feat(clean): add clean_duplication() function

Implements the clean_duplication() function for clustering and standardizing duplicate values.
sfu-db · Mar 31, 2021 · 98ff38d · 98ff38d
1 parent 7a8af96
commit 98ff38d
Show file tree

Hide file tree

Showing 6 changed files with 1,177 additions and 408 deletions.
diff --git a/dataprep/clean/__init__.py b/dataprep/clean/__init__.py
@@ -21,6 +21,7 @@
 
 from .clean_date import clean_date, validate_date
 
+from .clean_duplication import clean_duplication
 
 __all__ = [
     "clean_lat_long",
@@ -40,4 +41,5 @@
     "validate_address",
     "clean_date",
     "validate_date",
+    "clean_duplication",
 ]