X-Git-Url: https://code.communitydata.science/mediawiki_dump_tools.git/blobdiff_plain/3d12865c4ec7db67123443abb3d5dc26ee0f300d..cc551eef6e04e2f82b8dbc7870fd98bfc0997e13:/wikiq_users/wikiq_users_spark.py diff --git a/wikiq_users/wikiq_users_spark.py b/wikiq_users/wikiq_users_spark.py index 31d078a..edc2d4f 100755 --- a/wikiq_users/wikiq_users_spark.py +++ b/wikiq_users/wikiq_users_spark.py @@ -123,8 +123,7 @@ if __name__ == "__main__": # some kind of bad work around a bug # see https://issues.apache.org/jira/browse/SPARK-14948 - reverts_df = reverts_df.select(reverts_df.revid.alias("r_revid"),'editor_nth_revert','article_nth_r -evert') + reverts_df = reverts_df.select(reverts_df.revid.alias("r_revid"),'editor_nth_revert','article_nth_revert') df = df.join(reverts_df, df.revid == reverts_df.r_revid, how='left_outer') df = df.drop("r_revid") del(reverts_df)