basic.py 80.1 KB
Newer Older
wxchan's avatar
wxchan committed
1
# coding: utf-8
2
3
# pylint: disable = invalid-name, C0111, C0301
# pylint: disable = R0912, R0913, R0914, W0105, W0201, W0212
wxchan's avatar
wxchan committed
4
5
6
"""Wrapper c_api of LightGBM"""
from __future__ import absolute_import

7
import copy
wxchan's avatar
wxchan committed
8
import ctypes
9
import os
wxchan's avatar
wxchan committed
10
import warnings
wxchan's avatar
wxchan committed
11
from tempfile import NamedTemporaryFile
wxchan's avatar
wxchan committed
12
13
14
15

import numpy as np
import scipy.sparse

16
17
18
19
from .compat import (DataFrame, LGBMDeprecationWarning, Series,
                     decode_string, integer_types,
                     json, json_default_with_numpy,
                     numeric_types, range_, string_type)
wxchan's avatar
wxchan committed
20
21
from .libpath import find_lib_path

wxchan's avatar
wxchan committed
22

wxchan's avatar
wxchan committed
23
24
25
26
def _load_lib():
    """Load LightGBM Library."""
    lib_path = find_lib_path()
    if len(lib_path) == 0:
27
        return None
wxchan's avatar
wxchan committed
28
29
30
31
    lib = ctypes.cdll.LoadLibrary(lib_path[0])
    lib.LGBM_GetLastError.restype = ctypes.c_char_p
    return lib

wxchan's avatar
wxchan committed
32

wxchan's avatar
wxchan committed
33
34
_LIB = _load_lib()

wxchan's avatar
wxchan committed
35

wxchan's avatar
wxchan committed
36
37
38
39
class LightGBMError(Exception):
    """Error throwed by LightGBM"""
    pass

wxchan's avatar
wxchan committed
40

wxchan's avatar
wxchan committed
41
42
43
44
45
46
47
48
def _safe_call(ret):
    """Check the return value of C API call
    Parameters
    ----------
    ret : int
        return value from API calls
    """
    if ret != 0:
49
        raise LightGBMError(decode_string(_LIB.LGBM_GetLastError()))
wxchan's avatar
wxchan committed
50

wxchan's avatar
wxchan committed
51

wxchan's avatar
wxchan committed
52
53
54
55
56
def is_numeric(obj):
    """Check is a number or not, include numpy number etc."""
    try:
        float(obj)
        return True
wxchan's avatar
wxchan committed
57
58
59
    except (TypeError, ValueError):
        # TypeError: obj is not a string or a number
        # ValueError: invalid literal
wxchan's avatar
wxchan committed
60
61
        return False

wxchan's avatar
wxchan committed
62

wxchan's avatar
wxchan committed
63
def is_numpy_1d_array(data):
Guolin Ke's avatar
Guolin Ke committed
64
    """Check is 1d numpy array"""
65
    return isinstance(data, np.ndarray) and len(data.shape) == 1
wxchan's avatar
wxchan committed
66

wxchan's avatar
wxchan committed
67

wxchan's avatar
wxchan committed
68
def is_1d_list(data):
Guolin Ke's avatar
Guolin Ke committed
69
    """Check is 1d list"""
70
    return isinstance(data, list) and \
71
        (not data or is_numeric(data[0]))
wxchan's avatar
wxchan committed
72

wxchan's avatar
wxchan committed
73

74
def list_to_1d_numpy(data, dtype=np.float32, name='list'):
Guolin Ke's avatar
Guolin Ke committed
75
    """convert to 1d numpy array"""
wxchan's avatar
wxchan committed
76
77
78
79
80
81
82
    if is_numpy_1d_array(data):
        if data.dtype == dtype:
            return data
        else:
            return data.astype(dtype=dtype, copy=False)
    elif is_1d_list(data):
        return np.array(data, dtype=dtype, copy=False)
83
84
    elif isinstance(data, Series):
        return data.values.astype(dtype)
wxchan's avatar
wxchan committed
85
    else:
86
        raise TypeError("Wrong type({}) for {}, should be list or numpy array".format(type(data).__name__, name))
wxchan's avatar
wxchan committed
87

wxchan's avatar
wxchan committed
88

wxchan's avatar
wxchan committed
89
90
91
92
def cfloat32_array_to_numpy(cptr, length):
    """Convert a ctypes float pointer array to a numpy array.
    """
    if isinstance(cptr, ctypes.POINTER(ctypes.c_float)):
93
        return np.fromiter(cptr, dtype=np.float32, count=length)
wxchan's avatar
wxchan committed
94
    else:
95
        raise RuntimeError('Expected float pointer')
wxchan's avatar
wxchan committed
96

Guolin Ke's avatar
Guolin Ke committed
97

Guolin Ke's avatar
Guolin Ke committed
98
99
100
101
102
103
104
105
def cfloat64_array_to_numpy(cptr, length):
    """Convert a ctypes double pointer array to a numpy array.
    """
    if isinstance(cptr, ctypes.POINTER(ctypes.c_double)):
        return np.fromiter(cptr, dtype=np.float64, count=length)
    else:
        raise RuntimeError('Expected double pointer')

wxchan's avatar
wxchan committed
106

wxchan's avatar
wxchan committed
107
108
109
110
def cint32_array_to_numpy(cptr, length):
    """Convert a ctypes float pointer array to a numpy array.
    """
    if isinstance(cptr, ctypes.POINTER(ctypes.c_int32)):
111
        return np.fromiter(cptr, dtype=np.int32, count=length)
wxchan's avatar
wxchan committed
112
    else:
113
        raise RuntimeError('Expected int pointer')
wxchan's avatar
wxchan committed
114

wxchan's avatar
wxchan committed
115

wxchan's avatar
wxchan committed
116
117
118
119
def c_str(string):
    """Convert a python string to cstring."""
    return ctypes.c_char_p(string.encode('utf-8'))

wxchan's avatar
wxchan committed
120

wxchan's avatar
wxchan committed
121
122
123
124
def c_array(ctype, values):
    """Convert a python array to c array."""
    return (ctype * len(values))(*values)

wxchan's avatar
wxchan committed
125

wxchan's avatar
wxchan committed
126
def param_dict_to_str(data):
127
    if data is None or not data:
wxchan's avatar
wxchan committed
128
129
130
        return ""
    pairs = []
    for key, val in data.items():
131
        if isinstance(val, (list, tuple, set)) or is_numpy_1d_array(val):
wxchan's avatar
wxchan committed
132
            pairs.append(str(key) + '=' + ','.join(map(str, val)))
wxchan's avatar
wxchan committed
133
        elif isinstance(val, string_type) or isinstance(val, numeric_types) or is_numeric(val):
wxchan's avatar
wxchan committed
134
            pairs.append(str(key) + '=' + str(val))
135
        elif val is not None:
136
            raise TypeError('Unknown type of parameter:%s, got:%s'
wxchan's avatar
wxchan committed
137
138
                            % (key, type(val).__name__))
    return ' '.join(pairs)
139

wxchan's avatar
wxchan committed
140

141
class _temp_file(object):
142
143
144
145
    def __enter__(self):
        with NamedTemporaryFile(prefix="lightgbm_tmp_", delete=True) as f:
            self.name = f.name
        return self
wxchan's avatar
wxchan committed
146

147
148
149
    def __exit__(self, exc_type, exc_val, exc_tb):
        if os.path.isfile(self.name):
            os.remove(self.name)
wxchan's avatar
wxchan committed
150

151
152
153
154
    def readlines(self):
        with open(self.name, "r+") as f:
            ret = f.readlines()
        return ret
wxchan's avatar
wxchan committed
155

156
157
    def writelines(self, lines):
        with open(self.name, "w+") as f:
158
            f.writelines(lines)
159

wxchan's avatar
wxchan committed
160

wxchan's avatar
wxchan committed
161
162
163
164
165
"""marco definition of data type in c_api of LightGBM"""
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
166

wxchan's avatar
wxchan committed
167
168
169
"""Matric is row major in python"""
C_API_IS_ROW_MAJOR = 1

Guolin Ke's avatar
Guolin Ke committed
170
"""marco definition of prediction type in c_api of LightGBM"""
wxchan's avatar
wxchan committed
171
172
173
C_API_PREDICT_NORMAL = 0
C_API_PREDICT_RAW_SCORE = 1
C_API_PREDICT_LEAF_INDEX = 2
174
C_API_PREDICT_CONTRIB = 3
wxchan's avatar
wxchan committed
175

Guolin Ke's avatar
Guolin Ke committed
176
"""data type of data field"""
wxchan's avatar
wxchan committed
177
178
FIELD_TYPE_MAPPER = {"label": C_API_DTYPE_FLOAT32,
                     "weight": C_API_DTYPE_FLOAT32,
Guolin Ke's avatar
Guolin Ke committed
179
                     "init_score": C_API_DTYPE_FLOAT64,
wxchan's avatar
wxchan committed
180
181
                     "group": C_API_DTYPE_INT32}

wxchan's avatar
wxchan committed
182

183
184
185
186
def convert_from_sliced_object(data):
    """fix the memory of multi-dimensional sliced object"""
    if data.base is not None and isinstance(data, np.ndarray) and isinstance(data.base, np.ndarray):
        if not data.flags.c_contiguous:
187
            warnings.warn("Usage subset(sliced data) of np.ndarray is not recommended due to it will double the peak memory cost in LightGBM.")
188
189
190
191
            return np.copy(data)
    return data


wxchan's avatar
wxchan committed
192
def c_float_array(data):
Guolin Ke's avatar
Guolin Ke committed
193
    """get pointer of float numpy array / list"""
wxchan's avatar
wxchan committed
194
195
196
    if is_1d_list(data):
        data = np.array(data, copy=False)
    if is_numpy_1d_array(data):
197
198
        data = convert_from_sliced_object(data)
        assert data.flags.c_contiguous
wxchan's avatar
wxchan committed
199
200
201
202
203
204
205
        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:
206
            raise TypeError("Expected np.float32 or np.float64, met type({})"
wxchan's avatar
wxchan committed
207
208
                            .format(data.dtype))
    else:
209
        raise TypeError("Unknown type({})".format(type(data).__name__))
210
    return (ptr_data, type_data, data)  # return `data` to avoid the temporary copy is freed
wxchan's avatar
wxchan committed
211

wxchan's avatar
wxchan committed
212

wxchan's avatar
wxchan committed
213
def c_int_array(data):
Guolin Ke's avatar
Guolin Ke committed
214
    """get pointer of int numpy array / list"""
wxchan's avatar
wxchan committed
215
216
217
    if is_1d_list(data):
        data = np.array(data, copy=False)
    if is_numpy_1d_array(data):
218
219
        data = convert_from_sliced_object(data)
        assert data.flags.c_contiguous
wxchan's avatar
wxchan committed
220
221
222
223
224
225
226
        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:
227
            raise TypeError("Expected np.int32 or np.int64, met type({})"
wxchan's avatar
wxchan committed
228
229
                            .format(data.dtype))
    else:
230
        raise TypeError("Unknown type({})".format(type(data).__name__))
231
    return (ptr_data, type_data, data)  # return `data` to avoid the temporary copy is freed
wxchan's avatar
wxchan committed
232

wxchan's avatar
wxchan committed
233

234
235
236
237
238
239
PANDAS_DTYPE_MAPPER = {'int8': 'int', 'int16': 'int', 'int32': 'int',
                       'int64': 'int', 'uint8': 'int', 'uint16': 'int',
                       'uint32': 'int', 'uint64': 'int', 'float16': 'float',
                       'float32': 'float', 'float64': 'float', 'bool': 'int'}


