    if isinstance(self._predictor, _InnerPredictor) and self._predictor is not self.reference._predictor:
                        self.get_data()
                        self._set_init_score_by_predictor(self._predictor, self.data, used_indices)
wxchan's avatar
wxchan committed
1843
            else:
1844
                # create train
1845
                self._lazy_init(self.data, label=self.label,
1846
1847
                                weight=self.weight, group=self.group,
                                init_score=self.init_score, predictor=self._predictor,
1848
                                feature_name=self.feature_name, categorical_feature=self.categorical_feature, params=self.params)
wxchan's avatar
wxchan committed
1849
1850
            if self.free_raw_data:
                self.data = None
1851
            self.feature_name = self.get_feature_name()
wxchan's avatar
wxchan committed
1852
        return self
wxchan's avatar
wxchan committed
1853

1854
    def create_valid(self, data, label=None, weight=None, group=None, init_score=None, params=None):
1855
        """Create validation data align with current Dataset.
wxchan's avatar
wxchan committed
1856
1857
1858

        Parameters
        ----------
1859
        data : str, pathlib.Path, numpy array, pandas DataFrame, H2O DataTable's Frame, scipy.sparse, Sequence, list of Sequence or list of numpy array
wxchan's avatar
wxchan committed
1860
            Data source of Dataset.
1861
            If str or pathlib.Path, it represents the path to a text file (CSV, TSV, or LibSVM) or a LightGBM Dataset binary file.
1862
        label : list, numpy 1-D array, pandas Series / one-column DataFrame or None, optional (default=None)
1863
1864
            Label of the data.
        weight : list, numpy 1-D array, pandas Series or None, optional (default=None)
1865
            Weight for each instance. Weights should be non-negative.
1866
        group : list, numpy 1-D array, pandas Series or None, optional (default=None)
1867
1868
1869
            Group/query data.
            Only used in the learning-to-rank task.
            sum(group) = n_samples.
1870
1871
            For example, if you have a 100-document dataset with ``group = [10, 20, 40, 10, 10, 10]``, that means that you have 6 groups,
            where the first 10 records are in the first group, records 11-30 are in the second group, records 31-70 are in the third group, etc.
1872
        init_score : list, list of lists (for multi-class task), numpy array, pandas Series, pandas DataFrame (for multi-class task), or None, optional (default=None)
1873
            Init score for Dataset.
Nikita Titov's avatar
Nikita Titov committed
1874
        params : dict or None, optional (default=None)
1875
            Other parameters for validation Dataset.
1876
1877
1878

        Returns
        -------
Nikita Titov's avatar
Nikita Titov committed
1879
1880
        valid : Dataset
            Validation Dataset with reference to self.
wxchan's avatar
wxchan committed
1881
        """
1882
        ret = Dataset(data, label=label, reference=self,
1883
                      weight=weight, group=group, init_score=init_score,
1884
                      params=params, free_raw_data=self.free_raw_data)
wxchan's avatar
wxchan committed
1885
        ret._predictor = self._predictor
1886
        ret.pandas_categorical = self.pandas_categorical
wxchan's avatar
wxchan committed
1887
        return ret
wxchan's avatar
wxchan committed
1888

1889
1890
1891
1892
1893
    def subset(
        self,
        used_indices: List[int],
        params: Optional[Dict[str, Any]] = None
    ) -> "Dataset":
1894
        """Get subset of current Dataset.
wxchan's avatar
wxchan committed
1895
1896
1897
1898

        Parameters
        ----------
        used_indices : list of int
1899
            Indices used to create the subset.
Nikita Titov's avatar
Nikita Titov committed
1900
        params : dict or None, optional (default=None)
1901
            These parameters will be passed to Dataset constructor.
1902
1903
1904
1905
1906

        Returns
        -------
        subset : Dataset
            Subset of the current Dataset.
wxchan's avatar
wxchan committed
1907
        """
wxchan's avatar
wxchan committed
1908
1909
        if params is None:
            params = self.params
wxchan's avatar
wxchan committed
1910
        ret = Dataset(None, reference=self, feature_name=self.feature_name,
1911
1912
                      categorical_feature=self.categorical_feature, params=params,
                      free_raw_data=self.free_raw_data)
wxchan's avatar
wxchan committed
1913
        ret._predictor = self._predictor
1914
        ret.pandas_categorical = self.pandas_categorical
1915
        ret.used_indices = sorted(used_indices)
wxchan's avatar
wxchan committed
1916
1917
        return ret

1918
    def save_binary(self, filename: Union[str, Path]) -> "Dataset":
1919
        """Save Dataset to a binary file.
wxchan's avatar
wxchan committed
1920

1921
1922
1923
1924
1925
        .. note::

            Please note that `init_score` is not saved in binary file.
            If you need it, please set it again after loading Dataset.

wxchan's avatar
wxchan committed
1926
1927
        Parameters
        ----------
1928
        filename : str or pathlib.Path
wxchan's avatar
wxchan committed
1929
            Name of the output file.
Nikita Titov's avatar
Nikita Titov committed
1930
1931
1932
1933
1934

        Returns
        -------
        self : Dataset
            Returns self.
wxchan's avatar
wxchan committed
1935
1936
1937
        """
        _safe_call(_LIB.LGBM_DatasetSaveBinary(
            self.construct().handle,
1938
            c_str(str(filename))))
Nikita Titov's avatar
Nikita Titov committed
1939
        return self
wxchan's avatar
wxchan committed
1940
1941

    def _update_params(self, params):
1942
1943
        if not params:
            return self
1944
        params = deepcopy(params)
1945
1946
1947
1948
1949

        def update():
            if not self.params:
                self.params = params
            else:
1950
                self.params_back_up = deepcopy(self.params)
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
                self.params.update(params)

        if self.handle is None:
            update()
        elif params is not None:
            ret = _LIB.LGBM_DatasetUpdateParamChecking(
                c_str(param_dict_to_str(self.params)),
                c_str(param_dict_to_str(params)))
            if ret != 0:
                # could be updated if data is not freed
                if self.data is not None:
                    update()
                    self._free_handle()
                else:
1965
                    raise LightGBMError(_LIB.LGBM_GetLastError().decode('utf-8'))
Nikita Titov's avatar
Nikita Titov committed
1966
        return self
wxchan's avatar
wxchan committed
1967

1968
    def _reverse_update_params(self) -> "Dataset":
1969
        if self.handle is None:
1970
            self.params = deepcopy(self.params_back_up)
1971
            self.params_back_up = None
Nikita Titov's avatar
Nikita Titov committed
1972
        return self
1973

wxchan's avatar
wxchan committed
1974
    def set_field(self, field_name, data):
wxchan's avatar
wxchan committed
1975
        """Set property into the Dataset.
wxchan's avatar
wxchan committed
1976
1977
1978

        Parameters
        ----------
1979
        field_name : str
1980
            The field name of the information.
1981
1982
        data : list, list of lists (for multi-class task), numpy array, pandas Series, pandas DataFrame (for multi-class task), or None
            The data to be set.
Nikita Titov's avatar
Nikita Titov committed
1983
1984
1985
1986
1987

        Returns
        -------
        self : Dataset
            Dataset with set property.
wxchan's avatar
wxchan committed
1988
        """
1989
        if self.handle is None:
1990
            raise Exception(f"Cannot set {field_name} before construct dataset")
wxchan's avatar
wxchan committed
1991
        if data is None:
1992
            # set to None
wxchan's avatar
wxchan committed
1993
1994
1995
1996
            _safe_call(_LIB.LGBM_DatasetSetField(
                self.handle,
                c_str(field_name),
                None,
Guolin Ke's avatar
Guolin Ke committed
1997
1998
                ctypes.c_int(0),
                ctypes.c_int(FIELD_TYPE_MAPPER[field_name])))
Nikita Titov's avatar
Nikita Titov committed
1999
            return self
2000
        if field_name == 'init_score':
Guolin Ke's avatar
Guolin Ke committed
2001
            dtype = np.float64
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
            if _is_1d_collection(data):
                data = list_to_1d_numpy(data, dtype, name=field_name)
            elif _is_2d_collection(data):
                data = _data_to_2d_numpy(data, dtype, name=field_name)
                data = data.ravel(order='F')
            else:
                raise TypeError(
                    'init_score must be list, numpy 1-D array or pandas Series.\n'
                    'In multiclass classification init_score can also be a list of lists, numpy 2-D array or pandas DataFrame.'
                )
        else:
            dtype = np.int32 if field_name == 'group' else np.float32
            data = list_to_1d_numpy(data, dtype, name=field_name)

2016
2017
        if data.dtype == np.float32 or data.dtype == np.float64:
            ptr_data, type_data, _ = c_float_array(data)
wxchan's avatar
wxchan committed
2018
        elif data.dtype == np.int32:
2019
            ptr_data, type_data, _ = c_int_array(data)
wxchan's avatar
wxchan committed
2020
        else:
2021
            raise TypeError(f"Expected np.float32/64 or np.int32, met type({data.dtype})")
wxchan's avatar
wxchan committed
2022
        if type_data != FIELD_TYPE_MAPPER[field_name]:
2023
            raise TypeError("Input type error for set_field")
wxchan's avatar
wxchan committed
2024
2025
2026
2027
        _safe_call(_LIB.LGBM_DatasetSetField(
            self.handle,
            c_str(field_name),
            ptr_data,
Guolin Ke's avatar
Guolin Ke committed
2028
2029
            ctypes.c_int(len(data)),
            ctypes.c_int(type_data)))
2030
        self.version += 1
Nikita Titov's avatar
Nikita Titov committed
2031
        return self
wxchan's avatar
wxchan committed
2032

2033
    def get_field(self, field_name: str) -> Optional[np.ndarray]:
wxchan's avatar
wxchan committed
2034
        """Get property from the Dataset.
wxchan's avatar
wxchan committed
2035
2036
2037

        Parameters
        ----------
2038
        field_name : str
2039
            The field name of the information.
wxchan's avatar
wxchan committed
2040
2041
2042

        Returns
        -------
2043
        info : numpy array or None
2044
            A numpy array with information from the Dataset.
Guolin Ke's avatar
Guolin Ke committed
2045
        """
2046
        if self.handle is None:
2047
            raise Exception(f"Cannot get {field_name} before construct Dataset")
2048
2049
        tmp_out_len = ctypes.c_int(0)
        out_type = ctypes.c_int(0)
wxchan's avatar
wxchan committed
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
        ret = ctypes.POINTER(ctypes.c_void_p)()
        _safe_call(_LIB.LGBM_DatasetGetField(
            self.handle,
            c_str(field_name),
            ctypes.byref(tmp_out_len),
            ctypes.byref(ret),
            ctypes.byref(out_type)))
        if out_type.value != FIELD_TYPE_MAPPER[field_name]:
            raise TypeError("Return type error for get_field")
        if tmp_out_len.value == 0:
            return None
        if out_type.value == C_API_DTYPE_INT32:
2062
            arr = cint32_array_to_numpy(ctypes.cast(ret, ctypes.POINTER(ctypes.c_int32)), tmp_out_len.value)
wxchan's avatar
wxchan committed
2063
        elif out_type.value == C_API_DTYPE_FLOAT32:
2064
            arr = cfloat32_array_to_numpy(ctypes.cast(ret, ctypes.POINTER(ctypes.c_float)), tmp_out_len.value)
Guolin Ke's avatar
Guolin Ke committed
2065
        elif out_type.value == C_API_DTYPE_FLOAT64:
2066
            arr = cfloat64_array_to_numpy(ctypes.cast(ret, ctypes.POINTER(ctypes.c_double)), tmp_out_len.value)
2067
        else:
wxchan's avatar
wxchan committed
2068
            raise TypeError("Unknown type")
2069
2070
2071
2072
2073
2074
        if field_name == 'init_score':
            num_data = self.num_data()
            num_classes = arr.size // num_data
            if num_classes > 1:
                arr = arr.reshape((num_data, num_classes), order='F')
        return arr
Guolin Ke's avatar
Guolin Ke committed
2075

2076
2077
2078
2079
    def set_categorical_feature(
        self,
        categorical_feature: Union[List[int], List[str]]
    ) -> "Dataset":
2080
        """Set categorical features.
2081
2082
2083

        Parameters
        ----------
2084
        categorical_feature : list of int or str
2085
            Names or indices of categorical features.
Nikita Titov's avatar
Nikita Titov committed
2086
2087
2088
2089
2090

        Returns
        -------
        self : Dataset
            Dataset with set categorical features.
2091
2092
        """
        if self.categorical_feature == categorical_feature:
Nikita Titov's avatar
Nikita Titov committed
2093
            return self
2094
        if self.data is not None:
2095
2096
            if self.categorical_feature is None:
                self.categorical_feature = categorical_feature
Nikita Titov's avatar
Nikita Titov committed
2097
                return self._free_handle()
2098
            elif categorical_feature == 'auto':
Nikita Titov's avatar
Nikita Titov committed
2099
                return self
2100
            else:
2101
2102
2103
                if self.categorical_feature != 'auto':
                    _log_warning('categorical_feature in Dataset is overridden.\n'
                                 f'New categorical_feature is {sorted(list(categorical_feature))}')
2104
                self.categorical_feature = categorical_feature
Nikita Titov's avatar
Nikita Titov committed
2105
                return self._free_handle()
2106
        else:
2107
2108
            raise LightGBMError("Cannot set categorical feature after freed raw data, "
                                "set free_raw_data=False when construct Dataset to avoid this.")
2109

Guolin Ke's avatar
Guolin Ke committed
2110
    def _set_predictor(self, predictor):
2111
2112
2113
2114
        """Set predictor for continued training.

