sf_crime_12.py

sf_crime_12.py

def time_split(df, validation_pct=0.2):
    df = df.sort_values("Dates")
    split_date = df.loc[df.index[int(len(df) * (1 - validation_pct))], "Dates"]
    return df.index[df["Dates"] <= split_date], df.index[df["Dates"] > split_date]


train_idx, validation_idx = time_split(train, validation_pct=0.2)
print(f"Training data has {len(train_idx)} samples from {train.loc[train_idx, 'Dates'].min()} to {train.loc[train_idx, 'Dates'].max()}")
print(f"Validation data has {len(validation_idx)} samples from {train.loc[validation_idx, 'Dates'].min()} to {train.loc[validation_idx, 'Dates'].max()}")

train.drop("Dates", axis=1, inplace=True)
to = TabularPandas(train,
    procs=[Categorify, FillMissing, Normalize],
    cat_names=cat,
    cont_names=cont,
    y_names="TargetedCategory",
    splits=[list(train_idx), list(validation_idx)])