240
def _data_from_pandas(data, feature_name, categorical_feature, pandas_categorical):
241
    if isinstance(data, DataFrame):
242
243
        if len(data.shape) != 2 or data.shape[0] < 1:
            raise ValueError('Input data must be 2 dimensional and non empty.')
244
245
246
247
248
249
250
251
252
253
254
255
256
        if feature_name == 'auto' or feature_name is None:
            data = data.rename(columns=str)
        cat_cols = data.select_dtypes(include=['category']).columns
        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.')
            for col, category in zip(cat_cols, pandas_categorical):
                if list(data[col].cat.categories) != list(category):
                    data[col] = data[col].cat.set_categories(category)
        if len(cat_cols):  # cat_cols is pandas Index object
            data = data.copy()  # not alter origin DataFrame
257
            data[cat_cols] = data[cat_cols].apply(lambda x: x.cat.codes).replace({-1: np.nan})
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
        if categorical_feature is not None:
            if feature_name is None:
                feature_name = list(data.columns)
            if categorical_feature == 'auto':
                categorical_feature = list(cat_cols)
            else:
                categorical_feature = list(categorical_feature) + list(cat_cols)
        if feature_name == 'auto':
            feature_name = list(data.columns)
        data_dtypes = data.dtypes
        if not all(dtype.name in PANDAS_DTYPE_MAPPER for dtype in data_dtypes):
            bad_fields = [data.columns[i] for i, dtype in
                          enumerate(data_dtypes) if dtype.name not in PANDAS_DTYPE_MAPPER]

            msg = """DataFrame.dtypes for data must be int, float or bool. Did not expect the data types in fields """
            raise ValueError(msg + ', '.join(bad_fields))
274
        data = data.values.astype('float')
275
276
277
278
279
280
    else:
        if feature_name == 'auto':
            feature_name = None
        if categorical_feature == 'auto':
            categorical_feature = None
    return data, feature_name, categorical_feature, pandas_categorical
281
282
283
284
285
286
287
288
289
290
291
292
293


def _label_from_pandas(label):
    if isinstance(label, DataFrame):
        if len(label.columns) > 1:
            raise ValueError('DataFrame for label cannot have multiple columns')
        label_dtypes = label.dtypes
        if not all(dtype.name in PANDAS_DTYPE_MAPPER for dtype in label_dtypes):
            raise ValueError('DataFrame.dtypes for label must be int, float or bool')
        label = label.values.astype('float')
    return label


294
295
def _save_pandas_categorical(file_name, pandas_categorical):
    with open(file_name, 'a') as f:
Guolin Ke's avatar
Guolin Ke committed
296
        f.write('\npandas_categorical:' + json.dumps(pandas_categorical, default=json_default_with_numpy) + '\n')
297
298
299
300


def _load_pandas_categorical(file_name):
    with open(file_name, 'r') as f:
Guolin Ke's avatar
Guolin Ke committed
301
302
303
304
        lines = f.readlines()
        last_line = lines[-1]
        if last_line.strip() == "":
            last_line = lines[-2]
305
306
307
308
309
        if last_line.startswith('pandas_categorical:'):
            return json.loads(last_line[len('pandas_categorical:'):])
    return None


Guolin Ke's avatar
Guolin Ke committed
310
311
class _InnerPredictor(object):
    """
312
313
    A _InnerPredictor of LightGBM.
    Only used for prediction, usually used for continued-train
Guolin Ke's avatar
Guolin Ke committed
314
    Note: Can convert from Booster, but cannot convert to Booster
wxchan's avatar
wxchan committed
315
    """
316
    def __init__(self, model_file=None, booster_handle=None, pred_parameter=None):
Guolin Ke's avatar
Guolin Ke committed
317
        """Initialize the _InnerPredictor. Not expose to user
wxchan's avatar
wxchan committed
318
319
320
321
322

        Parameters
        ----------
        model_file : string
            Path to the model file.
Guolin Ke's avatar
Guolin Ke committed
323
324
        booster_handle : Handle of Booster
            use handle to init
325
326
        pred_parameter: dict
            Other parameters for the prediciton
wxchan's avatar
wxchan committed
327
328
329
330
331
        """
        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
332
            out_num_iterations = ctypes.c_int(0)
wxchan's avatar
wxchan committed
333
334
335
336
            _safe_call(_LIB.LGBM_BoosterCreateFromModelfile(
                c_str(model_file),
                ctypes.byref(out_num_iterations),
                ctypes.byref(self.handle)))
Guolin Ke's avatar
Guolin Ke committed
337
            out_num_class = ctypes.c_int(0)
wxchan's avatar
wxchan committed
338
339
340
341
            _safe_call(_LIB.LGBM_BoosterGetNumClasses(
                self.handle,
                ctypes.byref(out_num_class)))
            self.num_class = out_num_class.value
342
            self.num_total_iteration = out_num_iterations.value
343
            self.pandas_categorical = _load_pandas_categorical(model_file)
wxchan's avatar
wxchan committed
344
        elif booster_handle is not None:
Guolin Ke's avatar
Guolin Ke committed
345
            self.__is_manage_handle = False
wxchan's avatar
wxchan committed
346
            self.handle = booster_handle
Guolin Ke's avatar
Guolin Ke committed
347
            out_num_class = ctypes.c_int(0)
wxchan's avatar
wxchan committed
348
349
350
351
            _safe_call(_LIB.LGBM_BoosterGetNumClasses(
                self.handle,
                ctypes.byref(out_num_class)))
            self.num_class = out_num_class.value
Guolin Ke's avatar
Guolin Ke committed
352
            out_num_iterations = ctypes.c_int(0)
wxchan's avatar
wxchan committed
353
354
355
            _safe_call(_LIB.LGBM_BoosterGetCurrentIteration(
                self.handle,
                ctypes.byref(out_num_iterations)))
356
            self.num_total_iteration = out_num_iterations.value
357
            self.pandas_categorical = None
wxchan's avatar
wxchan committed
358
        else:
Guolin Ke's avatar
Guolin Ke committed
359
            raise TypeError('Need Model file or Booster handle to create a predictor')
wxchan's avatar
wxchan committed
360

361
362
        pred_parameter = {} if pred_parameter is None else pred_parameter
        self.pred_parameter = param_dict_to_str(pred_parameter)
cbecker's avatar
cbecker committed
363

wxchan's avatar
wxchan committed
364
    def __del__(self):
365
366
367
368
369
        try:
            if self.__is_manage_handle:
                _safe_call(_LIB.LGBM_BoosterFree(self.handle))
        except AttributeError:
            pass
wxchan's avatar
wxchan committed
370

371
372
373
374
375
    def __getstate__(self):
        this = self.__dict__.copy()
        this.pop('handle', None)
        return this

wxchan's avatar
wxchan committed
376
    def predict(self, data, num_iteration=-1,
377
                raw_score=False, pred_leaf=False, pred_contrib=False, data_has_header=False,
wxchan's avatar
wxchan committed
378
379
380
381
382
383
384
385
                is_reshape=True):
        """
        Predict logic

        Parameters
        ----------
        data : string/numpy array/scipy.sparse
            Data source for prediction
386
            When data type is string, it represents the path of txt file
wxchan's avatar
wxchan committed
387
        num_iteration : int
388
            Used iteration for prediction
wxchan's avatar
wxchan committed
389
390
391
392
        raw_score : bool
            True for predict raw score
        pred_leaf : bool
            True for predict leaf index
393
394
        pred_contrib : bool
            True for predict feature contributions
wxchan's avatar
wxchan committed
395
        data_has_header : bool
Guolin Ke's avatar
Guolin Ke committed
396
            Used for txt data, True if txt data has header
wxchan's avatar
wxchan committed
397
        is_reshape : bool
398
            Reshape to (nrow, ncol) if true
wxchan's avatar
wxchan committed
399
400
401
402
403

        Returns
        -------
        Prediction result
        """
wxchan's avatar
wxchan committed
404
        if isinstance(data, Dataset):
405
            raise TypeError("Cannot use Dataset instance for prediction, please use raw data instead")
406
        data = _data_from_pandas(data, None, None, self.pandas_categorical)[0]
wxchan's avatar
wxchan committed
407
408
409
410
411
        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
412
413
        if pred_contrib:
            predict_type = C_API_PREDICT_CONTRIB
wxchan's avatar
wxchan committed
414
        int_data_has_header = 1 if data_has_header else 0
415
416
        if num_iteration > self.num_total_iteration:
            num_iteration = self.num_total_iteration
cbecker's avatar
cbecker committed
417

wxchan's avatar
wxchan committed
418
        if isinstance(data, string_type):
419
            with _temp_file() as f:
wxchan's avatar
wxchan committed
420
421
422
                _safe_call(_LIB.LGBM_BoosterPredictForFile(
                    self.handle,
                    c_str(data),
Guolin Ke's avatar
Guolin Ke committed
423
424
425
                    ctypes.c_int(int_data_has_header),
                    ctypes.c_int(predict_type),
                    ctypes.c_int(num_iteration),
426
                    c_str(self.pred_parameter),
wxchan's avatar
wxchan committed
427
428
                    c_str(f.name)))
                lines = f.readlines()
429
430
                nrow = len(lines)
                preds = [float(token) for line in lines for token in line.split('\t')]
Guolin Ke's avatar
Guolin Ke committed
431
                preds = np.array(preds, dtype=np.float64, copy=False)
wxchan's avatar
wxchan committed
432
433
434
        elif isinstance(data, scipy.sparse.csr_matrix):
            preds, nrow = self.__pred_for_csr(data, num_iteration,
                                              predict_type)
Guolin Ke's avatar
Guolin Ke committed
435
436
437
        elif isinstance(data, scipy.sparse.csc_matrix):
            preds, nrow = self.__pred_for_csc(data, num_iteration,
                                              predict_type)
wxchan's avatar
wxchan committed
438
439
440
        elif isinstance(data, np.ndarray):
            preds, nrow = self.__pred_for_np2d(data, num_iteration,
                                               predict_type)
441
442
443
        elif isinstance(data, list):
            try:
                data = np.array(data)
444
            except BaseException:
445
446
447
                raise ValueError('Cannot convert data list to numpy array.')
            preds, nrow = self.__pred_for_np2d(data, num_iteration,
                                               predict_type)
wxchan's avatar
wxchan committed
448
449
        else:
            try:
450
                warnings.warn('Converting data to scipy sparse matrix.')
wxchan's avatar
wxchan committed
451
                csr = scipy.sparse.csr_matrix(data)
452
            except BaseException:
453
                raise TypeError('Cannot predict data for type {}'.format(type(data).__name__))
454
455
            preds, nrow = self.__pred_for_csr(csr, num_iteration,
                                              predict_type)
wxchan's avatar
wxchan committed
456
457
        if pred_leaf:
            preds = preds.astype(np.int32)
458
        if is_reshape and preds.size != nrow:
wxchan's avatar
wxchan committed
459
            if preds.size % nrow == 0:
460
                preds = preds.reshape(nrow, -1)
wxchan's avatar
wxchan committed
461
            else:
462
                raise ValueError('Length of predict result (%d) cannot be divide nrow (%d)'
wxchan's avatar
wxchan committed
463
464
465
466
                                 % (preds.size, nrow))
        return preds

    def __get_num_preds(self, num_iteration, nrow, predict_type):
Guolin Ke's avatar
Guolin Ke committed
467
468
469
        """
        Get size of prediction result
        """
Guolin Ke's avatar
Guolin Ke committed
470
471
472
        n_preds = ctypes.c_int64(0)
        _safe_call(_LIB.LGBM_BoosterCalcNumPredict(
            self.handle,
Guolin Ke's avatar
Guolin Ke committed
473
474
475
            ctypes.c_int(nrow),
            ctypes.c_int(predict_type),
            ctypes.c_int(num_iteration),
Guolin Ke's avatar
Guolin Ke committed
476
477
            ctypes.byref(n_preds)))
        return n_preds.value
wxchan's avatar
wxchan committed
478
479
480
481
482
483

