kNN, Naibe Bayesm, SVM, (Random Forrest)をScikit-learnでやってみた。データはiPython NotebookでReSTで出力したものをpandocでmarkdown_strictに変換しなおしてblogに貼り付けた。
描画用のヘルパー関数とデータセットの生成
from matplotlib.colors import ListedColormap import Image from numpy import * from pylab import * import pickle def myplot_2D_boundary(X,y): x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1 y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1 xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02), np.arange(y_min, y_max, 0.02)) Z = clf.predict(np.c_[xx.ravel(), yy.ravel()]) Z = Z.reshape(xx.shape) plt.figure() plt.pcolormesh(xx, yy, Z, cmap=cmap_light) plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold) plt.xlim(xx.min(), xx.max()) plt.ylim(yy.min(), yy.max()) plt.show() with open('points_normal.pkl', 'r') as f: class_1 = pickle.load(f) class_2 = pickle.load(f) labels = pickle.load(f) X_normal = np.r_[class_1, class_2] y_normal = labels with open('points_ring.pkl', 'r') as f: class_1 = pickle.load(f) class_2 = pickle.load(f) labels = pickle.load(f) X_ring = np.r_[class_1, class_2] y_ring = labels with open('points_normal_test.pkl', 'r') as f: class_1 = pickle.load(f) class_2 = pickle.load(f) labels = pickle.load(f) X_normal_test = np.r_[class_1, class_2] y_normal_test = labels with open('points_ring_test.pkl', 'r') as f: class_1 = pickle.load(f) class_2 = pickle.load(f) labels = pickle.load(f) X_ring_test = np.r_[class_1, class_2] y_ring_test = labels cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA']) cmap_bold = ListedColormap(['#FF0000', '#00FF00'])
kNN
import numpy as np import matplotlib.pyplot as plt from matplotlib.colors import ListedColormap from sklearn import neighbors, datasets clf = neighbors.KNeighborsClassifier(3) clf.fit(X_normal, y_normal) myplot_2D_boundary(X_normal,y_normal)
clf = neighbors.KNeighborsClassifier(3) clf.fit(X_ring, y_ring) myplot_2D_boundary(X_ring,y_ring)
ベイズ
from sklearn.naive_bayes import GaussianNB clf = GaussianNB() clf.fit(X_normal, y_normal) labels_pred = clf.predict(X_normal_test) print "Number of mislabeled points out of a total %d points : %d" % (y_normal_test.shape[0],(y_normal_test != labels_pred).sum()) myplot_2D_boundary(X_normal,y_normal)
clf = GaussianNB() clf.fit(X_ring, y_ring) labels_pred = clf.predict(X_ring_test) print "Number of mislabeled points out of a total %d points : %d" % (y_ring_test.shape[0],(y_ring_test != labels_pred).sum()) myplot_2D_boundary(X_ring,y_ring)
SVM
from sklearn import svm clf = svm.SVC() clf.fit(X_normal, y_normal) labels_pred = clf.predict(X_normal_test) print "Number of mislabeled points out of a total %d points : %d" % (y_normal_test.shape[0],(y_normal_test != labels_pred).sum()) myplot_2D_boundary(X_normal, y_normal)
clf = svm.SVC() clf.fit(X_ring, y_ring) labels_pred = clf.predict(X_ring_test) print "Number of mislabeled points out of a total %d points : %d" % (y_ring_test.shape[0],(y_ring_test != labels_pred).sum()) myplot_2D_boundary(X_ring,y_ring)
Random Forest
from sklearn.ensemble import RandomForestClassifier clf = RandomForestClassifier(n_estimators=10) clf.fit(X_normal, y_normal) labels_pred = clf.predict(X_normal_test) print "Number of mislabeled points out of a total %d points : %d" % (y_normal_test.shape[0],(y_normal_test != labels_pred).sum()) myplot_2D_boundary(X_normal,y_normal)
from sklearn.ensemble import RandomForestClassifier clf = RandomForestClassifier(n_estimators=10) clf.fit(X_ring, y_ring) labels_pred = clf.predict(X_ring_test) print "Number of mislabeled points out of a total %d points : %d" % (y_ring_test.shape[0],(y_ring_test != labels_pred).sum()) myplot_2D_boundary(X_ring,y_ring)
