use keep='first', keep='last' in duplicated()

updated pandas version requirement to match
jeremymcrae · Aug 10, 2017 · 288f753 · 288f753
1 parent 01c394c
commit 288f753
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 3 deletions.
diff --git a/scripts/get_validations.py b/scripts/get_validations.py
@@ -243,8 +243,8 @@ def remove_duplicates(data):
     """
 
     columns = ["person_id", "chrom", "start_pos"]
-    first = data.duplicated(take_last=False, subset=columns)
-    second = data.duplicated(take_last=True, subset=columns)
+    first = data.duplicated(keep='first', subset=columns)
+    second = data.duplicated(keep='last', subset=columns)
     dups = data[first | second]
     without_dups = data[~(first | second)]
 

diff --git a/setup.py b/setup.py
@@ -29,7 +29,7 @@
     description = ("Filtering candidate de novo variants."),
     license = "MIT",
     packages=["denovoFilter"],
-    install_requires=['pandas >= 0.13.1',
+    install_requires=['pandas >= 0.17.0',
                       'numpy >= 1.6.1',
                       'scipy >= 0.9.0',
                       'intervaltree >= 2.0',