From d9b08fbe28e2311d3b6ab0c79578ebd52b9ed19c Mon Sep 17 00:00:00 2001
From: Dayvid Victor <victor.dvro@gmail.com>
Date: Mon, 23 Jun 2014 18:58:47 -0300
Subject: [PATCH] enn example

---
 examples/enn_example.py      |  39 ++++++++++
 examples/plot_comparision.py | 137 +++++++++++++++++++++++++++++++++++
 examples/protopy             |   1 +
 protopy/selection/enn.py     |   7 +-
 4 files changed, 183 insertions(+), 1 deletion(-)
 create mode 100644 examples/enn_example.py
 create mode 100644 examples/plot_comparision.py
 create mode 120000 examples/protopy

diff --git a/examples/enn_example.py b/examples/enn_example.py
new file mode 100644
index 0000000..f45fdaf
--- /dev/null
+++ b/examples/enn_example.py
@@ -0,0 +1,39 @@
+import numpy as np
+import matplotlib.pyplot as plt
+
+from protopy.selection.enn import ENN
+
+mu1 = [4, 5]
+si1 = [[0.75, 0.25], [0.25, 0.75]]
+
+mu2 = [6, 5]
+si2 = [[0.25, 0.75], [0.75, 0.25]]
+
+samples = 200
+
+X1 = np.random.multivariate_normal(
+    np.asarray(mu1), np.asarray(si1), samples)
+X2 = np.random.multivariate_normal(
+    np.asarray(mu2), np.asarray(si2), samples)
+
+X = np.vstack((X1, X2))
+
+y = np.asarray([0] * samples + [1] * samples)
+
+
+plt.plot(X[y==0].T[0], X[y==0].T[1], 'bs', X[y==1].T[0], X[y==1].T[1],'ro')
+plt.axis([0, 10, 0, 10])
+plt.title('Original Dataset')
+plt.show()
+plt.clf()
+
+editednn = ENN()
+X_, y_ = editednn.reduce_data(X, y)
+
+plt.plot(X_[y_==0].T[0], X_[y_==0].T[1], 'bs', X_[y_==1].T[0], X_[y_==1].T[1],'ro')
+plt.axis([0, 10, 0, 10])
+plt.title('ENN')
+plt.show()
+plt.clf()
+
+
diff --git a/examples/plot_comparision.py b/examples/plot_comparision.py
new file mode 100644
index 0000000..94e3d09
--- /dev/null
+++ b/examples/plot_comparision.py
@@ -0,0 +1,137 @@
+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+
+"""
+======================
+Classifiers Comparison
+======================
+A comparison of a several classifiers in scikit-learn on synthetic datasets.
+The point of this example is to illustrate the nature of decision boundaries
+of different classifiers.
+This should be taken with a grain of salt, as the intuition conveyed by
+these examples does not necessarily carry over to real datasets.
+
+In particular in high dimensional spaces data can more easily be separated
+linearly and the simplicity of classifiers such as naive Bayes and linear SVMs
+might lead to better generalization.
+
+The plots show training points in solid colors and testing points
+semi-transparent. The lower right shows the classification accuracy on the test
+set.
+"""
+print(__doc__)
+
+
+# Code source: Gael Varoqueux
+#              Andreas Mueller
+# Modified for Documentation merge by Jaques Grobler
+# License: BSD 3 clause
+
+import numpy as np
+import pylab as pl
+from matplotlib.colors import ListedColormap
+from sklearn.cross_validation import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.datasets import make_moons, make_circles, make_classification
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.svm import SVC
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
+from sklearn.naive_bayes import GaussianNB
+from sklearn.lda import LDA
+from sklearn.qda import QDA
+from protopy.selection.enn import ENN
+
+h = .02  # step size in the mesh
+
+#names = ["Nearest Neighbors", "Linear SVM", "RBF SVM", "Decision Tree",
+#         "Random Forest", "AdaBoost", "Naive Bayes", "LDA", "QDA"]
+names = ["KNN", "ENN"]
+
+
+classifiers = [
+    KNeighborsClassifier(3),
+    ENN()]
+'''
+    SVC(kernel="linear", C=0.025),
+    SVC(gamma=2, C=1),
+    DecisionTreeClassifier(max_depth=5),
+    RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
+    AdaBoostClassifier(),
