Merelda mereldawu
mereldawu
/ pandas_to_spark.py
Created
January 27, 2021 13:57
— forked from zaloogarcia/pandas_to_spark.py
Script for converting Pandas DF to Spark's DF
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from pyspark.sql.types import * | |
| # Auxiliar functions | |
| # Pandas Types -> Sparks Types | |
| def equivalent_type(f): | |
| if f == 'datetime64[ns]': return DateType() | |
| elif f == 'int64': return LongType() | |
| elif f == 'int32': return IntegerType() | |
| elif f == 'float64': return FloatType() | |
| else: return StringType() |