使用Pandas进行时间序列分析的10个关键点详解

import pandas as pd

# 创建一个简单的DataFrame
data = {'Date': ['2022-01-01', '2022-01-02', '2022-01-03'],
        'Price': [100, 105, 110]}
df = pd.DataFrame(data)
df['Date'] = pd.to_datetime(df['Date'])
df.set_index('Date', inplace=True)
print(df)

# 将'Date'列转换为datetime类型，并设置为索引
df['Date'] = pd.to_datetime(df['Date'])
df.set_index('Date', inplace=True)

# 按月重采样并计算平均值
monthly_df = df.resample('M').mean()
print(monthly_df)

# 使用线性插值填补缺失值
df['Price'] = df['Price'].interpolate()

# 计算5日移动平均
df['MA_5'] = df['Price'].rolling(window=5).mean()

from statsmodels.tsa.seasonal import seasonal_decompose

# 进行季节性分解
result = seasonal_decompose(df['Price'], model='additive')
print(result.trend)
print(result.seasonal)
print(result.resid)

# 计算滞后1的列
df['Lag_1'] = df['Price'].shift(1)

# 计算一阶差分
df['Diff_1'] = df['Price'].diff()

# 将数据转换为每日频率并填充缺失值
daily_data = df.resample('D').ffill()

import matplotlib.pyplot as plt

​​​​​​​# 绘制原始时间序列数据
df.plot()
plt.show()