import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, confusion_matrix
import matplotlib.pyplot as plt
import seaborn as sns

# 数据集 URL
data_url = 'https://archive.ics.uci.edu/static/public/15/data.csv'

# 加载数据集
df = pd.read_csv(data_url)

# 查看数据集的前几行
print("数据集的前几行：")
print(df.head())

# 数据预处理
# 处理缺失值（将 '?' 替换为 NaN）
df['Bare_nuclei'] = df['Bare_nuclei'].replace('?', None).astype(float)  # 将 '?' 替换为 None
df = df.dropna()  # 删除含有缺失值的行

# 编码目标变量（将 2 和 4 转换为 0 和 1）
df['Class'] = df['Class'].map({2: 0, 4: 1})

# 特征和目标
X = df.drop(columns=['Sample_code_number', 'Class'])  # 特征
y = df['Class']  # 目标

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 训练模型
model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)

# 预测
y_pred = model.predict(X_test)

# 输出分类报告
print("\n分类报告：")
print(classification_report(y_test, y_pred))

# 可视化混淆矩阵
cm = confusion_matrix(y_test, y_pred)
plt.figure(figsize=(8, 6))
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=['Benign', 'Malignant'], yticklabels=['Benign', 'Malignant'])
plt.ylabel('Actual')
plt.xlabel('Predicted')
plt.title('Confusion Matrix')
plt.show()

# 可视化特征重要性
feature_importances = model.feature_importances_
features = X.columns
indices = range(len(features))

# 创建条形图
plt.figure(figsize=(12, 6))
sns.barplot(x=feature_importances, y=features)
plt.title('Feature Importance')
plt.xlabel('Importance')
plt.ylabel('Feature')
plt.show()


###############################################
from ucimlrepo import fetch_ucirepo 
  
# fetch dataset 
breast_cancer_wisconsin_original = fetch_ucirepo(id=15) 
  
# data (as pandas dataframes) 
X = breast_cancer_wisconsin_original.data.features 
y = breast_cancer_wisconsin_original.data.targets 
  
# metadata 
print(breast_cancer_wisconsin_original.metadata) 
  
# variable information 
print(breast_cancer_wisconsin_original.variables) 

##########################################################
#       0       0.93      0.99      0.96        79
#       1       0.98      0.90      0.94        58

#accuracy                           0.95       137