    def __pred_for_np2d(self, mat, num_iteration, predict_type):
        """
        Predict for a 2-D numpy matrix.
        """
        if len(mat.shape) != 2:
484
            raise ValueError('Input numpy.ndarray or list must be 2 dimensional')
wxchan's avatar
wxchan committed
485
486
487
488
489
490

        if mat.dtype == np.float32 or mat.dtype == np.float64:
            data = np.array(mat.reshape(mat.size), dtype=mat.dtype, copy=False)
        else:
            """change non-float data to float data, need to copy"""
            data = np.array(mat.reshape(mat.size), dtype=np.float32)
491
        ptr_data, type_ptr_data, _ = c_float_array(data)
wxchan's avatar
wxchan committed
492
493
        n_preds = self.__get_num_preds(num_iteration, mat.shape[0],
                                       predict_type)
Guolin Ke's avatar
Guolin Ke committed
494
        preds = np.zeros(n_preds, dtype=np.float64)
wxchan's avatar
wxchan committed
495
496
497
498
        out_num_preds = ctypes.c_int64(0)
        _safe_call(_LIB.LGBM_BoosterPredictForMat(
            self.handle,
            ptr_data,
Guolin Ke's avatar
Guolin Ke committed
499
500
501
502
503
504
            ctypes.c_int(type_ptr_data),
            ctypes.c_int(mat.shape[0]),
            ctypes.c_int(mat.shape[1]),
            ctypes.c_int(C_API_IS_ROW_MAJOR),
            ctypes.c_int(predict_type),
            ctypes.c_int(num_iteration),
505
            c_str(self.pred_parameter),
wxchan's avatar
wxchan committed
506
            ctypes.byref(out_num_preds),
wxchan's avatar
wxchan committed
507
            preds.ctypes.data_as(ctypes.POINTER(ctypes.c_double))))
wxchan's avatar
wxchan committed
508
        if n_preds != out_num_preds.value:
509
            raise ValueError("Wrong length for predict results")
wxchan's avatar
wxchan committed
510
511
512
513
514
515
516
517
        return preds, mat.shape[0]

    def __pred_for_csr(self, csr, num_iteration, predict_type):
        """
        Predict for a csr data
        """
        nrow = len(csr.indptr) - 1
        n_preds = self.__get_num_preds(num_iteration, nrow, predict_type)
Guolin Ke's avatar
Guolin Ke committed
518
        preds = np.zeros(n_preds, dtype=np.float64)
wxchan's avatar
wxchan committed
519
520
        out_num_preds = ctypes.c_int64(0)

521
522
        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
523
524
525
526

        _safe_call(_LIB.LGBM_BoosterPredictForCSR(
            self.handle,
            ptr_indptr,
Guolin Ke's avatar
Guolin Ke committed
527
            ctypes.c_int32(type_ptr_indptr),
wxchan's avatar
wxchan committed
528
529
            csr.indices.ctypes.data_as(ctypes.POINTER(ctypes.c_int32)),
            ptr_data,
Guolin Ke's avatar
Guolin Ke committed
530
531
532
533
534
535
            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),
            ctypes.c_int(num_iteration),
536
            c_str(self.pred_parameter),
wxchan's avatar
wxchan committed
537
            ctypes.byref(out_num_preds),
wxchan's avatar
wxchan committed
538
            preds.ctypes.data_as(ctypes.POINTER(ctypes.c_double))))
Guolin Ke's avatar
Guolin Ke committed
539
540
541
542
543
544
545
546
547
548
549
550
551
        if n_preds != out_num_preds.value:
            raise ValueError("Wrong length for predict results")
        return preds, nrow

    def __pred_for_csc(self, csc, num_iteration, predict_type):
        """
        Predict for a csc data
        """
        nrow = csc.shape[0]
        n_preds = self.__get_num_preds(num_iteration, nrow, predict_type)
        preds = np.zeros(n_preds, dtype=np.float64)
        out_num_preds = ctypes.c_int64(0)

552
553
        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
554
555
556
557

        _safe_call(_LIB.LGBM_BoosterPredictForCSC(
            self.handle,
            ptr_indptr,
Guolin Ke's avatar
Guolin Ke committed
558
            ctypes.c_int32(type_ptr_indptr),
Guolin Ke's avatar
Guolin Ke committed
559
560
            csc.indices.ctypes.data_as(ctypes.POINTER(ctypes.c_int32)),
            ptr_data,
Guolin Ke's avatar
Guolin Ke committed
561
562
563
564
565
566
            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),
            ctypes.c_int(num_iteration),
567
            c_str(self.pred_parameter),
Guolin Ke's avatar
Guolin Ke committed
568
            ctypes.byref(out_num_preds),
wxchan's avatar
wxchan committed
569
            preds.ctypes.data_as(ctypes.POINTER(ctypes.c_double))))
wxchan's avatar
wxchan committed
570
        if n_preds != out_num_preds.value:
571
            raise ValueError("Wrong length for predict results")
wxchan's avatar
wxchan committed
572
573
        return preds, nrow

wxchan's avatar
wxchan committed
574

wxchan's avatar
wxchan committed
575
576
class Dataset(object):
    """Dataset in LightGBM."""
577
    def __init__(self, data, label=None, reference=None,
578
                 weight=None, group=None, init_score=None, silent=False,
579
                 feature_name='auto', categorical_feature='auto', params=None,
wxchan's avatar
wxchan committed
580
                 free_raw_data=True):
581
582
        """Constract Dataset.

wxchan's avatar
wxchan committed
583
584
        Parameters
        ----------
585
        data : string, numpy array, scipy.sparse or list of numpy arrays
wxchan's avatar
wxchan committed
586
            Data source of Dataset.
587
            If string, it represents the path to txt file.
588
        label : list, numpy 1-D array or None, optional (default=None)
589
590
591
592
            Label of the data.
        reference : Dataset or None, optional (default=None)
            If this is Dataset for validation, training data should be used as reference.
        weight : list, numpy 1-D array or None, optional (default=None)
wxchan's avatar
wxchan committed
593
            Weight for each instance.
594
595
        group : list, numpy 1-D array or None, optional (default=None)
            Group/query size for Dataset.
596
597
        init_score : list, numpy 1-D array or None, optional (default=None)
            Init score for Dataset.
598
599
600
601
602
603
604
605
606
607
        silent : bool, optional (default=False)
            Whether to print messages during construction.
        feature_name : list of strings or 'auto', optional (default="auto")
            Feature names.
            If 'auto' and data is pandas DataFrame, data columns names are used.
        categorical_feature : list of strings or int, or 'auto', optional (default="auto")
            Categorical features.
            If list of int, interpreted as indices.
            If list of strings, interpreted as feature names (need to specify ``feature_name`` as well).
            If 'auto' and data is pandas DataFrame, pandas categorical columns are used.
608
            All values should be less than int32 max value (2147483647).
609
610
611
612
        params: dict or None, optional (default=None)
            Other parameters.
        free_raw_data: bool, optional (default=True)
            If True, raw data is freed after constructing inner Dataset.
wxchan's avatar
wxchan committed
613
        """
wxchan's avatar
wxchan committed
614
615
616
617
618
619
        self.handle = None
        self.data = data
        self.label = label
        self.reference = reference
        self.weight = weight
        self.group = group
620
        self.init_score = init_score
wxchan's avatar
wxchan committed
621
622
        self.silent = silent
        self.feature_name = feature_name
623
        self.categorical_feature = categorical_feature
624
        self.params = copy.deepcopy(params)
wxchan's avatar
wxchan committed
625
626
627
        self.free_raw_data = free_raw_data
        self.used_indices = None
        self._predictor = None
628
        self.pandas_categorical = None
629
        self.params_back_up = None
wxchan's avatar
wxchan committed
630
631

    def __del__(self):
632
633
634
635
        try:
            self._free_handle()
        except AttributeError:
            pass
636
637

    def _free_handle(self):
638
        if self.handle is not None:
639
            _safe_call(_LIB.LGBM_DatasetFree(self.handle))
640
            self.handle = None
wxchan's avatar
wxchan committed
641

642
    def _lazy_init(self, data, label=None, reference=None,
643
                   weight=None, group=None, init_score=None, predictor=None,
wxchan's avatar
wxchan committed
644
                   silent=False, feature_name='auto',
645
                   categorical_feature='auto', params=None):
wxchan's avatar
wxchan committed
646
647
648
        if data is None:
            self.handle = None
            return
Guolin Ke's avatar
Guolin Ke committed
649
650
651
        if reference is not None:
            self.pandas_categorical = reference.pandas_categorical
            categorical_feature = reference.categorical_feature
652
        data, feature_name, categorical_feature, self.pandas_categorical = _data_from_pandas(data, feature_name, categorical_feature, self.pandas_categorical)
wxchan's avatar
wxchan committed
653
654
        label = _label_from_pandas(label)
        self.data_has_header = False
655
        # process for args
wxchan's avatar
wxchan committed
656
        params = {} if params is None else params
657
658
659
660
661
        args_names = getattr(self.__class__, '_lazy_init').__code__.co_varnames[:getattr(self.__class__, '_lazy_init').__code__.co_argcount]
        for key, _ in params.items():
            if key in args_names:
                warnings.warn('{0} keyword has been found in `params` and will be ignored. '
                              'Please use {0} argument of the Dataset constructor to pass this parameter.'.format(key))
wxchan's avatar
wxchan committed
662
663
664
        self.predictor = predictor
        if silent:
            params["verbose"] = 0
665
        # get categorical features
666
667
668
669
670
671
672
673
674
675
676
677
678
        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:
                if isinstance(name, string_type) and name in feature_dict:
                    categorical_indices.add(feature_dict[name])
                elif isinstance(name, integer_types):
                    categorical_indices.add(name)
                else:
                    raise TypeError("Wrong type({}) or unknown name({}) in categorical_feature"
                                    .format(type(name).__name__, name))
679
            if categorical_indices:
680
                if "categorical_feature" in params or "categorical_column" in params:
681
                    warnings.warn('categorical_feature in param dict is overridden.')
682
683
                    params.pop("categorical_feature", None)
                    params.pop("categorical_column", None)
684
                params['categorical_column'] = sorted(categorical_indices)
685

