import pandas as pd
import numpy as np
from sklearn import linear_model
# 读取数据
sports = pd.read_csv(r'C:\Users\Administrator\Desktop\Run or Walk.csv')
# 提取出所有自变量名称
predictors = sports.columns[4:]
# 构建自变量矩阵
X = sports.ix[:,predictors]
# 提取y变量值
y = sports.activity
# 将数据集拆分为训练集和测试集
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y, test_size = 0.25, random_state = 1234)
# 利用训练集建模
sklearn_logistic = linear_model.LogisticRegression()
sklearn_logistic.fit(X_train, y_train)
# 返回模型的各个参数
print(sklearn_logistic.intercept_, sklearn_logistic.coef_)
# 模型预测
sklearn_predict = sklearn_logistic.predict(X_test)
# 预测结果统计
pd.Series(sklearn_predict).value_counts()
-------------------------------------------------------------------------------------------------------------------------------------------
# 导入第三方模块
from sklearn import metrics
# 混淆矩阵
cm = metrics.confusion_matrix(y_test, sklearn_predict, labels = [0,1])
cm
Accuracy = metrics.scorer.accuracy_score(y_test, sklearn_predict)
Sensitivity = metrics.scorer.recall_score(y_test, sklearn_predict)
Specificity = metrics.scorer.recall_score(y_test, sklearn_predict, pos_label=0)
print('模型准确率为%.2f%%:' %(Accuracy*100))
print('正例覆盖率为%.2f%%' %(Sensitivity*100))
print('负例覆盖率为%.2f%%' %(Specificity*100))
-------------------------------------------------------------------------------------------------------------------------------------------
# 混淆矩阵的可视化
# 导入第三方模块
import seaborn as sns
import matplotlib.pyplot as plt
# 绘制热力图
sns.heatmap(cm, annot = True, fmt = '.2e',cmap = 'GnBu')
plt.show()
------------------------------------------------------------------------------------------------------------------------------------------
# 绘制ROC曲线
# 计算真正率和假正率
fpr,tpr,threshold = metrics.roc_curve(y_test, sm_y_probability)
# 计算auc的值
roc_auc = metrics.auc(fpr,tpr)
# 绘制面积图
plt.stackplot(fpr, tpr, color='steelblue', alpha = 0.5, edgecolor = 'black')
# 添加边际线
plt.plot(fpr, tpr, color='black', lw = 1)
# 添加对角线
plt.plot([0,1],[0,1], color = 'red', linestyle = '--')
# 添加文本信息
plt.text(0.5,0.3,'ROC curve (area = %0.2f)' % roc_auc)
# 添加x轴与y轴标签
plt.xlabel('1-Specificity')
plt.ylabel('Sensitivity')
plt.show()
-------------------------------------------------------------------------------------------------------------------------------------------
#ks曲线 链接：https://www.jianshu.com/p/b1b1344bd99f 风控数据分析学习笔记（二）Python建立信用评分卡 - 简书
fig, ax = plt.subplots()
ax.plot(1 - threshold, tpr, label='tpr')# ks曲线要按照预测概率降序排列，所以需要1-threshold镜像
ax.plot(1 - threshold, fpr, label='fpr')
ax.plot(1 - threshold, tpr-fpr,label='KS')
plt.xlabel('score')
plt.title('KS Curve')
plt.ylim([0.0, 1.0])
plt.figure(figsize=(20,20))
legend = ax.legend(loc='upper left')
plt.show()
