upgini 1.2.68a3832.dev5__py3-none-any.whl → 1.2.68a3832.dev7__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.68a3832.dev5"
+__version__ = "1.2.68a3832.dev7"

upgini/metrics.py

@@ -1,11 +1,11 @@
 from __future__ import annotations
 
-from dataclasses import dataclass
 import inspect
 import logging
 import re
 from collections import defaultdict
 from copy import deepcopy
+from dataclasses import dataclass
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
 import numpy as np
@@ -26,11 +26,8 @@ except ImportError:
     from sklearn.metrics._scorer import SCORERS
 
     available_scorers = SCORERS
-from sklearn.metrics._regression import (
-    _check_reg_targets,
-    check_consistent_length,
-)
 from sklearn.metrics import mean_squared_error
+from sklearn.metrics._regression import _check_reg_targets, check_consistent_length
 from sklearn.model_selection import BaseCrossValidator
 
 from upgini.errors import ValidationError
@@ -101,6 +98,58 @@ LIGHTGBM_PARAMS = {
     "min_sum_hessian_in_leaf": 0.01,
 }
 
+LIGHTGBM_REGRESSION_PARAMS = {
+    "random_state": DEFAULT_RANDOM_STATE,
+    "deterministic": True,
+    "min_gain_to_split": 0.001,
+    "n_estimators": 275,
+    "max_depth": 5,
+    "max_cat_threshold": 80,
+    "min_data_per_group": 25,
+    "cat_l2": 10,
+    "cat_smooth": 12,
+    "learning_rate": 0.05,
+    "feature_fraction": 1.0,
+    "min_sum_hessian_in_leaf": 0.01,
+    "objective": "huber",
+    "verbosity": -1,
+}
+
+LIGHTGBM_MULTICLASS_PARAMS = {
+    "random_state": DEFAULT_RANDOM_STATE,
+    "deterministic": True,
+    "min_gain_to_split": 0.001,
+    "n_estimators": 275,
+    "max_depth": 3,
+    "max_cat_threshold": 80,
+    "min_data_per_group": 25,
+    "cat_l2": 10,
+    "cat_smooth": 12,
+    "learning_rate": 0.25,  # CatBoost 0.25
+    "min_sum_hessian_in_leaf": 0.01,
+    "objective": "softmax",
+    "class_weight": "balanced",  # TODO pass dict with weights for each class
+    "verbosity": -1,
+}
+
+LIGHTGBM_BINARY_PARAMS = {
+    "random_state": DEFAULT_RANDOM_STATE,
+    "deterministic": True,
+    "min_gain_to_split": 0.001,
+    "n_estimators": 275,
+    "max_depth": 5,
+    "max_cat_threshold": 80,
+    "min_data_per_group": 25,
+    "cat_l2": 10,
+    "cat_smooth": 12,
+    "learning_rate": 0.05,
+    "feature_fraction": 1.0,
+    "min_sum_hessian_in_leaf": 0.01,
+    "objective": "binary",
+    "class_weight": "balanced",  # TODO pass dict with weights for each class
+    "verbosity": -1,
+}
+
 N_FOLDS = 5
 BLOCKED_TS_TEST_SIZE = 0.2
 
@@ -220,6 +269,7 @@ SUPPORTED_CATBOOST_METRICS = {
 def is_catboost_estimator(estimator):
     try:
         from catboost import CatBoostClassifier, CatBoostRegressor
+
         return isinstance(estimator, (CatBoostClassifier, CatBoostRegressor))
     except ImportError:
         return False
@@ -441,28 +491,27 @@ class EstimatorWrapper:
         }
         if estimator is None:
             params = {}
-            params["has_time"] = has_date
             # if metric_name.upper() in SUPPORTED_CATBOOST_METRICS:
             #     params["eval_metric"] = SUPPORTED_CATBOOST_METRICS[metric_name.upper()]
             if target_type == ModelTaskType.MULTICLASS:
                 # params = _get_add_params(params, CATBOOST_MULTICLASS_PARAMS)
                 # params = _get_add_params(params, add_params)
                 # estimator = CatBoostWrapper(CatBoostClassifier(**params), **kwargs)
-                params = _get_add_params(params, LIGHTGBM_PARAMS)
+                params = _get_add_params(params, LIGHTGBM_MULTICLASS_PARAMS)
                 params = _get_add_params(params, add_params)
                 estimator = LightGBMWrapper(LGBMClassifier(**params), **kwargs)
             elif target_type == ModelTaskType.BINARY:
                 # params = _get_add_params(params, CATBOOST_BINARY_PARAMS)
                 # params = _get_add_params(params, add_params)
                 # estimator = CatBoostWrapper(CatBoostClassifier(**params), **kwargs)
-                params = _get_add_params(params, LIGHTGBM_PARAMS)
+                params = _get_add_params(params, LIGHTGBM_BINARY_PARAMS)
                 params = _get_add_params(params, add_params)
                 estimator = LightGBMWrapper(LGBMClassifier(**params), **kwargs)
             elif target_type == ModelTaskType.REGRESSION:
                 # params = _get_add_params(params, CATBOOST_REGRESSION_PARAMS)
                 # params = _get_add_params(params, add_params)
                 # estimator = CatBoostWrapper(CatBoostRegressor(**params), **kwargs)
-                params = _get_add_params(params, LIGHTGBM_PARAMS)
+                params = _get_add_params(params, LIGHTGBM_REGRESSION_PARAMS)
                 params = _get_add_params(params, add_params)
                 estimator = LightGBMWrapper(LGBMRegressor(**params), **kwargs)
             else:
@@ -474,15 +523,14 @@ class EstimatorWrapper:
                 estimator_copy = deepcopy(estimator)
             kwargs["estimator"] = estimator_copy
             if is_catboost_estimator(estimator):
+                params["has_time"] = has_date
                 if cat_features is not None:
                     for cat_feature in cat_features:
                         if cat_feature not in x.columns:
                             logger.error(
                                 f"Client cat_feature `{cat_feature}` not found in x columns: {x.columns.to_list()}"
                             )
-                    estimator_copy.set_params(
-                        cat_features=cat_features
-                    )
+                    estimator_copy.set_params(cat_features=cat_features)
                 estimator = CatBoostWrapper(**kwargs)
             else:
                 if isinstance(estimator, (LGBMClassifier, LGBMRegressor)):
@@ -530,8 +578,9 @@ class CatBoostWrapper(EstimatorWrapper):
         x, y, groups, params = super()._prepare_to_fit(x, y)
 
