From 0d7d738670c2b80a5d898045c5843d405fc5efe2 Mon Sep 17 00:00:00 2001
From: Raghav R V <ragvrv@gmail.com>
Date: Sat, 4 Jul 2015 22:43:39 +0530
Subject: [PATCH] FIX all the examples to use the new cv classes

---
 examples/applications/face_recognition.py     |  4 +--
 examples/calibration/plot_calibration.py      |  2 +-
 .../calibration/plot_calibration_curve.py     |  2 +-
 .../plot_classifier_comparison.py             |  2 +-
 ...e_agglomeration_vs_univariate_selection.py |  6 ++--
 .../covariance/plot_covariance_estimation.py  |  2 +-
 .../plot_pca_vs_fa_model_selection.py         |  4 +--
 .../ensemble/plot_gradient_boosting_oob.py    |  8 +++---
 examples/ensemble/plot_partial_dependence.py  |  2 +-
 examples/exercises/plot_cv_diabetes.py        | 16 +++++++----
 examples/exercises/plot_cv_digits.py          |  5 ++--
 ...lot_permutation_test_for_classification.py |  5 ++--
 .../plot_rfe_with_cross_validation.py         |  4 +--
 examples/feature_stacker.py                   |  2 +-
 .../gaussian_process/gp_diabetes_dataset.py   |  9 +++---
 examples/linear_model/plot_sgd_comparison.py  |  2 +-
 examples/missing_values.py                    |  2 +-
 examples/mixture/plot_gmm_classifier.py       |  6 ++--
 examples/model_selection/README.txt           |  3 +-
 .../model_selection/grid_search_digits.py     |  4 +--
 .../grid_search_text_feature_extraction.py    |  3 +-
 .../model_selection/plot_confusion_matrix.py  |  2 +-
 .../model_selection/plot_learning_curve.py    | 28 ++++++++++++-------
 .../model_selection/plot_precision_recall.py  |  2 +-
 examples/model_selection/plot_roc.py          |  2 +-
 examples/model_selection/plot_roc_crossval.py |  8 +++---
 .../plot_underfitting_overfitting.py          |  6 ++--
 .../model_selection/plot_validation_curve.py  |  2 +-
 examples/model_selection/randomized_search.py |  3 +-
 .../neighbors/plot_digits_kde_sampling.py     |  2 +-
 .../plot_rbm_logistic_classification.py       |  2 +-
 examples/plot_cv_predict.py                   |  2 +-
 examples/plot_digits_pipe.py                  |  2 +-
 examples/plot_kernel_ridge_regression.py      |  2 +-
 examples/svm/plot_rbf_parameters.py           |  6 ++--
 examples/svm/plot_svm_anova.py                |  5 ++--
 examples/svm/plot_svm_scale_c.py              |  8 +++---
 37 files changed, 96 insertions(+), 79 deletions(-)

diff --git a/examples/applications/face_recognition.py b/examples/applications/face_recognition.py
index be466e9532cdf..b79599ecb3a06 100644
--- a/examples/applications/face_recognition.py
+++ b/examples/applications/face_recognition.py
@@ -31,9 +31,9 @@
 import logging
 import matplotlib.pyplot as plt
 
-from sklearn.cross_validation import train_test_split
+from sklearn.model_selection import train_test_split
+from sklearn.model_selection import GridSearchCV
 from sklearn.datasets import fetch_lfw_people
-from sklearn.grid_search import GridSearchCV
 from sklearn.metrics import classification_report
 from sklearn.metrics import confusion_matrix
 from sklearn.decomposition import RandomizedPCA
diff --git a/examples/calibration/plot_calibration.py b/examples/calibration/plot_calibration.py
index 2267f02dd0022..299f924e2a468 100644
--- a/examples/calibration/plot_calibration.py
+++ b/examples/calibration/plot_calibration.py
@@ -36,7 +36,7 @@
 from sklearn.naive_bayes import GaussianNB
 from sklearn.metrics import brier_score_loss
 from sklearn.calibration import CalibratedClassifierCV
-from sklearn.cross_validation import train_test_split
+from sklearn.model_selection import train_test_split
 
 
 n_samples = 50000
diff --git a/examples/calibration/plot_calibration_curve.py b/examples/calibration/plot_calibration_curve.py
index 42dc8473e6c30..a37e3158c0c12 100644
--- a/examples/calibration/plot_calibration_curve.py
+++ b/examples/calibration/plot_calibration_curve.py
@@ -56,7 +56,7 @@
 from sklearn.metrics import (brier_score_loss, precision_score, recall_score,
                              f1_score)
 from sklearn.calibration import CalibratedClassifierCV, calibration_curve
-from sklearn.cross_validation import train_test_split
+from sklearn.model_selection import train_test_split
 
