Created
February 2, 2022 04:08
-
-
Save edwintyh/e866ebdcaf732bb8636dc7aa382bf027 to your computer and use it in GitHub Desktop.
Revisions
-
edwintyh created this gist
Feb 2, 2022 .There are no files selected for viewing
This file contains hidden or 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 charactersOriginal file line number Diff line number Diff line change @@ -0,0 +1,34 @@ def info(self, show = True): ''' Print concise summary of a pyspark.sql.DataFrame This method prints information about a DataFrame including the index dtype and columns, non-null values Args: show(bool): default True. show result Returns: pyspark.sql.DataFrame ''' subset = self.schema.names total_rows = self.count() _non_null = \ self.select([(total_rows - f.sum(f.when(f.col(col).isNull(),1).otherwise(0))).alias(col) for col in subset])\ .toPandas()\ .transpose()\ .reset_index()\ .rename(columns={'index':'Column', 0:'Non-Null Count'}) _non_null = spark.createDataFrame(_non_null) _dtype = spark.createDataFrame(self.dtypes).withColumnRenamed('_1','Column').withColumnRenamed('_2','Dtype') result = _dtype.join(_non_null, on = 'Column').select('Column', 'Non-Null Count', 'Dtype') if show: return result.show() else: return result pyspark.sql.DataFrame.info = info