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
from sklearn.feature_extraction.text import TfidfVectorizer
import matplotlib.pyplot as plt
import seaborn as sns

# 数据集 URL
data_url = 'https://archive.ics.uci.edu/static/public/591/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
# 将 Gender 列中的 M 和 F 转换为 1 和 0
df['Gender'] = df['Gender'].map({'M': 1, 'F': 0})

# 特征和目标
X = df[['Name', 'Count', 'Probability']]  # 特征
y = df['Gender']  # 目标

# 使用 TfidfVectorizer 对 Name 特征进行处理
vectorizer = TfidfVectorizer()
X_name = vectorizer.fit_transform(X['Name'])

# 将 Count 和 Probability 特征与 Name 特征合并
import scipy
X_combined = scipy.sparse.hstack((X_name, X[['Count', 'Probability']].values))

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X_combined, 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=['Female', 'Male'], yticklabels=['Female', 'Male'])
plt.ylabel('Actual')
plt.xlabel('Predicted')
plt.title('Confusion Matrix')
plt.show()

#############################################
from ucimlrepo import fetch_ucirepo 
  
# fetch dataset 
gender_by_name = fetch_ucirepo(id=591) 
  
# data (as pandas dataframes) 
X = gender_by_name.data.features 
y = gender_by_name.data.targets 
  
# metadata 
print(gender_by_name.metadata) 
  
# variable information 
print(gender_by_name.variables)