sklearn之逻辑回归

逻辑回归

import numpy as np
import matplotlib.pyplot as plt
from sklearn.metrics import classification_report # 评估分类结果的指标
from sklearn import preprocessing
from sklearn import linear_model
# 数据是否需要标准化
scale = False
# scale = True

# 导入数据
data = np.genfromtxt("C:\\ML\\chapter-1\\LR-testSet.csv",delimiter=",") # 这种方法只能读取数字，不能读取字符，字符会变成nan
# print(data)
x_data = data[:,:-1]
y_data = data[:,-1]

def plot():
    x0 = []
    x1 = []
    y0 = []
    y1 = []
    # 切分不同类型的数据
    for i in range(len(x_data)):
        if y_data[i] == 0:
            x0.append(x_data[i,0])
            y0.append(x_data[i,1])
        else:
            x1.append(x_data[i,0])
            y1.append(x_data[i,1])

    # 画图 散点图
    scatter0 = plt.scatter(x0,y0,c='b',marker='o')
    scatter1 = plt.scatter(x1,y1,c='r',marker='x')
    # 画图例
    plt.legend(handles=[scatter0,scatter1],labels=['label0','label1'],loc='best') # loc='best'会自动把图例放在最好的位置

# plot()
# plt.show()

logistic = linear_model.LogisticRegression()
logistic.fit(x_data,y_data)
print('相关系数:',logistic.coef_)

if scale == False:
    # 画图决策边界
    plot()
    x_test = np.array([[-4],[3]])
    y_test = (-logistic.intercept_-x_test*logistic.coef_[0][0])/logistic.coef_[0][1]
    plt.plot(x_test,y_test,'k')
    plt.show()

predictions = logistic.predict(x_data)

print(classification_report(y_data,predictions))

结果如下：