[python] use better names for imported classes from extra libraries (#3862)

python-package/lightgbm/basic.py

@@ -14,7 +14,7 @@ from typing import Any, Dict
 import numpy as np
 import scipy.sparse
 
-from .compat import PANDAS_INSTALLED, DataFrame, Series, concat, is_dtype_sparse, DataTable
+from .compat import PANDAS_INSTALLED, pd_DataFrame, pd_Series, concat, is_dtype_sparse, dt_DataTable
 from .libpath import find_lib_path
 
 
@@ -140,7 +140,7 @@ def list_to_1d_numpy(data, dtype=np.float32, name='list'):
             return data.astype(dtype=dtype, copy=False)
     elif is_1d_list(data):
         return np.array(data, dtype=dtype, copy=False)
-    elif isinstance(data, Series):
+    elif isinstance(data, pd_Series):
         if _get_bad_pandas_dtypes([data.dtypes]):
             raise ValueError('Series.dtypes must be int, float or bool')
         return np.array(data, dtype=dtype, copy=False)  # SparseArray should be supported as well
@@ -493,7 +493,7 @@ def _get_bad_pandas_dtypes(dtypes):
 
 
 def _data_from_pandas(data, feature_name, categorical_feature, pandas_categorical):
-    if isinstance(data, DataFrame):
+    if isinstance(data, pd_DataFrame):
         if len(data.shape) != 2 or data.shape[0] < 1:
             raise ValueError('Input data must be 2 dimensional and non empty.')
         if feature_name == 'auto' or feature_name is None:
@@ -537,7 +537,7 @@ def _data_from_pandas(data, feature_name, categorical_feature, pandas_categorica
 
 
 def _label_from_pandas(label):
-    if isinstance(label, DataFrame):
+    if isinstance(label, pd_DataFrame):
         if len(label.columns) > 1:
             raise ValueError('DataFrame for label cannot have multiple columns')
         if _get_bad_pandas_dtypes(label.dtypes):
@@ -720,7 +720,7 @@ class _InnerPredictor:
             except BaseException:
                 raise ValueError('Cannot convert data list to numpy array.')
             preds, nrow = self.__pred_for_np2d(data, start_iteration, num_iteration, predict_type)
-        elif isinstance(data, DataTable):
+        elif isinstance(data, dt_DataTable):
             preds, nrow = self.__pred_for_np2d(data.to_numpy(), start_iteration, num_iteration, predict_type)
         else:
             try:
@@ -1258,7 +1258,7 @@ class Dataset:
             self.__init_from_np2d(data, params_str, ref_dataset)
         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)
-        elif isinstance(data, DataTable):
+        elif isinstance(data, dt_DataTable):
             self.__init_from_np2d(data.to_numpy(), params_str, ref_dataset)
         else:
             try:
@@ -1939,9 +1939,9 @@ class Dataset:
             if self.data is not None:
                 if isinstance(self.data, np.ndarray) or scipy.sparse.issparse(self.data):
                     self.data = self.data[self.used_indices, :]
-                elif isinstance(self.data, DataFrame):
+                elif isinstance(self.data, pd_DataFrame):
                     self.data = self.data.iloc[self.used_indices].copy()
-                elif isinstance(self.data, DataTable):
+                elif isinstance(self.data, dt_DataTable):
                     self.data = self.data[self.used_indices, :]
                 else:
                     _log_warning("Cannot subset {} type of raw data.\n"
@@ -2061,9 +2061,9 @@ class Dataset:
                     self.data = np.hstack((self.data, other.data))
                 elif scipy.sparse.issparse(other.data):
                     self.data = np.hstack((self.data, other.data.toarray()))
-                elif isinstance(other.data, DataFrame):
+                elif isinstance(other.data, pd_DataFrame):
                     self.data = np.hstack((self.data, other.data.values))
-                elif isinstance(other.data, DataTable):
+                elif isinstance(other.data, dt_DataTable):
                     self.data = np.hstack((self.data, other.data.to_numpy()))
                 else:
                     self.data = None
@@ -2071,39 +2071,39 @@ class Dataset:
                 sparse_format = self.data.getformat()
                 if isinstance(other.data, np.ndarray) or scipy.sparse.issparse(other.data):
                     self.data = scipy.sparse.hstack((self.data, other.data), format=sparse_format)
-                elif isinstance(other.data, DataFrame):
+                elif isinstance(other.data, pd_DataFrame):
                     self.data = scipy.sparse.hstack((self.data, other.data.values), format=sparse_format)
-                elif isinstance(other.data, DataTable):
+                elif isinstance(other.data, dt_DataTable):
                     self.data = scipy.sparse.hstack((self.data, other.data.to_numpy()), format=sparse_format)
                 else:
                     self.data = None
-            elif isinstance(self.data, DataFrame):
+            elif isinstance(self.data, pd_DataFrame):
                 if not PANDAS_INSTALLED:
                     raise LightGBMError("Cannot add features to DataFrame type of raw data "
                                         "without pandas installed")
                 if isinstance(other.data, np.ndarray):
-                    self.data = concat((self.data, DataFrame(other.data)),
+                    self.data = concat((self.data, pd_DataFrame(other.data)),
                                        axis=1, ignore_index=True)
                 elif scipy.sparse.issparse(other.data):
-                    self.data = concat((self.data, DataFrame(other.data.toarray())),
+                    self.data = concat((self.data, pd_DataFrame(other.data.toarray())),
                                        axis=1, ignore_index=True)
-                elif isinstance(other.data, DataFrame):
+                elif isinstance(other.data, pd_DataFrame):
                     self.data = concat((self.data, other.data),
                                        axis=1, ignore_index=True)
-                elif isinstance(other.data, DataTable):
-                    self.data = concat((self.data, DataFrame(other.data.to_numpy())),
+                elif isinstance(other.data, dt_DataTable):
+                    self.data = concat((self.data, pd_DataFrame(other.data.to_numpy())),
                                        axis=1, ignore_index=True)
                 else:
                     self.data = None
-            elif isinstance(self.data, DataTable):
+            elif isinstance(self.data, dt_DataTable):
                 if isinstance(other.data, np.ndarray):
-                    self.data = DataTable(np.hstack((self.data.to_numpy(), other.data)))
+                    self.data = dt_DataTable(np.hstack((self.data.to_numpy(), other.data)))
                 elif scipy.sparse.issparse(other.data):
-                    self.data = DataTable(np.hstack((self.data.to_numpy(), other.data.toarray())))
-                elif isinstance(other.data, DataFrame):
-                    self.data = DataTable(np.hstack((self.data.to_numpy(), other.data.values)))
-                elif isinstance(other.data, DataTable):
-                    self.data = DataTable(np.hstack((self.data.to_numpy(), other.data.to_numpy())))
+                    self.data = dt_DataTable(np.hstack((self.data.to_numpy(), other.data.toarray())))
+                elif isinstance(other.data, pd_DataFrame):
+                    self.data = dt_DataTable(np.hstack((self.data.to_numpy(), other.data.values)))
+                elif isinstance(other.data, dt_DataTable):
+                    self.data = dt_DataTable(np.hstack((self.data.to_numpy(), other.data.to_numpy())))
                 else:
                     self.data = None
             else:
@@ -2496,7 +2496,7 @@ class Booster:
                                                      tree_index=tree['tree_index'],
                                                      feature_names=feature_names))
 
-        return DataFrame(model_list, columns=model_list[0].keys())
+        return pd_DataFrame(model_list, columns=model_list[0].keys())
 
     def set_train_data_name(self, name):
         """Set the name to the training Dataset.
@@ -3345,7 +3345,7 @@ class Booster:
             ret = np.column_stack((bin_edges[1:], hist))
             ret = ret[ret[:, 1] > 0]
             if PANDAS_INSTALLED:
-                return DataFrame(ret, columns=['SplitValue', 'Count'])
+                return pd_DataFrame(ret, columns=['SplitValue', 'Count'])
             else:
                 return ret
         else:

python-package/lightgbm/compat.py

@@ -3,18 +3,20 @@
 
 """pandas"""
 try:
-    from pandas import Series, DataFrame, concat
+    from pandas import concat
+    from pandas import Series as pd_Series
+    from pandas import DataFrame as pd_DataFrame
     from pandas.api.types import is_sparse as is_dtype_sparse
     PANDAS_INSTALLED = True
 except ImportError:
     PANDAS_INSTALLED = False
 
-    class Series:
+    class pd_Series:
         """Dummy class for pandas.Series."""
 
         pass
 
-    class DataFrame:
+    class pd_DataFrame:
         """Dummy class for pandas.DataFrame."""
 
         pass
@@ -40,15 +42,15 @@ except ImportError:
 try:
     import datatable
     if hasattr(datatable, "Frame"):
-        DataTable = datatable.Frame
+        dt_DataTable = datatable.Frame
     else:
-        DataTable = datatable.DataTable
+        dt_DataTable = datatable.DataTable
     DATATABLE_INSTALLED = True
 except ImportError:
     DATATABLE_INSTALLED = False
 
-    class DataTable:
-        """Dummy class for DataTable."""
+    class dt_DataTable:
+        """Dummy class for datatable.DataTable."""
 
         pass
 
@@ -128,6 +130,6 @@ except ImportError:
         pass
 
     class dask_Frame:
-        """Dummy class for ddask.dataframe._Frame."""
+        """Dummy class for dask.dataframe._Frame."""
 