        It is not recommended for user to call this function.
        Please use init_model argument in engine.train() or engine.cv() instead.
Guolin Ke's avatar
Guolin Ke committed
2115
        """
2116
        if predictor is self._predictor and (predictor is None or predictor.current_iteration() == self._predictor.current_iteration()):
Nikita Titov's avatar
Nikita Titov committed
2117
            return self
2118
        if self.handle is None:
Guolin Ke's avatar
Guolin Ke committed
2119
            self._predictor = predictor
2120
2121
2122
2123
2124
2125
        elif self.data is not None:
            self._predictor = predictor
            self._set_init_score_by_predictor(self._predictor, self.data)
        elif self.used_indices is not None and self.reference is not None and self.reference.data is not None:
            self._predictor = predictor
            self._set_init_score_by_predictor(self._predictor, self.reference.data, self.used_indices)
Guolin Ke's avatar
Guolin Ke committed
2126
        else:
2127
2128
            raise LightGBMError("Cannot set predictor after freed raw data, "
                                "set free_raw_data=False when construct Dataset to avoid this.")
2129
        return self
Guolin Ke's avatar
Guolin Ke committed
2130
2131

    def set_reference(self, reference):
2132
        """Set reference Dataset.
Guolin Ke's avatar
Guolin Ke committed
2133
2134
2135
2136

        Parameters
        ----------
        reference : Dataset
2137
            Reference that is used as a template to construct the current Dataset.
Nikita Titov's avatar
Nikita Titov committed
2138
2139
2140
2141
2142

        Returns
        -------
        self : Dataset
            Dataset with set reference.
Guolin Ke's avatar
Guolin Ke committed
2143
        """
2144
2145
2146
        self.set_categorical_feature(reference.categorical_feature) \
            .set_feature_name(reference.feature_name) \
            ._set_predictor(reference._predictor)
2147
        # we're done if self and reference share a common upstream reference
2148
        if self.get_ref_chain().intersection(reference.get_ref_chain()):
Nikita Titov's avatar
Nikita Titov committed
2149
            return self
Guolin Ke's avatar
Guolin Ke committed
2150
2151
        if self.data is not None:
            self.reference = reference
Nikita Titov's avatar
Nikita Titov committed
2152
            return self._free_handle()
Guolin Ke's avatar
Guolin Ke committed
2153
        else:
2154
2155
            raise LightGBMError("Cannot set reference after freed raw data, "
                                "set free_raw_data=False when construct Dataset to avoid this.")
Guolin Ke's avatar
Guolin Ke committed
2156

2157
    def set_feature_name(self, feature_name: List[str]) -> "Dataset":
2158
        """Set feature name.
Guolin Ke's avatar
Guolin Ke committed
2159
2160
2161

        Parameters
        ----------
2162
        feature_name : list of str
2163
            Feature names.
Nikita Titov's avatar
Nikita Titov committed
2164
2165
2166
2167
2168

        Returns
        -------
        self : Dataset
            Dataset with set feature name.
Guolin Ke's avatar
Guolin Ke committed
2169
        """
2170
2171
        if feature_name != 'auto':
            self.feature_name = feature_name
2172
        if self.handle is not None and feature_name is not None and feature_name != 'auto':
wxchan's avatar
wxchan committed
2173
            if len(feature_name) != self.num_feature():
2174
                raise ValueError(f"Length of feature_name({len(feature_name)}) and num_feature({self.num_feature()}) don't match")
2175
            c_feature_name = [c_str(name) for name in feature_name]
wxchan's avatar
wxchan committed
2176
2177
2178
            _safe_call(_LIB.LGBM_DatasetSetFeatureNames(
                self.handle,
                c_array(ctypes.c_char_p, c_feature_name),
Guolin Ke's avatar
Guolin Ke committed
2179
                ctypes.c_int(len(feature_name))))
Nikita Titov's avatar
Nikita Titov committed
2180
        return self
Guolin Ke's avatar
Guolin Ke committed
2181
2182

    def set_label(self, label):
2183
        """Set label of Dataset.
Guolin Ke's avatar
Guolin Ke committed
2184
2185
2186

        Parameters
        ----------
2187
        label : list, numpy 1-D array, pandas Series / one-column DataFrame or None
2188
            The label information to be set into Dataset.
Nikita Titov's avatar
Nikita Titov committed
2189
2190
2191
2192
2193

        Returns
        -------
        self : Dataset
            Dataset with set label.
Guolin Ke's avatar
Guolin Ke committed
2194
2195
        """
        self.label = label
2196
        if self.handle is not None:
2197
            label = list_to_1d_numpy(_label_from_pandas(label), name='label')
wxchan's avatar
wxchan committed
2198
            self.set_field('label', label)
2199
            self.label = self.get_field('label')  # original values can be modified at cpp side
Nikita Titov's avatar
Nikita Titov committed
2200
        return self
Guolin Ke's avatar
Guolin Ke committed
2201
2202

    def set_weight(self, weight):
2203
        """Set weight of each instance.
Guolin Ke's avatar
Guolin Ke committed
2204
2205
2206

        Parameters
        ----------
2207
        weight : list, numpy 1-D array, pandas Series or None
2208
            Weight to be set for each data point. Weights should be non-negative.
Nikita Titov's avatar
Nikita Titov committed
2209
2210
2211
2212
2213

        Returns
        -------
        self : Dataset
            Dataset with set weight.
Guolin Ke's avatar
Guolin Ke committed
2214
        """
2215
2216
        if weight is not None and np.all(weight == 1):
            weight = None
Guolin Ke's avatar
Guolin Ke committed
2217
        self.weight = weight
2218
        if self.handle is not None and weight is not None:
wxchan's avatar
wxchan committed
2219
2220
            weight = list_to_1d_numpy(weight, name='weight')
            self.set_field('weight', weight)
2221
            self.weight = self.get_field('weight')  # original values can be modified at cpp side
Nikita Titov's avatar
Nikita Titov committed
2222
        return self
Guolin Ke's avatar
Guolin Ke committed
2223
2224

    def set_init_score(self, init_score):
2225
        """Set init score of Booster to start from.
Guolin Ke's avatar
Guolin Ke committed
2226
2227
2228

        Parameters
        ----------
2229
        init_score : list, list of lists (for multi-class task), numpy array, pandas Series, pandas DataFrame (for multi-class task), or None
2230
            Init score for Booster.
Nikita Titov's avatar
Nikita Titov committed
2231
2232
2233
2234
2235

        Returns
        -------
        self : Dataset
            Dataset with set init score.
Guolin Ke's avatar
Guolin Ke committed
2236
2237
        """
        self.init_score = init_score
2238
        if self.handle is not None and init_score is not None:
wxchan's avatar
wxchan committed
2239
            self.set_field('init_score', init_score)
2240
            self.init_score = self.get_field('init_score')  # original values can be modified at cpp side
Nikita Titov's avatar
Nikita Titov committed
2241
        return self
Guolin Ke's avatar
Guolin Ke committed
2242
2243

    def set_group(self, group):
2244
        """Set group size of Dataset (used for ranking).
Guolin Ke's avatar
Guolin Ke committed
2245
2246
2247

        Parameters
        ----------
2248
        group : list, numpy 1-D array, pandas Series or None
2249
2250
2251
            Group/query data.
            Only used in the learning-to-rank task.
            sum(group) = n_samples.
2252
2253
            For example, if you have a 100-document dataset with ``group = [10, 20, 40, 10, 10, 10]``, that means that you have 6 groups,
            where the first 10 records are in the first group, records 11-30 are in the second group, records 31-70 are in the third group, etc.
Nikita Titov's avatar
Nikita Titov committed
2254
2255
2256
2257
2258

        Returns
        -------
        self : Dataset
            Dataset with set group.
Guolin Ke's avatar
Guolin Ke committed
2259
2260
        """
        self.group = group
2261
        if self.handle is not None and group is not None:
wxchan's avatar
wxchan committed
2262
2263
            group = list_to_1d_numpy(group, np.int32, name='group')
            self.set_field('group', group)
Nikita Titov's avatar
Nikita Titov committed
2264
        return self
Guolin Ke's avatar
Guolin Ke committed
2265

2266
    def get_feature_name(self) -> List[str]:
2267
2268
2269
2270
        """Get the names of columns (features) in the Dataset.

        Returns
        -------
2271
        feature_names : list of str
2272
2273
2274
2275
2276
2277
2278
2279
            The names of columns (features) in the Dataset.
        """
        if self.handle is None:
            raise LightGBMError("Cannot get feature_name before construct dataset")
        num_feature = self.num_feature()
        tmp_out_len = ctypes.c_int(0)
        reserved_string_buffer_size = 255
        required_string_buffer_size = ctypes.c_size_t(0)
2280
        string_buffers = [ctypes.create_string_buffer(reserved_string_buffer_size) for _ in range(num_feature)]
2281
2282
2283
        ptr_string_buffers = (ctypes.c_char_p * num_feature)(*map(ctypes.addressof, string_buffers))
        _safe_call(_LIB.LGBM_DatasetGetFeatureNames(
            self.handle,
2284
            ctypes.c_int(num_feature),
2285
            ctypes.byref(tmp_out_len),
2286
            ctypes.c_size_t(reserved_string_buffer_size),
2287
2288
2289
2290
            ctypes.byref(required_string_buffer_size),
            ptr_string_buffers))
        if num_feature != tmp_out_len.value:
            raise ValueError("Length of feature names doesn't equal with num_feature")
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
        actual_string_buffer_size = required_string_buffer_size.value
        # if buffer length is not long enough, reallocate buffers
        if reserved_string_buffer_size < actual_string_buffer_size:
            string_buffers = [ctypes.create_string_buffer(actual_string_buffer_size) for _ in range(num_feature)]
            ptr_string_buffers = (ctypes.c_char_p * num_feature)(*map(ctypes.addressof, string_buffers))
            _safe_call(_LIB.LGBM_DatasetGetFeatureNames(
                self.handle,
                ctypes.c_int(num_feature),
                ctypes.byref(tmp_out_len),
                ctypes.c_size_t(actual_string_buffer_size),
                ctypes.byref(required_string_buffer_size),
                ptr_string_buffers))
2303
        return [string_buffers[i].value.decode('utf-8') for i in range(num_feature)]
2304

Guolin Ke's avatar
Guolin Ke committed
2305
    def get_label(self):
2306
        """Get the label of the Dataset.
Guolin Ke's avatar
Guolin Ke committed
2307
2308
2309

        Returns
        -------
Nikita Titov's avatar
Nikita Titov committed
2310
        label : numpy array or None
2311
            The label information from the Dataset.
Guolin Ke's avatar
Guolin Ke committed
2312
        """
2313
        if self.label is None:
wxchan's avatar
wxchan committed
2314
            self.label = self.get_field('label')
Guolin Ke's avatar
Guolin Ke committed
2315
2316
2317
        return self.label

    def get_weight(self):
2318
        """Get the weight of the Dataset.
Guolin Ke's avatar
Guolin Ke committed
2319
2320
2321

        Returns
        -------
Nikita Titov's avatar
Nikita Titov committed
2322
        weight : numpy array or None
2323
            Weight for each data point from the Dataset. Weights should be non-negative.
Guolin Ke's avatar
Guolin Ke committed
2324
        """
2325
        if self.weight is None:
wxchan's avatar
wxchan committed
2326
            self.weight = self.get_field('weight')
Guolin Ke's avatar
Guolin Ke committed
2327
2328
2329
        return self.weight

    def get_init_score(self):
2330
        """Get the initial score of the Dataset.
Guolin Ke's avatar
Guolin Ke committed
2331
2332
2333

        Returns
        -------
Nikita Titov's avatar
Nikita Titov committed
2334
        init_score : numpy array or None
2335
            Init score of Booster.
Guolin Ke's avatar
Guolin Ke committed
2336
        """
2337
        if self.init_score is None:
wxchan's avatar
wxchan committed
2338
            self.init_score = self.get_field('init_score')
Guolin Ke's avatar
Guolin Ke committed
2339
2340
        return self.init_score

2341
2342
2343
2344
2345
    def get_data(self):
        """Get the raw data of the Dataset.

        Returns
        -------
2346
        data : str, pathlib.Path, numpy array, pandas DataFrame, H2O DataTable's Frame, scipy.sparse, Sequence, list of Sequence or list of numpy array or None
2347
2348
2349
2350
            Raw data used in the Dataset construction.
        """
        if self.handle is None:
            raise Exception("Cannot get data before construct Dataset")
Guolin Ke's avatar
Guolin Ke committed
2351
2352
2353
2354
2355
        if self.need_slice and self.used_indices is not None and self.reference is not None:
            self.data = self.reference.data
            if self.data is not None:
                if isinstance(self.data, np.ndarray) or scipy.sparse.issparse(self.data):
                    self.data = self.data[self.used_indices, :]
2356
                elif isinstance(self.data, pd_DataFrame):
Guolin Ke's avatar
Guolin Ke committed
2357
                    self.data = self.data.iloc[self.used_indices].copy()
2358
                elif isinstance(self.data, dt_DataTable):
Guolin Ke's avatar
Guolin Ke committed
2359
                    self.data = self.data[self.used_indices, :]
2360
2361
2362
2363
                elif isinstance(self.data, Sequence):
                    self.data = self.data[self.used_indices]
                elif isinstance(self.data, list) and len(self.data) > 0 and all(isinstance(x, Sequence) for x in self.data):
                    self.data = np.array([row for row in self._yield_row_from_seqlist(self.data, self.used_indices)])
Guolin Ke's avatar
Guolin Ke committed
2364
                else:
2365
2366
                    _log_warning(f"Cannot subset {type(self.data).__name__} type of raw data.\n"
                                 "Returning original raw data")
2367
            self.need_slice = False
Guolin Ke's avatar
Guolin Ke committed
2368
2369
2370
        if self.data is None:
            raise LightGBMError("Cannot call `get_data` after freed raw data, "
                                "set free_raw_data=False when construct Dataset to avoid this.")
2371
2372
        return self.data

Guolin Ke's avatar
Guolin Ke committed
2373
    def get_group(self):
2374
        """Get the group of the Dataset.
Guolin Ke's avatar
Guolin Ke committed
2375
2376
2377

        Returns
        -------
Nikita Titov's avatar
Nikita Titov committed
2378
        group : numpy array or None
2379
2380
2381
            Group/query data.
            Only used in the learning-to-rank task.
            sum(group) = n_samples.
2382
2383
            For example, if you have a 100-document dataset with ``group = [10, 20, 40, 10, 10, 10]``, that means that you have 6 groups,
            where the first 10 records are in the first group, records 11-30 are in the second group, records 31-70 are in the third group, etc.
Guolin Ke's avatar
Guolin Ke committed
2384
        """
2385
        if self.group is None:
wxchan's avatar
wxchan committed
2386
            self.group = self.get_field('group')
Guolin Ke's avatar
Guolin Ke committed
2387
2388
            if self.group is not None:
                # group data from LightGBM is boundaries data, need to convert to group size
Nikita Titov's avatar
Nikita Titov committed
2389
                self.group = np.diff(self.group)
Guolin Ke's avatar
Guolin Ke committed
2390
2391
        return self.group

2392
    def num_data(self) -> int:
2393
        """Get the number of rows in the Dataset.
Guolin Ke's avatar
Guolin Ke committed
2394
2395
2396

        Returns
        -------
2397
2398
        number_of_rows : int
            The number of rows in the Dataset.
Guolin Ke's avatar
Guolin Ke committed
2399
        """
2400
        if self.handle is not None:
2401
            ret = ctypes.c_int(0)
wxchan's avatar
wxchan committed
2402
2403
2404
            _safe_call(_LIB.LGBM_DatasetGetNumData(self.handle,
                                                   ctypes.byref(ret)))
            return ret.value
Guolin Ke's avatar
Guolin Ke committed
2405
        else:
2406
            raise LightGBMError("Cannot get num_data before construct dataset")
Guolin Ke's avatar
Guolin Ke committed
2407

2408
    def num_feature(self) -> int:
2409
        """Get the number of columns (features) in the Dataset.
Guolin Ke's avatar
Guolin Ke committed
2410
2411
2412

        Returns
        -------
2413
2414
        number_of_columns : int
            The number of columns (features) in the Dataset.
Guolin Ke's avatar
Guolin Ke committed
2415
        """
2416
        if self.handle is not None:
2417
            ret = ctypes.c_int(0)
wxchan's avatar
wxchan committed
2418
2419
2420
            _safe_call(_LIB.LGBM_DatasetGetNumFeature(self.handle,
                                                      ctypes.byref(ret)))
            return ret.value
Guolin Ke's avatar
Guolin Ke committed
2421
        else:
2422
            raise LightGBMError("Cannot get num_feature before construct dataset")
Guolin Ke's avatar
Guolin Ke committed
2423

2424
    def feature_num_bin(self, feature: Union[int, str]) -> int:
2425
2426
2427
2428
        """Get the number of bins for a feature.

        Parameters
        ----------
2429
2430
        feature : int or str
            Index or name of the feature.
2431
2432
2433
2434
2435
2436
2437

        Returns
        -------
        number_of_bins : int
            The number of constructed bins for the feature in the Dataset.
        """
        if self.handle is not None:
2438
2439
            if isinstance(feature, str):
                feature = self.feature_name.index(feature)
2440
2441
2442
2443
2444
2445
2446
2447
            ret = ctypes.c_int(0)
            _safe_call(_LIB.LGBM_DatasetGetFeatureNumBin(self.handle,
                                                         ctypes.c_int(feature),
                                                         ctypes.byref(ret)))
            return ret.value
        else:
            raise LightGBMError("Cannot get feature_num_bin before construct dataset")

2448
    def get_ref_chain(self, ref_limit=100):
2449
2450
2451
2452
2453
        """Get a chain of Dataset objects.

        Starts with r, then goes to r.reference (if exists),
        then to r.reference.reference, etc.
        until we hit ``ref_limit`` or a reference loop.
2454
2455
2456
2457
2458

        Parameters
        ----------
        ref_limit : int, optional (default=100)
            The limit number of references.
2459
2460
2461

        Returns
        -------
2462
2463
2464
        ref_chain : set of Dataset
            Chain of references of the Datasets.
        """
2465
        head = self
2466
        ref_chain = set()
2467
2468
        while len(ref_chain) < ref_limit:
            if isinstance(head, Dataset):
2469
                ref_chain.add(head)
2470
2471
2472
2473
2474
2475
                if (head.reference is not None) and (head.reference not in ref_chain):
                    head = head.reference
                else:
                    break
            else:
                break
Nikita Titov's avatar
Nikita Titov committed
2476
        return ref_chain
2477

2478
    def add_features_from(self, other: "Dataset") -> "Dataset":
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
        """Add features from other Dataset to the current Dataset.

        Both Datasets must be constructed before calling this method.

        Parameters
        ----------
        other : Dataset
            The Dataset to take features from.

        Returns
        -------
        self : Dataset
            Dataset with the new features added.
        """
        if self.handle is None or other.handle is None:
            raise ValueError('Both source and target Datasets must be constructed before adding features')
        _safe_call(_LIB.LGBM_DatasetAddFeaturesFrom(self.handle, other.handle))
Guolin Ke's avatar
Guolin Ke committed
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
        was_none = self.data is None
        old_self_data_type = type(self.data).__name__
        if other.data is None:
            self.data = None
        elif self.data is not None:
            if isinstance(self.data, np.ndarray):
                if isinstance(other.data, np.ndarray):
                    self.data = np.hstack((self.data, other.data))
                elif scipy.sparse.issparse(other.data):
                    self.data = np.hstack((self.data, other.data.toarray()))
2506
                elif isinstance(other.data, pd_DataFrame):
Guolin Ke's avatar
Guolin Ke committed
2507
                    self.data = np.hstack((self.data, other.data.values))
2508
                elif isinstance(other.data, dt_DataTable):
Guolin Ke's avatar
Guolin Ke committed
2509
2510
2511
2512
2513
2514
2515
                    self.data = np.hstack((self.data, other.data.to_numpy()))
                else:
                    self.data = None
            elif scipy.sparse.issparse(self.data):
                sparse_format = self.data.getformat()
                if isinstance(other.data, np.ndarray) or scipy.sparse.issparse(other.data):
                    self.data = scipy.sparse.hstack((self.data, other.data), format=sparse_format)
2516
                elif isinstance(other.data, pd_DataFrame):
Guolin Ke's avatar
Guolin Ke committed
2517
                    self.data = scipy.sparse.hstack((self.data, other.data.values), format=sparse_format)
2518
                elif isinstance(other.data, dt_DataTable):
Guolin Ke's avatar
Guolin Ke committed
2519
2520
2521
                    self.data = scipy.sparse.hstack((self.data, other.data.to_numpy()), format=sparse_format)
                else:
                    self.data = None
2522
            elif isinstance(self.data, pd_DataFrame):
Guolin Ke's avatar
Guolin Ke committed
2523
2524
                if not PANDAS_INSTALLED:
                    raise LightGBMError("Cannot add features to DataFrame type of raw data "
2525
2526
                                        "without pandas installed. "
                                        "Install pandas and restart your session.")
Guolin Ke's avatar
Guolin Ke committed
2527
                if isinstance(other.data, np.ndarray):
2528
                    self.data = concat((self.data, pd_DataFrame(other.data)),
Guolin Ke's avatar
Guolin Ke committed
2529
2530
                                       axis=1, ignore_index=True)
                elif scipy.sparse.issparse(other.data):
2531
                    self.data = concat((self.data, pd_DataFrame(other.data.toarray())),
Guolin Ke's avatar
Guolin Ke committed
2532
                                       axis=1, ignore_index=True)
2533
                elif isinstance(other.data, pd_DataFrame):
Guolin Ke's avatar
Guolin Ke committed
2534
2535
                    self.data = concat((self.data, other.data),
                                       axis=1, ignore_index=True)
2536
2537
                elif isinstance(other.data, dt_DataTable):
                    self.data = concat((self.data, pd_DataFrame(other.data.to_numpy())),
Guolin Ke's avatar
Guolin Ke committed
2538
2539
2540
                                       axis=1, ignore_index=True)
                else:
                    self.data = None
2541
            elif isinstance(self.data, dt_DataTable):
Guolin Ke's avatar
Guolin Ke committed
2542
                if isinstance(other.data, np.ndarray):
2543
                    self.data = dt_DataTable(np.hstack((self.data.to_numpy(), other.data)))
Guolin Ke's avatar
Guolin Ke committed
2544
                elif scipy.sparse.issparse(other.data):
2545
2546
2547
2548
2549
                    self.data = dt_DataTable(np.hstack((self.data.to_numpy(), other.data.toarray())))
                elif isinstance(other.data, pd_DataFrame):
                    self.data = dt_DataTable(np.hstack((self.data.to_numpy(), other.data.values)))
                elif isinstance(other.data, dt_DataTable):
                    self.data = dt_DataTable(np.hstack((self.data.to_numpy(), other.data.to_numpy())))
Guolin Ke's avatar
Guolin Ke committed
2550
2551
2552
2553
2554
                else:
                    self.data = None
            else:
                self.data = None
        if self.data is None:
2555
2556
            err_msg = (f"Cannot add features from {type(other.data).__name__} type of raw data to "
                       f"{old_self_data_type} type of raw data.\n")
Guolin Ke's avatar
Guolin Ke committed
2557
2558
            err_msg += ("Set free_raw_data=False when construct Dataset to avoid this"
                        if was_none else "Freeing raw data")
2559
            _log_warning(err_msg)
Guolin Ke's avatar
Guolin Ke committed
2560
        self.feature_name = self.get_feature_name()
2561
2562
        _log_warning("Reseting categorical features.\n"
                     "You can set new categorical features via ``set_categorical_feature`` method")
Guolin Ke's avatar
Guolin Ke committed
2563
2564
        self.categorical_feature = "auto"
        self.pandas_categorical = None
2565
2566
        return self

2567
    def _dump_text(self, filename: Union[str, Path]) -> "Dataset":
2568
2569
2570
2571
2572
2573
        """Save Dataset to a text file.

        This format cannot be loaded back in by LightGBM, but is useful for debugging purposes.

        Parameters
        ----------
2574
        filename : str or pathlib.Path
2575
2576
2577
2578
2579
2580
2581
2582
2583
            Name of the output file.

        Returns
        -------
        self : Dataset
            Returns self.
        """
        _safe_call(_LIB.LGBM_DatasetDumpText(
            self.construct().handle,
2584
            c_str(str(filename))))
2585
2586
        return self

wxchan's avatar
wxchan committed
2587

2588
2589
2590
2591
2592
2593
_LGBM_CustomObjectiveFunction = Callable[
    [np.ndarray, Dataset],
    Tuple[np.ndarray, np.ndarray]
]


2594
class Booster:
2595
    """Booster in LightGBM."""
2596

2597
2598
2599
2600
2601
2602
2603
    def __init__(
        self,
        params: Optional[Dict[str, Any]] = None,
        train_set: Optional[Dataset] = None,
        model_file: Optional[Union[str, Path]] = None,
        model_str: Optional[str] = None
    ):
2604
        """Initialize the Booster.
wxchan's avatar
wxchan committed
2605
2606
2607

        Parameters
        ----------
Nikita Titov's avatar
Nikita Titov committed
2608
        params : dict or None, optional (default=None)
2609
2610
2611
            Parameters for Booster.
        train_set : Dataset or None, optional (default=None)
            Training dataset.
2612
        model_file : str, pathlib.Path or None, optional (default=None)
wxchan's avatar
wxchan committed
2613
            Path to the model file.
2614
        model_str : str or None, optional (default=None)
2615
            Model will be loaded from this string.
wxchan's avatar
wxchan committed
2616
        """
2617
        self.handle = None
2618
        self.network = False
wxchan's avatar
wxchan committed
2619
        self.__need_reload_eval_info = True
2620
        self._train_data_name = "training"
2621
        self.__set_objective_to_none = False
wxchan's avatar
wxchan committed
2622
        self.best_iteration = -1
wxchan's avatar
wxchan committed
2623
        self.best_score = {}
2624
        params = {} if params is None else deepcopy(params)
wxchan's avatar
wxchan committed
2625
        if train_set is not None:
2626
            # Training task
wxchan's avatar
wxchan committed
2627
            if not isinstance(train_set, Dataset):
2628
                raise TypeError(f'Training data should be Dataset instance, met {type(train_set).__name__}')
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
            params = _choose_param_value(
                main_param_name="machines",
                params=params,
                default_value=None
            )
            # if "machines" is given, assume user wants to do distributed learning, and set up network
            if params["machines"] is None:
                params.pop("machines", None)
            else:
                machines = params["machines"]
                if isinstance(machines, str):
                    num_machines_from_machine_list = len(machines.split(','))
                elif isinstance(machines, (list, set)):
                    num_machines_from_machine_list = len(machines)
                    machines = ','.join(machines)
                else:
                    raise ValueError("Invalid machines in params.")

