strings.py

@@ -30,10 +30,11 @@ spark.read.json(folder_path)
         explode(col("raw_aff_string")).alias("aff_string") #this allows to split all the raw_aff_string and to parallelize better
     )
     .withColumn("Matchings", oalex_affro(col("doi"), col("aff_string"))) #this one says create a new column with name Matchinds as the result of the function as second argument
-    .select("DOI","OAlex","Matchins")
+    .drop(col("aff_string")
+    .select(col("DOI"),col("OAlex"),explode("Matchins").alias("match")
           .groupBy("DOI") #this groups by doi to have just one row per each doi
           .agg(first("OAlex").alias("OAlex"), #for each DOI it says what are the other columns Since OALEX is equal for each doi just select the first, while use the collect_list function to aggregate the Matchings
-               collect_list("Matchings").alias("Matchings"))
+               collect_list("match").alias("Matchings"))
           .write
           .mode("overwrite") #in case the folder already exists on hadoop it does not break
           .option("compression","gzip") #to reduce the space