 
 # Create dataset of classification task with many redundant and few
diff --git a/examples/classification/plot_classifier_comparison.py b/examples/classification/plot_classifier_comparison.py
index 7be3c0cacad9f..5c7673a5ff11e 100644
--- a/examples/classification/plot_classifier_comparison.py
+++ b/examples/classification/plot_classifier_comparison.py
@@ -31,7 +31,7 @@
 import numpy as np
 import matplotlib.pyplot as plt
 from matplotlib.colors import ListedColormap
-from sklearn.cross_validation import train_test_split
+from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import StandardScaler
 from sklearn.datasets import make_moons, make_circles, make_classification
 from sklearn.neighbors import KNeighborsClassifier
diff --git a/examples/cluster/plot_feature_agglomeration_vs_univariate_selection.py b/examples/cluster/plot_feature_agglomeration_vs_univariate_selection.py
index 488db4d64855d..a0152c85baf60 100644
--- a/examples/cluster/plot_feature_agglomeration_vs_univariate_selection.py
+++ b/examples/cluster/plot_feature_agglomeration_vs_univariate_selection.py
@@ -30,9 +30,9 @@
 from sklearn.cluster import FeatureAgglomeration
 from sklearn.linear_model import BayesianRidge
 from sklearn.pipeline import Pipeline
-from sklearn.grid_search import GridSearchCV
 from sklearn.externals.joblib import Memory
-from sklearn.cross_validation import KFold
+from sklearn.model_selection import GridSearchCV
+from sklearn.model_selection import KFold
 
 ###############################################################################
 # Generate data
@@ -60,7 +60,7 @@
 
 ###############################################################################
 # Compute the coefs of a Bayesian Ridge with GridSearch
-cv = KFold(len(y), 2)  # cross-validation generator for model selection
+cv = KFold(2)  # cross-validation generator for model selection
 ridge = BayesianRidge()
 cachedir = tempfile.mkdtemp()
 mem = Memory(cachedir=cachedir, verbose=1)
diff --git a/examples/covariance/plot_covariance_estimation.py b/examples/covariance/plot_covariance_estimation.py
index 85e26705b03e9..96f637974ee29 100644
--- a/examples/covariance/plot_covariance_estimation.py
+++ b/examples/covariance/plot_covariance_estimation.py
@@ -49,7 +49,7 @@
 
 from sklearn.covariance import LedoitWolf, OAS, ShrunkCovariance, \
     log_likelihood, empirical_covariance
-from sklearn.grid_search import GridSearchCV
+from sklearn.model_selection import GridSearchCV
 
 
 ###############################################################################
diff --git a/examples/decomposition/plot_pca_vs_fa_model_selection.py b/examples/decomposition/plot_pca_vs_fa_model_selection.py
index 067bcd7b6b479..89bb707a37699 100644
--- a/examples/decomposition/plot_pca_vs_fa_model_selection.py
+++ b/examples/decomposition/plot_pca_vs_fa_model_selection.py
@@ -35,8 +35,8 @@
 
 from sklearn.decomposition import PCA, FactorAnalysis
 from sklearn.covariance import ShrunkCovariance, LedoitWolf
-from sklearn.cross_validation import cross_val_score
-from sklearn.grid_search import GridSearchCV
+from sklearn.model_selection import cross_val_score
+from sklearn.model_selection import GridSearchCV
 
 ###############################################################################
 # Create the data
diff --git a/examples/ensemble/plot_gradient_boosting_oob.py b/examples/ensemble/plot_gradient_boosting_oob.py
index a39f709d36979..39e623f261cca 100644
--- a/examples/ensemble/plot_gradient_boosting_oob.py
+++ b/examples/ensemble/plot_gradient_boosting_oob.py
@@ -33,8 +33,8 @@
 import matplotlib.pyplot as plt
 
 from sklearn import ensemble
-from sklearn.cross_validation import KFold
-from sklearn.cross_validation import train_test_split
+from sklearn.model_selection import KFold
+from sklearn.model_selection import train_test_split
 
 
 # Generate data (adapted from G. Ridgeway's gbm example)
@@ -75,10 +75,10 @@ def heldout_score(clf, X_test, y_test):
 
 
 def cv_estimate(n_folds=3):
-    cv = KFold(n=X_train.shape[0], n_folds=n_folds)
+    cv = KFold(n_folds=n_folds)
     cv_clf = ensemble.GradientBoostingClassifier(**params)
     val_scores = np.zeros((n_estimators,), dtype=np.float64)
-    for train, test in cv:
+    for train, test in cv.split(X_train, y_train):
         cv_clf.fit(X_train[train], y_train[train])
         val_scores += heldout_score(cv_clf, X_train[test], y_train[test])
     val_scores /= n_folds
diff --git a/examples/ensemble/plot_partial_dependence.py b/examples/ensemble/plot_partial_dependence.py
index b480e228d3ca3..d4a26166944c3 100644
--- a/examples/ensemble/plot_partial_dependence.py
+++ b/examples/ensemble/plot_partial_dependence.py
@@ -51,7 +51,7 @@
 
 from mpl_toolkits.mplot3d import Axes3D
 
-from sklearn.cross_validation import train_test_split
+from sklearn.model_selection import train_test_split
 from sklearn.ensemble import GradientBoostingRegressor
 from sklearn.ensemble.partial_dependence import plot_partial_dependence
 from sklearn.ensemble.partial_dependence import partial_dependence
diff --git a/examples/exercises/plot_cv_diabetes.py b/examples/exercises/plot_cv_diabetes.py
index 424c037a5547e..5524d2e3c1334 100644
--- a/examples/exercises/plot_cv_diabetes.py
+++ b/examples/exercises/plot_cv_diabetes.py
@@ -14,13 +14,17 @@
 import numpy as np
 import matplotlib.pyplot as plt
 
-from sklearn import cross_validation, datasets, linear_model
+from sklearn import datasets
+from sklearn.linear_model import LassoCV
+from sklearn.linear_model import Lasso
+from sklearn.model_selection import KFold
+from sklearn.model_selection import cross_val_score
 
 diabetes = datasets.load_diabetes()
 X = diabetes.data[:150]
 y = diabetes.target[:150]
 
-lasso = linear_model.Lasso()
+lasso = Lasso()
 alphas = np.logspace(-4, -.5, 30)
 
 scores = list()
@@ -28,7 +32,7 @@
 
 for alpha in alphas:
     lasso.alpha = alpha
-    this_scores = cross_validation.cross_val_score(lasso, X, y, n_jobs=1)
+    this_scores = cross_val_score(lasso, X, y, n_jobs=1)
     scores.append(np.mean(this_scores))
     scores_std.append(np.std(this_scores))
 
@@ -51,15 +55,15 @@
 # performs cross-validation on the training data it receives).
 # We use external cross-validation to see how much the automatically obtained
 # alphas differ across different cross-validation folds.
-lasso_cv = linear_model.LassoCV(alphas=alphas)
-k_fold = cross_validation.KFold(len(X), 3)
+lasso_cv = LassoCV(alphas=alphas)
+k_fold = KFold(3)
 
 print("Answer to the bonus question:",
       "how much can you trust the selection of alpha?")
 print()
 print("Alpha parameters maximising the generalization score on different")
 print("subsets of the data:")
-for k, (train, test) in enumerate(k_fold):
+for k, (train, test) in enumerate(k_fold.split(X, y)):
     lasso_cv.fit(X[train], y[train])
     print("[fold {0}] alpha: {1:.5f}, score: {2:.5f}".
           format(k, lasso_cv.alpha_, lasso_cv.score(X[test], y[test])))
diff --git a/examples/exercises/plot_cv_digits.py b/examples/exercises/plot_cv_digits.py
index 92f04a935cc5a..a68f92afbdad9 100644
--- a/examples/exercises/plot_cv_digits.py
+++ b/examples/exercises/plot_cv_digits.py
@@ -12,7 +12,8 @@
 
 
 import numpy as np
-from sklearn import cross_validation, datasets, svm
+from sklearn.model_selection import cross_val_score
+from sklearn import datasets, svm
 
 digits = datasets.load_digits()
 X = digits.data
@@ -25,7 +26,7 @@
 scores_std = list()
 for C in C_s:
     svc.C = C
-    this_scores = cross_validation.cross_val_score(svc, X, y, n_jobs=1)
+    this_scores = cross_val_score(svc, X, y, n_jobs=1)
     scores.append(np.mean(this_scores))
     scores_std.append(np.std(this_scores))
 
diff --git a/examples/feature_selection/plot_permutation_test_for_classification.py b/examples/feature_selection/plot_permutation_test_for_classification.py
index 4df102578c9da..24b999451a067 100644
--- a/examples/feature_selection/plot_permutation_test_for_classification.py
+++ b/examples/feature_selection/plot_permutation_test_for_classification.py
@@ -20,7 +20,8 @@
 import matplotlib.pyplot as plt
 
 from sklearn.svm import SVC
-from sklearn.cross_validation import StratifiedKFold, permutation_test_score
+from sklearn.model_selection import StratifiedKFold
+from sklearn.model_selection import permutation_test_score
 from sklearn import datasets
 