                params = _choose_param_value(
                    main_param_name="num_machines",
                    params=params,
                    default_value=num_machines_from_machine_list
                )
                params = _choose_param_value(
                    main_param_name="local_listen_port",
                    params=params,
                    default_value=12400
                )
                self.set_network(
                    machines=machines,
                    local_listen_port=params["local_listen_port"],
                    listen_time_out=params.get("time_out", 120),
                    num_machines=params["num_machines"]
                )
2663
            # construct booster object
2664
2665
2666
2667
            train_set.construct()
            # copy the parameters from train_set
            params.update(train_set.get_params())
            params_str = param_dict_to_str(params)
2668
            self.handle = ctypes.c_void_p()
wxchan's avatar
wxchan committed
2669
            _safe_call(_LIB.LGBM_BoosterCreate(
2670
                train_set.handle,
wxchan's avatar
wxchan committed
2671
2672
                c_str(params_str),
                ctypes.byref(self.handle)))
2673
            # save reference to data
wxchan's avatar
wxchan committed
2674
2675
2676
2677
            self.train_set = train_set
            self.valid_sets = []
            self.name_valid_sets = []
            self.__num_dataset = 1
Guolin Ke's avatar
Guolin Ke committed
2678
2679
            self.__init_predictor = train_set._predictor
            if self.__init_predictor is not None:
wxchan's avatar
wxchan committed
2680
2681
                _safe_call(_LIB.LGBM_BoosterMerge(
                    self.handle,
Guolin Ke's avatar
Guolin Ke committed
2682
                    self.__init_predictor.handle))
Guolin Ke's avatar
Guolin Ke committed
2683
            out_num_class = ctypes.c_int(0)
wxchan's avatar
wxchan committed
2684
2685
2686
2687
            _safe_call(_LIB.LGBM_BoosterGetNumClasses(
                self.handle,
                ctypes.byref(out_num_class)))
            self.__num_class = out_num_class.value
2688
            # buffer for inner predict
wxchan's avatar
wxchan committed
2689
2690
2691
            self.__inner_predict_buffer = [None]
            self.__is_predicted_cur_iter = [False]
            self.__get_eval_info()
2692
            self.pandas_categorical = train_set.pandas_categorical
2693
            self.train_set_version = train_set.version
wxchan's avatar
wxchan committed
2694
        elif model_file is not None:
2695
            # Prediction task
Guolin Ke's avatar
Guolin Ke committed
2696
            out_num_iterations = ctypes.c_int(0)
2697
            self.handle = ctypes.c_void_p()
wxchan's avatar
wxchan committed
2698
            _safe_call(_LIB.LGBM_BoosterCreateFromModelfile(
2699
                c_str(str(model_file)),
wxchan's avatar
wxchan committed
2700
2701
                ctypes.byref(out_num_iterations),
                ctypes.byref(self.handle)))
Guolin Ke's avatar
Guolin Ke committed
2702
            out_num_class = ctypes.c_int(0)
wxchan's avatar
wxchan committed
2703
2704
2705
2706
            _safe_call(_LIB.LGBM_BoosterGetNumClasses(
                self.handle,
                ctypes.byref(out_num_class)))
            self.__num_class = out_num_class.value
2707
            self.pandas_categorical = _load_pandas_categorical(file_name=model_file)
2708
        elif model_str is not None:
2709
            self.model_from_string(model_str)
wxchan's avatar
wxchan committed
2710
        else:
2711
2712
            raise TypeError('Need at least one training dataset or model file or model string '
                            'to create Booster instance')
2713
        self.params = params
wxchan's avatar
wxchan committed
2714

2715
    def __del__(self) -> None:
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
        try:
            if self.network:
                self.free_network()
        except AttributeError:
            pass
        try:
            if self.handle is not None:
                _safe_call(_LIB.LGBM_BoosterFree(self.handle))
        except AttributeError:
            pass
wxchan's avatar
wxchan committed
2726

2727
    def __copy__(self) -> "Booster":
wxchan's avatar
wxchan committed
2728
2729
        return self.__deepcopy__(None)

2730
    def __deepcopy__(self, _) -> "Booster":
2731
        model_str = self.model_to_string(num_iteration=-1)
2732
        booster = Booster(model_str=model_str)
2733
        return booster
wxchan's avatar
wxchan committed
2734
2735
2736
2737
2738
2739
2740

    def __getstate__(self):
        this = self.__dict__.copy()
        handle = this['handle']
        this.pop('train_set', None)
        this.pop('valid_sets', None)
        if handle is not None:
2741
            this["handle"] = self.model_to_string(num_iteration=-1)
wxchan's avatar
wxchan committed
2742
2743
2744
        return this

    def __setstate__(self, state):
2745
2746
        model_str = state.get('handle', None)
        if model_str is not None:
wxchan's avatar
wxchan committed
2747
            handle = ctypes.c_void_p()
Guolin Ke's avatar
Guolin Ke committed
2748
            out_num_iterations = ctypes.c_int(0)
2749
2750
2751
2752
            _safe_call(_LIB.LGBM_BoosterLoadModelFromString(
                c_str(model_str),
                ctypes.byref(out_num_iterations),
                ctypes.byref(handle)))
wxchan's avatar
wxchan committed
2753
2754
2755
            state['handle'] = handle
        self.__dict__.update(state)

2756
    def free_dataset(self) -> "Booster":
Nikita Titov's avatar
Nikita Titov committed
2757
2758
2759
2760
2761
2762
2763
        """Free Booster's Datasets.

        Returns
        -------
        self : Booster
            Booster without Datasets.
        """
wxchan's avatar
wxchan committed
2764
2765
        self.__dict__.pop('train_set', None)
        self.__dict__.pop('valid_sets', None)
2766
        self.__num_dataset = 0
Nikita Titov's avatar
Nikita Titov committed
2767
        return self
wxchan's avatar
wxchan committed
2768

2769
    def _free_buffer(self) -> "Booster":
2770
2771
        self.__inner_predict_buffer = []
        self.__is_predicted_cur_iter = []
Nikita Titov's avatar
Nikita Titov committed
2772
        return self
2773

2774
2775
2776
2777
2778
2779
2780
    def set_network(
        self,
        machines: Union[List[str], Set[str], str],
        local_listen_port: int = 12400,
        listen_time_out: int = 120,
        num_machines: int = 1
    ) -> "Booster":
2781
2782
2783
2784
        """Set the network configuration.

        Parameters
        ----------
2785
        machines : list, set or str
2786
            Names of machines.
Nikita Titov's avatar
Nikita Titov committed
2787
        local_listen_port : int, optional (default=12400)
2788
            TCP listen port for local machines.
Nikita Titov's avatar
Nikita Titov committed
2789
        listen_time_out : int, optional (default=120)
2790
            Socket time-out in minutes.
Nikita Titov's avatar
Nikita Titov committed
2791
        num_machines : int, optional (default=1)
2792
            The number of machines for distributed learning application.
Nikita Titov's avatar
Nikita Titov committed
2793
2794
2795
2796
2797

        Returns
        -------
        self : Booster
            Booster with set network.
2798
        """
2799
2800
        if isinstance(machines, (list, set)):
            machines = ','.join(machines)
2801
2802
2803
2804
2805
        _safe_call(_LIB.LGBM_NetworkInit(c_str(machines),
                                         ctypes.c_int(local_listen_port),
                                         ctypes.c_int(listen_time_out),
                                         ctypes.c_int(num_machines)))
        self.network = True
Nikita Titov's avatar
Nikita Titov committed
2806
        return self
2807

2808
    def free_network(self) -> "Booster":
Nikita Titov's avatar
Nikita Titov committed
2809
2810
2811
2812
2813
2814
2815
        """Free Booster's network.

        Returns
        -------
        self : Booster
            Booster with freed network.
        """
2816
2817
        _safe_call(_LIB.LGBM_NetworkFree())
        self.network = False
Nikita Titov's avatar
Nikita Titov committed
2818
        return self
2819

2820
    def trees_to_dataframe(self) -> pd_DataFrame:
2821
2822
        """Parse the fitted model and return in an easy-to-read pandas DataFrame.

2823
2824
2825
2826
        The returned DataFrame has the following columns.

            - ``tree_index`` : int64, which tree a node belongs to. 0-based, so a value of ``6``, for example, means "this node is in the 7th tree".
            - ``node_depth`` : int64, how far a node is from the root of the tree. The root node has a value of ``1``, its direct children are ``2``, etc.
2827
2828
2829
2830
2831
            - ``node_index`` : str, unique identifier for a node.
            - ``left_child`` : str, ``node_index`` of the child node to the left of a split. ``None`` for leaf nodes.
            - ``right_child`` : str, ``node_index`` of the child node to the right of a split. ``None`` for leaf nodes.
            - ``parent_index`` : str, ``node_index`` of this node's parent. ``None`` for the root node.
            - ``split_feature`` : str, name of the feature used for splitting. ``None`` for leaf nodes.
2832
2833
            - ``split_gain`` : float64, gain from adding this split to the tree. ``NaN`` for leaf nodes.
            - ``threshold`` : float64, value of the feature used to decide which side of the split a record will go down. ``NaN`` for leaf nodes.
2834
            - ``decision_type`` : str, logical operator describing how to compare a value to ``threshold``.
2835
2836
              For example, ``split_feature = "Column_10", threshold = 15, decision_type = "<="`` means that
              records where ``Column_10 <= 15`` follow the left side of the split, otherwise follows the right side of the split. ``None`` for leaf nodes.
2837
2838
            - ``missing_direction`` : str, split direction that missing values should go to. ``None`` for leaf nodes.
            - ``missing_type`` : str, describes what types of values are treated as missing.
2839
            - ``value`` : float64, predicted value for this leaf node, multiplied by the learning rate.
2840
            - ``weight`` : float64 or int64, sum of Hessian (second-order derivative of objective), summed over observations that fall in this node.
2841
2842
            - ``count`` : int64, number of records in the training data that fall into this node.

2843
2844
2845
2846
2847
2848
        Returns
        -------
        result : pandas DataFrame
            Returns a pandas DataFrame of the parsed model.
        """
        if not PANDAS_INSTALLED:
2849
2850
            raise LightGBMError('This method cannot be run without pandas installed. '
                                'You must install pandas and restart your session to use this method.')
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861

        if self.num_trees() == 0:
            raise LightGBMError('There are no trees in this Booster and thus nothing to parse')

        def _is_split_node(tree):
            return 'split_index' in tree.keys()

        def create_node_record(tree, node_depth=1, tree_index=None,
                               feature_names=None, parent_node=None):

            def _get_node_index(tree, tree_index):
2862
                tree_num = f'{tree_index}-' if tree_index is not None else ''
2863
2864
2865
                is_split = _is_split_node(tree)
                node_type = 'S' if is_split else 'L'
                # if a single node tree it won't have `leaf_index` so return 0
2866
2867
                node_num = tree.get('split_index' if is_split else 'leaf_index', 0)
                return f"{tree_num}{node_type}{node_num}"
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879

            def _get_split_feature(tree, feature_names):
                if _is_split_node(tree):
                    if feature_names is not None:
                        feature_name = feature_names[tree['split_feature']]
                    else:
                        feature_name = tree['split_feature']
                else:
                    feature_name = None
                return feature_name

            def _is_single_node_tree(tree):
2880
                return set(tree.keys()) == {'leaf_value'}
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953

            # Create the node record, and populate universal data members
            node = OrderedDict()
            node['tree_index'] = tree_index
            node['node_depth'] = node_depth
            node['node_index'] = _get_node_index(tree, tree_index)
            node['left_child'] = None
            node['right_child'] = None
            node['parent_index'] = parent_node
            node['split_feature'] = _get_split_feature(tree, feature_names)
            node['split_gain'] = None
            node['threshold'] = None
            node['decision_type'] = None
            node['missing_direction'] = None
            node['missing_type'] = None
            node['value'] = None
            node['weight'] = None
            node['count'] = None

            # Update values to reflect node type (leaf or split)
            if _is_split_node(tree):
                node['left_child'] = _get_node_index(tree['left_child'], tree_index)
                node['right_child'] = _get_node_index(tree['right_child'], tree_index)
                node['split_gain'] = tree['split_gain']
                node['threshold'] = tree['threshold']
                node['decision_type'] = tree['decision_type']
                node['missing_direction'] = 'left' if tree['default_left'] else 'right'
                node['missing_type'] = tree['missing_type']
                node['value'] = tree['internal_value']
                node['weight'] = tree['internal_weight']
                node['count'] = tree['internal_count']
            else:
                node['value'] = tree['leaf_value']
                if not _is_single_node_tree(tree):
                    node['weight'] = tree['leaf_weight']
                    node['count'] = tree['leaf_count']

            return node

        def tree_dict_to_node_list(tree, node_depth=1, tree_index=None,
                                   feature_names=None, parent_node=None):

            node = create_node_record(tree,
                                      node_depth=node_depth,
                                      tree_index=tree_index,
                                      feature_names=feature_names,
                                      parent_node=parent_node)

            res = [node]

            if _is_split_node(tree):
                # traverse the next level of the tree
                children = ['left_child', 'right_child']
                for child in children:
                    subtree_list = tree_dict_to_node_list(
                        tree[child],
                        node_depth=node_depth + 1,
                        tree_index=tree_index,
                        feature_names=feature_names,
                        parent_node=node['node_index'])
                    # In tree format, "subtree_list" is a list of node records (dicts),
                    # and we add node to the list.
                    res.extend(subtree_list)
            return res

        model_dict = self.dump_model()
        feature_names = model_dict['feature_names']
        model_list = []
        for tree in model_dict['tree_info']:
            model_list.extend(tree_dict_to_node_list(tree['tree_structure'],
                                                     tree_index=tree['tree_index'],
                                                     feature_names=feature_names))

2954
        return pd_DataFrame(model_list, columns=model_list[0].keys())
2955

2956
    def set_train_data_name(self, name: str) -> "Booster":
2957
2958
2959
2960
        """Set the name to the training Dataset.

