Mastering Python for Finance - Second Edition

Removing trend by differencing

Differencing involves the difference of time series values with a time lag. The first-order difference of the time series is given by the following formula:

We can reuse the df_log variable in the previous section as our logarithmic transformed time series, and utilize the diff() and shift() methods of NumPy modules in our differencing, with the following code:

In [ ]:    df_log_diff = df_log.diff(periods=3).dropna()    # Mean and standard deviation of differenced data    df_diff_rolling = df_log_diff.rolling(12)    df_diff_ma = df_diff_rolling.mean()    df_diff_std = df_diff_rolling.std()    # Plot the stationary data plt.figure(figsize=(12, ...