dragon-ml-toolbox 10.12.0__py3-none-any.whl → 10.12.1__py3-none-any.whl

{dragon_ml_toolbox-10.12.0.dist-info → dragon_ml_toolbox-10.12.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 10.12.0
+Version: 10.12.1
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-10.12.0.dist-info → dragon_ml_toolbox-10.12.1.dist-info}/RECORD

@@ -1,6 +1,6 @@
-dragon_ml_toolbox-10.12.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-10.12.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
-ml_tools/ETL_cleaning.py,sha256=lSP5q6-ukGhJBPV8dlsqJvPXAzj4du_0J-SbtEd0Pjg,19292
+dragon_ml_toolbox-10.12.1.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-10.12.1.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
+ml_tools/ETL_cleaning.py,sha256=mkbcSTBspGWnHQUAj6hNqJdZ4VXLPFNk1qEY-8rmnZ8,19368
 ml_tools/ETL_engineering.py,sha256=a6KCWH6kRatZtjaFEF_o917ApPMK5_vRD-BjfCDAl-E,49400
 ml_tools/GUI_tools.py,sha256=kEQWg-bog3pB5tI22gMGKWaCGHnz9TB2Lvvfhf5F2CI,45412
 ml_tools/MICE_imputation.py,sha256=kVSythWfxJFR4-2mtcYCWQaQ1Oz5yyx_SJu5gjnS7H8,11670
@@ -30,7 +30,7 @@ ml_tools/keys.py,sha256=FDpbS3Jb0pjrVvvp2_8nZi919mbob_-xwuy5OOtKM_A,1848
 ml_tools/optimization_tools.py,sha256=P3I6lIpvZ8Xf2kX5FvvBKBmrK2pB6idBpkTzfUJxTeE,5073
 ml_tools/path_manager.py,sha256=ke0MYOhYheRPX599GUbrvRsYHn2JKUmMDldS5LP6LQA,18431
 ml_tools/utilities.py,sha256=uheMUjQJ1zI69gASsE-mCq4KlRPVGgrgqson02rGNYM,30755
-dragon_ml_toolbox-10.12.0.dist-info/METADATA,sha256=dgxB7Ad4a5Zf1CPzLZFo5ny2Siotmsm2mWjQ8B7Nsa4,6969
-dragon_ml_toolbox-10.12.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-10.12.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-10.12.0.dist-info/RECORD,,
+dragon_ml_toolbox-10.12.1.dist-info/METADATA,sha256=UIbMyYOgyuJjl1XBoVwWEYg_P-FQQJJmuLsrRNz4Mb4,6969
+dragon_ml_toolbox-10.12.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-10.12.1.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-10.12.1.dist-info/RECORD,,

ml_tools/ETL_cleaning.py

@@ -142,8 +142,8 @@ def _cleaner_core(df_in: pl.DataFrame) -> pl.DataFrame:
         r'[°˚]': '',
         
         # Replace special characters in entries
-        r'\\': '-',
-        '/': '-',
+        r'\\': '_',
+        # '/': '_', # keep forward slash 
         
         # Typographical standardization
         # Unify various dashes and hyphens to a standard hyphen
@@ -157,6 +157,8 @@ def _cleaner_core(df_in: pl.DataFrame) -> pl.DataFrame:
         r'\.{2,}': '.',      # Replace two or more dots with a single dot
         r'\?{2,}': '?',      # Replace two or more question marks with a single question mark
         r'!{2,}': '!',      # Replace two or more exclamation marks with a single one
+        r';{2,}': ';',
+        r'-{2,}': '-',
 
         # 2. Internal Whitespace Consolidation
         # Collapse any sequence of whitespace chars (including non-breaking spaces) to a single space
@@ -168,7 +170,7 @@ def _cleaner_core(df_in: pl.DataFrame) -> pl.DataFrame:
         
         # 4. Textual Null Standardization (New Step)
         # Convert common null-like text to actual nulls.
-        r'^(N/A|无|NA|NULL|NONE|NIL|)$': None,
+        r'^(N/A|无|NA|NULL|NONE|NIL|-|\.|;)$': None,
 
         # 5. Final Nullification of Empty Strings
         # After all cleaning, if a string is now empty, convert it to a null