用java实现svm分类器_sklearn从SVM分类器绘制结果

我正在尝试绘制我的svm分类器结果 . "mini-programm"显示为here . 为了绘图我继续使用this scikit-learn的例子 . 我've modify the code as you can see below. Well i don'知道我是否'm on the right way because i don' t了解当我试图拿大"dimensions"并将它们挤进2-D时 . 也许有人可以为我解释^^

#!/usr/bin/env python

import numpy as np

import pylab as pl

from matplotlib.colors import ListedColormap

from sklearn.decomposition import PCA

from sklearn.cluster import KMeans

def reduce_dim(datas):

pca = PCA(n_components=2)

pca.fit(datas)

data_pca = pca.transform(datas)

return data_pca

def plotter_plot(kmeans, clf, X, X_train, X_test, y_train, y_test):

names = ["RBF SVM"]

classifiers = []

classifiers.append(clf)

h = .01 # step size in the mesh

X_r = reduce_dim(X)

X_train_r = reduce_dim(X_train)

X_test_r = reduce_dim(X_test)

figure = pl.figure(figsize=(15, 5))

x_min, x_max = X_r[:, 0].min() - .5, X_r[:, 0].max() + .5

y_min, y_max = X_r[:, 1].min() - .5, X_r[:, 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(1, 2, 1)

# 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 = 2

for name, clf in zip(names, classifiers):

ax = pl.subplot(1, 2, i)

clf.fit(X_train_r, y_train)

score = clf.score(X_test_r, 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_r[:, 0], X_train_r[:, 1], c=y_train, cmap=cm_bright)

# and testing points

ax.scatter(X_test_r[:, 0], X_test_r[:, 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()

这是用clf重新拟合“减少数据”的正确方法吗？他们已经适合训练和分类！那么有错误还是我应该再次适应二维数据？

谢谢...