        Parameters
        ----------
2961
        name : str
Nikita Titov's avatar
Nikita Titov committed
2962
2963
2964
2965
2966
2967
            Name for the training Dataset.

        Returns
        -------
        self : Booster
            Booster with set training Dataset name.
2968
        """
2969
        self._train_data_name = name
Nikita Titov's avatar
Nikita Titov committed
2970
        return self
wxchan's avatar
wxchan committed
2971

2972
    def add_valid(self, data: Dataset, name: str) -> "Booster":
2973
        """Add validation data.
wxchan's avatar
wxchan committed
2974
2975
2976
2977

        Parameters
        ----------
        data : Dataset
2978
            Validation data.
2979
        name : str
2980
            Name of validation data.
Nikita Titov's avatar
Nikita Titov committed
2981
2982
2983
2984
2985

        Returns
        -------
        self : Booster
            Booster with set validation data.
wxchan's avatar
wxchan committed
2986
        """
Guolin Ke's avatar
Guolin Ke committed
2987
        if not isinstance(data, Dataset):
2988
            raise TypeError(f'Validation data should be Dataset instance, met {type(data).__name__}')
Guolin Ke's avatar
Guolin Ke committed
2989
        if data._predictor is not self.__init_predictor:
2990
2991
            raise LightGBMError("Add validation data failed, "
                                "you should use same predictor for these data")
wxchan's avatar
wxchan committed
2992
2993
        _safe_call(_LIB.LGBM_BoosterAddValidData(
            self.handle,
wxchan's avatar
wxchan committed
2994
            data.construct().handle))
wxchan's avatar
wxchan committed
2995
2996
2997
2998
2999
        self.valid_sets.append(data)
        self.name_valid_sets.append(name)
        self.__num_dataset += 1
        self.__inner_predict_buffer.append(None)
        self.__is_predicted_cur_iter.append(False)
Nikita Titov's avatar
Nikita Titov committed
3000
        return self
wxchan's avatar
wxchan committed
3001

3002
    def reset_parameter(self, params: Dict[str, Any]) -> "Booster":
3003
        """Reset parameters of Booster.
wxchan's avatar
wxchan committed
3004
3005
3006
3007

        Parameters
        ----------
        params : dict
3008
            New parameters for Booster.
Nikita Titov's avatar
Nikita Titov committed
3009
3010
3011
3012
3013

        Returns
        -------
        self : Booster
            Booster with new parameters.
wxchan's avatar
wxchan committed
3014
3015
3016
3017
3018
3019
        """
        params_str = param_dict_to_str(params)
        if params_str:
            _safe_call(_LIB.LGBM_BoosterResetParameter(
                self.handle,
                c_str(params_str)))
Guolin Ke's avatar
Guolin Ke committed
3020
        self.params.update(params)
Nikita Titov's avatar
Nikita Titov committed
3021
        return self
wxchan's avatar
wxchan committed
3022

3023
3024
3025
3026
3027
    def update(
        self,
        train_set: Optional[Dataset] = None,
        fobj: Optional[_LGBM_CustomObjectiveFunction] = None
    ) -> bool:
Nikita Titov's avatar
Nikita Titov committed
3028
        """Update Booster for one iteration.
3029

wxchan's avatar
wxchan committed
3030
3031
        Parameters
        ----------
3032
3033
3034
3035
        train_set : Dataset or None, optional (default=None)
            Training data.
            If None, last training data is used.
        fobj : callable or None, optional (default=None)
wxchan's avatar
wxchan committed
3036
            Customized objective function.
3037
3038
3039
            Should accept two parameters: preds, train_data,
            and return (grad, hess).

3040
                preds : numpy 1-D array or numpy 2-D array (for multi-class task)
3041
                    The predicted values.
3042
3043
                    Predicted values are returned before any transformation,
                    e.g. they are raw margin instead of probability of positive class for binary task.
3044
3045
                train_data : Dataset
                    The training dataset.
3046
                grad : numpy 1-D array or numpy 2-D array (for multi-class task)
3047
3048
                    The value of the first order derivative (gradient) of the loss
                    with respect to the elements of preds for each sample point.
3049
                hess : numpy 1-D array or numpy 2-D array (for multi-class task)
3050
3051
                    The value of the second order derivative (Hessian) of the loss
                    with respect to the elements of preds for each sample point.
wxchan's avatar
wxchan committed
3052

3053
            For multi-class task, preds are numpy 2-D array of shape = [n_samples, n_classes],
3054
            and grad and hess should be returned in the same format.
3055

wxchan's avatar
wxchan committed
3056
3057
        Returns
        -------
3058
3059
        is_finished : bool
            Whether the update was successfully finished.
wxchan's avatar
wxchan committed
3060
        """
3061
        # need reset training data
3062
3063
3064
3065
3066
3067
        if train_set is None and self.train_set_version != self.train_set.version:
            train_set = self.train_set
            is_the_same_train_set = False
        else:
            is_the_same_train_set = train_set is self.train_set and self.train_set_version == train_set.version
        if train_set is not None and not is_the_same_train_set:
Guolin Ke's avatar
Guolin Ke committed
3068
            if not isinstance(train_set, Dataset):
3069
                raise TypeError(f'Training data should be Dataset instance, met {type(train_set).__name__}')
Guolin Ke's avatar
Guolin Ke committed
3070
            if train_set._predictor is not self.__init_predictor:
3071
3072
                raise LightGBMError("Replace training data failed, "
                                    "you should use same predictor for these data")
wxchan's avatar
wxchan committed
3073
3074
3075
            self.train_set = train_set
            _safe_call(_LIB.LGBM_BoosterResetTrainingData(
                self.handle,
wxchan's avatar
wxchan committed
3076
                self.train_set.construct().handle))
wxchan's avatar
wxchan committed
3077
            self.__inner_predict_buffer[0] = None
3078
            self.train_set_version = self.train_set.version
wxchan's avatar
wxchan committed
3079
3080
        is_finished = ctypes.c_int(0)
        if fobj is None:
3081
            if self.__set_objective_to_none:
3082
                raise LightGBMError('Cannot update due to null objective function.')
wxchan's avatar
wxchan committed
3083
3084
3085
            _safe_call(_LIB.LGBM_BoosterUpdateOneIter(
                self.handle,
                ctypes.byref(is_finished)))
3086
            self.__is_predicted_cur_iter = [False for _ in range(self.__num_dataset)]
wxchan's avatar
wxchan committed
3087
3088
            return is_finished.value == 1
        else:
3089
            if not self.__set_objective_to_none:
Nikita Titov's avatar
Nikita Titov committed
3090
                self.reset_parameter({"objective": "none"}).__set_objective_to_none = True
wxchan's avatar
wxchan committed
3091
3092
3093
            grad, hess = fobj(self.__inner_predict(0), self.train_set)
            return self.__boost(grad, hess)

3094
3095
3096
3097
3098
    def __boost(
        self,
        grad: np.ndarray,
        hess: np.ndarray
    ) -> bool:
3099
        """Boost Booster for one iteration with customized gradient statistics.
Nikita Titov's avatar
Nikita Titov committed
3100

Nikita Titov's avatar
Nikita Titov committed
3101
3102
        .. note::

3103
3104
            Score is returned before any transformation,
            e.g. it is raw margin instead of probability of positive class for binary task.
3105
            For multi-class task, score are numpy 2-D array of shape = [n_samples, n_classes],
3106
            and grad and hess should be returned in the same format.
3107

wxchan's avatar
wxchan committed
3108
3109
        Parameters
        ----------
3110
        grad : numpy 1-D array or numpy 2-D array (for multi-class task)
3111
3112
            The value of the first order derivative (gradient) of the loss
            with respect to the elements of score for each sample point.
3113
        hess : numpy 1-D array or numpy 2-D array (for multi-class task)
3114
3115
            The value of the second order derivative (Hessian) of the loss
            with respect to the elements of score for each sample point.
wxchan's avatar
wxchan committed
3116
3117
3118

        Returns
        -------
Nikita Titov's avatar
Nikita Titov committed
3119
3120
        is_finished : bool
            Whether the boost was successfully finished.
wxchan's avatar
wxchan committed
3121
        """
3122
3123
3124
        if self.__num_class > 1:
            grad = grad.ravel(order='F')
            hess = hess.ravel(order='F')
3125
3126
        grad = list_to_1d_numpy(grad, name='gradient')
        hess = list_to_1d_numpy(hess, name='hessian')
3127
3128
        assert grad.flags.c_contiguous
        assert hess.flags.c_contiguous
wxchan's avatar
wxchan committed
3129
        if len(grad) != len(hess):
3130
3131
            raise ValueError(f"Lengths of gradient ({len(grad)}) and Hessian ({len(hess)}) don't match")
        num_train_data = self.train_set.num_data()
3132
        if len(grad) != num_train_data * self.__num_class:
3133
3134
3135
            raise ValueError(
                f"Lengths of gradient ({len(grad)}) and Hessian ({len(hess)}) "
                f"don't match training data length ({num_train_data}) * "
3136
                f"number of models per one iteration ({self.__num_class})"
3137
            )
wxchan's avatar
wxchan committed
3138
3139
3140
3141
3142
3143
        is_finished = ctypes.c_int(0)
        _safe_call(_LIB.LGBM_BoosterUpdateOneIterCustom(
            self.handle,
            grad.ctypes.data_as(ctypes.POINTER(ctypes.c_float)),
            hess.ctypes.data_as(ctypes.POINTER(ctypes.c_float)),
            ctypes.byref(is_finished)))
3144
        self.__is_predicted_cur_iter = [False for _ in range(self.__num_dataset)]
wxchan's avatar
wxchan committed
3145
3146
        return is_finished.value == 1

3147
    def rollback_one_iter(self) -> "Booster":
Nikita Titov's avatar
Nikita Titov committed
3148
3149
3150
3151
3152
3153
3154
        """Rollback one iteration.

        Returns
        -------
        self : Booster
            Booster with rolled back one iteration.
        """
wxchan's avatar
wxchan committed
3155
3156
        _safe_call(_LIB.LGBM_BoosterRollbackOneIter(
            self.handle))
3157
        self.__is_predicted_cur_iter = [False for _ in range(self.__num_dataset)]
Nikita Titov's avatar
Nikita Titov committed
3158
        return self
wxchan's avatar
wxchan committed
3159

3160
    def current_iteration(self) -> int:
3161
3162
3163
3164
3165
3166
3167
        """Get the index of the current iteration.

        Returns
        -------
        cur_iter : int
            The index of the current iteration.
        """
Guolin Ke's avatar
Guolin Ke committed
3168
        out_cur_iter = ctypes.c_int(0)
wxchan's avatar
wxchan committed
3169
3170
3171
3172
3173
        _safe_call(_LIB.LGBM_BoosterGetCurrentIteration(
            self.handle,
            ctypes.byref(out_cur_iter)))
        return out_cur_iter.value

3174
    def num_model_per_iteration(self) -> int:
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
        """Get number of models per iteration.

        Returns
        -------
        model_per_iter : int
            The number of models per iteration.
        """
        model_per_iter = ctypes.c_int(0)
        _safe_call(_LIB.LGBM_BoosterNumModelPerIteration(
            self.handle,
            ctypes.byref(model_per_iter)))
        return model_per_iter.value

3188
    def num_trees(self) -> int:
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
        """Get number of weak sub-models.

        Returns
        -------
        num_trees : int
            The number of weak sub-models.
        """
        num_trees = ctypes.c_int(0)
        _safe_call(_LIB.LGBM_BoosterNumberOfTotalModel(
            self.handle,
            ctypes.byref(num_trees)))
        return num_trees.value

3202
    def upper_bound(self) -> float:
3203
3204
3205
3206
        """Get upper bound value of a model.

        Returns
        -------
3207
        upper_bound : float
3208
3209
3210
3211
3212
3213
3214
3215
            Upper bound value of the model.
        """
        ret = ctypes.c_double(0)
        _safe_call(_LIB.LGBM_BoosterGetUpperBoundValue(
            self.handle,
            ctypes.byref(ret)))
        return ret.value

3216
    def lower_bound(self) -> float:
3217
3218
3219
3220
        """Get lower bound value of a model.

