MAINT: cleanup deprecation warning in tests and source code (#466)

Author: glemaitre

.travis.yml

@@ -35,7 +35,7 @@ matrix:
     - env: DISTRIB="conda" PYTHON_VERSION="2.7"
            NUMPY_VERSION="1.13.1" SCIPY_VERSION="0.19.1" SKLEARN_VERSION="0.20rc"
     - env: DISTRIB="conda" PYTHON_VERSION="3.6"
-           NUMPY_VERSION="1.13.1" SCIPY_VERSION="0.19.1" SKLEARN_VERSION="0.20rc"
+           NUMPY_VERSION="*" SCIPY_VERSION="*" SKLEARN_VERSION="0.20rc"
     - env: DISTRIB="conda" PYTHON_VERSION="3.7"
            NUMPY_VERSION="1.13.1" SCIPY_VERSION="0.19.1" SKLEARN_VERSION="0.20rc"
     - env: DISTRIB="conda" PYTHON_VERSION="3.7"

appveyor.yml

@@ -42,7 +42,7 @@ install:
   - activate testenv
   - conda install scipy numpy -y -q
   - pip install --pre scikit-learn
-  - "conda install %OPTIONAL_DEP% -y -q"
+  - conda install %OPTIONAL_DEP% -y -q
   - conda install pytest pytest-cov -y -q
   - pip install codecov
   - pip install .

build_tools/circle/build_doc.sh

@@ -88,11 +88,12 @@ conda update --yes --quiet conda
 
 # Configure the conda environment and put it in the path using the
 # provided versions
-conda create -n $CONDA_ENV_NAME --yes --quiet python=3
+conda create -n $CONDA_ENV_NAME --yes --quiet python=3.6
 source activate $CONDA_ENV_NAME
 
-conda install --yes pip numpy scipy scikit-learn pillow matplotlib sphinx \
+conda install --yes pip numpy scipy pillow matplotlib sphinx \
       sphinx_rtd_theme numpydoc pandas keras
+pip install --pre scikit-learn
 pip install -U git+https://github.com/sphinx-gallery/sphinx-gallery.git
 
 # Build and install imbalanced-learn in dev mode

build_tools/travis/install.sh

@@ -40,9 +40,9 @@ if [[ "$DISTRIB" == "conda" ]]; then
     source activate testenv
     conda install --yes numpy=$NUMPY_VERSION scipy=$SCIPY_VERSION
 
-    if [[ $PYTHON_VERSION == "3.7" ]]; then
-        conda install --yes pandas
-        conda install --yes -c conda-forge keras
+    if [[ $PYTHON_VERSION == "3.6" ]]; then
+        # Tensorflow is not available in Python 3.7 yet.
+        conda install --yes pandas keras tensorflow
         KERAS_BACKEND=tensorflow
         python -c "import keras.backend"
         sed -i -e 's/"backend":[[:space:]]*"[^"]*/"backend":\ "'$KERAS_BACKEND'/g' ~/.keras/keras.json;

doc/ensemble.rst

@@ -32,11 +32,11 @@ under-sampling the original set::
   >>> print(sorted(Counter(y).items()))
   [(0, 64), (1, 262), (2, 4674)]
   >>> from imblearn.ensemble import EasyEnsemble
-  >>> ee = EasyEnsemble(random_state=0, n_subsets=10)
-  >>> X_resampled, y_resampled = ee.fit_resample(X, y)
-  >>> print(X_resampled.shape)
+  >>> ee = EasyEnsemble(random_state=0, n_subsets=10) # doctest: +SKIP
+  >>> X_resampled, y_resampled = ee.fit_resample(X, y) # doctest: +SKIP
+  >>> print(X_resampled.shape) # doctest: +SKIP
   (10, 192, 2)
-  >>> print(sorted(Counter(y_resampled[0]).items()))
+  >>> print(sorted(Counter(y_resampled[0]).items())) # doctest: +SKIP
   [(0, 64), (1, 64), (2, 64)]
 
 :class:`EasyEnsemble` has two important parameters: (i) ``n_subsets`` will be
@@ -53,7 +53,9 @@ parameter ``n_max_subset`` and an additional bootstraping can be activated with
   >>> from imblearn.ensemble import BalanceCascade
   >>> from sklearn.linear_model import LogisticRegression
   >>> bc = BalanceCascade(random_state=0,
-  ...                     estimator=LogisticRegression(random_state=0),
+  ...                     estimator=LogisticRegression(solver='lbfgs',
+  ...                                                  multi_class='auto',
+  ...                                                  random_state=0),
   ...                     n_max_subset=4)
   >>> X_resampled, y_resampled = bc.fit_resample(X, y)
   >>> print(X_resampled.shape)

doc/under_sampling.rst

@@ -340,7 +340,7 @@ used as::
   >>> oss = OneSidedSelection(random_state=0)
   >>> X_resampled, y_resampled = oss.fit_resample(X, y)
   >>> print(sorted(Counter(y_resampled).items()))
-  [(0, 64), (1, 174), (2, 4403)]
+  [(0, 64), (1, 174), (2, 4404)]
 
