createDataset.py 文件源码

def model_data(data, LECAT=False, NAMEAN=False, NA999=False, OH=False, ONLYCONT=False, ONLYCAT=False, ONLYCATOH=False, COLSREMOVAL=False, cols=[], maxCategories=300):

    data = data.copy()

    cat_var = list(data.select_dtypes(["object"]).columns)
    cont_var = list(data.select_dtypes(["float", "int"]).columns)

    if COLSREMOVAL:
        data = data.drop(cols, 1, inplace=False)
        cat_var = list(data.select_dtypes(["object"]).columns)
        cont_var = list(data.select_dtypes(["float", "int"]).columns)


    if NAMEAN:
        for col in cont_var:
            data.loc[data[col].isnull(), col] = data[col].mean()

    if NA999:
        for col in cont_var:
            data.loc[data[col].isnull(), col] = -999

    if LECAT:
        for col in data[cat_var]: data[col] = pd.factorize(data[col])[0]

    if OH:
        cols2dummy = [col for col in data[cat_var] if len(data[col].unique()) <= maxCategories]
        colsNot2dummy = [col for col in data[cat_var] if len(data[col].unique()) > maxCategories]
        data = pd.get_dummies(data, dummy_na=True, columns=cols2dummy)

        #binning
        for col in colsNot2dummy:
            data[col] = pd.factorize(data[col])[0]
            dcb = DummycolumnsBins(cols=col, prefix=col, nb_bins=2000)
            dcb.fit(data)
            pd_binned = dcb.transform(data)
            data = pd.concat([data,pd_binned],1)
    if ONLYCONT:
        data = data[cont_var]

    if ONLYCAT:
        test_idx = data['ID']
        Y = data['target']
        data = data[cat_var]
        data['ID'] = test_idx
        data['target'] = Y

    if ONLYCATOH:
        test_idx = data['ID']
        Y = data['target']
        cols = list(set(data.columns).difference(set(cont_var))) ; print(cols)
        data = data[cols]
        data['ID'] = test_idx
        data['target'] = Y


    return data