第七章 逻辑回归 - 多元逻辑回归

0导入相关库

import numpy as np
import pandas as pd

from sklearn import metrics # 评估
import statsmodels.api as sm

1 加载数据

df=pd.read_csv('Regression/Regression7/multi_logit.csv',header=None)

df.columns = ["y", "x1", "x2"]

features = ["x1", "x2"]
labels = ["y"]

df.info()
# df.sample(frac=0.05) # 随机取样（分数 四舍五入）
df.sample(n=5) # 5行

2 一对多分类

from sklearn.linear_model import LogisticRegression

model = LogisticRegression(multi_class='ovr', solver='sag',
            max_iter=1000, random_state=42)
model.fit(df[features], df[labels])

print('系数：\n', model.coef_, '\n')
print('截距：\n', model.intercept_)

2.1 分类概率

prob = model.predict_proba(df[features])
pd.DataFrame(prob)

2.2 分类汇总情况

pred = model.predict(df[features])
print(metrics.classification_report(df['y'], pred))

2.3 混淆矩阵

confusion = metrics.confusion_matrix(df['y'], pred)
confusion

plt.matshow(confusion)
plt.title('混淆矩阵')
plt.colorbar() 
plt.ylabel('预测')
plt.xlabel('实际')
plt.show()

3 多元逻辑回归

model = LogisticRegression(multi_class='multinomial', solver='sag',
            max_iter=1000, random_state=42)
model.fit(df[features], df[labels])

print('系数：\n', model.coef_, '\n')
print('截距：\n', model.intercept_)

3.1 分类概率

prob = model.predict_proba(df[features])
pd.DataFrame(prob)

3.2 分类汇总情况

pred = model.predict(df[features])
print(metrics.classification_report(df['y'], pred))

3.3 混淆矩阵

confusion = metrics.confusion_matrix(df['y'], pred)
confusion

plt.matshow(confusion)
plt.title('混淆矩阵')
plt.colorbar() 
plt.ylabel('预测')
plt.xlabel('实际')
plt.show()
plt.tight_layout()