Python对时间序列进行数据分析与可视化的实战指南

pip install pandas matplotlib seaborn statsmodels yfinance

import yfinance as yf

# 下载数据（参数：股票代码，时间范围）
data = yf.download('600519.SS', start='2020-11-17', end='2025-11-17')
# 提取收盘价作为分析对象
close_prices = data['Close']
print(close_prices.head())

# 检查缺失值数量
print(f"缺失值数量：{close_prices.isnull().sum()}")

# 线性插值填充缺失值
close_prices = close_prices.interpolate(method='linear')

# 确保索引为datetime类型
close_prices.index = pd.to_datetime(close_prices.index)

# 重采样为周数据（可选）
weekly_data = close_prices.resample('W').last()

import matplotlib.pyplot as plt
plt.figure(figsize=(14, 6))
plt.plot(close_prices.index, close_prices.values, 
         label='贵州茅台收盘价', color='#1f77b4')
plt.title('2020-2025年贵州茅台股价走势', fontsize=16)
plt.xlabel('日期', fontsize=12)
plt.ylabel('价格（元）', fontsize=12)
plt.grid(True, linestyle='--', alpha=0.7)
plt.legend()
plt.tight_layout()
plt.show()

# 计算20日和60日移动平均
ma_20 = close_prices.rolling(window=20).mean()
ma_60 = close_prices.rolling(window=60).mean()

plt.figure(figsize=(14, 6))
plt.plot(close_prices.index, close_prices, label='收盘价', alpha=0.5)
plt.plot(close_prices.index, ma_20, label='20日均线', linewidth=2)
plt.plot(close_prices.index, ma_60, label='60日均线', linewidth=2)
plt.title('股价与移动平均线对比', fontsize=16)
plt.legend()
plt.show()

from statsmodels.tsa.seasonal import seasonal_decompose

# 按年周期分解（假设数据有年度季节性）
result = seasonal_decompose(close_prices, model='additive', period=252)  # 252个交易日≈1年

result.plot()
plt.suptitle('股价季节性分解', y=1.02)
plt.tight_layout()
plt.show()

from statsmodels.graphics.tsaplots import plot_acf

plt.figure(figsize=(12, 6))
plot_acf(close_prices.dropna(), lags=60, alpha=0.05)  # 显示60阶自相关
plt.title('股价自相关图', fontsize=16)
plt.xlabel('滞后阶数（交易日）', fontsize=12)
plt.ylabel('自相关系数', fontsize=12)
plt.show()

pip install plotly

import plotly.graph_objects as go

fig = go.Figure()
fig.add_trace(go.Scatter(
    x=close_prices.index,
    y=close_prices,
    name='收盘价',
    line=dict(color='#1f77b4', width=2)
))

# 添加移动平均线
fig.add_trace(go.Scatter(
    x=ma_20.index,
    y=ma_20,
    name='20日均线',
    line=dict(color='#ff7f0e', width=1.5, dash='dash')
))

fig.update_layout(
    title='贵州茅台股价交互式图表',
    xaxis_title='日期',
    yaxis_title='价格（元）',
    hovermode='x unified',
    template='plotly_white'
)

fig.show()

# 计算滚动均值和标准差
rolling_mean = close_prices.rolling(window=20).mean()
rolling_std = close_prices.rolling(window=20).std()

# 定义异常阈值
upper_bound = rolling_mean + 3 * rolling_std
lower_bound = rolling_mean - 3 * rolling_std

# 检测异常值
anomalies = close_prices[(close_prices > upper_bound) | (close_prices < lower_bound)]

# 可视化
plt.figure(figsize=(14, 6))
plt.plot(close_prices.index, close_prices, label='收盘价', alpha=0.7)
plt.plot(upper_bound.index, upper_bound, 'r--', label='上界')
plt.plot(lower_bound.index, lower_bound, 'r--', label='下界')
plt.scatter(anomalies.index, anomalies, color='red', label='异常值', zorder=5)
plt.title('股价异常值检测（3σ原则）', fontsize=16)
plt.legend()
plt.show()

# 生成完整日期范围
full_dates = pd.date_range(start='2020-11-17', end='2025-11-17', freq='B')  # B表示工作日
close_prices = close_prices.reindex(full_dates)
close_prices = close_prices.interpolate(method='linear')  # 线性插值填充

plt.savefig('stock_analysis.png', dpi=300, bbox_inches='tight')

fig.write_html('interactive_chart.html')  # 保存为HTML
fig.write_image("interactive_chart.png", scale=2)  # 需要安装kaleido库

# 获取多只股票数据
stocks = yf.download(['600519.SS', '000858.SZ', '601318.SH'], 
                    start='2020-11-17', end='2025-11-17')['Close']

# 绘制子图
fig, axes = plt.subplots(3, 1, figsize=(14, 12))
for i, code in enumerate(stocks.columns):
    axes[i].plot(stocks.index, stocks[code], label=code)
    axes[i].set_title(f'[code]股价走势')
    axes[i].legend()
plt.tight_layout()
plt.show()