wxchan's avatar
wxchan committed
686
        params_str = param_dict_to_str(params)
687
        # process for reference dataset
wxchan's avatar
wxchan committed
688
        ref_dataset = None
wxchan's avatar
wxchan committed
689
        if isinstance(reference, Dataset):
690
            ref_dataset = reference.construct().handle
wxchan's avatar
wxchan committed
691
692
        elif reference is not None:
            raise TypeError('Reference dataset should be None or dataset instance')
693
        # start construct data
wxchan's avatar
wxchan committed
694
        if isinstance(data, string_type):
695
            # check data has header or not
Guolin Ke's avatar
Guolin Ke committed
696
            if str(params.get("has_header", "")).lower() == "true" \
wxchan's avatar
wxchan committed
697
                    or str(params.get("header", "")).lower() == "true":
698
                self.data_has_header = True
wxchan's avatar
wxchan committed
699
700
701
702
703
704
705
706
            self.handle = ctypes.c_void_p()
            _safe_call(_LIB.LGBM_DatasetCreateFromFile(
                c_str(data),
                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
707
708
        elif isinstance(data, scipy.sparse.csc_matrix):
            self.__init_from_csc(data, params_str, ref_dataset)
wxchan's avatar
wxchan committed
709
710
        elif isinstance(data, np.ndarray):
            self.__init_from_np2d(data, params_str, ref_dataset)
711
712
        elif isinstance(data, list) and len(data) > 0 and all(isinstance(x, np.ndarray) for x in data):
            self.__init_from_list_np2d(data, params_str, ref_dataset)
wxchan's avatar
wxchan committed
713
714
715
716
        else:
            try:
                csr = scipy.sparse.csr_matrix(data)
                self.__init_from_csr(csr, params_str, ref_dataset)
717
            except BaseException:
wxchan's avatar
wxchan committed
718
                raise TypeError('Cannot initialize Dataset from {}'.format(type(data).__name__))
wxchan's avatar
wxchan committed
719
720
721
        if label is not None:
            self.set_label(label)
        if self.get_label() is None:
722
            raise ValueError("Label should not be None")
wxchan's avatar
wxchan committed
723
724
725
726
727
        if weight is not None:
            self.set_weight(weight)
        if group is not None:
            self.set_group(group)
        # load init score
728
729
730
        if init_score is not None:
            self.set_init_score(init_score)
            if self.predictor is not None:
731
                warnings.warn("The prediction of init_model will be overridden by init_score.")
732
        elif isinstance(self.predictor, _InnerPredictor):
wxchan's avatar
wxchan committed
733
734
735
736
737
738
            init_score = self.predictor.predict(data,
                                                raw_score=True,
                                                data_has_header=self.data_has_header,
                                                is_reshape=False)
            if self.predictor.num_class > 1:
                # need re group init score
wxchan's avatar
wxchan committed
739
                new_init_score = np.zeros(init_score.size, dtype=np.float32)
wxchan's avatar
wxchan committed
740
                num_data = self.num_data()
wxchan's avatar
wxchan committed
741
742
                for i in range_(num_data):
                    for j in range_(self.predictor.num_class):
wxchan's avatar
wxchan committed
743
744
745
                        new_init_score[j * num_data + i] = init_score[i * self.predictor.num_class + j]
                init_score = new_init_score
            self.set_init_score(init_score)
Guolin Ke's avatar
Guolin Ke committed
746
747
        elif self.predictor is not None:
            raise TypeError('wrong predictor type {}'.format(type(self.predictor).__name__))
Guolin Ke's avatar
Guolin Ke committed
748
749
        # set feature names
        self.set_feature_name(feature_name)
wxchan's avatar
wxchan committed
750
751
752
753
754
755
756
757
758
759
760
761

    def __init_from_np2d(self, mat, params_str, ref_dataset):
        """
        Initialize data from a 2-D numpy matrix.
        """
        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)
        else:
762
            # change non-float data to float data, need to copy
wxchan's avatar
wxchan committed
763
764
            data = np.array(mat.reshape(mat.size), dtype=np.float32)

765
        ptr_data, type_ptr_data, _ = c_float_array(data)
wxchan's avatar
wxchan committed
766
767
        _safe_call(_LIB.LGBM_DatasetCreateFromMat(
            ptr_data,
Guolin Ke's avatar
Guolin Ke committed
768
769
770
771
            ctypes.c_int(type_ptr_data),
            ctypes.c_int(mat.shape[0]),
            ctypes.c_int(mat.shape[1]),
            ctypes.c_int(C_API_IS_ROW_MAJOR),
wxchan's avatar
wxchan committed
772
773
774
775
            c_str(params_str),
            ref_dataset,
            ctypes.byref(self.handle)))

776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
    def __init_from_list_np2d(self, mats, params_str, ref_dataset):
        """
        Initialize data from list of 2-D numpy matrices.
        """
        ncol = mats[0].shape[1]
        nrow = np.zeros((len(mats),), np.int32)
        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)
            else:
                # change non-float data to float data, need to copy
                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(
            ctypes.c_int(len(mats)),
            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)),
            ctypes.c_int(ncol),
            ctypes.c_int(C_API_IS_ROW_MAJOR),
            c_str(params_str),
            ref_dataset,
            ctypes.byref(self.handle)))

wxchan's avatar
wxchan committed
824
825
826
827
828
    def __init_from_csr(self, csr, params_str, ref_dataset):
        """
        Initialize data from a CSR matrix.
        """
        if len(csr.indices) != len(csr.data):
829
            raise ValueError('Length mismatch: {} vs {}'.format(len(csr.indices), len(csr.data)))
wxchan's avatar
wxchan committed
830
831
        self.handle = ctypes.c_void_p()

832
833
        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
834
835
836

        _safe_call(_LIB.LGBM_DatasetCreateFromCSR(
            ptr_indptr,
Guolin Ke's avatar
Guolin Ke committed
837
            ctypes.c_int(type_ptr_indptr),
wxchan's avatar
wxchan committed
838
839
            csr.indices.ctypes.data_as(ctypes.POINTER(ctypes.c_int32)),
            ptr_data,
Guolin Ke's avatar
Guolin Ke committed
840
841
842
843
            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
844
845
846
847
            c_str(params_str),
            ref_dataset,
            ctypes.byref(self.handle)))

Guolin Ke's avatar
Guolin Ke committed
848
849
850
851
852
853
854
855
    def __init_from_csc(self, csc, params_str, ref_dataset):
        """
        Initialize data from a csc matrix.
        """
        if len(csc.indices) != len(csc.data):
            raise ValueError('Length mismatch: {} vs {}'.format(len(csc.indices), len(csc.data)))
        self.handle = ctypes.c_void_p()

856
857
        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
858
859
860

        _safe_call(_LIB.LGBM_DatasetCreateFromCSC(
            ptr_indptr,
Guolin Ke's avatar
Guolin Ke committed
861
            ctypes.c_int(type_ptr_indptr),
Guolin Ke's avatar
Guolin Ke committed
862
863
            csc.indices.ctypes.data_as(ctypes.POINTER(ctypes.c_int32)),
            ptr_data,
Guolin Ke's avatar
Guolin Ke committed
864
865
866
867
            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
868
869
870
871
            c_str(params_str),
            ref_dataset,
            ctypes.byref(self.handle)))

wxchan's avatar
wxchan committed
872
    def construct(self):
873
874
875
876
877
878
879
        """Lazy init.

        Returns
        -------
        self : Dataset
            Returns self.
        """
880
        if self.handle is None:
wxchan's avatar
wxchan committed
881
882
            if self.reference is not None:
                if self.used_indices is None:
883
                    # create valid
884
                    self._lazy_init(self.data, label=self.label, reference=self.reference,
885
                                    weight=self.weight, group=self.group, init_score=self.init_score, predictor=self._predictor,
886
                                    silent=self.silent, feature_name=self.feature_name, params=self.params)
wxchan's avatar
wxchan committed
887
                else:
888
                    # construct subset
wxchan's avatar
wxchan committed
889
                    used_indices = list_to_1d_numpy(self.used_indices, np.int32, name='used_indices')
890
                    assert used_indices.flags.c_contiguous
891
                    self.handle = ctypes.c_void_p()
wxchan's avatar
wxchan committed
892
893
                    params_str = param_dict_to_str(self.params)
                    _safe_call(_LIB.LGBM_DatasetGetSubset(
894
                        self.reference.construct().handle,
wxchan's avatar
wxchan committed
895
                        used_indices.ctypes.data_as(ctypes.POINTER(ctypes.c_int32)),
Guolin Ke's avatar
Guolin Ke committed
896
                        ctypes.c_int(used_indices.shape[0]),
wxchan's avatar
wxchan committed
897
898
899
900
901
                        c_str(params_str),
                        ctypes.byref(self.handle)))
                    if self.get_label() is None:
                        raise ValueError("Label should not be None.")
            else:
902
                # create train
903
                self._lazy_init(self.data, label=self.label,
904
905
                                weight=self.weight, group=self.group, init_score=self.init_score,
                                predictor=self._predictor, silent=self.silent, feature_name=self.feature_name,
906
                                categorical_feature=self.categorical_feature, params=self.params)
wxchan's avatar
wxchan committed
907
908
909
            if self.free_raw_data:
                self.data = None
        return self
wxchan's avatar
wxchan committed
910

wxchan's avatar
wxchan committed
911
    def create_valid(self, data, label=None, weight=None, group=None,
912
                     init_score=None, silent=False, params=None):
913
        """Create validation data align with current Dataset.
wxchan's avatar
wxchan committed
914
915
916

        Parameters
        ----------
917
        data : string, numpy array or scipy.sparse
wxchan's avatar
wxchan committed
918
            Data source of Dataset.
919
920
            If string, it represents the path to txt file.
        label : list or numpy 1-D array, optional (default=None)
wxchan's avatar
wxchan committed
921
            Label of the training data.
922
        weight : list, numpy 1-D array or None, optional (default=None)
wxchan's avatar
wxchan committed
923
            Weight for each instance.
924
925
        group : list, numpy 1-D array or None, optional (default=None)
            Group/query size for Dataset.
926
927
        init_score : list, numpy 1-D array or None, optional (default=None)
            Init score for Dataset.
928
929
930
931
932
933
934
935
936
        silent : bool, optional (default=False)
            Whether to print messages during construction.
        params: dict or None, optional (default=None)
            Other parameters.

        Returns
        -------
        self : Dataset
            Returns self.
wxchan's avatar
wxchan committed
937
        """
938
        ret = Dataset(data, label=label, reference=self,
939
940
                      weight=weight, group=group, init_score=init_score,
                      silent=silent, params=params, free_raw_data=self.free_raw_data)
wxchan's avatar
wxchan committed
941
        ret._predictor = self._predictor
942
        ret.pandas_categorical = self.pandas_categorical
wxchan's avatar
wxchan committed
943
        return ret
wxchan's avatar
wxchan committed
944

wxchan's avatar
wxchan committed
945
    def subset(self, used_indices, params=None):
946
        """Get subset of current Dataset.
wxchan's avatar
wxchan committed
947
948
949
950

        Parameters
        ----------
        used_indices : list of int
951
952
953
954
955
956
957
958
            Indices used to create the subset.
        params: dict or None, optional (default=None)
            Other parameters.

        Returns
        -------
        subset : Dataset
            Subset of the current Dataset.
wxchan's avatar
wxchan committed
959
        """
wxchan's avatar
wxchan committed
960
961
        if params is None:
            params = self.params
wxchan's avatar
wxchan committed
962
        ret = Dataset(None, reference=self, feature_name=self.feature_name,
963
                      categorical_feature=self.categorical_feature, params=params)
wxchan's avatar
wxchan committed
964
        ret._predictor = self._predictor
965
        ret.pandas_categorical = self.pandas_categorical
wxchan's avatar
wxchan committed
966
967
968
969
        ret.used_indices = used_indices
        return ret

    def save_binary(self, filename):
970
        """Save Dataset to binary file.
wxchan's avatar
wxchan committed
971
972
973
974
975
976
977
978
979
980
981
982
983

        Parameters
        ----------
        filename : string
            Name of the output file.
        """
        _safe_call(_LIB.LGBM_DatasetSaveBinary(
            self.construct().handle,
            c_str(filename)))

    def _update_params(self, params):
        if not self.params:
            self.params = params
wxchan's avatar
wxchan committed
984
        else:
985
            self.params_back_up = copy.deepcopy(self.params)
wxchan's avatar
wxchan committed
986
            self.params.update(params)
wxchan's avatar
wxchan committed
987

988
989
990
991
    def _reverse_update_params(self):
        self.params = copy.deepcopy(self.params_back_up)
        self.params_back_up = None

wxchan's avatar
wxchan committed
992
    def set_field(self, field_name, data):
wxchan's avatar
wxchan committed
993
        """Set property into the Dataset.
wxchan's avatar
wxchan committed
994
995
996

