Day6 逻辑回归

导入库 读数据 拆因果

import numpy as np
import pandas as pd

dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[:, [2,3]].values
Y = dataset.iloc[:, -1].values

数据标准化 简单理解就是缩放

from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X = scaler.fit_transform(X)

拆分 训练集 和 测试集

from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25, random_state=0)

使用逻辑回归训练

from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(solver='lbfgs')
classifier.fit(X_train, Y_train)

预测及可视化

#预测
Y_pred = classifier.predict(X_test)

#准确率
#score = classifier.score(X_train, Y_train)
#print(score)

#评估 混肴矩阵
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(Y_test, Y_pred)

#混肴矩阵可视化
import matplotlib.pyplot as plt
import seaborn as sns
sns.heatmap(cm, annot=True)


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))

xy = np.array([X1.ravel(), X2.ravel()]).T
plt.figure()
plt.contourf(X1, X2, classifier.predict(xy).reshape(X1.shape), alpha=0.75, cmap=ListedColormap(('red', 'blue')))

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], c = ListedColormap(('red', 'blue'))(i), label=j)
    
plt.title('logistic')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()