 Our implementation offer to set the number of seeds to put in the set :math:`C`
 originally by setting the parameter ``n_seeds_S``.
@@ -379,7 +379,8 @@ removed. The class can be used as::
   >>> from sklearn.linear_model import LogisticRegression
   >>> from imblearn.under_sampling import InstanceHardnessThreshold
   >>> iht = InstanceHardnessThreshold(random_state=0,
-  ...                                 estimator=LogisticRegression())
+  ...                                 estimator=LogisticRegression(
+  ...                                     solver='lbfgs', multi_class='auto'))
   >>> X_resampled, y_resampled = iht.fit_resample(X, y)
   >>> print(sorted(Counter(y_resampled).items()))
   [(0, 64), (1, 64), (2, 64)]

doc/whats_new/v0.0.4.rst

@@ -97,6 +97,9 @@ Maintenance
 - Upgrade requirements to scikit-learn 0.20.
   :issue:`379` by :user:`Guillaume Lemaitre <glemaitre>`.
 
+- Catch deprecation warning in testing.
+  :issue:`441` by :user:`Guillaume Lemaitre <glemaitre>`.
+
 Documentation
 .............
 

examples/plot_outlier_rejections.py

@@ -37,6 +37,7 @@ def plot_scatter(X, y, title):
     plt.legend()
     plt.title(title)
 
+
 ##############################################################################
 # Toy data generation
 ##############################################################################
@@ -82,11 +83,13 @@ def plot_scatter(X, y, title):
 # :class:`imblearn.FunctionSampler` will be called when using the method
 # ``fit_resample``.
 
+
 def outlier_rejection(X, y):
     """This will be our function used to resample our dataset."""
     model = IsolationForest(max_samples=100,
                             contamination=0.4,
-                            random_state=rng)
+                            random_state=rng,
+                            behaviour='new')
     model.fit(X)
     y_pred = model.predict(X)
     return X[y_pred == 1], y[y_pred == 1]
@@ -105,11 +108,12 @@ def outlier_rejection(X, y):
 # affected during the prediction.
 
 pipe = make_pipeline(FunctionSampler(func=outlier_rejection),
-                     LogisticRegression(random_state=rng))
+                     LogisticRegression(solver='lbfgs', multi_class='auto',
+                                        random_state=rng))
 y_pred = pipe.fit(X_train, y_train).predict(X_test)
 print(classification_report(y_test, y_pred))
 
-clf = LogisticRegression(random_state=rng)
+clf = LogisticRegression(solver='lbfgs', multi_class='auto', random_state=rng)
 y_pred = clf.fit(X_train, y_train).predict(X_test)
 print(classification_report(y_test, y_pred))
 

examples/under-sampling/plot_comparison_under_sampling.py

@@ -235,8 +235,9 @@ def plot_decision_function(X, y, clf, ax):
 clf = LinearSVC().fit(X, y)
 plot_decision_function(X, y, clf, ax1)
 ax1.set_title('Linear SVC with y={}'.format(Counter(y)))
-sampler = InstanceHardnessThreshold(random_state=0,
-                                    estimator=LogisticRegression())
+sampler = InstanceHardnessThreshold(
+    random_state=0, estimator=LogisticRegression(solver='lbfgs',
+                                                 multi_class='auto'))
 clf = make_pipeline(sampler, LinearSVC())
 clf.fit(X, y)
 plot_decision_function(X, y, clf, ax2)

examples/under-sampling/plot_instance_hardness_threshold.py

@@ -60,7 +60,9 @@ def plot_resampling(ax, X, y, title):
         c0, c1 = plot_resampling(ax, X_vis, y, 'Original set')
     else:
         iht = InstanceHardnessThreshold(sampling_strategy=sampling_strategy,
-                                        estimator=LogisticRegression(),
+                                        estimator=LogisticRegression(
+                                            solver='lbfgs',
+                                            multi_class='auto'),
                                         return_indices=True)
         X_res, y_res, idx_res = iht.fit_resample(X, y)
         X_res_vis = pca.transform(X_res)