def generate_coefs()

in econml/data/dynamic_panel_dgp.py [0:0]

• 48 lines of code
• 20 McCabe index (conditional complexity)

def generate_coefs(index, columns):
    simulated_coefs_df = pd.DataFrame(0, index=index, columns=columns)
    # get the indices of each group of features
    ind_demo = [columns.index(col) for col in columns if "demo" in col]
    ind_proxy = [columns.index(col) for col in columns if "proxy" in col]
    ind_investment = [columns.index(col)
                      for col in columns if "investment" in col]

    for i in range(7):
        outcome_name = simulated_coefs_df.index[i]
        if "proxy" in outcome_name:
            ind_same_proxy = [
                ind for ind in ind_proxy if outcome_name in columns[ind]]
            # print(ind_same_proxy)
            random_proxy_name = np.random.choice(
                [proxy for proxy in index[:4] if proxy != outcome_name]
            )
            ind_random_other_proxy = [
                ind for ind in ind_proxy if random_proxy_name in columns[ind]
            ]
            # demo
            simulated_coefs_df.iloc[
                i, np.random.choice(ind_demo, 2)
            ] = np.random.uniform(0.004, 0.05)
            # same proxy
            simulated_coefs_df.iloc[i, ind_same_proxy] = sorted(
                np.random.choice(expon.pdf(np.arange(10)) *
                                 5e-1, 6, replace=False)
            )
            simulated_coefs_df.iloc[i, ind_random_other_proxy] = sorted(
                np.random.choice(expon.pdf(np.arange(10)) *
                                 5e-2, 6, replace=False)
            )
        elif "investment" in outcome_name:
            ind_same_invest = [
                ind for ind in ind_investment if outcome_name in columns[ind]
            ]
            random_proxy_name = np.random.choice(index[:4])
            ind_random_other_proxy = [
                ind for ind in ind_proxy if random_proxy_name in columns[ind]
            ]
            simulated_coefs_df.iloc[
                i, np.random.choice(ind_demo, 2)
            ] = np.random.uniform(0.001, 0.05)
            simulated_coefs_df.iloc[i, ind_same_invest] = sorted(
                np.random.choice(expon.pdf(np.arange(10)) *
                                 5e-1, 6, replace=False)
            )
            simulated_coefs_df.iloc[i, ind_random_other_proxy] = sorted(
                np.random.choice(expon.pdf(np.arange(10)) *
                                 1e-1, 6, replace=False)
            )
    return simulated_coefs_df