Revert #3677 and #3674 (#3678)

* Revert "Add scikit-learn as dependency for doc build (#3677)"

This reverts commit 308f664ade0547242608e21f6198c895415f03da.

* Revert "Add scikit-learn tests (#3674)"

This reverts commit d176a0fbc8165e3afe3e42ff464ab7b253211555.

doc/conf.py

@@ -41,7 +41,7 @@ sys.path.insert(0, curr_path)
 
 # -- mock out modules
 import mock
-MOCK_MODULES = ['scipy', 'scipy.sparse', 'pandas']
+MOCK_MODULES = ['scipy', 'scipy.sparse', 'sklearn', 'pandas']
 for mod_name in MOCK_MODULES:
   sys.modules[mod_name] = mock.Mock()
 

doc/requirements.txt

@@ -6,4 +6,3 @@ sh>=1.12.14
 matplotlib>=2.1
 graphviz
 numpy
-scikit-learn

python-package/xgboost/core.py

@@ -9,6 +9,7 @@ import ctypes
 import os
 import re
 import sys
+
 import numpy as np
 import scipy.sparse
 
@@ -373,15 +374,11 @@ class DMatrix(object):
         if label is not None:
             if isinstance(label, np.ndarray):
                 self.set_label_npy2d(label)
-            elif getattr(label, '__array__', None) is not None:
-                self.set_label_npy2d(label.__array__())
             else:
                 self.set_label(label)
         if weight is not None:
             if isinstance(weight, np.ndarray):
                 self.set_weight_npy2d(weight)
-            elif getattr(weight, '__array__', None) is not None:
-                self.set_weight_npy2d(weight.__array__())
             else:
                 self.set_weight(weight)
 
@@ -431,7 +428,7 @@ class DMatrix(object):
         and type if memory use is a concern.
         """
         if len(mat.shape) != 2:
-            raise ValueError('Input numpy.ndarray must be 2 dimensional. Reshape your data.')
+            raise ValueError('Input numpy.ndarray must be 2 dimensional')
         # flatten the array by rows and ensure it is float32.
         # we try to avoid data copies if possible (reshape returns a view when possible
         # and we explicitly tell np.array to try and avoid copying)

python-package/xgboost/sklearn.py

@@ -1,12 +1,10 @@
 # coding: utf-8
-# pylint: disable=too-many-arguments, too-many-locals, invalid-name, fixme, E0012, R0912, C0302
+# pylint: disable=too-many-arguments, too-many-locals, invalid-name, fixme, E0012, R0912
 """Scikit-Learn Wrapper interface for XGBoost."""
 from __future__ import absolute_import
 
 import numpy as np
 import warnings
-from sklearn.exceptions import NotFittedError
-from sklearn.exceptions import DataConversionWarning
 from .core import Booster, DMatrix, XGBoostError
 from .training import train
 
@@ -16,16 +14,6 @@ from .compat import (SKLEARN_INSTALLED, XGBModelBase,
                      XGBClassifierBase, XGBRegressorBase, XGBLabelEncoder)
 
 
-def _check_label_1d(label):
-    """Produce warning if label is not 1D array"""
-    label = np.array(label, copy=False, dtype=np.float32)
-    if len(label.shape) == 2 and label.shape[1] == 1:
-        warnings.warn('A column-vector y was passed when a 1d array was'
-                      ' expected. Please change the shape of y to '
-                      '(n_samples, ), for example using ravel().',
-                      DataConversionWarning, stacklevel=2)
-
-
 def _objective_decorator(func):
     """Decorate an objective function
 
@@ -190,7 +178,7 @@ class XGBModel(XGBModelBase):
         booster : a xgboost booster of underlying model
         """
         if self._Booster is None:
-            raise NotFittedError('need to call fit or load_model beforehand')
+            raise XGBoostError('need to call fit or load_model beforehand')
         return self._Booster
 
     def get_params(self, deep=False):
@@ -298,7 +286,6 @@ class XGBModel(XGBModelBase):
             file name of stored xgb model or 'Booster' instance Xgb model to be
             loaded before training (allows training continuation).
         """
-        _check_label_1d(label=y)
         if sample_weight is not None:
             trainDmatrix = DMatrix(X, label=y, weight=sample_weight,
                                    missing=self.missing, nthread=self.n_jobs)
@@ -549,7 +536,6 @@ class XGBClassifier(XGBModel, XGBClassifierBase):
             file name of stored xgb model or 'Booster' instance Xgb model to be
             loaded before training (allows training continuation).
         """
-        _check_label_1d(label=y)
         evals_result = {}
         self.classes_ = np.unique(y)
         self.n_classes_ = len(self.classes_)
@@ -926,7 +912,6 @@ class XGBRanker(XGBModel):
             file name of stored xgb model or 'Booster' instance Xgb model to be
             loaded before training (allows training continuation).
         """
-        _check_label_1d(label=y)
         # check if group information is provided
         if group is None:
             raise ValueError("group is required for ranking task")

python-package/xgboost/training.py

@@ -203,18 +203,6 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
                       DeprecationWarning)
         callbacks.append(callback.reset_learning_rate(learning_rates))
 
-    nrow = dtrain.num_row()
-    ncol = dtrain.num_col()
-    if nrow <= 0:
-        raise ValueError('{} row(s) (shape=({}, {})) while a minimum of 1 is required.'
-                         .format(nrow, nrow, ncol))
-    if ncol <= 0:
-        raise ValueError('{} feature(s) (shape=({}, {})) while a minimum of 1 is required.'
-                         .format(ncol, nrow, ncol))
-    label = dtrain.get_label()
-    if nrow != len(label):
-        raise ValueError('Label must have same length as the number of data rows')
-
     return _train_internal(params, dtrain,
                            num_boost_round=num_boost_round,
                            evals=evals,