Skip to content

Commit

Permalink
Fix handling numeric column
Browse files Browse the repository at this point in the history
  • Loading branch information
argenisleon committed Nov 25, 2019
1 parent e0f1c68 commit dde0f6b
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion optimus/ml/distancecluster.py
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ def levenshtein_cluster(df, input_col, threshold: int = None, output: str = "dic
where = (F.col(distance_col) == 0) | (F.col(distance_col) > threshold)

df_r = (df.rows.drop(where)
.cols.replace(distance_col, 0, None)
.cols.replace(distance_col, 0, None, search_by="numeric")
.groupby(temp_col_1)
.agg(F.min(distance_col).alias(distance_r_col))
# .cols.rename(distance_col, distance_r_col)
Expand Down

0 comments on commit dde0f6b

Please sign in to comment.