mlgear 0.4__py3-none-any.whl → 0.5__py3-none-any.whl

mlgear/cv.py

@@ -51,7 +51,10 @@ def run_cv_model(train, test=None, target=None, model_fn=None, params={}, eval_f
         models[i] = model
         if importances is not None and isinstance(train, pd.DataFrame):
             fold_importance_df = pd.DataFrame()
-            fold_importance_df['feature'] = train.columns.values
+            if params.get('group') is None:
+                fold_importance_df['feature'] = train.columns.values
+            else:
+                fold_importance_df['feature'] = [c for c in train.columns.values if c != params['group']]
             fold_importance_df['importance'] = importances
             fold_importance_df['fold'] = i
             feature_importance_df = pd.concat([feature_importance_df, fold_importance_df], axis=0)

mlgear/models.py

@@ -11,16 +11,13 @@ from mlgear.utils import print_step
 def runLGB(train_X, train_y, test_X=None, test_y=None, test_X2=None, params={}, meta=None, verbose=True):
     if verbose:
         print_step('Prep LGB')
-    d_train = lgb.Dataset(train_X, label=train_y)
-    if test_X is not None:
-        d_valid = lgb.Dataset(test_X, label=test_y)
-        watchlist = [d_train, d_valid]
+
+    if params.get('group'):
+        group = params.pop('group')
     else:
-        watchlist = [d_train]
-    if verbose:
-        print_step('Train LGB')
+        group = None
+
     num_rounds = params.pop('num_rounds')
-    verbose_eval = params.pop('verbose_eval')
     early_stop = None
     if params.get('early_stop'):
         early_stop = params.pop('early_stop')
@@ -37,6 +34,31 @@ def runLGB(train_X, train_y, test_X=None, test_y=None, test_X2=None, params={},
     else:
         feval = None
 
+    if group is None:
+        d_train = lgb.Dataset(train_X, label=train_y)
+    else:
+        d_train = lgb.Dataset(train_X.drop(group, axis=1),
+                              label=train_y,
+                              group=train_X.groupby(group).size().to_numpy())
+
+    if test_X is not None:
+        if group is None:
+            d_valid = lgb.Dataset(test_X, label=test_y)
+        else:
+            d_valid = lgb.Dataset(test_X.drop(group, axis=1),
+                                  label=test_y,
+                                  group=test_X.groupby(group).size().to_numpy()) 
+            test_X = test_X.drop(group, axis=1)
+        watchlist = [d_train, d_valid]
+    else:
+        watchlist = [d_train]
+
+    if test_X2 is not None and group is not None:
+        test_X2 = test_X2.drop(group, axis=1)
+
+    if verbose:
+        print_step('Train LGB')
+
     preds_test_y = []
     preds_test_y2 = []
     for b in range(nbag):
@@ -45,9 +67,7 @@ def runLGB(train_X, train_y, test_X=None, test_y=None, test_X2=None, params={},
                           train_set=d_train,
                           num_boost_round=num_rounds,
                           valid_sets=watchlist,
-                          verbose_eval=verbose_eval,
-                          early_stopping_rounds=early_stop,
-                          categorical_feature=cat_cols,
+                          callbacks=[lgb.early_stopping(stopping_rounds=early_stop)] if early_stop else [],
                           feval=feval)
         if test_X is not None:
             if verbose:
@@ -75,8 +95,7 @@ def get_lgb_feature_importance(train, target, params):
     train_d = lgb.Dataset(train, label=target)
     lgb_params2 = params.copy()
     rounds = lgb_params2.pop('num_rounds', 400)
-    verbose_eval = lgb_params2.pop('verbose_eval', 100)
-    model = lgb.train(lgb_params2, train_d, rounds, valid_sets = [train_d], verbose_eval=verbose_eval)
+    model = lgb.train(lgb_params2, train_d, rounds, valid_sets = [train_d])
     feature_df = pd.DataFrame(sorted(zip(model.feature_importance(), train.columns)),
                                columns=['Value', 'Feature']).sort_values('Value', ascending=False)
     return feature_df

mlgear/utils.py

@@ -14,7 +14,7 @@ def show(df, max_rows=10, max_cols=None, digits=6):
 
 
 def display_column(df, var):
-	if df[var].nunique() > 9 and (df[var].dtype == int or df[var].dtype == float):
+	if df[var].astype(str).nunique() > 9 and (df[var].dtype == int or df[var].dtype == float):
 		print('Mean: {} Median: {} SD: {}'.format(df[var].mean(), df[var].median(), df[var].std()))
 	else:
 		print(df[var].value_counts(normalize=True) * 100)
@@ -36,3 +36,7 @@ def chunk(l, n):
     for i in range(0, len(l), n):
         out.append(l[i:i + n])
     return out
+
+
+def min_max(dat):
+    return (min(dat), max(dat))