        Parameters
        ----------
997
998
999
1000
        field_name: string
            The field name of the information.
        data: list, numpy array or None
            The array of data to be set.
wxchan's avatar
wxchan committed
1001
        """
1002
1003
        if self.handle is None:
            raise Exception("Cannot set %s before construct dataset" % field_name)
wxchan's avatar
wxchan committed
1004
        if data is None:
1005
            # set to None
wxchan's avatar
wxchan committed
1006
1007
1008
1009
            _safe_call(_LIB.LGBM_DatasetSetField(
                self.handle,
                c_str(field_name),
                None,
Guolin Ke's avatar
Guolin Ke committed
1010
1011
                ctypes.c_int(0),
                ctypes.c_int(FIELD_TYPE_MAPPER[field_name])))
wxchan's avatar
wxchan committed
1012
            return
Guolin Ke's avatar
Guolin Ke committed
1013
1014
1015
1016
1017
        dtype = np.float32
        if field_name == 'group':
            dtype = np.int32
        elif field_name == 'init_score':
            dtype = np.float64
1018
        data = list_to_1d_numpy(data, dtype, name=field_name)
1019
1020
        if data.dtype == np.float32 or data.dtype == np.float64:
            ptr_data, type_data, _ = c_float_array(data)
wxchan's avatar
wxchan committed
1021
        elif data.dtype == np.int32:
1022
            ptr_data, type_data, _ = c_int_array(data)
wxchan's avatar
wxchan committed
1023
        else:
Guolin Ke's avatar
Guolin Ke committed
1024
            raise TypeError("Excepted np.float32/64 or np.int32, meet type({})".format(data.dtype))
wxchan's avatar
wxchan committed
1025
        if type_data != FIELD_TYPE_MAPPER[field_name]:
1026
            raise TypeError("Input type error for set_field")
wxchan's avatar
wxchan committed
1027
1028
1029
1030
        _safe_call(_LIB.LGBM_DatasetSetField(
            self.handle,
            c_str(field_name),
            ptr_data,
Guolin Ke's avatar
Guolin Ke committed
1031
1032
            ctypes.c_int(len(data)),
            ctypes.c_int(type_data)))
wxchan's avatar
wxchan committed
1033

wxchan's avatar
wxchan committed
1034
1035
    def get_field(self, field_name):
        """Get property from the Dataset.
wxchan's avatar
wxchan committed
1036
1037
1038

        Parameters
        ----------
1039
1040
        field_name: string
            The field name of the information.
wxchan's avatar
wxchan committed
1041
1042
1043

        Returns
        -------
1044
1045
        info : numpy array
            A numpy array with information from the Dataset.
Guolin Ke's avatar
Guolin Ke committed
1046
        """
1047
        if self.handle is None:
1048
            raise Exception("Cannot get %s before construct Dataset" % field_name)
Guolin Ke's avatar
Guolin Ke committed
1049
1050
        tmp_out_len = ctypes.c_int()
        out_type = ctypes.c_int()
wxchan's avatar
wxchan committed
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
        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:
            return cint32_array_to_numpy(ctypes.cast(ret, ctypes.POINTER(ctypes.c_int32)), tmp_out_len.value)
        elif out_type.value == C_API_DTYPE_FLOAT32:
            return cfloat32_array_to_numpy(ctypes.cast(ret, ctypes.POINTER(ctypes.c_float)), tmp_out_len.value)
Guolin Ke's avatar
Guolin Ke committed
1066
1067
        elif out_type.value == C_API_DTYPE_FLOAT64:
            return cfloat64_array_to_numpy(ctypes.cast(ret, ctypes.POINTER(ctypes.c_double)), tmp_out_len.value)
1068
        else:
wxchan's avatar
wxchan committed
1069
            raise TypeError("Unknown type")
Guolin Ke's avatar
Guolin Ke committed
1070

1071
    def set_categorical_feature(self, categorical_feature):
1072
        """Set categorical features.
1073
1074
1075

        Parameters
        ----------
1076
1077
        categorical_feature : list of int or strings
            Names or indices of categorical features.
1078
1079
1080
1081
        """
        if self.categorical_feature == categorical_feature:
            return
        if self.data is not None:
1082
1083
1084
1085
1086
1087
            if self.categorical_feature is None:
                self.categorical_feature = categorical_feature
                self._free_handle()
            elif categorical_feature == 'auto':
                warnings.warn('Using categorical_feature in Dataset.')
            else:
1088
                warnings.warn('categorical_feature in Dataset is overridden. New categorical_feature is {}'.format(sorted(list(categorical_feature))))
1089
1090
                self.categorical_feature = categorical_feature
                self._free_handle()
1091
1092
1093
        else:
            raise LightGBMError("Cannot set categorical feature after freed raw data, set free_raw_data=False when construct Dataset to avoid this.")

Guolin Ke's avatar
Guolin Ke committed
1094
1095
    def _set_predictor(self, predictor):
        """
1096
        Set predictor for continued training, not recommended for user to call this function.
Guolin Ke's avatar
Guolin Ke committed
1097
1098
1099
1100
1101
1102
        Please set init_model in engine.train or engine.cv
        """
        if predictor is self._predictor:
            return
        if self.data is not None:
            self._predictor = predictor
1103
            self._free_handle()
Guolin Ke's avatar
Guolin Ke committed
1104
        else:
1105
            raise LightGBMError("Cannot set predictor after freed raw data, set free_raw_data=False when construct Dataset to avoid this.")
Guolin Ke's avatar
Guolin Ke committed
1106
1107

    def set_reference(self, reference):
1108
        """Set reference Dataset.
Guolin Ke's avatar
Guolin Ke committed
1109
1110
1111
1112

        Parameters
        ----------
        reference : Dataset
1113
            Reference that is used as a template to consturct the current Dataset.
Guolin Ke's avatar
Guolin Ke committed
1114
        """
1115
        self.set_categorical_feature(reference.categorical_feature)
Guolin Ke's avatar
Guolin Ke committed
1116
1117
        self.set_feature_name(reference.feature_name)
        self._set_predictor(reference._predictor)
1118
1119
        # we're done if self and reference share a common upstrem reference
        if self.get_ref_chain().intersection(reference.get_ref_chain()):
Guolin Ke's avatar
Guolin Ke committed
1120
1121
1122
            return
        if self.data is not None:
            self.reference = reference
1123
            self._free_handle()
Guolin Ke's avatar
Guolin Ke committed
1124
        else:
1125
            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
1126
1127

    def set_feature_name(self, feature_name):
1128
        """Set feature name.
Guolin Ke's avatar
Guolin Ke committed
1129
1130
1131

        Parameters
        ----------
1132
1133
        feature_name : list of strings
            Feature names.
Guolin Ke's avatar
Guolin Ke committed
1134
        """
1135
1136
        if feature_name != 'auto':
            self.feature_name = feature_name
1137
        if self.handle is not None and feature_name is not None and feature_name != 'auto':
wxchan's avatar
wxchan committed
1138
1139
            if len(feature_name) != self.num_feature():
                raise ValueError("Length of feature_name({}) and num_feature({}) don't match".format(len(feature_name), self.num_feature()))
1140
            c_feature_name = [c_str(name) for name in feature_name]
wxchan's avatar
wxchan committed
1141
1142
1143
            _safe_call(_LIB.LGBM_DatasetSetFeatureNames(
                self.handle,
                c_array(ctypes.c_char_p, c_feature_name),
Guolin Ke's avatar
Guolin Ke committed
1144
                ctypes.c_int(len(feature_name))))
Guolin Ke's avatar
Guolin Ke committed
1145
1146

    def set_label(self, label):
1147
        """Set label of Dataset
Guolin Ke's avatar
Guolin Ke committed
1148
1149
1150

        Parameters
        ----------
1151
1152
        label: list, numpy array or None
            The label information to be set into Dataset.
Guolin Ke's avatar
Guolin Ke committed
1153
1154
        """
        self.label = label
1155
        if self.handle is not None:
wxchan's avatar
wxchan committed
1156
1157
            label = list_to_1d_numpy(label, name='label')
            self.set_field('label', label)
Guolin Ke's avatar
Guolin Ke committed
1158
1159

    def set_weight(self, weight):
1160
        """Set weight of each instance.
Guolin Ke's avatar
Guolin Ke committed
1161
1162
1163

        Parameters
        ----------
1164
1165
        weight : list, numpy array or None
            Weight to be set for each data point.
Guolin Ke's avatar
Guolin Ke committed
1166
        """
1167
1168
        if weight is not None and np.all(weight == 1):
            weight = None
Guolin Ke's avatar
Guolin Ke committed
1169
        self.weight = weight
1170
        if self.handle is not None and weight is not None:
wxchan's avatar
wxchan committed
1171
1172
            weight = list_to_1d_numpy(weight, name='weight')
            self.set_field('weight', weight)
Guolin Ke's avatar
Guolin Ke committed
1173
1174

    def set_init_score(self, init_score):
1175
        """Set init score of Booster to start from.
Guolin Ke's avatar
Guolin Ke committed
1176
1177
1178

        Parameters
        ----------
1179
1180
        init_score : list, numpy array or None
            Init score for Booster.
Guolin Ke's avatar
Guolin Ke committed
1181
1182
        """
        self.init_score = init_score
1183
        if self.handle is not None and init_score is not None:
Guolin Ke's avatar
Guolin Ke committed
1184
            init_score = list_to_1d_numpy(init_score, np.float64, name='init_score')
wxchan's avatar
wxchan committed
1185
            self.set_field('init_score', init_score)
Guolin Ke's avatar
Guolin Ke committed
1186
1187

    def set_group(self, group):
1188
        """Set group size of Dataset (used for ranking).
Guolin Ke's avatar
Guolin Ke committed
1189
1190
1191

        Parameters
        ----------
1192
1193
        group : list, numpy array or None
            Group size of each group.
Guolin Ke's avatar
Guolin Ke committed
1194
1195
        """
        self.group = group
1196
        if self.handle is not None and group is not None:
wxchan's avatar
wxchan committed
1197
1198
            group = list_to_1d_numpy(group, np.int32, name='group')
            self.set_field('group', group)
Guolin Ke's avatar
Guolin Ke committed
1199
1200

    def get_label(self):
1201
        """Get the label of the Dataset.
Guolin Ke's avatar
Guolin Ke committed
1202
1203
1204

        Returns
        -------
1205
1206
        label : numpy array
            The label information from the Dataset.
Guolin Ke's avatar
Guolin Ke committed
1207
        """
1208
        if self.label is None:
wxchan's avatar
wxchan committed
1209
            self.label = self.get_field('label')
Guolin Ke's avatar
Guolin Ke committed
1210
1211
1212
        return self.label

    def get_weight(self):
1213
        """Get the weight of the Dataset.
Guolin Ke's avatar
Guolin Ke committed
1214
1215
1216

        Returns
        -------
1217
1218
        weight : numpy array
            Weight for each data point from the Dataset.
Guolin Ke's avatar
Guolin Ke committed
1219
        """
1220
        if self.weight is None:
wxchan's avatar
wxchan committed
1221
            self.weight = self.get_field('weight')
Guolin Ke's avatar
Guolin Ke committed
1222
1223
1224
        return self.weight

    def get_init_score(self):
1225
        """Get the initial score of the Dataset.
Guolin Ke's avatar
Guolin Ke committed
1226
1227
1228

        Returns
        -------
1229
1230
        init_score : numpy array
            Init score of Booster.
Guolin Ke's avatar
Guolin Ke committed
1231
        """
1232
        if self.init_score is None:
wxchan's avatar
wxchan committed
1233
            self.init_score = self.get_field('init_score')
Guolin Ke's avatar
Guolin Ke committed
1234
1235
1236
        return self.init_score

    def get_group(self):
1237
        """Get the group of the Dataset.
Guolin Ke's avatar
Guolin Ke committed
1238
1239
1240

