Merge pull request #80 from chkoar/pipeline

[WIP] Modify Pipeline object to conform the current API of samplers

Author: glemaitre

examples/pipeline/pipeline_classification.py

@@ -0,0 +1,47 @@
+"""
+=========================
+Pipeline Object
+=========================
+An example of the Pipeline object working with transformers and resamplers.
+"""
+
+print(__doc__)
+
+from sklearn.cross_validation import train_test_split as tts
+from sklearn.datasets import make_classification
+from sklearn.decomposition import PCA
+from sklearn.neighbors import KNeighborsClassifier as KNN
+from sklearn.metrics import classification_report
+
+
+from unbalanced_dataset.pipeline import make_pipeline
+from unbalanced_dataset.under_sampling import EditedNearestNeighbours, \
+    RepeatedEditedNearestNeighbours
+
+# Generate the dataset
+X, y = make_classification(n_classes=2, class_sep=1.25, weights=[0.3, 0.7],
+                           n_informative=3, n_redundant=1, flip_y=0,
+                           n_features=5, n_clusters_per_class=1,
+                           n_samples=5000, random_state=10)
+
+# Instanciate a PCA object for the sake of easy visualisation
+pca = PCA(n_components=2)
+
+# Create the samplers
+enn = EditedNearestNeighbours()
+renn = RepeatedEditedNearestNeighbours()
+
+# Create teh classifier
+knn = KNN(1)
+
+
+# Make the splits
+X_train, X_test, y_train, y_test = tts(X, y, random_state=42)
+
+# Add one transformers and two samplers in the pipeline object
+pipeline = make_pipeline(pca, enn, renn, knn)
+
+pipeline.fit(X_train, y_train)
+y_hat = pipeline.predict(X_test)
+
+print(classification_report(y_test, y_hat))

examples/pipeline/plot_enn_and_renn_in_pipeline.py

@@ -0,0 +1,65 @@
+"""
+=========================
+Repeated Edited nearest-neighbours
+=========================
+
+An illustration of the edited nearest-neighbours and repeated 
+edited nearest-neighbours method combined in a pipeline object.
+
+"""
+
+print(__doc__)
+
+import matplotlib.pyplot as plt
+import seaborn as sns
+sns.set()
+
+# Define some color for the plotting
+almost_black = '#262626'
+palette = sns.color_palette()
+
+from sklearn.datasets import make_classification
+from sklearn.decomposition import PCA
+
+from unbalanced_dataset.under_sampling import EditedNearestNeighbours, \
+    RepeatedEditedNearestNeighbours
+from unbalanced_dataset.pipeline import make_pipeline
+
+# Generate the dataset
+X, y = make_classification(n_classes=2, class_sep=1.25, weights=[0.3, 0.7],
+                           n_informative=3, n_redundant=1, flip_y=0,
+                           n_features=5, n_clusters_per_class=1,
+                           n_samples=5000, random_state=10)
+
+
+# Fit and transform x to visualise inside a 2D feature space
+pca = PCA(n_components=2)
+X_vis = pca.fit_transform(X)
+
+# Three subplots, unpack the axes array immediately
+f, (ax1, ax3) = plt.subplots(1, 2)
+
+ax1.scatter(X_vis[y == 0, 0], X_vis[y == 0, 1], label="Class #0", alpha=.5,
+            edgecolor=almost_black, facecolor=palette[0], linewidth=0.15)
+ax1.scatter(X_vis[y == 1, 0], X_vis[y == 1, 1], label="Class #1", alpha=.5,
+            edgecolor=almost_black, facecolor=palette[2], linewidth=0.15)
+ax1.set_title('Original set')
+
+# Create the samplers
+enn = EditedNearestNeighbours()
+renn = RepeatedEditedNearestNeighbours()
+
+# Add the samplers in the pipeline
+pipeline = make_pipeline(enn, renn)
+X_resampled, y_resampled = pipeline.fit_sample(X, y)
+X_res_vis = pca.transform(X_resampled)
+
+ax3.scatter(X_res_vis[y_resampled == 0, 0], X_res_vis[y_resampled == 0, 1],
+            label="Class #0", alpha=.5, edgecolor=almost_black,
+            facecolor=palette[0], linewidth=0.15)
+ax3.scatter(X_res_vis[y_resampled == 1, 0], X_res_vis[y_resampled == 1, 1],
+            label="Class #1", alpha=.5, edgecolor=almost_black,
+            facecolor=palette[2], linewidth=0.15)
+ax3.set_title('RENN + ENN ')
+
+plt.show()

unbalanced_dataset/__init__.py

@@ -34,4 +34,4 @@
            'ensemble',
            'over_sampling',
            'under_sampling',
-           'utils']
+           'pipeline']

unbalanced_dataset/base.py

@@ -13,6 +13,7 @@
 
 from sklearn.base import BaseEstimator
 from sklearn.utils import check_X_y
+from sklearn.utils import check_array
 from sklearn.externals import six
 
 from six import string_types