{mlgear-0.4.dist-info → mlgear-0.5.dist-info}/METADATA

@@ -1,16 +1,28 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: mlgear
-Version: 0.4
+Version: 0.5
 Summary: Utility scripts for machine learning
-Home-page: https://github.com/peterhurford/mlgear
+License: MIT
 Author: Peter Hurford
 Author-email: peter@peterhurford.com
-License: UNKNOWN
-Platform: UNKNOWN
+Requires-Python: >=3.7,<4.0
 Classifier: Development Status :: 3 - Alpha
-Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: keras
+Requires-Dist: lightgbm
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: scikit-learn
+Project-URL: Repository, https://github.com/peterhurford/mlgear
 Description-Content-Type: text/markdown
 
 ## MLGear
@@ -45,6 +57,23 @@ results = run_cv_model(train, test, target, runLGB, lgb_params, rmse)
 
 ### Installation
 
-`pip3 install mlgear`
+```
+pip install mlgear
+```
+
+For development:
 
+```
+# Install poetry if you don't have it
+pip install poetry
+
+# Install dependencies
+poetry install
+
+# Build the package
+poetry build
+
+# Publish to PyPI
+poetry publish
+```
 

mlgear-0.5.dist-info/RECORD

@@ -0,0 +1,13 @@
+mlgear/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+mlgear/aggregators.py,sha256=k_GGL8zuBqpBKPYR_v14SqPcJyAUalHcQN2o7gjApiw,373
+mlgear/cv.py,sha256=Dk1ajLFITWgu5nQP-R1rpT-KQ9oYaQRhgSYqQi0IwX0,4009
+mlgear/encoders.py,sha256=_NRqTNSdCNhT04Odxa9xRQq7nrr9bTFRwskARx1rgnU,5044
+mlgear/lr_scheduler.py,sha256=S7DlTAWTzAUAQbmzm-yWIWI5r49Htz1jRBQ98IQHdgg,5272
+mlgear/metrics.py,sha256=_zQwjz4X3-vUQEqu2yIfq2w2XnuH8YUSD_M_u6szToo,1188
+mlgear/models.py,sha256=RtvmsjMFoecdce_ikj3fa9cukGdvQEj3Y72hz5Qw-fY,6249
+mlgear/tracker.py,sha256=U2OXm9tjAWSc5B5_-oTvj_YAJdpkU4nsmPE7tH8BSN4,447
+mlgear/utils.py,sha256=I72-qBgiisV1hcoUT5almb8GXwfmhTQgwvP6gl8kJEY,1096
+mlgear-0.5.dist-info/LICENSE.txt,sha256=qkKmWAzXQC3lYVyoucB3x4iW2xnGEmaORCB4ADTAik4,1081
+mlgear-0.5.dist-info/METADATA,sha256=sRhbP8yNadrRqDX3mY1wOKpjbWD2DPnLbwmibEFYvYc,1994
+mlgear-0.5.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
+mlgear-0.5.dist-info/RECORD,,

{mlgear-0.4.dist-info → mlgear-0.5.dist-info}/WHEEL

@@ -1,5 +1,4 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.35.1)
+Generator: poetry-core 2.1.2
 Root-Is-Purelib: true
 Tag: py3-none-any
-

mlgear-0.4.dist-info/RECORD

@@ -1,14 +0,0 @@
-mlgear/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mlgear/aggregators.py,sha256=k_GGL8zuBqpBKPYR_v14SqPcJyAUalHcQN2o7gjApiw,373
-mlgear/cv.py,sha256=6gHFOVHcisu6qs0mYUcHKmCvP4ygWBUnLmUOWBtBQ08,3837
-mlgear/encoders.py,sha256=_NRqTNSdCNhT04Odxa9xRQq7nrr9bTFRwskARx1rgnU,5044
-mlgear/lr_scheduler.py,sha256=S7DlTAWTzAUAQbmzm-yWIWI5r49Htz1jRBQ98IQHdgg,5272
-mlgear/metrics.py,sha256=_zQwjz4X3-vUQEqu2yIfq2w2XnuH8YUSD_M_u6szToo,1188
-mlgear/models.py,sha256=6X2VA7On6ioPFHDbB9YTbO3pXlI71GGJb-PhVK8nddY,5740
-mlgear/tracker.py,sha256=U2OXm9tjAWSc5B5_-oTvj_YAJdpkU4nsmPE7tH8BSN4,447
-mlgear/utils.py,sha256=E8lb0gsTf4tun7PHUQ5GFxwwxY3ZRxwIMzNCTZCb1rM,1032
-mlgear-0.4.dist-info/LICENSE.txt,sha256=qkKmWAzXQC3lYVyoucB3x4iW2xnGEmaORCB4ADTAik4,1081
-mlgear-0.4.dist-info/METADATA,sha256=mQSNZAZRZBNO1IU7EiifAN0w4u9ECVVkvKgl2TejG8o,1309
-mlgear-0.4.dist-info/WHEEL,sha256=EVRjI69F5qVjm_YgqcTXPnTAv3BfSUr0WVAHuSP3Xoo,92
-mlgear-0.4.dist-info/top_level.txt,sha256=TM51_lbw1nIKS5TvY-qVQEBGw1tMrgBKGUcB5BISu-Y,7
-mlgear-0.4.dist-info/RECORD,,

mlgear-0.4.dist-info/top_level.txt

@@ -1 +0,0 @@
-mlgear