 
@@ -39,7 +40,7 @@
 X = np.c_[X, E]
 
 svm = SVC(kernel='linear')
-cv = StratifiedKFold(y, 2)
+cv = StratifiedKFold(2)
 
 score, permutation_scores, pvalue = permutation_test_score(
     svm, X, y, scoring="accuracy", cv=cv, n_permutations=100, n_jobs=1)
diff --git a/examples/feature_selection/plot_rfe_with_cross_validation.py b/examples/feature_selection/plot_rfe_with_cross_validation.py
index 232aa115c2d77..8b22ab0d54108 100644
--- a/examples/feature_selection/plot_rfe_with_cross_validation.py
+++ b/examples/feature_selection/plot_rfe_with_cross_validation.py
@@ -10,7 +10,7 @@
 
 import matplotlib.pyplot as plt
 from sklearn.svm import SVC
-from sklearn.cross_validation import StratifiedKFold
+from sklearn.model_selection import StratifiedKFold
 from sklearn.feature_selection import RFECV
 from sklearn.datasets import make_classification
 
@@ -23,7 +23,7 @@
 svc = SVC(kernel="linear")
 # The "accuracy" scoring is proportional to the number of correct
 # classifications
-rfecv = RFECV(estimator=svc, step=1, cv=StratifiedKFold(y, 2),
+rfecv = RFECV(estimator=svc, step=1, cv=StratifiedKFold(2),
               scoring='accuracy')
 rfecv.fit(X, y)
 
diff --git a/examples/feature_stacker.py b/examples/feature_stacker.py
index d1f9453e28e58..4ce574aa36bca 100644
--- a/examples/feature_stacker.py
+++ b/examples/feature_stacker.py
@@ -20,7 +20,7 @@
 # License: BSD 3 clause
 
 from sklearn.pipeline import Pipeline, FeatureUnion
-from sklearn.grid_search import GridSearchCV
+from sklearn.model_selection import GridSearchCV
 from sklearn.svm import SVC
 from sklearn.datasets import load_iris
 from sklearn.decomposition import PCA
diff --git a/examples/gaussian_process/gp_diabetes_dataset.py b/examples/gaussian_process/gp_diabetes_dataset.py
index 9baaeccf17d6d..d188e268a0959 100644
--- a/examples/gaussian_process/gp_diabetes_dataset.py
+++ b/examples/gaussian_process/gp_diabetes_dataset.py
@@ -25,7 +25,8 @@
 
 from sklearn import datasets
 from sklearn.gaussian_process import GaussianProcess
-from sklearn.cross_validation import cross_val_score, KFold
+from sklearn.model_selection import cross_val_score
+from sklearn.model_selection import KFold
 
 # Load the dataset from scikit's data sets
 diabetes = datasets.load_diabetes()
@@ -43,9 +44,9 @@
 gp.theta0 = gp.theta_  # Given correlation parameter = MLE
 gp.thetaL, gp.thetaU = None, None  # None bounds deactivate MLE
 
-# Perform a cross-validation estimate of the coefficient of determination using
-# the cross_validation module using all CPUs available on the machine
+# Perform a cross-validated estimate of the coefficient of determination using
+# the model_selection.cross_val_score using all CPUs available on the machine
 K = 20  # folds
-R2 = cross_val_score(gp, X, y=y, cv=KFold(y.size, K), n_jobs=1).mean()
+R2 = cross_val_score(gp, X, y=y, cv=KFold(K), n_jobs=1).mean()
 print("The %d-Folds estimate of the coefficient of determination is R2 = %s"
       % (K, R2))
diff --git a/examples/linear_model/plot_sgd_comparison.py b/examples/linear_model/plot_sgd_comparison.py
index 123aff9f06a6b..049a35e3309a4 100644
--- a/examples/linear_model/plot_sgd_comparison.py
+++ b/examples/linear_model/plot_sgd_comparison.py
@@ -14,7 +14,7 @@
 import matplotlib.pyplot as plt
 from sklearn import datasets
 
-from sklearn.cross_validation import train_test_split
+from sklearn.model_selection import train_test_split
 from sklearn.linear_model import SGDClassifier, Perceptron
 from sklearn.linear_model import PassiveAggressiveClassifier
 
diff --git a/examples/missing_values.py b/examples/missing_values.py
index 59444b36490e3..8a0895f9a589f 100644
--- a/examples/missing_values.py
+++ b/examples/missing_values.py
@@ -28,7 +28,7 @@
 from sklearn.ensemble import RandomForestRegressor
 from sklearn.pipeline import Pipeline
 from sklearn.preprocessing import Imputer
-from sklearn.cross_validation import cross_val_score
+from sklearn.model_selection import cross_val_score
 
 rng = np.random.RandomState(0)
 
diff --git a/examples/mixture/plot_gmm_classifier.py b/examples/mixture/plot_gmm_classifier.py
index cebbe36cada69..201bd7dd3934a 100644
--- a/examples/mixture/plot_gmm_classifier.py
+++ b/examples/mixture/plot_gmm_classifier.py
@@ -33,7 +33,7 @@
 import numpy as np
 
 from sklearn import datasets
-from sklearn.cross_validation import StratifiedKFold
+from sklearn.model_selection import StratifiedKFold
 from sklearn.externals.six.moves import xrange
 from sklearn.mixture import GMM
 
