collective/mediawiki_dump_tools
16
0
Fork 0
Code Issues Pull Requests Activity

Merge branch 'user_level_wikiq' of code.communitydata.cc:mediawiki_dump_tools into user_level_wikiq

Browse Source
This commit is contained in:
Nathan TeBlunthuis 2018-08-31 16:01:07 -07:00
commit cc551eef6e
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
wikiq_users/wikiq_users_spark.py
View File

@ -123,8 +123,7 @@ if __name__ == "__main__":
# some kind of bad work around a bug # some kind of bad work around a bug
# see https://issues.apache.org/jira/browse/SPARK-14948 # 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 reverts_df = reverts_df.select(reverts_df.revid.alias("r_revid"),'editor_nth_revert','article_nth_revert')
evert')
df = df.join(reverts_df, df.revid == reverts_df.r_revid, how='left_outer') df = df.join(reverts_df, df.revid == reverts_df.r_revid, how='left_outer')
df = df.drop("r_revid") df = df.drop("r_revid")
del(reverts_df) del(reverts_df)