        Returns
        -------
1241
        group : numpy array
1242
            Group size of each group.
Guolin Ke's avatar
Guolin Ke committed
1243
        """
1244
        if self.group is None:
wxchan's avatar
wxchan committed
1245
            self.group = self.get_field('group')
Guolin Ke's avatar
Guolin Ke committed
1246
1247
1248
            if self.group is not None:
                # group data from LightGBM is boundaries data, need to convert to group size
                new_group = []
wxchan's avatar
wxchan committed
1249
                for i in range_(len(self.group) - 1):
Guolin Ke's avatar
Guolin Ke committed
1250
1251
                    new_group.append(self.group[i + 1] - self.group[i])
                self.group = new_group
Guolin Ke's avatar
Guolin Ke committed
1252
1253
1254
        return self.group

    def num_data(self):
1255
        """Get the number of rows in the Dataset.
Guolin Ke's avatar
Guolin Ke committed
1256
1257
1258

        Returns
        -------
1259
1260
        number_of_rows : int
            The number of rows in the Dataset.
Guolin Ke's avatar
Guolin Ke committed
1261
        """
1262
        if self.handle is not None:
Guolin Ke's avatar
Guolin Ke committed
1263
            ret = ctypes.c_int()
wxchan's avatar
wxchan committed
1264
1265
1266
            _safe_call(_LIB.LGBM_DatasetGetNumData(self.handle,
                                                   ctypes.byref(ret)))
            return ret.value
Guolin Ke's avatar
Guolin Ke committed
1267
        else:
1268
            raise LightGBMError("Cannot get num_data before construct dataset")
Guolin Ke's avatar
Guolin Ke committed
1269
1270

    def num_feature(self):
1271
        """Get the number of columns (features) in the Dataset.
Guolin Ke's avatar
Guolin Ke committed
1272
1273
1274

        Returns
        -------
1275
1276
        number_of_columns : int
            The number of columns (features) in the Dataset.
Guolin Ke's avatar
Guolin Ke committed
1277
        """
1278
        if self.handle is not None:
Guolin Ke's avatar
Guolin Ke committed
1279
            ret = ctypes.c_int()
wxchan's avatar
wxchan committed
1280
1281
1282
            _safe_call(_LIB.LGBM_DatasetGetNumFeature(self.handle,
                                                      ctypes.byref(ret)))
            return ret.value
Guolin Ke's avatar
Guolin Ke committed
1283
        else:
1284
            raise LightGBMError("Cannot get num_feature before construct dataset")
Guolin Ke's avatar
Guolin Ke committed
1285

1286
    def get_ref_chain(self, ref_limit=100):
1287
1288
1289
1290
1291
1292
1293
        """Get a chain of Dataset objects, starting with r, then going to r.reference if exists,
        then to r.reference.reference, etc. until we hit ``ref_limit`` or a reference loop.

        Parameters
        ----------
        ref_limit : int, optional (default=100)
            The limit number of references.
1294
1295
1296

        Returns
        -------
1297
1298
1299
        ref_chain : set of Dataset
            Chain of references of the Datasets.
        """
1300
        head = self
1301
        ref_chain = set()
1302
1303
        while len(ref_chain) < ref_limit:
            if isinstance(head, Dataset):
1304
                ref_chain.add(head)
1305
1306
1307
1308
1309
1310
                if (head.reference is not None) and (head.reference not in ref_chain):
                    head = head.reference
                else:
                    break
            else:
                break
1311
        return(ref_chain)
1312

wxchan's avatar
wxchan committed
1313

wxchan's avatar
wxchan committed
1314
class Booster(object):
1315
    """Booster in LightGBM."""
wxchan's avatar
wxchan committed
1316
    def __init__(self, params=None, train_set=None, model_file=None, silent=False):
1317
        """Initialize the Booster.
wxchan's avatar
wxchan committed
1318
1319
1320

        Parameters
        ----------
1321
1322
1323
1324
1325
        params: dict or None, optional (default=None)
            Parameters for Booster.
        train_set : Dataset or None, optional (default=None)
            Training dataset.
        model_file : string or None, optional (default=None)
wxchan's avatar
wxchan committed
1326
            Path to the model file.
1327
1328
        silent : bool, optional (default=False)
            Whether to print messages during construction.
wxchan's avatar
wxchan committed
1329
        """
1330
        self.handle = None
1331
        self.network = False
wxchan's avatar
wxchan committed
1332
1333
1334
        self.__need_reload_eval_info = True
        self.__train_data_name = "training"
        self.__attr = {}
1335
        self.__set_objective_to_none = False
wxchan's avatar
wxchan committed
1336
        self.best_iteration = -1
wxchan's avatar
wxchan committed
1337
        self.best_score = {}
wxchan's avatar
wxchan committed
1338
1339
1340
1341
        params = {} if params is None else params
        if silent:
            params["verbose"] = 0
        if train_set is not None:
1342
            # Training task
wxchan's avatar
wxchan committed
1343
            if not isinstance(train_set, Dataset):
1344
                raise TypeError('Training data should be Dataset instance, met {}'.format(type(train_set).__name__))
wxchan's avatar
wxchan committed
1345
            params_str = param_dict_to_str(params)
1346
            # construct booster object
1347
            self.handle = ctypes.c_void_p()
wxchan's avatar
wxchan committed
1348
            _safe_call(_LIB.LGBM_BoosterCreate(
wxchan's avatar
wxchan committed
1349
                train_set.construct().handle,
wxchan's avatar
wxchan committed
1350
1351
                c_str(params_str),
                ctypes.byref(self.handle)))
1352
            # save reference to data
wxchan's avatar
wxchan committed
1353
1354
1355
1356
            self.train_set = train_set
            self.valid_sets = []
            self.name_valid_sets = []
            self.__num_dataset = 1
Guolin Ke's avatar
Guolin Ke committed
1357
1358
            self.__init_predictor = train_set._predictor
            if self.__init_predictor is not None:
wxchan's avatar
wxchan committed
1359
1360
                _safe_call(_LIB.LGBM_BoosterMerge(
                    self.handle,
Guolin Ke's avatar
Guolin Ke committed
1361
                    self.__init_predictor.handle))
Guolin Ke's avatar
Guolin Ke committed
1362
            out_num_class = ctypes.c_int(0)
wxchan's avatar
wxchan committed
1363
1364
1365
1366
            _safe_call(_LIB.LGBM_BoosterGetNumClasses(
                self.handle,
                ctypes.byref(out_num_class)))
            self.__num_class = out_num_class.value
1367
            # buffer for inner predict
wxchan's avatar
wxchan committed
1368
1369
1370
            self.__inner_predict_buffer = [None]
            self.__is_predicted_cur_iter = [False]
            self.__get_eval_info()
1371
            self.pandas_categorical = train_set.pandas_categorical
1372
            # set network if necessary
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
            for alias in ["machines", "workers", "nodes"]:
                if alias in params:
                    machines = params[alias]
                    if isinstance(machines, string_type):
                        num_machines = len(machines.split(','))
                    elif isinstance(machines, (list, set)):
                        num_machines = len(machines)
                        machines = ','.join(machines)
                    else:
                        raise ValueError("Invalid machines in params.")
                    self.set_network(machines,
                                     local_listen_port=params.get("local_listen_port", 12400),
                                     listen_time_out=params.get("listen_time_out", 120),
                                     num_machines=params.get("num_machines", num_machines))
                    break
wxchan's avatar
wxchan committed
1388
        elif model_file is not None:
1389
            # Prediction task
Guolin Ke's avatar
Guolin Ke committed
1390
            out_num_iterations = ctypes.c_int(0)
1391
            self.handle = ctypes.c_void_p()
wxchan's avatar
wxchan committed
1392
1393
1394
1395
            _safe_call(_LIB.LGBM_BoosterCreateFromModelfile(
                c_str(model_file),
                ctypes.byref(out_num_iterations),
                ctypes.byref(self.handle)))
Guolin Ke's avatar
Guolin Ke committed
1396
            out_num_class = ctypes.c_int(0)
wxchan's avatar
wxchan committed
1397
1398
1399
1400
            _safe_call(_LIB.LGBM_BoosterGetNumClasses(
                self.handle,
                ctypes.byref(out_num_class)))
            self.__num_class = out_num_class.value
1401
            self.pandas_categorical = _load_pandas_categorical(model_file)
1402
        elif 'model_str' in params:
1403
            self._load_model_from_string(params['model_str'])
wxchan's avatar
wxchan committed
1404
        else:
1405
            raise TypeError('Need at least one training dataset or model file to create booster instance')
wxchan's avatar
wxchan committed
1406
1407

    def __del__(self):
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
        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
1418

wxchan's avatar
wxchan committed
1419
1420
1421
1422
    def __copy__(self):
        return self.__deepcopy__(None)

    def __deepcopy__(self, _):
1423
        model_str = self._save_model_to_string()
1424
        booster = Booster({'model_str': model_str})
1425
        booster.pandas_categorical = self.pandas_categorical
1426
        return booster
wxchan's avatar
wxchan committed
1427
1428
1429
1430
1431
1432
1433

    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:
1434
            this["handle"] = self._save_model_to_string()
wxchan's avatar
wxchan committed
1435
1436
1437
        return this

    def __setstate__(self, state):
1438
1439
        model_str = state.get('handle', None)
        if model_str is not None:
wxchan's avatar
wxchan committed
1440
            handle = ctypes.c_void_p()
Guolin Ke's avatar
Guolin Ke committed
1441
            out_num_iterations = ctypes.c_int(0)
1442
1443
1444
1445
            _safe_call(_LIB.LGBM_BoosterLoadModelFromString(
                c_str(model_str),
                ctypes.byref(out_num_iterations),
                ctypes.byref(handle)))
wxchan's avatar
wxchan committed
1446
1447
1448
            state['handle'] = handle
        self.__dict__.update(state)

wxchan's avatar
wxchan committed
1449
    def free_dataset(self):
1450
        """Free Booster's Datasets."""
wxchan's avatar
wxchan committed
1451
1452
        self.__dict__.pop('train_set', None)
        self.__dict__.pop('valid_sets', None)
1453
        self.__num_dataset = 0
wxchan's avatar
wxchan committed
1454

1455
1456
1457
1458
    def _free_buffer(self):
        self.__inner_predict_buffer = []
        self.__is_predicted_cur_iter = []

1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
    def set_network(self, machines, local_listen_port=12400,
                    listen_time_out=120, num_machines=1):
        """Set the network configuration.

        Parameters
        ----------
        machines: list, set or string
            Names of machines.
        local_listen_port: int, optional (default=12400)
            TCP listen port for local machines.
        listen_time_out: int, optional (default=120)
            Socket time-out in minutes.
        num_machines: int, optional (default=1)
            The number of machines for parallel learning application.
        """
        _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

    def free_network(self):
1481
        """Free network."""
1482
1483
1484
        _safe_call(_LIB.LGBM_NetworkFree())
        self.network = False

wxchan's avatar
wxchan committed
1485
    def set_train_data_name(self, name):
1486
1487
1488
1489
1490
1491
1492
        """Set the name to the training Dataset.

        Parameters
        ----------
        name: string
            Name for training Dataset.
        """
wxchan's avatar
wxchan committed
1493
1494
1495
        self.__train_data_name = name

    def add_valid(self, data, name):
1496
        """Add validation data.
wxchan's avatar
wxchan committed
1497
1498
1499
1500

        Parameters
        ----------
        data : Dataset
1501
1502
1503
            Validation data.
        name : string
            Name of validation data.
wxchan's avatar
wxchan committed
1504
        """
Guolin Ke's avatar
Guolin Ke committed
1505
        if not isinstance(data, Dataset):
1506
            raise TypeError('Validation data should be Dataset instance, met {}'.format(type(data).__name__))
Guolin Ke's avatar
Guolin Ke committed
1507
1508
        if data._predictor is not self.__init_predictor:
            raise LightGBMError("Add validation data failed, you should use same predictor for these data")
wxchan's avatar
wxchan committed
1509
1510
        _safe_call(_LIB.LGBM_BoosterAddValidData(
            self.handle,
wxchan's avatar
wxchan committed
1511
            data.construct().handle))
wxchan's avatar
wxchan committed
1512
1513
1514
1515
1516
1517
1518
        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)

    def reset_parameter(self, params):
1519
        """Reset parameters of Booster.
wxchan's avatar
wxchan committed
1520
1521
1522
1523

        Parameters
        ----------
        params : dict
1524
            New parameters for Booster.
wxchan's avatar
wxchan committed
1525
        """
1526
        if any(metric_alias in params for metric_alias in ('metric', 'metrics', 'metric_types')):
wxchan's avatar
wxchan committed
1527
1528
1529
1530
1531
1532
1533
1534
            self.__need_reload_eval_info = True
        params_str = param_dict_to_str(params)
        if params_str:
            _safe_call(_LIB.LGBM_BoosterResetParameter(
                self.handle,
                c_str(params_str)))

    def update(self, train_set=None, fobj=None):
1535
        """Update for one iteration.
1536

wxchan's avatar
wxchan committed
1537
1538
        Parameters
        ----------
1539
1540
1541
1542
        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
1543
1544
            Customized objective function.

