【Python】机器学习模型在红酒质量等级评价中的案例应用

【Python】机器学习模型在红酒质量等级评价中的案例应用

1.红酒质量数据

import pandas as pd
import numpy as np
import warnings
warnings.filterwarnings("ignore")
df = pd.read_csv('white wine data.csv')

df

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
0	7.4	0.700	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5
1	7.8	0.880	0.00	2.6	0.098	25.0	67.0	0.9968	3.20	0.68	9.8	5
2	7.8	0.760	0.04	2.3	0.092	15.0	54.0	0.9970	3.26	0.65	9.8	5
3	11.2	0.280	0.56	1.9	0.075	17.0	60.0	0.9980	3.16	0.58	9.8	6
4	7.4	0.700	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5
...	...	...	...	...	...	...	...	...	...	...	...	...
2192	6.4	0.450	0.07	1.1	0.030	10.0	131.0	0.9905	2.97	0.28	10.8	5
2193	6.4	0.475	0.06	1.0	0.030	9.0	131.0	0.9904	2.97	0.29	10.8	5
2194	6.3	0.270	0.38	0.9	0.051	7.0	140.0	0.9926	3.45	0.50	10.5	7
2195	6.9	0.410	0.33	10.1	0.043	28.0	152.0	0.9968	3.20	0.52	9.4	5
2196	7.0	0.290	0.37	4.9	0.034	26.0	127.0	0.9928	3.17	0.44	10.8	6

2197 rows × 12 columns

2. 划分数据并训练机器学习模型

X,y = df.iloc[:,0:-1].values,df.iloc[:,-1].values.reshape([-1,1])


from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
# 对数据进行标准化处理， 主要是X_train
from sklearn.preprocessing import StandardScaler
ss = StandardScaler()
ss = ss.fit(X_train)
X_train_std = ss.fit_transform(X_train)
X_test_std = ss.fit_transform(X_test)
# ss1 = StandardScaler()
# ss1 = ss1.fit(y_train)
# y_train_std = ss1.fit_transform(y_train)
# y_test_std = ss1.fit_transform(y_test)

#---------------  Modllong

# SVM Classifier  
def svm_classifier(train_x, train_y):  
    from sklearn.svm import SVC  
    model = SVC(kernel='rbf', probability=True)  
    model.fit(train_x, train_y)  
    return model 



# KNN Classifier  
def knn_classifier(train_x, train_y):  
    from sklearn.neighbors import KNeighborsClassifier  
    model = KNeighborsClassifier()  
    model.fit(train_x, train_y)  
    return model  
    
# Logistic Regression Classifier  
def logistic_regression_classifier(train_x, train_y):  
    from sklearn.linear_model import LogisticRegression  
    model = LogisticRegression(penalty='l2')  
    model.fit(train_x, train_y)  
    return model 

# Random Forest Classifier  
def random_forest_classifier(train_x, train_y):  
    from sklearn.ensemble import RandomForestClassifier  
    model = RandomForestClassifier(n_estimators=8)  
    model.fit(train_x, train_y)  
    return model

train_x = X_train_std
train_y = y_train

model_svc = svm_classifier(train_x, train_y)
model_knn = knn_classifier(train_x, train_y)
model_logistic =  logistic_regression_classifier(train_x, train_y)
model_rf = random_forest_classifier(train_x, train_y)
# ----------

y_svc = model_svc.predict(X_test_std)
y_knn = model_knn.predict(X_test_std)
y_logistic = model_logistic.predict(X_test_std)
y_rf = model_rf.predict(X_test_std)

# 结果分析

from sklearn.metrics import f1_score
from sklearn.metrics import accuracy_score
from sklearn.metrics import  precision_score
from sklearn.metrics import recall_score

print('分类准确率为：',accuracy_score(y_test,y_svc),accuracy_score(y_test,y_knn),accuracy_score(y_test,y_logistic),accuracy_score(y_test,y_rf))
print('宏平均准确率：',precision_score(y_test,y_svc,average='macro'),precision_score(y_test,y_knn,average='macro'),precision_score(y_test,y_logistic,average='macro'),precision_score(y_test,y_rf,average='macro'))
print('微平均准确率：',precision_score(y_test,y_svc,average='micro'),precision_score(y_test,y_knn,average='micro'),precision_score(y_test,y_logistic,average='micro'),precision_score(y_test,y_rf,average='micro'))
print('宏平均召回率为：',recall_score(y_test,y_svc,average='macro'),recall_score(y_test,y_knn,average='macro'),recall_score(y_test,y_logistic,average='macro'),recall_score(y_test,y_rf,average='macro'))
print('微平均召回率为：',recall_score(y_test,y_svc,average='micro'),recall_score(y_test,y_knn,average='micro'),recall_score(y_test,y_logistic,average='micro'),recall_score(y_test,y_rf,average='micro'))
print('宏平均f1值为：',f1_score(y_test,y_svc,average='macro'),f1_score(y_test,y_knn,average='macro'),f1_score(y_test,y_logistic,average='macro'),f1_score(y_test,y_rf,average='macro'))
print('微平均f1值为：',f1_score(y_test,y_svc,average='micro'),f1_score(y_test,y_knn,average='micro'),f1_score(y_test,y_logistic,average='micro'),f1_score(y_test,y_rf,average='micro'))
# 误差评估

分类准确率为： 0.5818181818181818 0.5515151515151515 0.5575757575757576 0.6075757575757575
宏平均准确率： 0.280583340709923 0.2986745934975547 0.3499023740988492 0.3984623113419726
微平均准确率： 0.5818181818181818 0.5515151515151515 0.5575757575757576 0.6075757575757575
宏平均召回率为： 0.27642774299410267 0.27744523345842165 0.2858453966079045 0.3401924573344921
微平均召回率为： 0.5818181818181818 0.5515151515151515 0.5575757575757576 0.6075757575757575
宏平均f1值为： 0.27488434754737406 0.27950149117164064 0.29807537284434943 0.3552209623496858
微平均f1值为： 0.5818181818181818 0.5515151515151515 0.5575757575757576 0.6075757575757575