+    GaussianNB(),
+    LDA(),
+    QDA()]
+'''
+X, y = make_classification(n_features=2, n_redundant=0, n_informative=2,
+                           random_state=1, n_clusters_per_class=1)
+rng = np.random.RandomState(2)
+X += 2 * rng.uniform(size=X.shape)
+linearly_separable = (X, y)
+
+datasets = [make_moons(noise=0.3, random_state=0),
+            make_circles(noise=0.2, factor=0.5, random_state=1),
+            linearly_separable
+            ]
+
+figure = pl.figure(figsize=(27, 9))
+i = 1
+# iterate over datasets
+for ds in datasets:
+    # preprocess dataset, split into training and test part
+    X, y = ds
+    X = StandardScaler().fit_transform(X)
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.4)
+
+    x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
+    y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
+    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
+                         np.arange(y_min, y_max, h))
+
+    # just plot the dataset first
+    cm = pl.cm.RdBu
+    cm_bright = ListedColormap(['#FF0000', '#0000FF'])
+    ax = pl.subplot(len(datasets), len(classifiers) + 1, i)
+    # Plot the training points
+    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
+    # and testing points
+    ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6)
+    ax.set_xlim(xx.min(), xx.max())
+    ax.set_ylim(yy.min(), yy.max())
+    ax.set_xticks(())
+    ax.set_yticks(())
+    i += 1
+
+    # iterate over classifiers
+    for name, clf in zip(names, classifiers):
+        ax = pl.subplot(len(datasets), len(classifiers) + 1, i)
+        clf.fit(X_train, y_train)
+        score = clf.score(X_test, y_test)
+
+        # Plot the decision boundary. For that, we will assign a color to each
+        # point in the mesh [x_min, m_max]x[y_min, y_max].
+        if hasattr(clf, "decision_function"):
+            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
+        else:
+            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]
+
+        # Put the result into a color plot
+        Z = Z.reshape(xx.shape)
+        ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)
+
+        # Plot also the training points
+        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
+        # and testing points
+        ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,
+                   alpha=0.6)
+
+        ax.set_xlim(xx.min(), xx.max())
+        ax.set_ylim(yy.min(), yy.max())
+        ax.set_xticks(())
+        ax.set_yticks(())
+        ax.set_title(name)
+        ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),
+                size=15, horizontalalignment='right')
+        i += 1
+
+figure.subplots_adjust(left=.02, right=.98)
+pl.show()
diff --git a/examples/protopy b/examples/protopy
new file mode 120000
index 0000000..2a100ac
--- /dev/null
+++ b/examples/protopy
@@ -0,0 +1 @@
+../protopy
\ No newline at end of file
diff --git a/protopy/selection/enn.py b/protopy/selection/enn.py
index 825f44a..2e369b2 100644
--- a/protopy/selection/enn.py
+++ b/protopy/selection/enn.py
@@ -41,7 +41,7 @@ class ENN(InstanceReductionMixin):
 
     Examples
     --------
-    >>> from protopy.selection import ENN
+    >>> from protopy.selection.enn import ENN
     >>> import numpy as np
     >>> X = np.array([[-1, 0], [-0.8, 1], [-0.8, -1], [-0.5, 0] , [0.5, 0], [1, 0], [0.8, 1], [0.8, -1]])
     >>> y = np.array([1, 1, 1, 2, 1, 2, 2, 2])
@@ -90,3 +90,8 @@ def reduce_data(self, X, y):
         self.y_ = np.asarray(y[mask])
         self.reduction_ = 1.0 - float(len(self.y_)) / len(y)
         return self.X_, self.y_
+
+
+    def predict_proba(self, X):
+        return self.classifier.predict_proba(X)
+