import xlrd
import matplotlib.pyplot as plt
import numpy as np
from sklearn import model_selection
from sklearn.linear_model import LogisticRegression
from sklearn import metrics
data = xlrd.open_workbook('gua.xlsx')
sheet = data.sheet_by_index(0)
Density = sheet.col_values(6)
Sugar = sheet.col_values(7)
Res = sheet.col_values(8)
# 讀取原始數(shù)據(jù)
X = np.array([Density, Sugar])
# y的尺寸為(17,)
y = np.array(Res)
X = X.reshape(17,2)
# 繪制分類數(shù)據(jù)
f1 = plt.figure(1)
plt.title('watermelon_3a')
plt.xlabel('density')
plt.ylabel('ratio_sugar')
# 繪制散點(diǎn)圖（x軸為密度，y軸為含糖率）
plt.scatter(X[y == 0,0], X[y == 0,1], marker = 'o', color = 'k', s=100, label = 'bad')
plt.scatter(X[y == 1,0], X[y == 1,1], marker = 'o', color = 'g', s=100, label = 'good')
plt.legend(loc = 'upper right')
plt.show()
# 從原始數(shù)據(jù)中選取一半數(shù)據(jù)進(jìn)行訓(xùn)練，另一半數(shù)據(jù)進(jìn)行測(cè)試
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.5, random_state=0)
# 邏輯回歸模型
log_model = LogisticRegression()
# 訓(xùn)練邏輯回歸模型
log_model.fit(X_train, y_train)
# 預(yù)測(cè)y的值
y_pred = log_model.predict(X_test)
# 查看測(cè)試結(jié)果
print(metrics.confusion_matrix(y_test, y_pred))
print(metrics.classification_report(y_test, y_pred))