@@ -55,9 +55,9 @@ def make_ellipses(gmm, ax):
 
 # Break up the dataset into non-overlapping training (75%) and testing
 # (25%) sets.
-skf = StratifiedKFold(iris.target, n_folds=4)
+skf = StratifiedKFold(n_folds=4)
 # Only take the first fold.
-train_index, test_index = next(iter(skf))
+train_index, test_index = next(iter(skf.split(iris.data, iris.target)))
 
 
 X_train = iris.data[train_index]
diff --git a/examples/model_selection/README.txt b/examples/model_selection/README.txt
index 553c6e7d6498e..b35a778b28a7f 100644
--- a/examples/model_selection/README.txt
+++ b/examples/model_selection/README.txt
@@ -3,5 +3,4 @@
 Model Selection
 -----------------------
 
-Examples concerning model selection, mostly contained in the
-:mod:`sklearn.grid_search` and :mod:`sklearn.cross_validation` modules.
+Examples related to the :mod:`sklearn.model_selection` module.
diff --git a/examples/model_selection/grid_search_digits.py b/examples/model_selection/grid_search_digits.py
index c8aec1bab8c0f..e7ae63069d656 100644
--- a/examples/model_selection/grid_search_digits.py
+++ b/examples/model_selection/grid_search_digits.py
@@ -19,8 +19,8 @@
 from __future__ import print_function
 
 from sklearn import datasets
-from sklearn.cross_validation import train_test_split
-from sklearn.grid_search import GridSearchCV
+from sklearn.model_selection import train_test_split
+from sklearn.model_selection import GridSearchCV
 from sklearn.metrics import classification_report
 from sklearn.svm import SVC
 
diff --git a/examples/model_selection/grid_search_text_feature_extraction.py b/examples/model_selection/grid_search_text_feature_extraction.py
index 11b690d91e2ef..daf82718d42e1 100644
--- a/examples/model_selection/grid_search_text_feature_extraction.py
+++ b/examples/model_selection/grid_search_text_feature_extraction.py
@@ -1,3 +1,4 @@
+
 """
 ==========================================================
 Sample pipeline for text feature extraction and evaluation
@@ -56,7 +57,7 @@
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.feature_extraction.text import TfidfTransformer
 from sklearn.linear_model import SGDClassifier
-from sklearn.grid_search import GridSearchCV
+from sklearn.model_selection import GridSearchCV
 from sklearn.pipeline import Pipeline
 
 print(__doc__)
diff --git a/examples/model_selection/plot_confusion_matrix.py b/examples/model_selection/plot_confusion_matrix.py
index 771d058e2a4a5..250d71c08c442 100644
--- a/examples/model_selection/plot_confusion_matrix.py
+++ b/examples/model_selection/plot_confusion_matrix.py
@@ -30,7 +30,7 @@
 import matplotlib.pyplot as plt
 
 from sklearn import svm, datasets
-from sklearn.cross_validation import train_test_split
+from sklearn.model_selection import train_test_split
 from sklearn.metrics import confusion_matrix
 
 # import some data to play with
diff --git a/examples/model_selection/plot_learning_curve.py b/examples/model_selection/plot_learning_curve.py
index 7a47fd574635d..c358471e1eebc 100644
--- a/examples/model_selection/plot_learning_curve.py
+++ b/examples/model_selection/plot_learning_curve.py
@@ -17,11 +17,11 @@
 
 import numpy as np
 import matplotlib.pyplot as plt
-from sklearn import cross_validation
 from sklearn.naive_bayes import GaussianNB
 from sklearn.svm import SVC
 from sklearn.datasets import load_digits
-from sklearn.learning_curve import learning_curve
+from sklearn.model_selection import learning_curve
+from sklearn.model_selection import ShuffleSplit
 
 
 def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
@@ -48,10 +48,20 @@ def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
     ylim : tuple, shape (ymin, ymax), optional
         Defines minimum and maximum yvalues plotted.
 
-    cv : integer, cross-validation generator, optional
-        If an integer is passed, it is the number of folds (defaults to 3).
-        Specific cross-validation objects can be passed, see
-        sklearn.cross_validation module for the list of possible objects
+    cv : int, cross-validation generator or an iterable, optional
+        Determines the cross-validation splitting strategy.
+        Possible inputs for cv are:
+          - None, to use the default 3-fold cross-validation,
+          - integer, to specify the number of folds.
+          - An object to be used as a cross-validation generator.
+          - An iterable yielding train/test splits.
+
+        For integer/None inputs, if ``y`` is binary or multiclass,
+        :class:`StratifiedKFold` used. If classifier is False or if ``y`` is
+        neither binary nor multiclass, :class:`KFold` is used.
+
+        Refer :ref:`User Guide <cross_validation>` for the various
+        cross-validators that can be used here.
 
     n_jobs : integer, optional
         Number of jobs to run in parallel (default 1).
@@ -91,16 +101,14 @@ def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
 title = "Learning Curves (Naive Bayes)"
 # Cross validation with 100 iterations to get smoother mean test and train
 # score curves, each time with 20% data randomly selected as a validation set.
-cv = cross_validation.ShuffleSplit(digits.data.shape[0], n_iter=100,
-                                   test_size=0.2, random_state=0)
+cv = ShuffleSplit(n_iter=100, test_size=0.2, random_state=0)
 
 estimator = GaussianNB()
 plot_learning_curve(estimator, title, X, y, ylim=(0.7, 1.01), cv=cv, n_jobs=4)
 
 title = "Learning Curves (SVM, RBF kernel, $\gamma=0.001$)"
 # SVC is more expensive so we do a lower number of CV iterations:
-cv = cross_validation.ShuffleSplit(digits.data.shape[0], n_iter=10,
-                                   test_size=0.2, random_state=0)
+cv = ShuffleSplit(n_iter=10, test_size=0.2, random_state=0)
 estimator = SVC(gamma=0.001)
 plot_learning_curve(estimator, title, X, y, (0.7, 1.01), cv=cv, n_jobs=4)
 
diff --git a/examples/model_selection/plot_precision_recall.py b/examples/model_selection/plot_precision_recall.py
index 6617a6b5d88fa..9f48d93d8b298 100644
--- a/examples/model_selection/plot_precision_recall.py
+++ b/examples/model_selection/plot_precision_recall.py
@@ -78,7 +78,7 @@
 from sklearn import svm, datasets
 from sklearn.metrics import precision_recall_curve
 from sklearn.metrics import average_precision_score
-from sklearn.cross_validation import train_test_split
+from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import label_binarize
 from sklearn.multiclass import OneVsRestClassifier
 
diff --git a/examples/model_selection/plot_roc.py b/examples/model_selection/plot_roc.py
index 49ae4b5fe5ce7..94aeecab05fd8 100644
--- a/examples/model_selection/plot_roc.py
+++ b/examples/model_selection/plot_roc.py
@@ -34,7 +34,7 @@
 import matplotlib.pyplot as plt
 from sklearn import svm, datasets
 from sklearn.metrics import roc_curve, auc
-from sklearn.cross_validation import train_test_split
+from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import label_binarize
 from sklearn.multiclass import OneVsRestClassifier
 
diff --git a/examples/model_selection/plot_roc_crossval.py b/examples/model_selection/plot_roc_crossval.py
index 0599813653640..91a41ffbaadcb 100644
--- a/examples/model_selection/plot_roc_crossval.py
+++ b/examples/model_selection/plot_roc_crossval.py
@@ -37,7 +37,7 @@
 
 from sklearn import svm, datasets
 from sklearn.metrics import roc_curve, auc
-from sklearn.cross_validation import StratifiedKFold
+from sklearn.model_selection import StratifiedKFold
 
 ###############################################################################
 # Data IO and generation
@@ -57,7 +57,7 @@
 # Classification and ROC analysis
 
 # Run classifier with cross-validation and plot ROC curves
-cv = StratifiedKFold(y, n_folds=6)
+cv = StratifiedKFold(n_folds=6)
 classifier = svm.SVC(kernel='linear', probability=True,
                      random_state=random_state)
 
@@ -65,7 +65,7 @@
 mean_fpr = np.linspace(0, 1, 100)
 all_tpr = []
 
-for i, (train, test) in enumerate(cv):
+for i, (train, test) in enumerate(cv.split(X, y)):
     probas_ = classifier.fit(X[train], y[train]).predict_proba(X[test])
     # Compute ROC curve and area the curve
     fpr, tpr, thresholds = roc_curve(y[test], probas_[:, 1])
@@ -76,7 +76,7 @@
 
 plt.plot([0, 1], [0, 1], '--', color=(0.6, 0.6, 0.6), label='Luck')
 
