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'花萼長度', u'花萼寬度', u'花瓣長度', u'花瓣寬度', u'類別'
path = '8.iris.data'  # 資料檔案路徑
data = pd.read_csv(path, header=None)
data.columns = iris_feature  # 將data的每一列的標籤設定為iris_feature,如果不設定就預設為0到n的數字
data['類別'] = pd.Categorical(data['類別']).codes  # 對每一個類別做統計進行打標籤賦予數字
x_train = data[['花萼長度', '花瓣長度']]
y_train = data['類別']
lr = Pipeline([('sc', StandardScaler()),
                        ('clf', LogisticRegression()) ])
lr.fit(x_train, y_train)
N, M = 500, 500  # 橫縱各取樣多少個值
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)  # 生成網格取樣點
x_test = np.stack((x1.flat, x2.flat), axis=1)  # 測試點
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)              # 使之與輸入的形狀相同
plt.pcolormesh(x1, x2, y_hat, cmap=cm_light)     # 預測值的顯示
plt.scatter(x_train['花萼長度'], x_train['花瓣長度'], c=y_train, cmap=cm_dark, marker='o', edgecolors='k')    # 樣本的顯示
plt.show()