SVM实战

SVM实战

import numpy as np
# import matplotlib.pyplot as plt
import pandas as pd
import warnings
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
warnings.filterwarnings("ignore")

# 读文件
dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[:, [2, 3]].values
y = dataset.iloc[:, 4].values

# 切分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=0)

# 数据预处理 ：生成的数据均值为 0；方差为1
# 数据预处理 可以让训练和预测更准确
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)


# 对数据进行训练
from sklearn.svm import SVC
classifier = SVC(random_state=0)
# classifier = SVC(random_state = 0, kernel="linear")
# classifier = SVC(random_state = 0, kernel="sigmoid")
# classifier = SVC(random_state = 0, kernel="poly", degree=6)
classifier.fit(X_train, y_train)


# 预测结果
y_pred = classifier.predict(X_test)
print(y_pred)


# 生成混淆矩阵，是对分类结果的评价
# 详细了解可以看下面的网站
#  https://blog.youkuaiyun.com/Orange_Spotty_Cat/article/details/80520839
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
print(cm)

# 将训练集的分类结果可视化
from matplotlib.colors import ListedColormap
X_set, y_set = X_train, y_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
             alpha = 0.75, cmap = ListedColormap(('red', 'green')))
             
#上面的代码是把红色和绿色的区域画出来，下面的代码是把点画出来

plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
                color = ListedColormap(('darkred', 'darkgreen'))(i), label = j)
plt.title('Logistic Regression (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

# 将测试集的分类结果可视化
from matplotlib.colors import ListedColormap
X_set, y_set = X_test, y_test
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
             alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
print(np.unique(y_set))
for i, j in enumerate(np.unique(y_set)):
    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
                color = ListedColormap(('darkred', 'darkgreen'))(i), label = j)
plt.title('Logistic Regression (Test set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()