process_cinetic_shift_analysis.py

# Let's see how the correlation coefficient evolves as the shift number increases
# and record the successive values into a DataFrame
shift_corr_results = pd.DataFrame(columns=["x1_shifted","x2_shifted","x3_shifted"], dtype=float)

for feature in shift_corr_results.columns:

  # We define a shift range from 0 to 50 but it should be adapted to every use-case
  for shift_value in range(0,50):

    # The correlation coefficient is calculated
    tmp_corr_value = df["y"].corr(df[feature].shift(shift_value))

    # And recorded into the results DataFrame
    shift_corr_results.loc[shift_value, feature] = tmp_corr_value

  # After each feature analysis, we identity the best shift to apply to maximize the correlation
  print("Best shift of", feature, "at", shift_corr_results[[feature]].idxmax()[0] , "with", shift_corr_results[feature].max())