        Returns
        -------
3221
        lower_bound : float
3222
3223
3224
3225
3226
3227
3228
3229
            Lower bound value of the model.
        """
        ret = ctypes.c_double(0)
        _safe_call(_LIB.LGBM_BoosterGetLowerBoundValue(
            self.handle,
            ctypes.byref(ret)))
        return ret.value

wxchan's avatar
wxchan committed
3230
    def eval(self, data, name, feval=None):
3231
        """Evaluate for data.
wxchan's avatar
wxchan committed
3232
3233
3234

        Parameters
        ----------
3235
3236
        data : Dataset
            Data for the evaluating.
3237
        name : str
3238
            Name of the data.
3239
        feval : callable, list of callable, or None, optional (default=None)
3240
            Customized evaluation function.
3241
            Each evaluation function should accept two parameters: preds, eval_data,
3242
            and return (eval_name, eval_result, is_higher_better) or list of such tuples.
3243

3244
                preds : numpy 1-D array or numpy 2-D array (for multi-class task)
3245
                    The predicted values.
3246
                    For multi-class task, preds are numpy 2-D array of shape = [n_samples, n_classes].
3247
                    If custom objective function is used, predicted values are returned before any transformation,
3248
                    e.g. they are raw margin instead of probability of positive class for binary task in this case.
3249
                eval_data : Dataset
3250
                    A ``Dataset`` to evaluate.
3251
                eval_name : str
Andrew Ziem's avatar
Andrew Ziem committed
3252
                    The name of evaluation function (without whitespace).
3253
3254
3255
3256
3257
                eval_result : float
                    The eval result.
                is_higher_better : bool
                    Is eval result higher better, e.g. AUC is ``is_higher_better``.

wxchan's avatar
wxchan committed
3258
3259
        Returns
        -------
Nikita Titov's avatar
Nikita Titov committed
3260
        result : list
3261
            List with evaluation results.
wxchan's avatar
wxchan committed
3262
        """
Guolin Ke's avatar
Guolin Ke committed
3263
3264
        if not isinstance(data, Dataset):
            raise TypeError("Can only eval for Dataset instance")
wxchan's avatar
wxchan committed
3265
3266
3267
3268
        data_idx = -1
        if data is self.train_set:
            data_idx = 0
        else:
3269
            for i in range(len(self.valid_sets)):
wxchan's avatar
wxchan committed
3270
3271
3272
                if data is self.valid_sets[i]:
                    data_idx = i + 1
                    break
3273
        # need to push new valid data
wxchan's avatar
wxchan committed
3274
3275
3276
3277
3278
3279
3280
        if data_idx == -1:
            self.add_valid(data, name)
            data_idx = self.__num_dataset - 1

        return self.__inner_eval(name, data_idx, feval)

    def eval_train(self, feval=None):
3281
        """Evaluate for training data.
wxchan's avatar
wxchan committed
3282
3283
3284

        Parameters
        ----------
3285
        feval : callable, list of callable, or None, optional (default=None)
3286
            Customized evaluation function.
3287
            Each evaluation function should accept two parameters: preds, eval_data,
3288
            and return (eval_name, eval_result, is_higher_better) or list of such tuples.
3289

3290
                preds : numpy 1-D array or numpy 2-D array (for multi-class task)
3291
                    The predicted values.
3292
                    For multi-class task, preds are numpy 2-D array of shape = [n_samples, n_classes].
3293
                    If custom objective function is used, predicted values are returned before any transformation,
3294
                    e.g. they are raw margin instead of probability of positive class for binary task in this case.
Akshita Dixit's avatar
Akshita Dixit committed
3295
                eval_data : Dataset
3296
                    The training dataset.
3297
                eval_name : str
Andrew Ziem's avatar
Andrew Ziem committed
3298
                    The name of evaluation function (without whitespace).
3299
3300
3301
3302
3303
                eval_result : float
                    The eval result.
                is_higher_better : bool
                    Is eval result higher better, e.g. AUC is ``is_higher_better``.

wxchan's avatar
wxchan committed
3304
3305
        Returns
        -------
Nikita Titov's avatar
Nikita Titov committed
3306
        result : list
3307
            List with evaluation results.
wxchan's avatar
wxchan committed
3308
        """
3309
        return self.__inner_eval(self._train_data_name, 0, feval)
wxchan's avatar
wxchan committed
3310
3311

    def eval_valid(self, feval=None):
3312
        """Evaluate for validation data.
wxchan's avatar
wxchan committed
3313
3314
3315

        Parameters
        ----------
3316
        feval : callable, list of callable, or None, optional (default=None)
3317
            Customized evaluation function.
3318
            Each evaluation function should accept two parameters: preds, eval_data,
3319
            and return (eval_name, eval_result, is_higher_better) or list of such tuples.
3320

3321
                preds : numpy 1-D array or numpy 2-D array (for multi-class task)
3322
                    The predicted values.
3323
                    For multi-class task, preds are numpy 2-D array of shape = [n_samples, n_classes].
3324
                    If custom objective function is used, predicted values are returned before any transformation,
3325
                    e.g. they are raw margin instead of probability of positive class for binary task in this case.
Akshita Dixit's avatar
Akshita Dixit committed
3326
                eval_data : Dataset
3327
                    The validation dataset.
3328
                eval_name : str
Andrew Ziem's avatar
Andrew Ziem committed
3329
                    The name of evaluation function (without whitespace).
3330
3331
3332
3333
3334
                eval_result : float
                    The eval result.
                is_higher_better : bool
                    Is eval result higher better, e.g. AUC is ``is_higher_better``.

wxchan's avatar
wxchan committed
3335
3336
        Returns
        -------
Nikita Titov's avatar
Nikita Titov committed
3337
        result : list
3338
            List with evaluation results.
wxchan's avatar
wxchan committed
3339
        """
3340
        return [item for i in range(1, self.__num_dataset)
wxchan's avatar
wxchan committed
3341
                for item in self.__inner_eval(self.name_valid_sets[i - 1], i, feval)]
wxchan's avatar
wxchan committed
3342

3343
    def save_model(self, filename, num_iteration=None, start_iteration=0, importance_type='split'):
3344
        """Save Booster to file.
wxchan's avatar
wxchan committed
3345
3346
3347

        Parameters
        ----------
3348
        filename : str or pathlib.Path
3349
            Filename to save Booster.
3350
3351
3352
3353
        num_iteration : int or None, optional (default=None)
            Index of the iteration that should be saved.
            If None, if the best iteration exists, it is saved; otherwise, all iterations are saved.
            If <= 0, all iterations are saved.
Nikita Titov's avatar
Nikita Titov committed
3354
        start_iteration : int, optional (default=0)
3355
            Start index of the iteration that should be saved.
3356
        importance_type : str, optional (default="split")
3357
3358
3359
            What type of feature importance should be saved.
            If "split", result contains numbers of times the feature is used in a model.
            If "gain", result contains total gains of splits which use the feature.
Nikita Titov's avatar
Nikita Titov committed
3360
3361
3362
3363
3364

        Returns
        -------
        self : Booster
            Returns self.
wxchan's avatar
wxchan committed
3365
        """
3366
        if num_iteration is None:
3367
            num_iteration = self.best_iteration
3368
        importance_type_int = FEATURE_IMPORTANCE_TYPE_MAPPER[importance_type]
wxchan's avatar
wxchan committed
3369
3370
        _safe_call(_LIB.LGBM_BoosterSaveModel(
            self.handle,
3371
            ctypes.c_int(start_iteration),
Guolin Ke's avatar
Guolin Ke committed
3372
            ctypes.c_int(num_iteration),
3373
            ctypes.c_int(importance_type_int),
3374
            c_str(str(filename))))
3375
        _dump_pandas_categorical(self.pandas_categorical, filename)
Nikita Titov's avatar
Nikita Titov committed
3376
        return self
wxchan's avatar
wxchan committed
3377

3378
    def shuffle_models(self, start_iteration=0, end_iteration=-1):
3379
        """Shuffle models.
Nikita Titov's avatar
Nikita Titov committed
3380

3381
3382
3383
        Parameters
        ----------
        start_iteration : int, optional (default=0)
3384
            The first iteration that will be shuffled.
3385
3386
        end_iteration : int, optional (default=-1)
            The last iteration that will be shuffled.
3387
            If <= 0, means the last available iteration.
3388

Nikita Titov's avatar
Nikita Titov committed
3389
3390
3391
3392
        Returns
        -------
        self : Booster
            Booster with shuffled models.
3393
        """
3394
3395
        _safe_call(_LIB.LGBM_BoosterShuffleModels(
            self.handle,
Guolin Ke's avatar
Guolin Ke committed
3396
3397
            ctypes.c_int(start_iteration),
            ctypes.c_int(end_iteration)))
Nikita Titov's avatar
Nikita Titov committed
3398
        return self
3399

3400
    def model_from_string(self, model_str: str) -> "Booster":
3401
3402
3403
3404
        """Load Booster from a string.

        Parameters
        ----------
3405
        model_str : str
3406
3407
3408
3409
            Model will be loaded from this string.

        Returns
        -------
Nikita Titov's avatar
Nikita Titov committed
3410
        self : Booster
3411
3412
            Loaded Booster object.
        """
3413
3414
3415
3416
        if self.handle is not None:
            _safe_call(_LIB.LGBM_BoosterFree(self.handle))
        self._free_buffer()
        self.handle = ctypes.c_void_p()
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
        out_num_iterations = ctypes.c_int(0)
        _safe_call(_LIB.LGBM_BoosterLoadModelFromString(
            c_str(model_str),
            ctypes.byref(out_num_iterations),
            ctypes.byref(self.handle)))
        out_num_class = ctypes.c_int(0)
        _safe_call(_LIB.LGBM_BoosterGetNumClasses(
            self.handle,
            ctypes.byref(out_num_class)))
        self.__num_class = out_num_class.value
3427
        self.pandas_categorical = _load_pandas_categorical(model_str=model_str)
3428
3429
        return self

3430
    def model_to_string(self, num_iteration=None, start_iteration=0, importance_type='split'):
3431
        """Save Booster to string.
3432

3433
3434
3435
3436
3437
3438
        Parameters
        ----------
        num_iteration : int or None, optional (default=None)
            Index of the iteration that should be saved.
            If None, if the best iteration exists, it is saved; otherwise, all iterations are saved.
            If <= 0, all iterations are saved.
Nikita Titov's avatar
Nikita Titov committed
3439
        start_iteration : int, optional (default=0)
3440
            Start index of the iteration that should be saved.
3441
        importance_type : str, optional (default="split")
3442
3443
3444
            What type of feature importance should be saved.
            If "split", result contains numbers of times the feature is used in a model.
            If "gain", result contains total gains of splits which use the feature.
3445
3446
3447

        Returns
        -------
3448
        str_repr : str
3449
3450
            String representation of Booster.
        """
3451
        if num_iteration is None:
3452
            num_iteration = self.best_iteration
3453
        importance_type_int = FEATURE_IMPORTANCE_TYPE_MAPPER[importance_type]
3454
        buffer_len = 1 << 20
3455
        tmp_out_len = ctypes.c_int64(0)
3456
3457
3458
3459
        string_buffer = ctypes.create_string_buffer(buffer_len)
        ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
        _safe_call(_LIB.LGBM_BoosterSaveModelToString(
            self.handle,
3460
            ctypes.c_int(start_iteration),
3461
            ctypes.c_int(num_iteration),
3462
            ctypes.c_int(importance_type_int),
3463
            ctypes.c_int64(buffer_len),
3464
3465
3466
            ctypes.byref(tmp_out_len),
            ptr_string_buffer))
        actual_len = tmp_out_len.value
3467
        # if buffer length is not long enough, re-allocate a buffer
3468
3469
3470
3471
3472
        if actual_len > buffer_len:
            string_buffer = ctypes.create_string_buffer(actual_len)
            ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
            _safe_call(_LIB.LGBM_BoosterSaveModelToString(
                self.handle,
3473
                ctypes.c_int(start_iteration),
3474
                ctypes.c_int(num_iteration),
3475
                ctypes.c_int(importance_type_int),
3476
                ctypes.c_int64(actual_len),
3477
3478
                ctypes.byref(tmp_out_len),
                ptr_string_buffer))
3479
        ret = string_buffer.value.decode('utf-8')
3480
3481
        ret += _dump_pandas_categorical(self.pandas_categorical)
        return ret
3482

3483
    def dump_model(self, num_iteration=None, start_iteration=0, importance_type='split', object_hook=None):
Nikita Titov's avatar
Nikita Titov committed
3484
        """Dump Booster to JSON format.
wxchan's avatar
wxchan committed
3485

