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

# 数据集 URL
data_url = 'https://archive.ics.uci.edu/static/public/17/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
# 编码目标变量（将 M 和 B 转换为 1 和 0）
df['Diagnosis'] = df['Diagnosis'].map({'M': 1, 'B': 0})

# 特征和目标
X = df.drop(columns=['ID', 'Diagnosis'])  # 特征
y = df['Diagnosis']  # 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('特征重要性')
plt.xlabel('重要性')
plt.ylabel('特征')
plt.show()

####################################################################
from ucimlrepo import fetch_ucirepo 
  
# fetch dataset 
breast_cancer_wisconsin_diagnostic = fetch_ucirepo(id=17) 
  
# data (as pandas dataframes) 
X = breast_cancer_wisconsin_diagnostic.data.features 
y = breast_cancer_wisconsin_diagnostic.data.targets 
  
# metadata 
print(breast_cancer_wisconsin_diagnostic.metadata) 
  
# variable information 
print(breast_cancer_wisconsin_diagnostic.variables) 


##################################################################
#       0       0.96      0.99      0.97        71
#       1       0.98      0.93      0.95        43

#accuracy                           0.96       114