@浙大疏锦行

import pandas as pd
import pandas as pd    #用于数据处理和分析，可处理表格数据。
import numpy as np     #用于数值计算，提供了高效的数组操作。
import matplotlib.pyplot as plt    #用于绘制各种类型的图表
import seaborn as sns   #基于matplotlib的高级绘图库，能绘制更美观的统计图形。
import warnings
warnings.filterwarnings('ignore')
 
 # 设置中文字体（解决中文显示问题）
plt.rcParams['font.sans-serif'] = ['SimHei']  # Windows系统常用黑体字体
plt.rcParams['axes.unicode_minus'] = False    # 正常显示负号

data = pd.read_csv(r'heart.csv')    #读取数据

feature_name_mapping={
    'age':'年龄',
    'sex':'性别',
    'cp':'胸痛类型',
    'trestbps':'静息血压',
    'chol':'胆固醇',
    'fbs':'空腹血糖正常',
    'restecg':'静息心电图',
    'thalach':'最大心率',
    'exang':'运动诱发心绞痛',
    'oldpeak':'ST段压低值',
    'slope':'ST段斜率',
    'ca':'主要血管染色数量',
    'thal':'铊负荷实验',
    'target':'是否患心脏病'
}
data=data.rename(columns=feature_name_mapping)
data.head(10)

plt.figure(figsize=(8, 6))
sns.boxplot(x=data['静息血压'])
plt.title('静息血压箱线图')
plt.xlabel('静息血压')
plt.show()

column_name = '静息血压'

# 1. 计算 Q1, Q3 和 IQR
Q1 = data[column_name].quantile(0.25)
Q3 = data[column_name].quantile(0.75)
IQR = Q3 - Q1

# 2. 确定异常值边界 (使用 1.5 倍 IQR)
lower_bound = Q1 - 1.5 * IQR
upper_bound = Q3 + 1.5 * IQR

print(f"--- '{column_name}' 异常值处理信息 ---")
print(f"Q1 (25th Percentile): {Q1:.2f}")
print(f"Q3 (75th Percentile): {Q3:.2f}")
print(f"IQR (Q3 - Q1): {IQR:.2f}")
print(f"下限 (Lower Bound): {lower_bound:.2f}")
print(f"上限 (Upper Bound): {upper_bound:.2f}")

# 3. 筛选数据：保留在边界内的数据
data_before_drop = len(data)
data_filtered = data[
    (data[column_name] >= lower_bound) & 
    (data[column_name] <= upper_bound)
].copy() # 使用 .copy() 避免 SettingWithCopyWarning

# 4. 更新 DataFrame 并报告结果
data = data_filtered
data_after_drop = len(data)
rows_dropped = data_before_drop - data_after_drop

print(f"\n原始数据行数: {data_before_drop}")
print(f"删除异常值后行数: {data_after_drop}")
print(f"共删除异常值 (行): {rows_dropped}")

# print(f"\nDataFrame 已更新，'{column_name}' 的异常值已被移除。")'

# 1. 计算 Q1, Q3 和 IQR
Q1 = data[column_name].quantile(0.25)
Q3 = data[column_name].quantile(0.75)
IQR = Q3 - Q1

# 2. 确定异常值边界 (使用 1.5 倍 IQR)
lower_bound = Q1 - 1.5 * IQR
upper_bound = Q3 + 1.5 * IQR

print(f"--- '{column_name}' 异常值处理信息 ---")
print(f"Q1 (25th Percentile): {Q1:.2f}")
print(f"Q3 (75th Percentile): {Q3:.2f}")
print(f"IQR (Q3 - Q1): {IQR:.2f}")
print(f"下限 (Lower Bound): {lower_bound:.2f}")
print(f"上限 (Upper Bound): {upper_bound:.2f}")

# 3. 筛选数据：保留在边界内的数据
data_before_drop = len(data)
data_filtered = data[
    (data[column_name] >= lower_bound) & 
    (data[column_name] <= upper_bound)
].copy() # 使用 .copy() 避免 SettingWithCopyWarning

# 4. 更新 DataFrame 并报告结果
data = data_filtered
data_after_drop = len(data)
rows_dropped = data_before_drop - data_after_drop

print(f"\n原始数据行数: {data_before_drop}")
print(f"删除异常值后行数: {data_after_drop}")
print(f"共删除异常值 (行): {rows_dropped}")

print(f"\nDataFrame 已更新，'{column_name}' 的异常值已被移除。")

