|
|
#coding=gbk
|
|
|
import numpy as np
|
|
|
import pandas as pd
|
|
|
from sklearn.metrics import accuracy_score
|
|
|
import matplotlib.pyplot as plt
|
|
|
import seaborn as sns
|
|
|
from sklearn.linear_model import LogisticRegression
|
|
|
from sklearn.ensemble import RandomForestClassifier
|
|
|
from sklearn.svm import SVC
|
|
|
from sklearn.model_selection import cross_val_score
|
|
|
from sklearn.metrics import precision_recall_curve
|
|
|
from sklearn.metrics import roc_curve, auc
|
|
|
import matplotlib.pyplot as plt
|
|
|
import warnings
|
|
|
warnings.filterwarnings("ignore")
|
|
|
|
|
|
#数据进一步处理，删去Survived列
|
|
|
train=pd.read_csv("E:\\python1\\123\\Data\\new_train.csv")
|
|
|
test=pd.read_csv("E:\\python1\\123\\Data\\new_test.csv")
|
|
|
gender=pd.read_csv("E:\\python1\\123\\Data\\gender_submission.csv")
|
|
|
sur_train=train.Survived
|
|
|
train.drop(['Survived'], axis=1, inplace =True)
|
|
|
test.drop(['Survived'], axis=1, inplace =True)
|
|
|
|
|
|
#逻辑回归
|
|
|
def Logistic_Regression():
|
|
|
LRmodel=LogisticRegression()
|
|
|
LRmodel.fit(train,sur_train)
|
|
|
LR_prediction=LRmodel.predict(test)
|
|
|
# 0.9186602870813397
|
|
|
print("逻辑回归模型accuracy_score验证准确率：",accuracy_score(gender['Survived'], LR_prediction))
|
|
|
LR_cross_val_scores = cross_val_score(LRmodel, train, sur_train, cv=5)
|
|
|
print("逻辑回归模型交叉验证准确率:", LR_cross_val_scores.mean())
|
|
|
return LR_prediction
|
|
|
|
|
|
#随机森林分类器
|
|
|
def Forest():
|
|
|
Fmodel=RandomForestClassifier(n_estimators=500,max_depth=10,min_samples_split=1.0,min_samples_leaf=1)
|
|
|
Fmodel.fit(train,sur_train)
|
|
|
F_prediction=Fmodel.predict(test)
|
|
|
print("随机森林模型accuracy_score验证准确率：",accuracy_score(gender['Survived'], F_prediction))
|
|
|
F_cross_val_scores = cross_val_score(Fmodel, train, sur_train, cv=5)
|
|
|
print("随机森林模型交叉验证准确率:", F_cross_val_scores.mean())
|
|
|
#0.6363636363636364
|
|
|
return F_prediction
|
|
|
|
|
|
#向量机模型
|
|
|
def SVM():
|
|
|
SVMmodel=SVC()
|
|
|
SVMmodel.fit(train,sur_train)
|
|
|
SVM_prediction=SVMmodel.predict(test)
|
|
|
#0.6483253588516746
|
|
|
print("向量机模型accuracy_score验证准确率：",accuracy_score(gender['Survived'], SVM_prediction))
|
|
|
SVM_cross_val_scores = cross_val_score(SVMmodel, train, sur_train, cv=5)
|
|
|
print("向量机模型交叉验证准确率:", SVM_cross_val_scores.mean())
|
|
|
return SVM_prediction
|
|
|
|
|
|
|
|
|
# 绘制 Precision-Recall 曲线
|
|
|
#PR曲线越靠近右上角，模型性能越好
|
|
|
def PrecisionRecall(LR_prediction,F_prediction,SVM_prediction):
|
|
|
LR_precision, LR_recall, _ = precision_recall_curve(gender['Survived'], LR_prediction)
|
|
|
F_precision, F_recall, _ = precision_recall_curve(gender['Survived'], F_prediction)
|
|
|
SVM_precision, SVM_recall, _ = precision_recall_curve(gender['Survived'], SVM_prediction)
|
|
|
plt.figure(figsize=(8, 6))
|
|
|
plt.plot(LR_recall, LR_precision, label='LR', marker='o')
|
|
|
plt.plot(F_recall, F_precision, label='FOREST', marker='o')
|
|
|
plt.plot(SVM_recall, SVM_precision, label='SVM', marker='o')
|
|
|
plt.xlabel('Recall')
|
|
|
plt.ylabel('Precision')
|
|
|
plt.title('Precision-Recall 曲线')
|
|
|
plt.legend()
|
|
|
plt.grid(True)
|
|
|
plt.show()
|
|
|
|
|
|
#绘制ROC曲线
|
|
|
def ROC(LR_prediction,F_prediction,SVM_prediction):
|
|
|
LR_fpr, LR_tpr, _ = roc_curve(gender['Survived'], LR_prediction)
|
|
|
LR_auc = auc(LR_fpr, LR_tpr)
|
|
|
F_fpr, F_tpr, _ = roc_curve(gender['Survived'], F_prediction)
|
|
|
F_auc = auc(F_fpr, F_tpr)
|
|
|
SVM_fpr, SVM_tpr, _ = roc_curve(gender['Survived'], SVM_prediction)
|
|
|
SVM_auc = auc(SVM_fpr, SVM_tpr)
|
|
|
plt.figure(figsize=(8, 6))
|
|
|
plt.plot(LR_fpr, LR_tpr, color='blue', lw=2, label='LR (AUC = %0.2f)' % LR_auc)
|
|
|
plt.plot(F_fpr, F_tpr, color='green', lw=2, label='Forest (AUC = %0.2f)' % F_auc)
|
|
|
plt.plot(SVM_fpr, SVM_tpr, color='red', lw=2, label='SVM (AUC = %0.2f)' % SVM_auc)
|
|
|
plt.plot([0, 1], [0, 1], color='gray', lw=1, linestyle='--')
|
|
|
plt.xlim([0.0, 1.0])
|
|
|
plt.ylim([0.0, 1.05])
|
|
|
plt.xlabel('False Positive Rate (FPR)')
|
|
|
plt.ylabel('True Positive Rate (TPR)')
|
|
|
plt.title('ROC')
|
|
|
plt.legend(loc="lower right")
|
|
|
plt.grid(True)
|
|
|
plt.show()
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
LR_prediction=Logistic_Regression()
|
|
|
F_prediction=Forest()
|
|
|
SVM_prediction=SVM()
|
|
|
PrecisionRecall(LR_prediction,F_prediction,SVM_prediction)
|
|
|
ROC(LR_prediction,F_prediction,SVM_prediction) |
