dragon-ml-toolbox 3.5.0__py3-none-any.whl → 3.5.1__py3-none-any.whl

{dragon_ml_toolbox-3.5.0.dist-info → dragon_ml_toolbox-3.5.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 3.5.0
+Version: 3.5.1
 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-3.5.0.dist-info → dragon_ml_toolbox-3.5.1.dist-info}/RECORD

@@ -1,6 +1,6 @@
-dragon_ml_toolbox-3.5.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-3.5.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=6cfpIeQ6D4Mcs10nkogQrkVyq1T7i2qXjjNHFoUMOyE,1892
-ml_tools/ETL_engineering.py,sha256=9dojA9RqE7bq1A70tegsERszoqll7UmcJelVeQeefik,39519
+dragon_ml_toolbox-3.5.1.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-3.5.1.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=6cfpIeQ6D4Mcs10nkogQrkVyq1T7i2qXjjNHFoUMOyE,1892
+ml_tools/ETL_engineering.py,sha256=URol7s45fVIdLqnhyOU1Etbi-D7MksFg-qtNwsKiunY,39488
 ml_tools/GUI_tools.py,sha256=uFx6zIrQZzDPSTtOSHz8ptz-fxZiQz-lXHcrqwuYV_E,20385
 ml_tools/MICE_imputation.py,sha256=ed-YeQkEAeHxTNkWIHs09T4YeYNF0aqAnrUTcdIEp9E,11372
 ml_tools/ML_callbacks.py,sha256=gHZk-lyzAax6iEtG26zHuoobdAZCFJ6BmI6pWoXkOrw,13189
@@ -13,13 +13,13 @@ ml_tools/VIF_factor.py,sha256=4b3HmrrolN7ZIAo16TWwLlExqj_xaa8MxbkXD1xPCys,10295
 ml_tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ml_tools/_particle_swarm_optimization.py,sha256=b_eNNkA89Y40hj76KauivT8KLScH1B9wF2IXptOqkOw,22220
 ml_tools/_pytorch_models.py,sha256=bpWZsrSwCvHJQkR6UfoPpElsMv9AvmiNErNHC8NYB_I,10132
-ml_tools/data_exploration.py,sha256=IkpOyIRPKdu4qKeUdvvMvNPelSVWegNEKMqX3IInmpw,25003
+ml_tools/data_exploration.py,sha256=41q0ux4rsf6ktQDzX1haYOk0iRZzmNucrHRi_rqlNLs,25013
 ml_tools/datasetmaster.py,sha256=N-uwfzWnl_qnoAqjbfS98I1pVNra5u6rhKLdWbFIReA,30122
 ml_tools/ensemble_learning.py,sha256=PPtBBLgLvaYOdY-MlcjXuxWWXf3JQavLNEysFgzjc_s,37470
 ml_tools/handle_excel.py,sha256=lwds7rDLlGSCWiWGI7xNg-Z7kxAepogp0lstSFa0590,12949
 ml_tools/logger.py,sha256=jC4Q2OqmDm8ZO9VpuZqBSWdXryqaJvLscqVJ6caNMOk,6009
 ml_tools/utilities.py,sha256=7cVWXjdxgSoIbZunuxJEOnJDSYp29liYsZexbrVDabs,23132
-dragon_ml_toolbox-3.5.0.dist-info/METADATA,sha256=yxz0lVEDn3k40f3nZk_pocW8WCOXifF6ItuUMJ8LFsM,3273
-dragon_ml_toolbox-3.5.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-3.5.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-3.5.0.dist-info/RECORD,,
+dragon_ml_toolbox-3.5.1.dist-info/METADATA,sha256=F1RicIFxIpnKadElu8EU_k6P0FYKwGPRjHF2YXe9F6E,3273
+dragon_ml_toolbox-3.5.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-3.5.1.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-3.5.1.dist-info/RECORD,,

ml_tools/ETL_engineering.py

@@ -48,13 +48,12 @@ class ColumnCleaner:
     ## Usage Example
 
     ```python
-    phone_rules = {
-        # Matches (123) 456-7890 and reformats to 123-456-7890
-        r'\((\d{3})\)\s*(\d{3})-(\d{4})': r'$1-$2-$3'
+    id_rules = {
+        # Matches 'ID-12345' or 'ID 12345' and reformats to 'ID:12345'
+        r'ID[- ](\d+)': r'ID:$1'
     }
 
-    phone_cleaner = ColumnCleaner(column_name='phone_number', rules=phone_rules)
-
+    id_cleaner = ColumnCleaner(column_name='user_id', rules=id_rules)
     # This object would then be passed to a DataFrameCleaner.
     ```
     """
@@ -529,7 +528,7 @@ class KeywordDummifier:
         
         categorize_expr = categorize_expr.otherwise(None).alias("category")
 
-        temp_df = pl.DataFrame(categorize_expr)
+        temp_df = pl.select(categorize_expr)
         df_with_dummies = temp_df.to_dummies(columns=["category"])
         
         final_columns = []

ml_tools/data_exploration.py

@@ -91,7 +91,7 @@ def drop_zero_only_columns(df: pd.DataFrame, verbose: bool=True) -> pd.DataFrame
             continue
 
         # For numeric columns, check if there's at least one non-zero value.
-        if (column != 0).any():
+        if (column.fillna(0) != 0).any():
             cols_to_keep.append(col_name)
     
     dropped_columns = original_columns - set(cols_to_keep)