六、逻辑回归

##载入相关模块

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

%matplotlib inline

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split

from collections import Counter

##载入数据

iris = load_iris()

df = pd.DataFrame(iris.data, columns=iris.feature_names)

df['label'] = iris.target

df.columns = ['sepal length', 'sepal width', 'petal length', 'petal width', 'label']

##提取特征和样品

#取前面100个数，第一列、第二列和最后一列

data = np.array(df.iloc[:100, [0, 1, -1]])

#最后一个特征作为标签，其他的作为特征

X, y = data[:,:-1], data[:,-1]

#取80%作为训练，20%作为测试

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

载入sklearn中的逻辑回归模块

from sklearn.linear_model import LogisticRegression

模型训练

clf = LogisticRegression(max_iter=200)

clf.fit(X_train, y_train)

输出模型参数

print(clf.coef_, clf.intercept_)

验证算法精度

clf.score(X_test, y_test)

绘制图

x_ponits = np.arange(4, 8)

y_ = -(clf.coef_[0][0]*x_ponits + clf.intercept_)/clf.coef_[0][1]

plt.plot(x_ponits, y_)

plt.plot(X[:50, 0], X[:50, 1], 'bo', color='blue', label='0')

plt.plot(X[50:, 0], X[50:, 1], 'bo', color='orange', label='1')

plt.xlabel('sepal length')

plt.ylabel('sepal width')

plt.legend()