rgwfuncs 0.0.10__py3-none-any.whl → 0.0.11__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- rgwfuncs/df_lib.py +10 -1
- {rgwfuncs-0.0.10.dist-info → rgwfuncs-0.0.11.dist-info}/METADATA +1 -1
- rgwfuncs-0.0.11.dist-info/RECORD +8 -0
- rgwfuncs-0.0.10.dist-info/RECORD +0 -8
- {rgwfuncs-0.0.10.dist-info → rgwfuncs-0.0.11.dist-info}/LICENSE +0 -0
- {rgwfuncs-0.0.10.dist-info → rgwfuncs-0.0.11.dist-info}/WHEEL +0 -0
- {rgwfuncs-0.0.10.dist-info → rgwfuncs-0.0.11.dist-info}/entry_points.txt +0 -0
- {rgwfuncs-0.0.10.dist-info → rgwfuncs-0.0.11.dist-info}/top_level.txt +0 -0
rgwfuncs/df_lib.py
CHANGED
@@ -1631,18 +1631,27 @@ def union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:
|
|
1631
1631
|
if set(df1.columns) != set(df2.columns):
|
1632
1632
|
raise ValueError("Both DataFrames must have the same columns for a union join")
|
1633
1633
|
|
1634
|
+
# Inspect initial columns
|
1635
|
+
print("Initial df1 columns:", df1.columns)
|
1636
|
+
print("Initial df2 columns:", df2.columns)
|
1637
|
+
|
1634
1638
|
# Drop all-NA columns, if any
|
1635
1639
|
df1_clean = df1.dropna(axis=1, how='all')
|
1636
1640
|
df2_clean = df2.dropna(axis=1, how='all')
|
1637
1641
|
|
1642
|
+
# Inspect resulting columns after dropping all-NA columns
|
1643
|
+
print("Cleaned df1 columns:", df1_clean.columns)
|
1644
|
+
print("Cleaned df2 columns:", df2_clean.columns)
|
1645
|
+
|
1638
1646
|
# Ensure they still have the same columns after dropping all-NA columns
|
1639
1647
|
if set(df1_clean.columns) != set(df2_clean.columns):
|
1640
1648
|
raise ValueError("Both DataFrames must have the same columns after dropping all-NA columns")
|
1641
|
-
|
1649
|
+
|
1642
1650
|
result_df = pd.concat([df1_clean, df2_clean], ignore_index=True).drop_duplicates()
|
1643
1651
|
return result_df
|
1644
1652
|
|
1645
1653
|
|
1654
|
+
|
1646
1655
|
def bag_union_join(df1: pd.DataFrame, df2: pd.DataFrame) -> pd.DataFrame:
|
1647
1656
|
"""
|
1648
1657
|
Perform a bag union join, concatenating the two DataFrames without dropping duplicates.
|
@@ -0,0 +1,8 @@
|
|
1
|
+
rgwfuncs/__init__.py,sha256=BP8Nh8ivyCCz8Ga-21JW3NWInJFOElKoIfRuioJRWbA,1076
|
2
|
+
rgwfuncs/df_lib.py,sha256=N5XCe9LYMIVjh0pg2Xc1i3Md--mdNJyJ5t7NpO9x4-s,63973
|
3
|
+
rgwfuncs-0.0.11.dist-info/LICENSE,sha256=7EI8xVBu6h_7_JlVw-yPhhOZlpY9hP8wal7kHtqKT_E,1074
|
4
|
+
rgwfuncs-0.0.11.dist-info/METADATA,sha256=mqOIwsthIDAdpgtcFt35vW_xc99f2xtu5O_k4_Y-wQY,32059
|
5
|
+
rgwfuncs-0.0.11.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
|
6
|
+
rgwfuncs-0.0.11.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
|
7
|
+
rgwfuncs-0.0.11.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
|
8
|
+
rgwfuncs-0.0.11.dist-info/RECORD,,
|
rgwfuncs-0.0.10.dist-info/RECORD
DELETED
@@ -1,8 +0,0 @@
|
|
1
|
-
rgwfuncs/__init__.py,sha256=BP8Nh8ivyCCz8Ga-21JW3NWInJFOElKoIfRuioJRWbA,1076
|
2
|
-
rgwfuncs/df_lib.py,sha256=RzQRjtIqiXB00xbx5jAyjVz6Gn4C18Qr7shheq0B8M4,63682
|
3
|
-
rgwfuncs-0.0.10.dist-info/LICENSE,sha256=7EI8xVBu6h_7_JlVw-yPhhOZlpY9hP8wal7kHtqKT_E,1074
|
4
|
-
rgwfuncs-0.0.10.dist-info/METADATA,sha256=mbs1IZjuzL9ZV5HGisK1gK9Ub2Mh55rIiUrP1b3Avvw,32059
|
5
|
-
rgwfuncs-0.0.10.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
|
6
|
-
rgwfuncs-0.0.10.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
|
7
|
-
rgwfuncs-0.0.10.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
|
8
|
-
rgwfuncs-0.0.10.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|