def train_metric()

in jobs/ltv_daily.py [0:0]

• 25 lines of code
• 2 McCabe index (conditional complexity)

def train_metric(d, metric, plot=True, penalty=0):
    frequency = metric + "_frequency"
    recency = metric + "_recency"
    T = metric + "_T"
    train = d
    train = train[(train[frequency] > 0) & (train[recency] >= 0)]
    train[frequency] = train[frequency] - 1

    bgf = BetaGeoFitter(penalizer_coef=penalty)
    bgf.fit(train[frequency], train[recency], train[T])
    n = bgf.data.shape[0]
    simulated_data = bgf.generate_new_data(size=n)

    model_counts = pd.DataFrame(
        bgf.data["frequency"].value_counts().sort_index().iloc[:28]
    )
    simulated_counts = pd.DataFrame(
        simulated_data["frequency"].value_counts().sort_index().iloc[:28]
    )
    combined_counts = model_counts.merge(
        simulated_counts, how="outer", left_index=True, right_index=True
    ).fillna(0)
    combined_counts.columns = ["Actual", "Model"]
    if plot:
        combined_counts.plot.bar()
        display()
    return combined_counts, bgf