代码.-参数优化代码.-参数优化代码.-参数优化

import numpy as np import pandas as pd import matplotlib.dates as mdates from datetime import datetime from statsmodels.tsa.seasonal import seasonal_decompose import os # print(data_x) # 热力图------------- import matplotlib.pyplot as plt import seaborn as sns plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签 plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号 import numpy as np import pandas as pd import re import matplotlib.dates as mdates from datetime import datetime from statsmodels.tsa.seasonal import seasonal_decompose import os # print(data_x) # 热力图------------- import matplotlib.pyplot as plt import seaborn as sns plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签 plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号 data = pd.read_csv("心脏病数据.csv") data = data.fillna(0) print(data.head(5)) print(data.columns) data = data[['Age', 'Sex', 'ChestPainType', 'RestingBP', 'Cholesterol', 'FastingBS', 'RestingECG', 'MaxHR', 'ExerciseAngina', 'Oldpeak', 'ST_Slope', 'HeartDisease']] data['Sex'] = pd.factorize(data['Sex'])[0] data['ChestPainType'] = pd.factorize(data['ChestPainType'])[0] data['RestingECG'] = pd.factorize(data['RestingECG'])[0] data['ExerciseAngina'] = pd.factorize(data['ExerciseAngina'])[0] data['ST_Slope'] = pd.factorize(data['ST_Slope'])[0] # 产品类型占比饼状图 # 绘制饼状图 value_counts = data['HeartDisease'].value_counts() plt.figure(figsize=(8, 8)) plt.pie(value_counts, labels=value_counts.index, autopct='%1.1f%%', startangle=90, colors=['orange','blue', 'green', 'blue','orange']) plt.title('HeartDisease Distribution') plt.show() # 绘制饼状图 value_counts = data['Sex'].value_counts() plt.figure(figsize=(8, 8)) plt.pie(value_counts, labels=value_counts.index, autopct='%1.1f%%', startangle=90, colors=['red','yellow', 'green', 'blue','orange']) plt.title('Sex Distribution') plt.show() plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签 plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号 plt.subplots(figsize=(20, 50)) print(data.corr()) plt.figure(figsize=(8, 6)) sns.heatmap(data.corr(), annot=True, cmap='coolwarm', linewidths=.5) plt.title('Correlation Heatmap') plt.show() # 计算特征与目标列的相关性 correlation_matrix = data.corr() correlation_with_target = correlation_matrix['HeartDisease'].abs().sort_values(ascending=False) # 筛选与目标列相关性较高的特征 selected_features = correlation_with_target[correlation_with_target > 0.5].index # 打印相关性排序 print("特征与目标列的相关性排序:") print(correlation_with_target) # 绘制柱状图显示相关性 plt.figure(figsize=(10, 6)) sns.barplot(x=correlation_with_target.values, y=correlation_with_target.index, palette='viridis') plt.title('Feature Correlation with HeartDisease') plt.xlabel('Correlation') plt.ylabel('Feature') plt.show()