vector_assembler.py

from pyspark.ml.feature import VectorAssembler

# specify the input and output columns of the vector assembler
assembler = VectorAssembler(inputCols=['Isboundary',
                                       'Iswicket',
                                       'Over',
                                       'Runs',
                                       'Batsman_Index',
                                       'Bowler_Index',
                                       'Batsman_OHE',
                                       'Bowler_OHE'],
                           outputCol='vector')

# fill the null values
my_data = my_data.fillna(0)

# transform the data
final_data = assembler.transform(my_data)

# view the transformed vector
final_data.select('vector').show()