机器学习：基于心脏病数据集的XGBoost分类预测

 import requests

    
  
    
 url = 'https://tianchi-media.oss-cn-beijing.aliyuncs.com/DSW/7XGBoost/train.csv'
    
 response = requests.get(url)
    
 with open('train.csv', 'wb') as f:
    
     f.write(response.content)

 ##  基础函数库

    
 import numpy as np 
    
 import pandas as pd
    
  
    
 ## 绘图函数库
    
 import matplotlib.pyplot as plt
    
 import seaborn as sns

 ## 我们利用Pandas自带的read_csv函数读取并转化为DataFrame格式

    
  
    
 data = pd.read_csv('heart.csv')

 ## 利用.info()查看数据的整体信息

    
 data.info()

 ## 进行简单的数据查看，我们可以利用 .head() 头部.tail()尾部

    
 data.head()
    
  
    
 data = data.fillna(-1)
    
 data.tail()

    print(pd.Series(data['DEATH_EVENT']).value_counts())

 ## 对于特征进行一些统计描述

    
 data.describe()

    numerical_features = [x for x in data.columns if data[x].dtype == np.float]

    category_features = [x for x in data.columns if data[x].dtype != np.float and x != 'DEATH_EVENT']

 ## 选取三个特征与标签组合的散点可视化

    
 sns.pairplot(data=data[['age',
    
 'creatinine_phosphokinase',
    
 'ejection_fraction'] + ['DEATH_EVENT']], diag_kind='hist', hue= 'DEATH_EVENT')
    
 plt.show()

 for col in data[numerical_features].columns:

    
     if col != 'DEATH_EVENT':
    
     sns.boxplot(x='DEATH_EVENT', y=col, saturation=0.5, palette='pastel', data=data)
    
     plt.title(col)
    
     plt.show()

 tlog = {}

    
 for i in category_features:
    
     tlog[i] = data[data['DEATH_EVENT'] == 1][i].dropna().value_counts()
    
  
    
 flog = {}
    
 for i in category_features:
    
     flog[i] = data[data['DEATH_EVENT'] == 0][i].dropna().value_counts()
    
  
    
  
    
  
    
 plt.figure(figsize=(10,2))
    
 plt.subplot(1,2,1)
    
 plt.title('DEATH')
    
 sns.barplot(x = pd.DataFrame(tlog['smoking'][:2]).sort_index()['smoking'], y = pd.DataFrame(tlog['smoking'][:2]).sort_index().index, color = "red")
    
 plt.subplot(1,2,2)
    
 plt.title('Not DEATH')
    
 sns.barplot(x = pd.DataFrame(flog['smoking'][:2]).sort_index()['smoking'], y = pd.DataFrame(flog['smoking'][:2]).sort_index().index, color = "blue")
    
 plt.show()

 ## 把所有的相同类别的特征编码为同一个值

    
 def get_mapfunction(x):
    
     mapp = dict(zip(x.unique().tolist(),
    
      range(len(x.unique().tolist()))))
    
     def mapfunction(y):
    
     if y in mapp:
    
         return mapp[y]
    
     else:
    
         return -1
    
     return mapfunction
    
 for i in category_features:
    
     data[i] = data[i].apply(get_mapfunction(data[i]))

 ## 为了正确评估模型性能，将数据划分为训练集和测试集，并在训练集上训练模型，在测试集上验证模型性能。

    
 from sklearn.model_selection import train_test_split
    
  
    
 ## 选择其类别为0和1的样本 （不包括类别为2的样本）
    
 data_target_part = data['RainTomorrow']
    
 data_features_part = data[[x for x in data.columns if x != 'RainTomorrow']]
    
  
    
 ## 测试集大小为20%， 80%/20%分
    
 x_train, x_test, y_train, y_test = train_test_split(data_features_part, data_target_part, test_size = 0.2, random_state = 2020)

 #查看标签数据

    
 print(y_train[0:2],y_test[0:2])
    