-mean_tpr /= len(cv)
+mean_tpr /= cv.n_splits(X, y)
 mean_tpr[-1] = 1.0
 mean_auc = auc(mean_fpr, mean_tpr)
 plt.plot(mean_fpr, mean_tpr, 'k--',
diff --git a/examples/model_selection/plot_underfitting_overfitting.py b/examples/model_selection/plot_underfitting_overfitting.py
index f8958cbffe21b..ff454664c7b18 100644
--- a/examples/model_selection/plot_underfitting_overfitting.py
+++ b/examples/model_selection/plot_underfitting_overfitting.py
@@ -27,7 +27,7 @@
 from sklearn.pipeline import Pipeline
 from sklearn.preprocessing import PolynomialFeatures
 from sklearn.linear_model import LinearRegression
-from sklearn import cross_validation
+from sklearn.model_selection import cross_val_score
 
 np.random.seed(0)
 
@@ -51,8 +51,8 @@
     pipeline.fit(X[:, np.newaxis], y)
 
     # Evaluate the models using crossvalidation
-    scores = cross_validation.cross_val_score(pipeline,
-        X[:, np.newaxis], y, scoring="mean_squared_error", cv=10)
+    scores = cross_val_score(pipeline, X[:, np.newaxis], y,
+                             scoring="mean_squared_error", cv=10)
 
     X_test = np.linspace(0, 1, 100)
     plt.plot(X_test, pipeline.predict(X_test[:, np.newaxis]), label="Model")
diff --git a/examples/model_selection/plot_validation_curve.py b/examples/model_selection/plot_validation_curve.py
index 336e0349eacbf..4b1c5c87ce7ff 100644
--- a/examples/model_selection/plot_validation_curve.py
+++ b/examples/model_selection/plot_validation_curve.py
@@ -17,7 +17,7 @@
 import numpy as np
 from sklearn.datasets import load_digits
 from sklearn.svm import SVC
-from sklearn.learning_curve import validation_curve
+from sklearn.model_selection import validation_curve
 
 digits = load_digits()
 X, y = digits.data, digits.target
diff --git a/examples/model_selection/randomized_search.py b/examples/model_selection/randomized_search.py
index 0682b24689813..85a16c6f52d55 100644
--- a/examples/model_selection/randomized_search.py
+++ b/examples/model_selection/randomized_search.py
@@ -26,7 +26,8 @@
 from operator import itemgetter
 from scipy.stats import randint as sp_randint
 
-from sklearn.grid_search import GridSearchCV, RandomizedSearchCV
+from sklearn.model_selection import GridSearchCV
+from sklearn.model_selection import RandomizedSearchCV
 from sklearn.datasets import load_digits
 from sklearn.ensemble import RandomForestClassifier
 
diff --git a/examples/neighbors/plot_digits_kde_sampling.py b/examples/neighbors/plot_digits_kde_sampling.py
index 4680a41780aed..ba59fb5ece537 100644
--- a/examples/neighbors/plot_digits_kde_sampling.py
+++ b/examples/neighbors/plot_digits_kde_sampling.py
@@ -16,7 +16,7 @@
 from sklearn.datasets import load_digits
 from sklearn.neighbors import KernelDensity
 from sklearn.decomposition import PCA
-from sklearn.grid_search import GridSearchCV
+from sklearn.model_selection import GridSearchCV
 
 # load the data
 digits = load_digits()
diff --git a/examples/neural_networks/plot_rbm_logistic_classification.py b/examples/neural_networks/plot_rbm_logistic_classification.py
index 9f085036d2013..2b9b15fe3d966 100644
--- a/examples/neural_networks/plot_rbm_logistic_classification.py
+++ b/examples/neural_networks/plot_rbm_logistic_classification.py
@@ -37,7 +37,7 @@
 
 from scipy.ndimage import convolve
 from sklearn import linear_model, datasets, metrics
-from sklearn.cross_validation import train_test_split
+from sklearn.model_selection import train_test_split
 from sklearn.neural_network import BernoulliRBM
 from sklearn.pipeline import Pipeline
 
diff --git a/examples/plot_cv_predict.py b/examples/plot_cv_predict.py
index 5a9e541949dc9..4657ff816369a 100644
--- a/examples/plot_cv_predict.py
+++ b/examples/plot_cv_predict.py
@@ -8,7 +8,7 @@
 
