Calculating Differences

This is the code we used in this notebook;

def reshuffle(dataf):
    return (dataf
            .sample(36)
            .reset_index(drop=True)
            .assign(sleep=lambda d: np.where(d.index < 15, 'deprived', 'normal')))

def calc_diff(dataf):
    agg = (dataf
          .groupby('sleep')
          .agg(mean_unit_tests=('passed_unit_tests', np.mean),
                mean_asserts=('passed_asserts', np.mean),
                mean_user_stories=('tackled_user_stories', np.mean),)).T
    return agg['deprived'] - agg['normal']

n = 1000
results = np.zeros((n, 3))
for i in range(n):
    results[i, :] = calc_diff(reshuffle(df))
df_diff = pd.DataFrame(results,
                       columns=['diff_unit_tests',
                                'diff_asserts',
                                'diff_user_stories'])