PYTHON

save dataframe to a csv local file pyspark

df.repartition(1).write.format('com.databricks.spark.csv').save("/path/to/file/myfile.csv",header = 'true')

write PySpark dataframe to csv

# In this example, change the field column_as_array to column_as_string before saving.

from pyspark.sql.functions import udf
from pyspark.sql.types import StringType

def array_to_string(my_list):
    return '[' + ','.join([str(elem) for elem in my_list]) + ']'

array_to_string_udf = udf(array_to_string, StringType())

df = df.withColumn('column_as_str', array_to_string_udf(df["column_as_array"]))

# Then you can drop the old column (array type) before saving.
df.drop("column_as_array").write.csv(...)