 """
 from sklearn import datasets
-from sklearn.cross_validation import cross_val_predict
+from sklearn.model_selection import cross_val_predict
 from sklearn import linear_model
 import matplotlib.pyplot as plt
 
diff --git a/examples/plot_digits_pipe.py b/examples/plot_digits_pipe.py
index 139ade15ba7c2..cd134fe20ddec 100644
--- a/examples/plot_digits_pipe.py
+++ b/examples/plot_digits_pipe.py
@@ -25,7 +25,7 @@
 
 from sklearn import linear_model, decomposition, datasets
 from sklearn.pipeline import Pipeline
-from sklearn.grid_search import GridSearchCV
+from sklearn.model_selection import GridSearchCV
 
 logistic = linear_model.LogisticRegression()
 
diff --git a/examples/plot_kernel_ridge_regression.py b/examples/plot_kernel_ridge_regression.py
index 19aeece6658cc..30d2025e2020c 100644
--- a/examples/plot_kernel_ridge_regression.py
+++ b/examples/plot_kernel_ridge_regression.py
@@ -41,7 +41,7 @@
 import numpy as np
 
 from sklearn.svm import SVR
-from sklearn.grid_search import GridSearchCV
+from sklearn.model_selection import GridSearchCV
 from sklearn.learning_curve import learning_curve
 from sklearn.kernel_ridge import KernelRidge
 import matplotlib.pyplot as plt
diff --git a/examples/svm/plot_rbf_parameters.py b/examples/svm/plot_rbf_parameters.py
index ead630e2933ec..eea9c0e6fc621 100644
--- a/examples/svm/plot_rbf_parameters.py
+++ b/examples/svm/plot_rbf_parameters.py
@@ -74,8 +74,8 @@
 from sklearn.svm import SVC
 from sklearn.preprocessing import StandardScaler
 from sklearn.datasets import load_iris
-from sklearn.cross_validation import StratifiedShuffleSplit
-from sklearn.grid_search import GridSearchCV
+from sklearn.model_selection import StratifiedShuffleSplit
+from sklearn.model_selection import GridSearchCV
 
 
 # Utility function to move the midpoint of a colormap to be around
@@ -128,7 +128,7 @@ def __call__(self, value, clip=None):
 C_range = np.logspace(-2, 10, 13)
 gamma_range = np.logspace(-9, 3, 13)
 param_grid = dict(gamma=gamma_range, C=C_range)
-cv = StratifiedShuffleSplit(y, n_iter=5, test_size=0.2, random_state=42)
+cv = StratifiedShuffleSplit(n_iter=5, test_size=0.2, random_state=42)
 grid = GridSearchCV(SVC(), param_grid=param_grid, cv=cv)
 grid.fit(X, y)
 
diff --git a/examples/svm/plot_svm_anova.py b/examples/svm/plot_svm_anova.py
index 9ce225bf980e5..45da4c35e0a64 100644
--- a/examples/svm/plot_svm_anova.py
+++ b/examples/svm/plot_svm_anova.py
@@ -10,7 +10,8 @@
 
 import numpy as np
 import matplotlib.pyplot as plt
-from sklearn import svm, datasets, feature_selection, cross_validation
+from sklearn import svm, datasets, feature_selection
+from sklearn.model_selection import cross_val_score
 from sklearn.pipeline import Pipeline
 
 ###############################################################################
@@ -42,7 +43,7 @@
 for percentile in percentiles:
     clf.set_params(anova__percentile=percentile)
     # Compute cross-validation score using all CPUs
-    this_scores = cross_validation.cross_val_score(clf, X, y, n_jobs=1)
+    this_scores = cross_val_score(clf, X, y, n_jobs=1)
     score_means.append(this_scores.mean())
     score_stds.append(this_scores.std())
 
diff --git a/examples/svm/plot_svm_scale_c.py b/examples/svm/plot_svm_scale_c.py
index c977d3d9b997d..ea0ed9b3e555a 100644
--- a/examples/svm/plot_svm_scale_c.py
+++ b/examples/svm/plot_svm_scale_c.py
@@ -88,8 +88,8 @@
 import matplotlib.pyplot as plt
 
 from sklearn.svm import LinearSVC
-from sklearn.cross_validation import ShuffleSplit
-from sklearn.grid_search import GridSearchCV
+from sklearn.model_selection import ShuffleSplit
+from sklearn.model_selection import GridSearchCV
 from sklearn.utils import check_random_state
 from sklearn import datasets
 
@@ -128,8 +128,8 @@
         # To get nice curve, we need a large number of iterations to
         # reduce the variance
         grid = GridSearchCV(clf, refit=False, param_grid=param_grid,
-                            cv=ShuffleSplit(n=n_samples, train_size=train_size,
-                                            n_iter=250, random_state=1))
+                            cv=ShuffleSplit(train_size=train_size, n_iter=250,
+                                            random_state=1))
         grid.fit(X, y)
         scores = [x[1] for x in grid.grid_scores_]