3486
3487
        Parameters
        ----------
3488
3489
3490
3491
        num_iteration : int or None, optional (default=None)
            Index of the iteration that should be dumped.
            If None, if the best iteration exists, it is dumped; otherwise, all iterations are dumped.
            If <= 0, all iterations are dumped.
Nikita Titov's avatar
Nikita Titov committed
3492
        start_iteration : int, optional (default=0)
3493
            Start index of the iteration that should be dumped.
3494
        importance_type : str, optional (default="split")
3495
3496
3497
            What type of feature importance should be dumped.
            If "split", result contains numbers of times the feature is used in a model.
            If "gain", result contains total gains of splits which use the feature.
3498
3499
3500
3501
3502
3503
3504
3505
3506
        object_hook : callable or None, optional (default=None)
            If not None, ``object_hook`` is a function called while parsing the json
            string returned by the C API. It may be used to alter the json, to store
            specific values while building the json structure. It avoids
            walking through the structure again. It saves a significant amount
            of time if the number of trees is huge.
            Signature is ``def object_hook(node: dict) -> dict``.
            None is equivalent to ``lambda node: node``.
            See documentation of ``json.loads()`` for further details.
3507

wxchan's avatar
wxchan committed
3508
3509
        Returns
        -------
3510
        json_repr : dict
Nikita Titov's avatar
Nikita Titov committed
3511
            JSON format of Booster.
wxchan's avatar
wxchan committed
3512
        """
3513
        if num_iteration is None:
3514
            num_iteration = self.best_iteration
3515
        importance_type_int = FEATURE_IMPORTANCE_TYPE_MAPPER[importance_type]
wxchan's avatar
wxchan committed
3516
        buffer_len = 1 << 20
3517
        tmp_out_len = ctypes.c_int64(0)
wxchan's avatar
wxchan committed
3518
3519
3520
3521
        string_buffer = ctypes.create_string_buffer(buffer_len)
        ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
        _safe_call(_LIB.LGBM_BoosterDumpModel(
            self.handle,
3522
            ctypes.c_int(start_iteration),
Guolin Ke's avatar
Guolin Ke committed
3523
            ctypes.c_int(num_iteration),
3524
            ctypes.c_int(importance_type_int),
3525
            ctypes.c_int64(buffer_len),
wxchan's avatar
wxchan committed
3526
            ctypes.byref(tmp_out_len),
Guolin Ke's avatar
Guolin Ke committed
3527
            ptr_string_buffer))
wxchan's avatar
wxchan committed
3528
        actual_len = tmp_out_len.value
3529
        # if buffer length is not long enough, reallocate a buffer
wxchan's avatar
wxchan committed
3530
3531
3532
3533
3534
        if actual_len > buffer_len:
            string_buffer = ctypes.create_string_buffer(actual_len)
            ptr_string_buffer = ctypes.c_char_p(*[ctypes.addressof(string_buffer)])
            _safe_call(_LIB.LGBM_BoosterDumpModel(
                self.handle,
3535
                ctypes.c_int(start_iteration),
Guolin Ke's avatar
Guolin Ke committed
3536
                ctypes.c_int(num_iteration),
3537
                ctypes.c_int(importance_type_int),
3538
                ctypes.c_int64(actual_len),
wxchan's avatar
wxchan committed
3539
                ctypes.byref(tmp_out_len),
Guolin Ke's avatar
Guolin Ke committed
3540
                ptr_string_buffer))
3541
        ret = json.loads(string_buffer.value.decode('utf-8'), object_hook=object_hook)
3542
3543
3544
        ret['pandas_categorical'] = json.loads(json.dumps(self.pandas_categorical,
                                                          default=json_default_with_numpy))
        return ret
wxchan's avatar
wxchan committed
3545

3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
    def predict(
        self,
        data,
        start_iteration: int = 0,
        num_iteration: Optional[int] = None,
        raw_score: bool = False,
        pred_leaf: bool = False,
        pred_contrib: bool = False,
        data_has_header: bool = False,
        validate_features: bool = False,
        **kwargs: Any
    ):
3558
        """Make a prediction.
wxchan's avatar
wxchan committed
3559
3560
3561

        Parameters
        ----------
3562
        data : str, pathlib.Path, numpy array, pandas DataFrame, H2O DataTable's Frame or scipy.sparse
3563
            Data source for prediction.
3564
            If str or pathlib.Path, it represents the path to a text file (CSV, TSV, or LibSVM).
3565
        start_iteration : int, optional (default=0)
3566
            Start index of the iteration to predict.
3567
            If <= 0, starts from the first iteration.
3568
        num_iteration : int or None, optional (default=None)
3569
3570
3571
3572
            Total number of iterations used in the prediction.
            If None, if the best iteration exists and start_iteration <= 0, the best iteration is used;
            otherwise, all iterations from ``start_iteration`` are used (no limits).
            If <= 0, all iterations from ``start_iteration`` are used (no limits).
3573
3574
3575
3576
        raw_score : bool, optional (default=False)
            Whether to predict raw scores.
        pred_leaf : bool, optional (default=False)
            Whether to predict leaf index.
3577
3578
        pred_contrib : bool, optional (default=False)
            Whether to predict feature contributions.
3579

Nikita Titov's avatar
Nikita Titov committed
3580
3581
3582
3583
3584
3585
3586
            .. note::

                If you want to get more explanations for your model's predictions using SHAP values,
                like SHAP interaction values,
                you can install the shap package (https://github.com/slundberg/shap).
                Note that unlike the shap package, with ``pred_contrib`` we return a matrix with an extra
                column, where the last column is the expected value.
3587

3588
3589
        data_has_header : bool, optional (default=False)
            Whether the data has header.
3590
            Used only if data is str.
3591
3592
3593
        validate_features : bool, optional (default=False)
            If True, ensure that the features used to predict match the ones used to train.
            Used only if data is pandas DataFrame.
3594
3595
        **kwargs
            Other parameters for the prediction.
wxchan's avatar
wxchan committed
3596
3597
3598

        Returns
        -------
3599
        result : numpy array, scipy.sparse or list of scipy.sparse
3600
            Prediction result.
3601
            Can be sparse or a list of sparse objects (each element represents predictions for one class) for feature contributions (when ``pred_contrib=True``).
wxchan's avatar
wxchan committed
3602
        """
3603
        predictor = self._to_predictor(deepcopy(kwargs))
3604
        if num_iteration is None:
3605
            if start_iteration <= 0:
3606
3607
3608
3609
                num_iteration = self.best_iteration
            else:
                num_iteration = -1
        return predictor.predict(data, start_iteration, num_iteration,
3610
                                 raw_score, pred_leaf, pred_contrib,
3611
                                 data_has_header, validate_features)
wxchan's avatar
wxchan committed
3612

3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
    def refit(
        self,
        data,
        label,
        decay_rate=0.9,
        reference=None,
        weight=None,
        group=None,
        init_score=None,
        feature_name='auto',
        categorical_feature='auto',
        dataset_params=None,
        free_raw_data=True,
3626
        validate_features=False,
3627
3628
        **kwargs
    ):
Guolin Ke's avatar
Guolin Ke committed
3629
3630
3631
3632
        """Refit the existing Booster by new data.

        Parameters
        ----------
3633
        data : str, pathlib.Path, numpy array, pandas DataFrame, H2O DataTable's Frame or scipy.sparse
Guolin Ke's avatar
Guolin Ke committed
3634
            Data source for refit.
3635
            If str or pathlib.Path, it represents the path to a text file (CSV, TSV, or LibSVM).
3636
        label : list, numpy 1-D array or pandas Series / one-column DataFrame
Guolin Ke's avatar
Guolin Ke committed
3637
3638
            Label for refit.
        decay_rate : float, optional (default=0.9)
3639
3640
            Decay rate of refit,
            will use ``leaf_output = decay_rate * old_leaf_output + (1.0 - decay_rate) * new_leaf_output`` to refit trees.
3641
3642
3643
        reference : Dataset or None, optional (default=None)
            Reference for ``data``.
        weight : list, numpy 1-D array, pandas Series or None, optional (default=None)
3644
            Weight for each ``data`` instance. Weights should be non-negative.
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
        group : list, numpy 1-D array, pandas Series or None, optional (default=None)
            Group/query size for ``data``.
            Only used in the learning-to-rank task.
            sum(group) = n_samples.
            For example, if you have a 100-document dataset with ``group = [10, 20, 40, 10, 10, 10]``, that means that you have 6 groups,
            where the first 10 records are in the first group, records 11-30 are in the second group, records 31-70 are in the third group, etc.
        init_score : list, list of lists (for multi-class task), numpy array, pandas Series, pandas DataFrame (for multi-class task), or None, optional (default=None)
            Init score for ``data``.
        feature_name : list of str, or 'auto', optional (default="auto")
            Feature names for ``data``.
            If 'auto' and data is pandas DataFrame, data columns names are used.
        categorical_feature : list of str or int, or 'auto', optional (default="auto")
            Categorical features for ``data``.
            If list of int, interpreted as indices.
            If list of str, interpreted as feature names (need to specify ``feature_name`` as well).
            If 'auto' and data is pandas DataFrame, pandas unordered categorical columns are used.
3661
            All values in categorical features will be cast to int32 and thus should be less than int32 max value (2147483647).
3662
3663
3664
            Large values could be memory consuming. Consider using consecutive integers starting from zero.
            All negative values in categorical features will be treated as missing values.
            The output cannot be monotonically constrained with respect to a categorical feature.
3665
            Floating point numbers in categorical features will be rounded towards 0.
3666
3667
3668
3669
        dataset_params : dict or None, optional (default=None)
            Other parameters for Dataset ``data``.
        free_raw_data : bool, optional (default=True)
            If True, raw data is freed after constructing inner Dataset for ``data``.
3670
3671
3672
        validate_features : bool, optional (default=False)
            If True, ensure that the features used to refit the model match the original ones.
            Used only if data is pandas DataFrame.
3673
3674
        **kwargs
            Other parameters for refit.
3675
            These parameters will be passed to ``predict`` method.
Guolin Ke's avatar
Guolin Ke committed
3676
3677
3678
3679
3680
3681

        Returns
        -------
        result : Booster
            Refitted Booster.
        """
3682
3683
        if self.__set_objective_to_none:
            raise LightGBMError('Cannot refit due to null objective function.')
3684
3685
        if dataset_params is None:
            dataset_params = {}
3686
        predictor = self._to_predictor(deepcopy(kwargs))
3687
        leaf_preds = predictor.predict(data, -1, pred_leaf=True, validate_features=validate_features)
3688
        nrow, ncol = leaf_preds.shape
3689
        out_is_linear = ctypes.c_int(0)
3690
3691
3692
        _safe_call(_LIB.LGBM_BoosterGetLinear(
            self.handle,
            ctypes.byref(out_is_linear)))
Nikita Titov's avatar
Nikita Titov committed
3693
3694
3695
3696
3697
        new_params = _choose_param_value(
            main_param_name="linear_tree",
            params=self.params,
            default_value=None
        )
3698
        new_params["linear_tree"] = bool(out_is_linear.value)
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
        new_params.update(dataset_params)
        train_set = Dataset(
            data=data,
            label=label,
            reference=reference,
            weight=weight,
            group=group,
            init_score=init_score,
            feature_name=feature_name,
            categorical_feature=categorical_feature,
            params=new_params,
            free_raw_data=free_raw_data,
        )
3712
        new_params['refit_decay_rate'] = decay_rate
3713
        new_booster = Booster(new_params, train_set)
Guolin Ke's avatar
Guolin Ke committed
3714
3715
3716
3717
3718
        # Copy models
        _safe_call(_LIB.LGBM_BoosterMerge(
            new_booster.handle,
            predictor.handle))
        leaf_preds = leaf_preds.reshape(-1)
3719
        ptr_data, _, _ = c_int_array(leaf_preds)
Guolin Ke's avatar
Guolin Ke committed
3720
3721
3722
        _safe_call(_LIB.LGBM_BoosterRefit(
            new_booster.handle,
            ptr_data,
3723
3724
            ctypes.c_int32(nrow),
            ctypes.c_int32(ncol)))
3725
        new_booster.network = self.network
Guolin Ke's avatar
Guolin Ke committed
3726
3727
        return new_booster

3728
    def get_leaf_output(self, tree_id: int, leaf_id: int) -> float:
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
        """Get the output of a leaf.

        Parameters
        ----------
        tree_id : int
            The index of the tree.
        leaf_id : int
            The index of the leaf in the tree.

        Returns
        -------
        result : float
            The output of the leaf.
        """
3743
3744
3745
3746
3747
3748
3749
3750
        ret = ctypes.c_double(0)
        _safe_call(_LIB.LGBM_BoosterGetLeafValue(
            self.handle,
            ctypes.c_int(tree_id),
            ctypes.c_int(leaf_id),
            ctypes.byref(ret)))
        return ret.value

3751
    def _to_predictor(self, pred_parameter=None):
3752
        """Convert to predictor."""
3753
        predictor = _InnerPredictor(booster_handle=self.handle, pred_parameter=pred_parameter)
3754
        predictor.pandas_categorical = self.pandas_categorical
wxchan's avatar
wxchan committed
3755
3756
        return predictor

3757
    def num_feature(self) -> int:
3758
3759
3760
3761
3762
3763
3764
        """Get number of features.

        Returns
        -------
        num_feature : int
            The number of features.
        """
3765
3766
3767
3768
3769
3770
        out_num_feature = ctypes.c_int(0)
        _safe_call(_LIB.LGBM_BoosterGetNumFeature(
            self.handle,
            ctypes.byref(out_num_feature)))
        return out_num_feature.value

3771
    def feature_name(self) -> List[str]:
3772
        """Get names of features.
wxchan's avatar
wxchan committed
3773
3774
3775

        Returns
        -------
3776
        result : list of str
3777
            List with names of features.
wxchan's avatar
wxchan committed
3778
        """
3779
        num_feature = self.num_feature()
3780
        # Get name of features
wxchan's avatar
wxchan committed
3781
        tmp_out_len = ctypes.c_int(0)
3782
3783
        reserved_string_buffer_size = 255
        required_string_buffer_size = ctypes.c_size_t(0)
3784
        string_buffers = [ctypes.create_string_buffer(reserved_string_buffer_size) for _ in range(num_feature)]
wxchan's avatar
wxchan committed
3785
3786
3787
        ptr_string_buffers = (ctypes.c_char_p * num_feature)(*map(ctypes.addressof, string_buffers))
        _safe_call(_LIB.LGBM_BoosterGetFeatureNames(
            self.handle,
3788
            ctypes.c_int(num_feature),
wxchan's avatar
wxchan committed
3789
            ctypes.byref(tmp_out_len),
3790
            ctypes.c_size_t(reserved_string_buffer_size),
3791
            ctypes.byref(required_string_buffer_size),
wxchan's avatar
wxchan committed
3792
3793
3794
            ptr_string_buffers))
        if num_feature != tmp_out_len.value:
            raise ValueError("Length of feature names doesn't equal with num_feature")
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
        actual_string_buffer_size = required_string_buffer_size.value
        # if buffer length is not long enough, reallocate buffers
        if reserved_string_buffer_size < actual_string_buffer_size:
            string_buffers = [ctypes.create_string_buffer(actual_string_buffer_size) for _ in range(num_feature)]
            ptr_string_buffers = (ctypes.c_char_p * num_feature)(*map(ctypes.addressof, string_buffers))
            _safe_call(_LIB.LGBM_BoosterGetFeatureNames(
                self.handle,
                ctypes.c_int(num_feature),
                ctypes.byref(tmp_out_len),
                ctypes.c_size_t(actual_string_buffer_size),
                ctypes.byref(required_string_buffer_size),
                ptr_string_buffers))
3807
        return [string_buffers[i].value.decode('utf-8') for i in range(num_feature)]
wxchan's avatar
wxchan committed
3808

3809
3810
3811
3812
3813
    def feature_importance(
        self,
        importance_type: str = 'split',
        iteration: Optional[int] = None
    ) -> np.ndarray:
3814
        """Get feature importances.
3815

3816
3817
        Parameters
        ----------
3818
        importance_type : str, optional (default="split")
3819
3820
3821
            How the importance is calculated.
            If "split", result contains numbers of times the feature is used in a model.
            If "gain", result contains total gains of splits which use the feature.
3822
3823
3824
3825
        iteration : int or None, optional (default=None)
            Limit number of iterations in the feature importance calculation.
            If None, if the best iteration exists, it is used; otherwise, all trees are used.
            If <= 0, all trees are used (no limits).
3826

3827
3828
        Returns
        -------
3829
3830
        result : numpy array
            Array with feature importances.
3831
        """
3832
3833
        if iteration is None:
            iteration = self.best_iteration
3834
        importance_type_int = FEATURE_IMPORTANCE_TYPE_MAPPER[importance_type]
3835
        result = np.empty(self.num_feature(), dtype=np.float64)
3836
3837
3838
3839
3840
        _safe_call(_LIB.LGBM_BoosterFeatureImportance(
            self.handle,
            ctypes.c_int(iteration),
            ctypes.c_int(importance_type_int),
            result.ctypes.data_as(ctypes.POINTER(ctypes.c_double))))
3841
        if importance_type_int == C_API_FEATURE_IMPORTANCE_SPLIT:
3842
            return result.astype(np.int32)
3843
3844
        else:
            return result
3845

3846
3847
3848
3849
3850
    def get_split_value_histogram(self, feature, bins=None, xgboost_style=False):
        """Get split value histogram for the specified feature.

        Parameters
        ----------
3851
        feature : int or str
3852
3853
            The feature name or index the histogram is calculated for.
            If int, interpreted as index.
3854
            If str, interpreted as name.
3855

Nikita Titov's avatar
Nikita Titov committed
3856
3857
3858
            .. warning::

                Categorical features are not supported.
3859

3860
        bins : int, str or None, optional (default=None)
3861
3862
3863
            The maximum number of bins.
            If None, or int and > number of unique split values and ``xgboost_style=True``,
            the number of bins equals number of unique split values.
3864
            If str, it should be one from the list of the supported values by ``numpy.histogram()`` function.
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
        xgboost_style : bool, optional (default=False)
            Whether the returned result should be in the same form as it is in XGBoost.
            If False, the returned value is tuple of 2 numpy arrays as it is in ``numpy.histogram()`` function.
            If True, the returned value is matrix, in which the first column is the right edges of non-empty bins
            and the second one is the histogram values.

        Returns
        -------
        result_tuple : tuple of 2 numpy arrays
            If ``xgboost_style=False``, the values of the histogram of used splitting values for the specified feature
            and the bin edges.
        result_array_like : numpy array or pandas DataFrame (if pandas is installed)
            If ``xgboost_style=True``, the histogram of used splitting values for the specified feature.
        """
        def add(root):
            """Recursively add thresholds."""
            if 'split_index' in root:  # non-leaf
3882
                if feature_names is not None and isinstance(feature, str):
3883
3884
3885
3886
                    split_feature = feature_names[root['split_feature']]
                else:
                    split_feature = root['split_feature']
                if split_feature == feature:
3887
                    if isinstance(root['threshold'], str):
3888
3889
3890
                        raise LightGBMError('Cannot compute split value histogram for the categorical feature')
                    else:
                        values.append(root['threshold'])
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
                add(root['left_child'])
                add(root['right_child'])

        model = self.dump_model()
        feature_names = model.get('feature_names')
        tree_infos = model['tree_info']
        values = []
        for tree_info in tree_infos:
            add(tree_info['tree_structure'])

3901
        if bins is None or isinstance(bins, int) and xgboost_style:
3902
3903
3904
3905
3906
3907
3908
            n_unique = len(np.unique(values))
            bins = max(min(n_unique, bins) if bins is not None else n_unique, 1)
        hist, bin_edges = np.histogram(values, bins=bins)
        if xgboost_style:
            ret = np.column_stack((bin_edges[1:], hist))
            ret = ret[ret[:, 1] > 0]
            if PANDAS_INSTALLED:
3909
                return pd_DataFrame(ret, columns=['SplitValue', 'Count'])
3910
3911
3912
3913
3914
            else:
                return ret
        else:
            return hist, bin_edges

wxchan's avatar
wxchan committed
3915
    def __inner_eval(self, data_name, data_idx, feval=None):
3916
        """Evaluate training or validation data."""
wxchan's avatar
wxchan committed
3917
        if data_idx >= self.__num_dataset:
3918
            raise ValueError("Data_idx should be smaller than number of dataset")
wxchan's avatar
wxchan committed
3919
3920
3921
        self.__get_eval_info()
        ret = []
        if self.__num_inner_eval > 0:
3922
            result = np.empty(self.__num_inner_eval, dtype=np.float64)
Guolin Ke's avatar
Guolin Ke committed
3923
            tmp_out_len = ctypes.c_int(0)
wxchan's avatar
wxchan committed
3924
3925
            _safe_call(_LIB.LGBM_BoosterGetEval(
                self.handle,
Guolin Ke's avatar
Guolin Ke committed
3926
                ctypes.c_int(data_idx),
wxchan's avatar
wxchan committed
3927
                ctypes.byref(tmp_out_len),
Guolin Ke's avatar
Guolin Ke committed
3928
                result.ctypes.data_as(ctypes.POINTER(ctypes.c_double))))
wxchan's avatar
wxchan committed
3929
            if tmp_out_len.value != self.__num_inner_eval:
3930
                raise ValueError("Wrong length of eval results")
3931
            for i in range(self.__num_inner_eval):
3932
3933
                ret.append((data_name, self.__name_inner_eval[i],
                            result[i], self.__higher_better_inner_eval[i]))
3934
3935
        if callable(feval):
            feval = [feval]
wxchan's avatar
wxchan committed
3936
3937
3938
3939
3940
        if feval is not None:
            if data_idx == 0:
                cur_data = self.train_set
            else:
                cur_data = self.valid_sets[data_idx - 1]
3941
3942
3943
3944
3945
3946
3947
3948
3949
            for eval_function in feval:
                if eval_function is None:
                    continue
                feval_ret = eval_function(self.__inner_predict(data_idx), cur_data)
                if isinstance(feval_ret, list):
                    for eval_name, val, is_higher_better in feval_ret:
                        ret.append((data_name, eval_name, val, is_higher_better))
                else:
                    eval_name, val, is_higher_better = feval_ret
wxchan's avatar
wxchan committed
3950
3951
3952
                    ret.append((data_name, eval_name, val, is_higher_better))
        return ret

3953
    def __inner_predict(self, data_idx: int):
3954
        """Predict for training and validation dataset."""
wxchan's avatar
wxchan committed
3955
        if data_idx >= self.__num_dataset:
3956
            raise ValueError("Data_idx should be smaller than number of dataset")
wxchan's avatar
wxchan committed
3957
3958
3959
3960
3961
        if self.__inner_predict_buffer[data_idx] is None:
            if data_idx == 0:
                n_preds = self.train_set.num_data() * self.__num_class
            else:
                n_preds = self.valid_sets[data_idx - 1].num_data() * self.__num_class
3962
            self.__inner_predict_buffer[data_idx] = np.empty(n_preds, dtype=np.float64)
3963
        # avoid to predict many time in one iteration
wxchan's avatar
wxchan committed
3964
3965
        if not self.__is_predicted_cur_iter[data_idx]:
            tmp_out_len = ctypes.c_int64(0)
Guolin Ke's avatar
Guolin Ke committed
3966
            data_ptr = self.__inner_predict_buffer[data_idx].ctypes.data_as(ctypes.POINTER(ctypes.c_double))
wxchan's avatar
wxchan committed
3967
3968
            _safe_call(_LIB.LGBM_BoosterGetPredict(
                self.handle,
Guolin Ke's avatar
Guolin Ke committed
3969
                ctypes.c_int(data_idx),
wxchan's avatar
wxchan committed
3970
3971
3972
                ctypes.byref(tmp_out_len),
                data_ptr))
            if tmp_out_len.value != len(self.__inner_predict_buffer[data_idx]):
3973
                raise ValueError(f"Wrong length of predict results for data {data_idx}")
wxchan's avatar
wxchan committed
3974
            self.__is_predicted_cur_iter[data_idx] = True
3975
3976
3977
3978
3979
        result = self.__inner_predict_buffer[data_idx]
        if self.__num_class > 1:
            num_data = result.size // self.__num_class
            result = result.reshape(num_data, self.__num_class, order='F')
        return result
wxchan's avatar
wxchan committed
3980

3981
    def __get_eval_info(self) -> None:
3982
        """Get inner evaluation count and names."""
wxchan's avatar
wxchan committed
3983
3984
        if self.__need_reload_eval_info:
            self.__need_reload_eval_info = False
Guolin Ke's avatar
Guolin Ke committed
3985
            out_num_eval = ctypes.c_int(0)
3986
            # Get num of inner evals
wxchan's avatar
wxchan committed
3987
3988
3989
3990
3991
            _safe_call(_LIB.LGBM_BoosterGetEvalCounts(
                self.handle,
                ctypes.byref(out_num_eval)))
            self.__num_inner_eval = out_num_eval.value
            if self.__num_inner_eval > 0:
3992
                # Get name of eval metrics
Guolin Ke's avatar
Guolin Ke committed
3993
                tmp_out_len = ctypes.c_int(0)
3994
3995
3996
                reserved_string_buffer_size = 255
                required_string_buffer_size = ctypes.c_size_t(0)
                string_buffers = [
3997
                    ctypes.create_string_buffer(reserved_string_buffer_size) for _ in range(self.__num_inner_eval)
3998
                ]
wxchan's avatar
wxchan committed
3999
                ptr_string_buffers = (ctypes.c_char_p * self.__num_inner_eval)(*map(ctypes.addressof, string_buffers))
wxchan's avatar
wxchan committed
4000
4001
                _safe_call(_LIB.LGBM_BoosterGetEvalNames(
                    self.handle,
4002
                    ctypes.c_int(self.__num_inner_eval),
wxchan's avatar
wxchan committed
4003
                    ctypes.byref(tmp_out_len),
4004
                    ctypes.c_size_t(reserved_string_buffer_size),
4005
                    ctypes.byref(required_string_buffer_size),
wxchan's avatar
wxchan committed
4006
4007
                    ptr_string_buffers))
                if self.__num_inner_eval != tmp_out_len.value:
4008
                    raise ValueError("Length of eval names doesn't equal with num_evals")
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
                actual_string_buffer_size = required_string_buffer_size.value
                # if buffer length is not long enough, reallocate buffers
                if reserved_string_buffer_size < actual_string_buffer_size:
                    string_buffers = [
                        ctypes.create_string_buffer(actual_string_buffer_size) for _ in range(self.__num_inner_eval)
                    ]
                    ptr_string_buffers = (ctypes.c_char_p * self.__num_inner_eval)(*map(ctypes.addressof, string_buffers))
                    _safe_call(_LIB.LGBM_BoosterGetEvalNames(
                        self.handle,
                        ctypes.c_int(self.__num_inner_eval),
                        ctypes.byref(tmp_out_len),
                        ctypes.c_size_t(actual_string_buffer_size),
                        ctypes.byref(required_string_buffer_size),
                        ptr_string_buffers))
                self.__name_inner_eval = [
                    string_buffers[i].value.decode('utf-8') for i in range(self.__num_inner_eval)
                ]
                self.__higher_better_inner_eval = [
                    name.startswith(('auc', 'ndcg@', 'map@', 'average_precision')) for name in self.__name_inner_eval
                ]