         pass

python-package/lightgbm/dask.py

@@ -16,7 +16,7 @@ import numpy as np
 import scipy.sparse as ss
 
 from .basic import _choose_param_value, _ConfigAliases, _LIB, _log_warning, _safe_call, LightGBMError
-from .compat import (PANDAS_INSTALLED, DataFrame, Series, concat,
+from .compat import (PANDAS_INSTALLED, pd_DataFrame, pd_Series, concat,
                      SKLEARN_INSTALLED,
                      DASK_INSTALLED, dask_Frame, dask_Array, delayed, Client, default_client, get_worker, wait)
 from .sklearn import LGBMClassifier, LGBMRegressor, LGBMRanker
@@ -105,7 +105,7 @@ def _find_ports_for_workers(client: Client, worker_addresses: Iterable[str], loc
 def _concat(seq):
     if isinstance(seq[0], np.ndarray):
         return np.concatenate(seq, axis=0)
-    elif isinstance(seq[0], (DataFrame, Series)):
+    elif isinstance(seq[0], (pd_DataFrame, pd_Series)):
         return concat(seq, axis=0)
     elif isinstance(seq[0], ss.spmatrix):
         return ss.vstack(seq, format='csr')
@@ -304,7 +304,7 @@ def _train(client, data, label, params, model_factory, sample_weight=None, group
 
 
 def _predict_part(part, model, raw_score, pred_proba, pred_leaf, pred_contrib, **kwargs):
-    data = part.values if isinstance(part, DataFrame) else part
+    data = part.values if isinstance(part, pd_DataFrame) else part
 
     if data.shape[0] == 0:
         result = np.array([])
@@ -325,11 +325,11 @@ def _predict_part(part, model, raw_score, pred_proba, pred_leaf, pred_contrib, *
             **kwargs
         )
 
-    if isinstance(part, DataFrame):
+    if isinstance(part, pd_DataFrame):
         if pred_proba or pred_contrib:
-            result = DataFrame(result, index=part.index)
+            result = pd_DataFrame(result, index=part.index)
         else:
-            result = Series(result, index=part.index, name='predictions')
+            result = pd_Series(result, index=part.index, name='predictions')
 
     return result
 
@@ -361,7 +361,7 @@ def _predict(model, data, raw_score=False, pred_proba=False, pred_leaf=False, pr
     -------
     predicted_result : dask array of shape = [n_samples] or shape = [n_samples, n_classes]
         The predicted values.
-    X_leaves : dask arrayof shape = [n_samples, n_trees] or shape = [n_samples, n_trees * n_classes]
+    X_leaves : dask array of shape = [n_samples, n_trees] or shape = [n_samples, n_trees * n_classes]
         If ``pred_leaf=True``, the predicted leaf of every tree for each sample.
     X_SHAP_values : dask array of shape = [n_samples, n_features + 1] or shape = [n_samples, (n_features + 1) * n_classes] or list with n_classes length of such objects
         If ``pred_contrib=True``, the feature contributions for each sample.

python-package/lightgbm/sklearn.py

@@ -11,7 +11,7 @@ from .compat import (SKLEARN_INSTALLED, _LGBMClassifierBase,
                      LGBMNotFittedError, _LGBMLabelEncoder, _LGBMModelBase,
                      _LGBMRegressorBase, _LGBMCheckXY, _LGBMCheckArray, _LGBMCheckSampleWeight,
                      _LGBMAssertAllFinite, _LGBMCheckClassificationTargets, _LGBMComputeSampleWeight,
-                     DataFrame, DataTable)
+                     pd_DataFrame, dt_DataTable)
 from .engine import train
 
 
@@ -560,7 +560,7 @@ class LGBMModel(_LGBMModelBase):
         params['metric'] = [e for e in eval_metrics_builtin if e not in original_metric] + original_metric
         params['metric'] = [metric for metric in params['metric'] if metric is not None]
 
-        if not isinstance(X, (DataFrame, DataTable)):
+        if not isinstance(X, (pd_DataFrame, dt_DataTable)):
             _X, _y = _LGBMCheckXY(X, y, accept_sparse=True, force_all_finite=False, ensure_min_samples=2)
             if sample_weight is not None:
                 sample_weight = _LGBMCheckSampleWeight(sample_weight, _X)
@@ -695,7 +695,7 @@ class LGBMModel(_LGBMModelBase):
         """
         if self._n_features is None:
             raise LGBMNotFittedError("Estimator not fitted, call `fit` before exploiting the model.")
-        if not isinstance(X, (DataFrame, DataTable)):
+        if not isinstance(X, (pd_DataFrame, dt_DataTable)):
             X = _LGBMCheckArray(X, accept_sparse=True, force_all_finite=False)
         n_features = X.shape[1]
         if self._n_features != n_features: