Logistics回归分类鸢尾花数据集

import numpy as np
from sklearn.linear_model import LogisticRegression
import matplotlib.pyplot as plt
import matplotlib as mpl
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline

iris_feature = u'花萼长度', u'花萼宽度', u'花瓣长度', u'花瓣宽度', u'类别'
path = '8.iris.data'  # 数据文件路径
data = pd.read_csv(path, header=None)
data.columns = iris_feature  # 将data的每一列的标签设置为iris_feature,如果不设置就默认为0到n的数字
data['类别'] = pd.Categorical(data['类别']).codes  # 对每一个类别做统计进行打标签赋予数字
x_train = data[['花萼长度', '花瓣长度']]
y_train = data['类别']
lr = Pipeline([('sc', StandardScaler()),
                        ('clf', LogisticRegression()) ])
lr.fit(x_train, y_train)
N, M = 500, 500  # 横纵各采样多少个值
x1_min, x2_min = x_train.min(axis=0)
x1_max, x2_max = x_train.max(axis=0)
t1 = np.linspace(x1_min, x1_max, N)
t2 = np.linspace(x2_min, x2_max, M)
x1, x2 = np.meshgrid(t1, t2)  # 生成网格采样点
x_test = np.stack((x1.flat, x2.flat), axis=1)  # 测试点
cm_light = mpl.colors.ListedColormap(['#77E0A0', '#FF8080', '#A0A0FF'])
cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
y_hat = lr.predict(x_test)
y_hat = y_hat.reshape(x1.shape)              # 使之与输入的形状相同
plt.pcolormesh(x1, x2, y_hat, cmap=cm_light)     # 预测值的显示
plt.scatter(x_train['花萼长度'], x_train['花瓣长度'], c=y_train, cmap=cm_dark, marker='o', edgecolors='k')    # 样本的显示
plt.show()