  
    
 # 打印修改后的结果
    
 print(y_train[0:2],y_test[0:2])

 ## 导入XGBoost模型

    
 from xgboost.sklearn import XGBClassifier
    
 ## 定义 XGBoost模型 
    
 clf = XGBClassifier(use_label_encoder=False)
    
 # 在训练集上训练XGBoost模型
    
 clf.fit(x_train, y_train)

 ## 在训练集和测试集上分布利用训练好的模型进行预测

    
 train_predict = clf.predict(x_train)
    
 test_predict = clf.predict(x_test)
    
 from sklearn import metrics
    
  
    
 ## 利用accuracy（准确度）【预测正确的样本数目占总预测样本数目的比例】评估模型效果
    
 print('The accuracy of the Logistic Regression is:',metrics.accuracy_score(y_train,train_predict))
    
 print('The accuracy of the Logistic Regression is:',metrics.accuracy_score(y_test,test_predict))
    
  
    
 ## 查看混淆矩阵 (预测值和真实值的各类情况统计矩阵)
    
 confusion_matrix_result = metrics.confusion_matrix(test_predict,y_test)
    
 print('The confusion matrix result:\n',confusion_matrix_result)
    
  
    
 # 利用热力图对于结果进行可视化
    
 plt.figure(figsize=(8, 6))
    
 sns.heatmap(confusion_matrix_result, annot=True, cmap='Blues')
    
 plt.xlabel('Predicted labels')
    
 plt.ylabel('True labels')
    
 plt.show()

 plt.figure(figsize=(8, 6))

    
 sns.barplot(y=data_features_part.columns, x=clf.feature_importances_)
    
 plt.show()

 ## 从sklearn库中导入网格调参函数

    
 from sklearn.model_selection import GridSearchCV
    
  
    
 ## 定义参数取值范围
    
 learning_rate = [0.1, 0.3,]
    
 subsample = [0.8]
    
 colsample_bytree = [0.6, 0.8]
    
 max_depth = [3,5]
    
  
    
 parameters = { 'learning_rate': learning_rate,
    
           'subsample': subsample,
    
           'colsample_bytree':colsample_bytree,
    
           'max_depth': max_depth}
    
 model = XGBClassifier(n_estimators = 20)
    
  
    
 ## 进行网格搜索
    
 clf = GridSearchCV(model, parameters, cv=3, scoring='accuracy',verbose=1,n_jobs=-1)
    
  
    
 clf = clf.fit(x_train, y_train)

 ## 在训练集和测试集上分布利用最好的模型参数进行预测

    
  
    
 ## 定义带参数的 XGBoost模型 
    
 clf = XGBClassifier(colsample_bytree = 0.6, learning_rate = 0.3, max_depth= 8, subsample = 0.9)
    
 # 在训练集上训练XGBoost模型
    
 clf.fit(x_train, y_train)
    
  
    
 train_predict = clf.predict(x_train)
    
 test_predict = clf.predict(x_test)
    
  
    
 ## 利用accuracy（准确度）【预测正确的样本数目占总预测样本数目的比例】评估模型效果
    
 print('The accuracy of the Logistic Regression is:',metrics.accuracy_score(y_train,train_predict))
    
 print('The accuracy of the Logistic Regression is:',metrics.accuracy_score(y_test,test_predict))
    
  
    
 ## 查看混淆矩阵 (预测值和真实值的各类情况统计矩阵)
    
 confusion_matrix_result = metrics.confusion_matrix(test_predict,y_test)
    
 print('The confusion matrix result:\n',confusion_matrix_result)
    
  
    
 # 利用热力图对于结果进行可视化
    
 plt.figure(figsize=(8, 6))
    
 sns.heatmap(confusion_matrix_result, annot=True, cmap='Blues')
    
 plt.xlabel('Predicted labels')
    
 plt.ylabel('True labels')
    
 plt.show()