1545
1546
1547
1548
            For multi-class task, the score is group by class_id first, then group by row_id.
            If you want to get i-th row score in j-th class, the access way is score[j * num_data + i]
            and you should group grad and hess in this way as well.

wxchan's avatar
wxchan committed
1549
1550
        Returns
        -------
1551
1552
        is_finished : bool
            Whether the update was successfully finished.
wxchan's avatar
wxchan committed
1553
1554
        """

1555
        # need reset training data
wxchan's avatar
wxchan committed
1556
        if train_set is not None and train_set is not self.train_set:
Guolin Ke's avatar
Guolin Ke committed
1557
1558
            if not isinstance(train_set, Dataset):
                raise TypeError('Training data should be Dataset instance, met {}'.format(type(train_set).__name__))
Guolin Ke's avatar
Guolin Ke committed
1559
1560
            if train_set._predictor is not self.__init_predictor:
                raise LightGBMError("Replace training data failed, you should use same predictor for these data")
wxchan's avatar
wxchan committed
1561
1562
1563
            self.train_set = train_set
            _safe_call(_LIB.LGBM_BoosterResetTrainingData(
                self.handle,
wxchan's avatar
wxchan committed
1564
                self.train_set.construct().handle))
wxchan's avatar
wxchan committed
1565
1566
1567
            self.__inner_predict_buffer[0] = None
        is_finished = ctypes.c_int(0)
        if fobj is None:
1568
1569
            if self.__set_objective_to_none:
                raise ValueError('Cannot update due to null objective function.')
wxchan's avatar
wxchan committed
1570
1571
1572
            _safe_call(_LIB.LGBM_BoosterUpdateOneIter(
                self.handle,
                ctypes.byref(is_finished)))
wxchan's avatar
wxchan committed
1573
            self.__is_predicted_cur_iter = [False for _ in range_(self.__num_dataset)]
wxchan's avatar
wxchan committed
1574
1575
            return is_finished.value == 1
        else:
1576
1577
1578
            if not self.__set_objective_to_none:
                self.reset_parameter({"objective": "none"})
                self.__set_objective_to_none = True
wxchan's avatar
wxchan committed
1579
1580
1581
1582
1583
1584
1585
1586
1587
            grad, hess = fobj(self.__inner_predict(0), self.train_set)
            return self.__boost(grad, hess)

    def __boost(self, grad, hess):
        """
        Boost the booster for one iteration, with customized gradient statistics.
        Note: for multi-class task, the score is group by class_id first, then group by row_id
              if you want to get i-th row score in j-th class, the access way is score[j*num_data+i]
              and you should group grad and hess in this way as well
1588

wxchan's avatar
wxchan committed
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
        Parameters
        ----------
        grad : 1d numpy or 1d list
            The first order of gradient.
        hess : 1d numpy or 1d list
            The second order of gradient.

        Returns
        -------
        is_finished, bool
        """
1600
1601
        grad = list_to_1d_numpy(grad, name='gradient')
        hess = list_to_1d_numpy(hess, name='hessian')
1602
1603
        assert grad.flags.c_contiguous
        assert hess.flags.c_contiguous
wxchan's avatar
wxchan committed
1604
        if len(grad) != len(hess):
1605
            raise ValueError("Lengths of gradient({}) and hessian({}) don't match".format(len(grad), len(hess)))
wxchan's avatar
wxchan committed
1606
1607
1608
1609
1610
1611
        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)))
wxchan's avatar
wxchan committed
1612
        self.__is_predicted_cur_iter = [False for _ in range_(self.__num_dataset)]
wxchan's avatar
wxchan committed
1613
1614
1615
        return is_finished.value == 1

    def rollback_one_iter(self):
1616
        """Rollback one iteration."""
wxchan's avatar
wxchan committed
1617
1618
        _safe_call(_LIB.LGBM_BoosterRollbackOneIter(
            self.handle))
wxchan's avatar
wxchan committed
1619
        self.__is_predicted_cur_iter = [False for _ in range_(self.__num_dataset)]
wxchan's avatar
wxchan committed
1620
1621

    def current_iteration(self):
1622
1623
1624
1625
1626
1627
1628
        """Get the index of the current iteration.

        Returns
        -------
        cur_iter : int
            The index of the current iteration.
        """
Guolin Ke's avatar
Guolin Ke committed
1629
        out_cur_iter = ctypes.c_int(0)
wxchan's avatar
wxchan committed
1630
1631
1632
1633
1634
1635
        _safe_call(_LIB.LGBM_BoosterGetCurrentIteration(
            self.handle,
            ctypes.byref(out_cur_iter)))
        return out_cur_iter.value

    def eval(self, data, name, feval=None):
1636
        """Evaluate for data.
wxchan's avatar
wxchan committed
1637
1638
1639

        Parameters
        ----------
1640
1641
1642
1643
1644
        data : Dataset
            Data for the evaluating.
        name : string
            Name of the data.
        feval : callable or None, optional (default=None)
1645
1646
1647
1648
1649
            Customized evaluation function.
            Should accept two parameters: preds, train_data.
            For multi-class task, the preds is group by class_id first, then group by row_id.
            If you want to get i-th row preds in j-th class, the access way is preds[j * num_data + i].
            Note: should return (eval_name, eval_result, is_higher_better) or list of such tuples.
1650

wxchan's avatar
wxchan committed
1651
1652
1653
        Returns
        -------
        result: list
1654
            List with evaluation results.
wxchan's avatar
wxchan committed
1655
        """
Guolin Ke's avatar
Guolin Ke committed
1656
1657
        if not isinstance(data, Dataset):
            raise TypeError("Can only eval for Dataset instance")
wxchan's avatar
wxchan committed
1658
1659
1660
1661
        data_idx = -1
        if data is self.train_set:
            data_idx = 0
        else:
wxchan's avatar
wxchan committed
1662
            for i in range_(len(self.valid_sets)):
wxchan's avatar
wxchan committed
1663
1664
1665
                if data is self.valid_sets[i]:
                    data_idx = i + 1
                    break
1666
        # need to push new valid data
wxchan's avatar
wxchan committed
1667
1668
1669
1670
1671
1672
1673
        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):
1674
        """Evaluate for training data.
wxchan's avatar
wxchan committed
1675
1676
1677

        Parameters
        ----------
1678
        feval : callable or None, optional (default=None)
1679
1680
1681
1682
1683
            Customized evaluation function.
            Should accept two parameters: preds, train_data.
            For multi-class task, the preds is group by class_id first, then group by row_id.
            If you want to get i-th row preds in j-th class, the access way is preds[j * num_data + i].
            Note: should return (eval_name, eval_result, is_higher_better) or list of such tuples.
wxchan's avatar
wxchan committed
1684
1685
1686

        Returns
        -------
1687
1688
        result: list
            List with evaluation results.
wxchan's avatar
wxchan committed
1689
1690
1691
1692
        """
        return self.__inner_eval(self.__train_data_name, 0, feval)

    def eval_valid(self, feval=None):
1693
        """Evaluate for validation data.
wxchan's avatar
wxchan committed
1694
1695
1696

        Parameters
        ----------
1697
        feval : callable or None, optional (default=None)
1698
1699
1700
1701
1702
            Customized evaluation function.
            Should accept two parameters: preds, train_data.
            For multi-class task, the preds is group by class_id first, then group by row_id.
            If you want to get i-th row preds in j-th class, the access way is preds[j * num_data + i].
            Note: should return (eval_name, eval_result, is_higher_better) or list of such tuples.
wxchan's avatar
wxchan committed
1703
1704
1705

        Returns
        -------
1706
1707
        result: list
            List with evaluation results.
wxchan's avatar
wxchan committed
1708
        """
wxchan's avatar
wxchan committed
1709
        return [item for i in range_(1, self.__num_dataset)
wxchan's avatar
wxchan committed
1710
                for item in self.__inner_eval(self.name_valid_sets[i - 1], i, feval)]
wxchan's avatar
wxchan committed
1711
1712

    def save_model(self, filename, num_iteration=-1):
1713
        """Save Booster to file.
wxchan's avatar
wxchan committed
1714
1715
1716

        Parameters
        ----------
1717
1718
1719
1720
1721
        filename : string
            Filename to save Booster.
        num_iteration: int, optional (default=-1)
            Index of the iteration that should to saved.
            If <0, the best iteration (if exists) is saved.
wxchan's avatar
wxchan committed
1722
        """
1723
1724
        if num_iteration <= 0:
            num_iteration = self.best_iteration
wxchan's avatar
wxchan committed
1725
1726
        _safe_call(_LIB.LGBM_BoosterSaveModel(
            self.handle,
Guolin Ke's avatar
Guolin Ke committed
1727
            ctypes.c_int(num_iteration),
wxchan's avatar
wxchan committed
1728
            c_str(filename)))
1729
        _save_pandas_categorical(filename, self.pandas_categorical)
wxchan's avatar
wxchan committed
1730

1731
    def _load_model_from_string(self, model_str, verbose=True):
1732
        """[Private] Load model from string"""
1733
1734
1735
1736
        if self.handle is not None:
            _safe_call(_LIB.LGBM_BoosterFree(self.handle))
        self._free_buffer()
        self.handle = ctypes.c_void_p()
1737
1738
1739
1740
1741
1742
1743
1744
1745
        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)))
1746
1747
        if verbose:
            print('Finished loading model, total used %d iterations' % (int(out_num_iterations.value)))
1748
1749
        self.__num_class = out_num_class.value

1750
    def _save_model_to_string(self, num_iteration=-1):
1751
1752
1753
1754
        """[Private] Save model to string"""
        if num_iteration <= 0:
            num_iteration = self.best_iteration
        buffer_len = 1 << 20
1755
        tmp_out_len = ctypes.c_int64(0)
1756
1757
1758
1759
1760
        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,
            ctypes.c_int(num_iteration),
1761
            ctypes.c_int64(buffer_len),
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
            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_BoosterSaveModelToString(
                self.handle,
                ctypes.c_int(num_iteration),
1772
                ctypes.c_int64(actual_len),
1773
1774
1775
1776
                ctypes.byref(tmp_out_len),
                ptr_string_buffer))
        return string_buffer.value.decode()

1777
    def dump_model(self, num_iteration=-1):
1778
        """Dump Booster to json format.
wxchan's avatar
wxchan committed
1779