         # Find embeddings
-        from catboost import CatBoostClassifier
         import catboost
+        from catboost import CatBoostClassifier
+
         if hasattr(CatBoostClassifier, "get_embedding_feature_indices"):
             emb_pattern = r"(.+)_emb\d+"
             self.emb_features = [c for c in x.columns if re.match(emb_pattern, c) and is_numeric_dtype(x[c])]
@@ -655,6 +704,7 @@ class CatBoostWrapper(EstimatorWrapper):
     def calculate_shap(self, x: pd.DataFrame, y: pd.Series, estimator) -> Optional[Dict[str, float]]:
         try:
             from catboost import Pool
+
             # Create Pool for fold data, if need (for example, when categorical features are present)
             fold_pool = Pool(
                 x,
@@ -712,6 +762,14 @@ class LightGBMWrapper(EstimatorWrapper):
 
     def _prepare_to_fit(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, pd.Series, np.ndarray, dict]:
         x, y, groups, params = super()._prepare_to_fit(x, y)
+        if self.target_type == ModelTaskType.MULTICLASS:
+            params["num_class"] = y.nunique()
+        emb_pattern = r"(.+)_emb\d+"
+        emb_features = [c for c in x.columns if re.match(emb_pattern, c) and is_numeric_dtype(x[c])]
+        max_bin_by_feature_type = {
+            feature: 63 if feature in emb_features else 255 for feature in x.columns
+        }
+        params["max_bin_by_feature_type"] = max_bin_by_feature_type
         self.cat_features = _get_cat_features(x)
         x = fill_na_cat_features(x, self.cat_features)
         for feature in self.cat_features:
@@ -733,8 +791,8 @@ class LightGBMWrapper(EstimatorWrapper):
 
     def calculate_shap(self, x: pd.DataFrame, y: pd.Series, estimator) -> Optional[Dict[str, float]]:
         try:
-            import shap
             import lightgbm as lgb
+            import shap
 
             if not isinstance(estimator, (lgb.LGBMRegressor, lgb.LGBMClassifier)):
                 return None

{upgini-1.2.68a3832.dev5.dist-info → upgini-1.2.68a3832.dev7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.68a3832.dev5
+Version: 1.2.68a3832.dev7
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

{upgini-1.2.68a3832.dev5.dist-info → upgini-1.2.68a3832.dev7.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=7DKSsnFO8h8_6mNOcY1H-BxP7lm1gyUPvtuFwHwu1x8,33
+upgini/__about__.py,sha256=CR4sN9ZhYNXzf0xJ61KtPk3O9k_pn-EljmzdfIfJyoM,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=1rb6BzyuiQFGVCTDmKL2wox3UFRNjtNaIJOwQnZ801A,34956
@@ -7,7 +7,7 @@ upgini/features_enricher.py,sha256=GXXx14jwf3F26_KrfJ6O40Vcu1hRx5iBjUB_jxy3Xvg,2
 upgini/http.py,sha256=ud0Cp7h0jNeHuuZGpU_1dAAEiabGoJjGxc1X5oeBQr4,43496
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=Jh6YTaS00m_nbaOY_owvlSyn9zgkErkqu8iTr9ZjKI8,12279
-upgini/metrics.py,sha256=0WIe1IQx9vzUK0pVGv3hODBrOL3zaLDybXbs5S_ntvQ,36991
+upgini/metrics.py,sha256=onr-wFpP0idy0SH3Wxv2xnqxT5H5MiP70o44f1PhfFw,38808
 upgini/search_task.py,sha256=qxUxAD-bed-FpZYmTB_4orW7YJsW_O6a1TcgnZIRFr4,17307
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -70,7 +70,7 @@ upgini/utils/target_utils.py,sha256=b1GzO8_gMcwXSZ2v98CY50MJJBzKbWHId_BJGybXfkM,
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.68a3832.dev5.dist-info/METADATA,sha256=DYYPHgDqV3PqCiz7WUUXZs4xnkC3Zh89hX-q5NKsFzk,49149
-upgini-1.2.68a3832.dev5.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.68a3832.dev5.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.68a3832.dev5.dist-info/RECORD,,
+upgini-1.2.68a3832.dev7.dist-info/METADATA,sha256=LZ6mg6092FrqWu_yNWdMKTMgOC9lYclcPCQFLyMQAW0,49149
+upgini-1.2.68a3832.dev7.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.68a3832.dev7.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.68a3832.dev7.dist-info/RECORD,,