# 划分训练集和测试集 
from sklearn.model_selection import train_test_split
X = data.drop(['是否患心脏病'], axis=1)  # 特征，axis=1表示按列删除
y = data['是否患心脏病']  # 标签
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)  # 划分数据集，20%作为测试集，随机种子为42
# 训练集和测试集的形状
print(f"训练集形状: {X_train.shape}, 测试集形状: {X_test.shape}")  # 打印训练集和测试集的形状

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler,MinMaxScaler
continuous_features=['年龄','静息血压','胆固醇','最大心率','ST段压低值']
scaler=MinMaxScaler()
X_train[continuous_features]=scaler.fit_transform(X_train[continuous_features])
X_test[continuous_features]=scaler.transform(X_test[continuous_features])
X_test

# SVM
svm_model = SVC(random_state=42)
svm_model.fit(X_train, y_train)
svm_pred = svm_model.predict(X_test)

print("\nSVM 分类报告：")
print(classification_report(y_test, svm_pred))  # 打印分类报告
print("SVM 混淆矩阵：")
print(confusion_matrix(y_test, svm_pred))  # 打印混淆矩阵

# 计算 SVM 评估指标，这些指标默认计算正类的性能
svm_accuracy = accuracy_score(y_test, svm_pred)
svm_precision = precision_score(y_test, svm_pred)
svm_recall = recall_score(y_test, svm_pred)
svm_f1 = f1_score(y_test, svm_pred)
print("SVM 模型评估指标：")
print(f"准确率: {svm_accuracy:.4f}")
print(f"精确率: {svm_precision:.4f}")
print(f"召回率: {svm_recall:.4f}")
print(f"F1 值: {svm_f1:.4f}")

# KNN
knn_model=KNeighborsClassifier()
knn_model.fit(X_train,y_train)
knn_pred=knn_model.predict(X_test)

print("\nKNN分类报告")
print(classification_report(y_test,knn_pred))
print("KNN混淆矩阵：")
print(confusion_matrix(y_test,knn_pred))

knn_accuracy=accuracy_score(y_test,knn_pred)
knn_precision=precision_score(y_test,knn_pred)
knn_recall=recall_score(y_test,knn_pred)
knn_f1=f1_score(y_test,knn_pred)
print("KNN 模型评估指标：")
print(f"准确率：{knn_accuracy:.4f}")
print(f"精确率：{knn_precision:.4f}")
print(f"召回率：{knn_recall:.4f}")
print(f"F1值：{knn_f1:.4f}")

# 朴素贝叶斯
nb_model = GaussianNB()
nb_model.fit(X_train, y_train)
nb_pred = nb_model.predict(X_test)

print("\n朴素贝叶斯 分类报告：")
print(classification_report(y_test, nb_pred))
print("朴素贝叶斯 混淆矩阵：")
print(confusion_matrix(y_test, nb_pred))

nb_accuracy = accuracy_score(y_test, nb_pred)
nb_precision = precision_score(y_test, nb_pred)
nb_recall = recall_score(y_test, nb_pred)
nb_f1 = f1_score(y_test, nb_pred)
print("朴素贝叶斯 模型评估指标：")
print(f"准确率: {nb_accuracy:.4f}")
print(f"精确率: {nb_precision:.4f}")
print(f"召回率: {nb_recall:.4f}")
print(f"F1 值: {nb_f1:.4f}")

# XGBoost
xgb_model = xgb.XGBClassifier(random_state=42)
xgb_model.fit(X_train, y_train)
xgb_pred = xgb_model.predict(X_test)

print("\nXGBoost 分类报告：")
print(classification_report(y_test, xgb_pred))
print("XGBoost 混淆矩阵：")
print(confusion_matrix(y_test, xgb_pred))

xgb_accuracy = accuracy_score(y_test, xgb_pred)
xgb_precision = precision_score(y_test, xgb_pred)
xgb_recall = recall_score(y_test, xgb_pred)
xgb_f1 = f1_score(y_test, xgb_pred)
print("XGBoost 模型评估指标：")
print(f"准确率: {xgb_accuracy:.4f}")
print(f"精确率: {xgb_precision:.4f}")
print(f"召回率: {xgb_recall:.4f}")
print(f"F1 值: {xgb_f1:.4f}")