Last active
January 15, 2021 13:46
-
-
Save Arqentum/3fa04e97eac507d139d61a5cbf556ab7 to your computer and use it in GitHub Desktop.
normalize column names #Spark
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
| def normalize_column_names(df: DataFrame) : DataFrame = { | |
| df.toDF(df.columns map(_ | |
| .toLowerCase | |
| .replaceAll("\\s", "_") | |
| .replaceAll("\"+", "") | |
| ): _*) | |
| } | |
| def load_path_as_df(dict: List[List[String]]) { | |
| dict.foreach{ l => | |
| val name :: delimiter :: path :: extra = l | |
| normalize_column_names(spark.read.option("header", "true").option("delimiter", delimiter).csv(path.replaceAll("%3D","=")).toDF() ).createOrReplaceTempView(name) | |
| } | |
| } | |
| val lt = List( | |
| List("standard_thesaurus" ,",","s3a://adaptive-data-lake/staging/data_provider%3DAdaptive/standard_tickers.csv") | |
| , List("all_thesaurus_names",",","s3://adaptive-data-lake/prod/data_provider=Adaptive/prod_thesauri_with_names.csv") | |
| , List("all_sections" ,",","s3://adaptive-data-lake/prod/data_provider%3DAdaptive/a_section__201911221610.csv") | |
| , List("mscience" ,",","s3://adaptive-data-lake/prod/data_provider%3Dmscience/namespace%3Dapi.mscience.swipev2.txs_per_shopper/year%3D2019/month%3D12/day%3D15/") | |
| , List("req_daily" ,",","s3://adaptive-data-lake/dev/test_stanis/miscellaneous/fundmanager_inf_manually_changed.csv") | |
| , List("req_full" ,",","s3://adaptive-data-lake/dev/test_stanis/miscellaneous/fundmanager_inf.csv") | |
| ) | |
| load_path_as_df(lt) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment