examples/keras_spark_rossmann_run.py [159:180]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        weather = weather_csv.join(state_names_csv, weather_csv.file == state_names_csv.StateName)
        df = df.join(weather, ['State', 'Date'])

        # Fix null values.
        df = df \
            .withColumn('CompetitionOpenSinceYear', F.coalesce(df.CompetitionOpenSinceYear, F.lit(1900))) \
            .withColumn('CompetitionOpenSinceMonth', F.coalesce(df.CompetitionOpenSinceMonth, F.lit(1))) \
            .withColumn('Promo2SinceYear', F.coalesce(df.Promo2SinceYear, F.lit(1900))) \
            .withColumn('Promo2SinceWeek', F.coalesce(df.Promo2SinceWeek, F.lit(1)))

        # Days & months competition was open, cap to 2 years.
        df = df.withColumn('CompetitionOpenSince',
                           F.to_date(F.format_string('%s-%s-15', df.CompetitionOpenSinceYear,
                                                     df.CompetitionOpenSinceMonth)))
        df = df.withColumn('CompetitionDaysOpen',
                           F.when(df.CompetitionOpenSinceYear > 1900,
                                  F.greatest(F.lit(0), F.least(F.lit(360 * 2), F.datediff(df.Date, df.CompetitionOpenSince))))
                           .otherwise(0))
        df = df.withColumn('CompetitionMonthsOpen', (df.CompetitionDaysOpen / 30).cast(T.IntegerType()))

        # Days & weeks of promotion, cap to 25 weeks.
        df = df.withColumn('Promo2Since',
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



examples/keras_spark3_rossmann.py [169:190]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        weather = weather_csv.join(state_names_csv, weather_csv.file == state_names_csv.StateName)
        df = df.join(weather, ['State', 'Date'])

        # Fix null values.
        df = df \
            .withColumn('CompetitionOpenSinceYear', F.coalesce(df.CompetitionOpenSinceYear, F.lit(1900))) \
            .withColumn('CompetitionOpenSinceMonth', F.coalesce(df.CompetitionOpenSinceMonth, F.lit(1))) \
            .withColumn('Promo2SinceYear', F.coalesce(df.Promo2SinceYear, F.lit(1900))) \
            .withColumn('Promo2SinceWeek', F.coalesce(df.Promo2SinceWeek, F.lit(1)))

        # Days & months competition was open, cap to 2 years.
        df = df.withColumn('CompetitionOpenSince',
                           F.to_date(F.format_string('%s-%s-15', df.CompetitionOpenSinceYear,
                                                     df.CompetitionOpenSinceMonth)))
        df = df.withColumn('CompetitionDaysOpen',
                           F.when(df.CompetitionOpenSinceYear > 1900,
                                  F.greatest(F.lit(0), F.least(F.lit(360 * 2), F.datediff(df.Date, df.CompetitionOpenSince))))
                           .otherwise(0))
        df = df.withColumn('CompetitionMonthsOpen', (df.CompetitionDaysOpen / 30).cast(T.IntegerType()))

        # Days & weeks of promotion, cap to 25 weeks.
        df = df.withColumn('Promo2Since',
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



examples/keras_spark_rossmann_estimator.py [164:185]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        weather = weather_csv.join(state_names_csv, weather_csv.file == state_names_csv.StateName)
        df = df.join(weather, ['State', 'Date'])

        # Fix null values.
        df = df \
            .withColumn('CompetitionOpenSinceYear', F.coalesce(df.CompetitionOpenSinceYear, F.lit(1900))) \
            .withColumn('CompetitionOpenSinceMonth', F.coalesce(df.CompetitionOpenSinceMonth, F.lit(1))) \
            .withColumn('Promo2SinceYear', F.coalesce(df.Promo2SinceYear, F.lit(1900))) \
            .withColumn('Promo2SinceWeek', F.coalesce(df.Promo2SinceWeek, F.lit(1)))

        # Days & months competition was open, cap to 2 years.
        df = df.withColumn('CompetitionOpenSince',
                           F.to_date(F.format_string('%s-%s-15', df.CompetitionOpenSinceYear,
                                                     df.CompetitionOpenSinceMonth)))
        df = df.withColumn('CompetitionDaysOpen',
                           F.when(df.CompetitionOpenSinceYear > 1900,
                                  F.greatest(F.lit(0), F.least(F.lit(360 * 2), F.datediff(df.Date, df.CompetitionOpenSince))))
                           .otherwise(0))
        df = df.withColumn('CompetitionMonthsOpen', (df.CompetitionDaysOpen / 30).cast(T.IntegerType()))

        # Days & weeks of promotion, cap to 25 weeks.
        df = df.withColumn('Promo2Since',
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -