spark_features

spark_features.py

from pyspark.ml.feature import VectorAssembler
from pyspark.ml.pipeline import Pipeline

taxi = taxi.withColumn('pickup_weekday', F.dayofweek(taxi.tpep_pickup_datetime).cast(DoubleType()))
taxi = taxi.withColumn('pickup_hour', F.hour(taxi.tpep_pickup_datetime).cast(DoubleType()))
taxi = taxi.withColumn('pickup_minute', F.minute(taxi.tpep_pickup_datetime).cast(DoubleType()))
taxi = taxi.withColumn('pickup_week_hour', ((taxi.pickup_weekday * 24) + taxi.pickup_hour).cast(DoubleType()))
taxi = taxi.withColumn('store_and_fwd_flag', F.when(taxi.store_and_fwd_flag == 'Y', 1).otherwise(0))
taxi = taxi.withColumn('label', taxi.total_amount)  
taxi = taxi.fillna(-1)

assembler = VectorAssembler(
    inputCols=features,
    outputCol='features',
)

pipeline = Pipeline(stages=[assembler])
assembler_fitted = pipeline.fit(taxi)
X = assembler_fitted.transform(taxi)
X.cache()
X.count()