indexing.py

from pyspark.ml.recommendation import ALS 
from pyspark.ml.evaluation import RegressionEvaluator 
from pyspark.ml.feature import StringIndexer 

indexer = StringIndexer(inputCol = "isbn", outputCol = "isbn_indexed") 

indexed = indexer.fit(filtered_with_location).transform(filtered_with_location)\
                 .withColumn('isbn_indexed',F.col('isbn_indexed')\
                 .cast("int"))\
                 .drop('isbn')

indexed.printSchema()