拉取美股数据

[QYiYang]

No description provided.

[QYiYang]

pip install yfinance scikit-learn xgboost matplotlib
import yfinance as yf
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt

1. 获取美股数据（以Apple为例）
   ticker = 'AAPL' # 可以替换为任何美股代码，如 'TSLA'，'GOOG' 等
   data = yf.download(ticker, start='2010-01-01', end='2024-01-01')

2. 数据预处理：计算技术指标，如移动平均线
   data['MA5'] = data['Close'].rolling(window=5).mean() # 5日均线
   data['MA20'] = data['Close'].rolling(window=20).mean() # 20日均线
   data['RSI'] = 100 - (100 / (1 + (data['Close'].diff().clip(lower=0).rolling(window=14).mean() /
   data['Close'].diff().clip(upper=0).rolling(window=14).mean()).fillna(0))) # RSI
   删除缺失值
   data = data.dropna()

3. 特征和标签：使用收盘价和技术指标预测下一天的收盘价
   X = data[['Close', 'MA5', 'MA20', 'RSI']]
   y = data['Close'].shift(-1) # 预测下一天的收盘价
   X = X[:-1]
   y = y[:-1]

4. 数据标准化
   scaler = StandardScaler()
   X_scaled = scaler.fit_transform(X)

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

6. 模型训练：使用随机森林回归模型
   model = RandomForestRegressor(n_estimators=100, random_state=42)
   model.fit(X_train, y_train)

7. 预测
   y_pred = model.predict(X_test)

8. 评估模型：计算均方误差（MSE）和R²分数
   mse = mean_squared_error(y_test, y_pred)
   r2_score = model.score(X_test, y_test)
   print(f'Mean Squared Error: {mse}')
   print(f'R^2 Score: {r2_score}')

9. 可视化：预测结果与真实值对比
   plt.figure(figsize=(10, 6))
   plt.plot(y_test.index, y_test, label='Real Price', color='blue')
   plt.plot(y_test.index, y_pred, label='Predicted Price', color='red')
   plt.title(f'{ticker} Stock Price Prediction')
   plt.xlabel('Date')
   plt.ylabel('Price')
   plt.legend()
   plt.show()