红酒和白酒检测

# -*- coding: utf-8 -*-
""" Created on Tue May 22 11:39:44 2018 @author: DELL """
import pandas as pd
import numpy as np
from sklearn.tree import DecisionTreeClassifier
from sklearn.linear_model import LogisticRegression
#读取数据
train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")
#预测量定义
y = train.type
## 特征定义
predictors = ['fixedAcidity', 'volatileAcidity', 'citricAcid', 'residualSugar',
          'chlorides', 'freeSulfurDioxide', 'totalSulfurDioxide',
          'density', 'pH', 'sulphates', 'alcohol', 'quality']
## 生成结构化数据
X = train[predictors]
# 定义模型
wine_model = LogisticRegression()
# 模型训练
wine_model.fit(X, y)
# print("Making predictions for the following 5 wines:")
# print(X.head())
# print("The predictions are")
# print(wine_model.predict_proba(X.head()))
# 生成预测结果
prediction = wine_model.predict_proba(test[predictors])
submission = pd.DataFrame({'id': test['id'], 'type': prediction[:, 1]})
submission.to_csv('test_prediction.csv', index=False)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import division
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.cross_validation import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report 
from sklearn.metrics import precision_recall_curve, roc_curve, auc 
data = pd.read_csv('ex2data1.txt', sep=',', \
    skiprows=[2], names=['score1','score2','result'])
score_data = data.loc[:,['score1','score2']]
result_data = data.result
p = 0
for i in xrange(10):
    x_train, x_test, y_train, y_test = \
        train_test_split(score_data, result_data, test_size = 0.2)
    model = LogisticRegression(C=1e9)
    model.fit(x_train, y_train)
    predict_y = model.predict(x_test)
    p += np.mean(predict_y == y_test)
# 绘制图像
pos_data = data[data.result == 1].loc[:,['score1','score2']]
neg_data = data[data.result == 0].loc[:,['score1','score2']]
h = 0.02
x_min, x_max = score_data.loc[:, ['score1']].min() - .5, score_data.loc[:, ['score1']].max() + .5
y_min, y_max = score_data.loc[:, ['score2']].min() - .5, score_data.loc[:, ['score2']].max() + .5
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
Z = model.predict(np.c_[xx.ravel(), yy.ravel()])
# 绘制边界和散点
Z = Z.reshape(xx.shape)
plt.pcolormesh(xx, yy, Z, cmap=plt.cm.Paired)
plt.scatter(x=pos_data.score1, y=pos_data.score2, color='black', marker='o')
plt.scatter(x=neg_data.score1, y=neg_data.score2, color='red', marker='*')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.show()
# 模型表现
answer = model.predict_proba(x_test)[:,1]  
precision, recall, thresholds = precision_recall_curve(y_test, answer)      
report = answer > 0.5  
print(classification_report(y_test, report, target_names = ['neg', 'pos']))  
print("average precision:", p/100)