1780
1781
        Parameters
        ----------
1782
1783
1784
        num_iteration: int, optional (default=-1)
            Index of the iteration that should to dumped.
            If <0, the best iteration (if exists) is dumped.
1785

wxchan's avatar
wxchan committed
1786
1787
        Returns
        -------
1788
1789
        json_repr : dict
            Json format of Booster.
wxchan's avatar
wxchan committed
1790
        """
1791
1792
        if num_iteration <= 0:
            num_iteration = self.best_iteration
wxchan's avatar
wxchan committed
1793
        buffer_len = 1 << 20
1794
        tmp_out_len = ctypes.c_int64(0)
wxchan's avatar
wxchan committed
1795
1796
1797
1798
        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,
Guolin Ke's avatar
Guolin Ke committed
1799
            ctypes.c_int(num_iteration),
1800
            ctypes.c_int64(buffer_len),
wxchan's avatar
wxchan committed
1801
            ctypes.byref(tmp_out_len),
Guolin Ke's avatar
Guolin Ke committed
1802
            ptr_string_buffer))
wxchan's avatar
wxchan committed
1803
        actual_len = tmp_out_len.value
1804
        '''if buffer length is not long enough, reallocate a buffer'''
wxchan's avatar
wxchan committed
1805
1806
1807
1808
1809
        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,
Guolin Ke's avatar
Guolin Ke committed
1810
                ctypes.c_int(num_iteration),
1811
                ctypes.c_int64(actual_len),
wxchan's avatar
wxchan committed
1812
                ctypes.byref(tmp_out_len),
Guolin Ke's avatar
Guolin Ke committed
1813
                ptr_string_buffer))
wxchan's avatar
wxchan committed
1814
1815
        return json.loads(string_buffer.value.decode())

1816
    def predict(self, data, num_iteration=-1, raw_score=False, pred_leaf=False, pred_contrib=False,
1817
                data_has_header=False, is_reshape=True, pred_parameter=None, **kwargs):
1818
        """Make a prediction.
wxchan's avatar
wxchan committed
1819
1820
1821

        Parameters
        ----------
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
        data : string, numpy array or scipy.sparse
            Data source for prediction.
            If string, it represents the path to txt file.
        num_iteration : int, optional (default=-1)
            Iteration used for prediction.
            If <0, the best iteration (if exists) is 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.
1832
1833
        pred_contrib : bool, optional (default=False)
            Whether to predict feature contributions.
1834
1835
1836
1837
1838
        data_has_header : bool, optional (default=False)
            Whether the data has header.
            Used only if data is string.
        is_reshape : bool, optional (default=True)
            If True, result is reshaped to [nrow, ncol].
1839
1840
        pred_parameter : dict or None, optional (default=None)
            Deprecated.
1841
            Other parameters for the prediction.
1842
        **kwargs : other parameters for the prediction
wxchan's avatar
wxchan committed
1843
1844
1845

        Returns
        -------
1846
1847
        result : numpy array
            Prediction result.
wxchan's avatar
wxchan committed
1848
        """
1849
1850
1851
1852
1853
1854
        if pred_parameter:
            warnings.warn("pred_parameter is deprecated and will be removed in 2.2 version.\n"
                          "Please use kwargs instead.", LGBMDeprecationWarning)
            pred_parameter.update(kwargs)
        else:
            pred_parameter = kwargs
1855
        predictor = self._to_predictor(pred_parameter)
1856
1857
        if num_iteration <= 0:
            num_iteration = self.best_iteration
1858
        return predictor.predict(data, num_iteration, raw_score, pred_leaf, pred_contrib, data_has_header, is_reshape)
wxchan's avatar
wxchan committed
1859

1860
    def get_leaf_output(self, tree_id, leaf_id):
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
        """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.
        """
1875
1876
1877
1878
1879
1880
1881
1882
        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

1883
    def _to_predictor(self, pred_parameter=None):
wxchan's avatar
wxchan committed
1884
        """Convert to predictor"""
1885
        predictor = _InnerPredictor(booster_handle=self.handle, pred_parameter=pred_parameter)
1886
        predictor.pandas_categorical = self.pandas_categorical
wxchan's avatar
wxchan committed
1887
1888
        return predictor

1889
    def num_feature(self):
1890
1891
1892
1893
1894
1895
1896
        """Get number of features.

        Returns
        -------
        num_feature : int
            The number of features.
        """
1897
1898
1899
1900
1901
1902
        out_num_feature = ctypes.c_int(0)
        _safe_call(_LIB.LGBM_BoosterGetNumFeature(
            self.handle,
            ctypes.byref(out_num_feature)))
        return out_num_feature.value

wxchan's avatar
wxchan committed
1903
    def feature_name(self):
1904
        """Get names of features.
wxchan's avatar
wxchan committed
1905
1906
1907

        Returns
        -------
1908
1909
        result : list
            List with names of features.
wxchan's avatar
wxchan committed
1910
        """
1911
        num_feature = self.num_feature()
1912
        # Get name of features
wxchan's avatar
wxchan committed
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
        tmp_out_len = ctypes.c_int(0)
        string_buffers = [ctypes.create_string_buffer(255) for i 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.byref(tmp_out_len),
            ptr_string_buffers))
        if num_feature != tmp_out_len.value:
            raise ValueError("Length of feature names doesn't equal with num_feature")
        return [string_buffers[i].value.decode() for i in range_(num_feature)]

1924
    def feature_importance(self, importance_type='split', iteration=-1):
1925
        """Get feature importances.
1926

1927
1928
        Parameters
        ----------
1929
1930
1931
1932
        importance_type : string, optional (default="split")
            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.
1933

1934
1935
        Returns
        -------
1936
1937
        result : numpy array
            Array with feature importances.
1938
        """
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
        if importance_type == "split":
            importance_type_int = 0
        elif importance_type == "gain":
            importance_type_int = 1
        else:
            importance_type_int = -1
        num_feature = self.num_feature()
        result = np.array([0 for _ in range_(num_feature)], dtype=np.float64)
        _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))))
        if importance_type_int == 0:
            return result.astype(int)
        else:
            return result
1956

wxchan's avatar
wxchan committed
1957
1958
    def __inner_eval(self, data_name, data_idx, feval=None):
        """
1959
        Evaulate training or validation data
wxchan's avatar
wxchan committed
1960
1961
        """
        if data_idx >= self.__num_dataset:
1962
            raise ValueError("Data_idx should be smaller than number of dataset")
wxchan's avatar
wxchan committed
1963
1964
1965
        self.__get_eval_info()
        ret = []
        if self.__num_inner_eval > 0:
1966
            result = np.zeros(self.__num_inner_eval, dtype=np.float64)
Guolin Ke's avatar
Guolin Ke committed
1967
            tmp_out_len = ctypes.c_int(0)
wxchan's avatar
wxchan committed
1968
1969
            _safe_call(_LIB.LGBM_BoosterGetEval(
                self.handle,
Guolin Ke's avatar
Guolin Ke committed
1970
                ctypes.c_int(data_idx),
wxchan's avatar
wxchan committed
1971
                ctypes.byref(tmp_out_len),
Guolin Ke's avatar
Guolin Ke committed
1972
                result.ctypes.data_as(ctypes.POINTER(ctypes.c_double))))
wxchan's avatar
wxchan committed
1973
            if tmp_out_len.value != self.__num_inner_eval:
1974
                raise ValueError("Wrong length of eval results")
wxchan's avatar
wxchan committed
1975
            for i in range_(self.__num_inner_eval):
wxchan's avatar
wxchan committed
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
                ret.append((data_name, self.__name_inner_eval[i], result[i], self.__higher_better_inner_eval[i]))
        if feval is not None:
            if data_idx == 0:
                cur_data = self.train_set
            else:
                cur_data = self.valid_sets[data_idx - 1]
            feval_ret = feval(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
                ret.append((data_name, eval_name, val, is_higher_better))
        return ret

    def __inner_predict(self, data_idx):
        """
        Predict for training and validation dataset
        """
        if data_idx >= self.__num_dataset:
1996
            raise ValueError("Data_idx should be smaller than number of dataset")
wxchan's avatar
wxchan committed
1997
1998
1999
2000
2001
        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
2002
            self.__inner_predict_buffer[data_idx] = np.zeros(n_preds, dtype=np.float64)
2003
        # avoid to predict many time in one iteration
wxchan's avatar
wxchan committed
2004
2005
        if not self.__is_predicted_cur_iter[data_idx]:
            tmp_out_len = ctypes.c_int64(0)
Guolin Ke's avatar
Guolin Ke committed
2006
            data_ptr = self.__inner_predict_buffer[data_idx].ctypes.data_as(ctypes.POINTER(ctypes.c_double))
wxchan's avatar
wxchan committed
2007
2008
            _safe_call(_LIB.LGBM_BoosterGetPredict(
                self.handle,
Guolin Ke's avatar
Guolin Ke committed
2009
                ctypes.c_int(data_idx),
wxchan's avatar
wxchan committed
2010
2011
2012
                ctypes.byref(tmp_out_len),
                data_ptr))
            if tmp_out_len.value != len(self.__inner_predict_buffer[data_idx]):
2013
                raise ValueError("Wrong length of predict results for data %d" % (data_idx))
wxchan's avatar
wxchan committed
2014
2015
2016
2017
2018
2019
2020
2021
2022
            self.__is_predicted_cur_iter[data_idx] = True
        return self.__inner_predict_buffer[data_idx]

    def __get_eval_info(self):
        """
        Get inner evaluation count and names
        """
        if self.__need_reload_eval_info:
            self.__need_reload_eval_info = False
Guolin Ke's avatar
Guolin Ke committed
2023
            out_num_eval = ctypes.c_int(0)
2024
            # Get num of inner evals
wxchan's avatar
wxchan committed
2025
2026
2027
2028
2029
            _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:
2030
                # Get name of evals
Guolin Ke's avatar
Guolin Ke committed
2031
                tmp_out_len = ctypes.c_int(0)
wxchan's avatar
wxchan committed
2032
                string_buffers = [ctypes.create_string_buffer(255) for i in range_(self.__num_inner_eval)]
wxchan's avatar
wxchan committed
2033
                ptr_string_buffers = (ctypes.c_char_p * self.__num_inner_eval)(*map(ctypes.addressof, string_buffers))
wxchan's avatar
wxchan committed
2034
2035
2036
2037
2038
                _safe_call(_LIB.LGBM_BoosterGetEvalNames(
                    self.handle,
                    ctypes.byref(tmp_out_len),
                    ptr_string_buffers))
                if self.__num_inner_eval != tmp_out_len.value:
2039
                    raise ValueError("Length of eval names doesn't equal with num_evals")
2040
                self.__name_inner_eval = \
wxchan's avatar
wxchan committed
2041
                    [string_buffers[i].value.decode() for i in range_(self.__num_inner_eval)]
2042
                self.__higher_better_inner_eval = \
2043
                    [name.startswith(('auc', 'ndcg@', 'map@')) for name in self.__name_inner_eval]
2044

wxchan's avatar
wxchan committed
2045
    def attr(self, key):
2046
        """Get attribute string from the Booster.
wxchan's avatar
wxchan committed
2047
2048
2049

        Parameters
        ----------
2050
2051
        key : string
            The name of the attribute.
wxchan's avatar
wxchan committed
2052
2053
2054

        Returns
        -------
2055
2056
2057
        value : string or None
            The attribute value.
            Returns None if attribute do not exist.
wxchan's avatar
wxchan committed
2058
        """
2059
        return self.__attr.get(key, None)
wxchan's avatar
wxchan committed
2060
2061

    def set_attr(self, **kwargs):
2062
        """Set the attribute of the Booster.
wxchan's avatar
wxchan committed
2063
2064
2065
2066

        Parameters
        ----------
        **kwargs
2067
2068
            The attributes to set.
            Setting a value to None deletes an attribute.
wxchan's avatar
wxchan committed
2069
2070
2071
        """
        for key, value in kwargs.items():
            if value is not None:
wxchan's avatar
wxchan committed
2072
                if not isinstance(value, string_type):
2073
                    raise ValueError("Set attr only accepts strings")
wxchan's avatar
wxchan committed
2074
2075
2076
                self.__attr[key] = value
            else:
                self.__attr.pop(key, None)