利用Python进行金融数据分析的全过程

pip install pandas numpy matplotlib yfinance

import yfinance as yf
import pandas as pd

# 获取AAPL股票数据
ticker = 'AAPL'
data = yf.download(ticker, start='2020-01-01', end='2023-12-31')
print(data.head())

# 检查缺失值
print(data.isnull().sum())

# 去除缺失值
data.dropna(inplace=True)

# 检查异常值（如价格为0的情况）
data = data[data['Close'] > 0]

# 计算日收益率
data['Daily Return'] = data['Close'].pct_change()

# 计算移动平均线
data['20 Day MA'] = data['Close'].rolling(window=20).mean()
data['50 Day MA'] = data['Close'].rolling(window=50).mean()

import matplotlib.pyplot as plt

# 绘制收盘价和移动平均线
plt.figure(figsize=(14, 7))
plt.plot(data['Close'], label='Close Price')
plt.plot(data['20 Day MA'], label='20 Day MA')
plt.plot(data['50 Day MA'], label='50 Day MA')
plt.title('AAPL Stock Price and Moving Averages')
plt.xlabel('Date')
plt.ylabel('Price')
plt.legend()
plt.show()

# 绘制日收益率直方图
plt.figure(figsize=(14, 7))
data['Daily Return'].hist(bins=50)
plt.title('AAPL Daily Return Histogram')
plt.xlabel('Daily Return')
plt.ylabel('Frequency')
plt.show()

# 计算RSI
def calculate_rsi(data, window):
    diff = data.diff(1).dropna()
    gain = (diff.where(diff > 0, 0)).rolling(window=window).mean()
    loss = (-diff.where(diff < 0, 0)).rolling(window=window).mean()
    rs = gain / loss
    rsi = 100 - (100 / (1 + rs))
    return rsi

data['RSI'] = calculate_rsi(data['Close'], 14)

# 绘制RSI
plt.figure(figsize=(14, 7))
plt.plot(data['RSI'], label='RSI')
plt.title('AAPL RSI')
plt.xlabel('Date')
plt.ylabel('RSI')
plt.legend()
plt.show()