PyML（二）——用sklearn训练感知机模型
# -*- coding: utf-8 -*-
# @Time : 2018/7/17 20:39
# @Author : Alan
# @Email : [email protected]
# @File : perceptron_sk1.py
# @Software: PyCharm
from sklearn import datasets
import numpy as np
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import Perceptron
from sklearn.metrics import accuracy_score
from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt
iris = datasets.load_iris()
X = iris.data[:,[2,3]]
y = iris.target
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.3,random_state=0)
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
ppn = Perceptron(n_iter=40,eta0=0.1,random_state = 0)
ppn.fit(X_train_std,y_train)
y_pred = ppn.predict(X_test_std)
print('Misclassified samples:%d'%(y_test != y_pred).sum())
print('Accuracy:%.2f'% accuracy_score(y_test,y_pred))
def plot_decision_regions(X, y, classifier,test_idx=None, resolution=0.02):
# setup marker generator and color map
markers = ('s', 'x', 'o', '^', 'v')
colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
cmap = ListedColormap(colors[:len(np.unique(y))])
# plot the decision surface
x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
np.arange(x2_min, x2_max, resolution))
Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
Z = Z.reshape(xx1.shape)
plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
plt.xlim(xx1.min(), xx1.max())
plt.ylim(xx2.min(), xx2.max())
# plot all samples
X_test, y_test = X[test_idx, :], y[test_idx]
for idx, cl in enumerate(np.unique(y)):
plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1],
alpha=0.8, c=cmap(idx),
marker=markers[idx], label=cl)
# highlight test samples
if test_idx:
X_test, y_test = X[test_idx, :], y[test_idx]
plt.scatter(X_test[:, 0], X_test[:, 1], c='',
alpha=1.0, linewidth=1, marker='o',
s=55, label='test set')
'''
这部分是看一下当用np.vstack和np.hstack后维度是怎么变化的
'''
print('X_train.shape:{}'.format(X_train.shape))
print('X_test_std.shape"{}'.format(X_test_std.shape))
print('y_train.shape:{}'.format(y_train.shape))
print('y_test.shape:{}'.format(y_test.shape))
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
print('X_combined_std.shape:{}'.format(X_combined_std.shape))
print('y_combined.shape:{}'.format(y_combined.shape))
plot_decision_regions(X=X_combined_std,y=y_combined,classifier=ppn,test_idx=range(105,150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.show()程序输出结果：
Misclassified samples:4
Accuracy:0.91
X_train.shape:(105, 2)
X_test_std.shape"(45, 2)
y_train.shape:(105,)
y_test.shape:(45,)
X_combined_std.shape:(150, 2)
y_combined.shape:(150,)
Process finished with exit code 0图形：
关于np.vstack()和np.hstack()，在这里推荐两篇文章：
https://blog.csdn.net/csdn15698845876/article/details/73380803
https://my.oschina.net/amui/blog/1601432
关于np.meshgrid函数与ravel函数，上一篇文章也介绍了，meshgrid的作用适用于生成网格型数据，可以接受两个一维数组生成两个二维矩阵，对应两个数组中所有的(x,y)对。接下来通过程序实现一下。
In [2]: import numpy as np
In [3]: xnums =np.arange(4)
In [4]: ynums =np.arange(5)
In [5]: data_list= np.meshgrid(xnums,ynums)
In [6]: data_list
Out[6]:
[array([[0, 1, 2, 3],
[0, 1, 2, 3],
[0, 1, 2, 3],
[0, 1, 2, 3],
[0, 1, 2, 3]]), array([[0, 0, 0, 0],
[1, 1, 1, 1],
[2, 2, 2, 2],
[3, 3, 3, 3],
[4, 4, 4, 4]])]
In [7]: x,y =data_list
In [8]: x.shape
Out[8]: (5, 4)
In [9]: y.shape
Out[9]: (5, 4)
In [10]: x
Out[10]:
array([[0, 1, 2, 3],
[0, 1, 2, 3],
[0, 1, 2, 3],
[0, 1, 2, 3],
[0, 1, 2, 3]])
In [11]: y
Out[11]:
array([[0, 0, 0, 0],
[1, 1, 1, 1],
[2, 2, 2, 2],
[3, 3, 3, 3],
[4, 4, 4, 4]])
In [12]: x.ravel()
Out[12]: array([0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3])
In [13]: y.ravel()
Out[13]: array([0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4])
reference：
《python machine learning》