upgini 1.2.81a3832.dev7__py3-none-any.whl → 1.2.81a3832.dev9__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.81a3832.dev7"
+__version__ = "1.2.81a3832.dev9"

upgini/features_enricher.py

@@ -1768,10 +1768,10 @@ class FeaturesEnricher(TransformerMixin):
             df = generator.generate(df)
             generated_features.extend(generator.generated_features)
 
-        # normalizer = Normalizer(self.bundle, self.logger)
-        # df, search_keys, generated_features = normalizer.normalize(df, search_keys, generated_features)
-        # columns_renaming = normalizer.columns_renaming
-        columns_renaming = {c: c for c in df.columns}
+        normalizer = Normalizer(self.bundle, self.logger)
+        df, search_keys, generated_features = normalizer.normalize(df, search_keys, generated_features)
+        columns_renaming = normalizer.columns_renaming
+        # columns_renaming = {c: c for c in df.columns}
 
         df, _ = clean_full_duplicates(df, logger=self.logger, bundle=self.bundle)
 
@@ -3881,7 +3881,7 @@ if response.status_code == 200:
         if features_meta is None:
             raise Exception(self.bundle.get("missing_features_meta"))
 
-        return [f.name for f in features_meta if f.type == "categorical" and f.shap_value > 0.0]
+        return [f.name for f in features_meta if f.type == "categorical"]
 
     def __prepare_feature_importances(
         self, trace_id: str, df: pd.DataFrame, updated_shaps: Optional[Dict[str, float]] = None, silent=False

upgini/metrics.py

@@ -6,7 +6,7 @@ import re
 from collections import defaultdict
 from copy import deepcopy
 from dataclasses import dataclass
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union
+from typing import Any, Callable, Dict, List, Literal, Optional, Tuple, Union
 
 import lightgbm as lgb
 import numpy as np
@@ -18,6 +18,7 @@ from numpy import log1p
 from pandas.api.types import is_numeric_dtype
 from sklearn.metrics import check_scoring, get_scorer, make_scorer, roc_auc_score
 
+from upgini.utils.blocked_time_series import BlockedTimeSeriesSplit
 from upgini.utils.features_validator import FeaturesValidator
 from upgini.utils.sklearn_ext import cross_validate
 
@@ -31,7 +32,7 @@ except ImportError:
     available_scorers = SCORERS
 from sklearn.metrics import mean_squared_error
 from sklearn.metrics._regression import _check_reg_targets, check_consistent_length
-from sklearn.model_selection import BaseCrossValidator  # , TimeSeriesSplit
+from sklearn.model_selection import BaseCrossValidator, TimeSeriesSplit  # , TimeSeriesSplit
 
 from upgini.errors import ValidationError
 from upgini.metadata import ModelTaskType
@@ -250,6 +251,8 @@ class _CrossValResults:
 
 
 class EstimatorWrapper:
+    default_estimator: Literal["catboost", "lightgbm"] = "catboost"
+
     def __init__(
         self,
         estimator,
@@ -303,6 +306,8 @@ class EstimatorWrapper:
             else:
                 if x[c].dtype == "category" and x[c].cat.categories.dtype == np.int64:
                     x[c] = x[c].astype(np.int64)
+                elif not is_numeric_dtype(x[c]):
+                    x[c] = x[c].astype(str).astype("category")
 
         if not isinstance(y, pd.Series):
             raise Exception(bundle.get("metrics_unsupported_target_type").format(type(y)))
@@ -352,6 +357,7 @@ class EstimatorWrapper:
             self.logger.info("Calculate baseline GINI on passed baseline_score_column and target")
             metric = roc_auc_score(y, x[baseline_score_column])
         else:
+            self.logger.info(f"Cross validate with estimeator: {self.estimator}")
             cv_results = cross_validate(
                 estimator=self.estimator,
                 x=x,
@@ -458,31 +464,43 @@ class EstimatorWrapper:
             "logger": logger,
         }
         if estimator is None:
-            params = {"has_time": has_date}
-            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_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_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)
-                # if not isinstance(cv, TimeSeriesSplit) and not isinstance(cv, BlockedTimeSeriesSplit):
-                #     params = _get_add_params(params, LIGHTGBM_REGRESSION_PARAMS)
-                # params = _get_add_params(params, add_params)
-                # estimator = LightGBMWrapper(LGBMRegressor(**params), **kwargs)
+            if EstimatorWrapper.default_estimator == "catboost":
+                logger.info("Using CatBoost as default estimator")
+                params = {"has_time": has_date}
+                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)
+                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)
+                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)
+                else:
+                    raise Exception(bundle.get("metrics_unsupported_target_type").format(target_type))
+            elif EstimatorWrapper.default_estimator == "lightgbm":
+                logger.info("Using LightGBM as default estimator")
+                params = {"random_state": DEFAULT_RANDOM_STATE, "verbose": -1}
+                if target_type == ModelTaskType.MULTICLASS:
+                    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, LIGHTGBM_BINARY_PARAMS)
+                    params = _get_add_params(params, add_params)
+                    estimator = LightGBMWrapper(LGBMClassifier(**params), **kwargs)
+                elif target_type == ModelTaskType.REGRESSION:
+                    if not isinstance(cv, TimeSeriesSplit) and not isinstance(cv, BlockedTimeSeriesSplit):
+                        params = _get_add_params(params, LIGHTGBM_REGRESSION_PARAMS)
+                    params = _get_add_params(params, add_params)
+                    estimator = LightGBMWrapper(LGBMRegressor(**params), **kwargs)
+                else:
+                    raise Exception(bundle.get("metrics_unsupported_target_type").format(target_type))
             else:
-                raise Exception(bundle.get("metrics_unsupported_target_type").format(target_type))
+                raise Exception("Unsupported default_estimator. Available: catboost, lightgbm")
         else:
             if hasattr(estimator, "copy"):
                 estimator_copy = estimator.copy()
@@ -490,8 +508,8 @@ class EstimatorWrapper:
                 estimator_copy = deepcopy(estimator)
             kwargs["estimator"] = estimator_copy
             if is_catboost_estimator(estimator):
-                if cat_features is not None:
-                    estimator_copy.set_params(cat_features=cat_features, has_time=has_date)
+                if has_date is not None:
+                    estimator_copy.set_params(has_time=has_date)
                 estimator = CatBoostWrapper(**kwargs)
             else:
                 if isinstance(estimator, (LGBMClassifier, LGBMRegressor)):
@@ -941,8 +959,8 @@ def _get_cat_features(
 
     logger.info(f"Selected categorical features: {cat_features}")
 
-    non_encode_features = list(set(x.select_dtypes(exclude=[np.number, np.datetime64, pd.CategoricalDtype()]).columns))
-    features_to_encode = [f for f in cat_features if f not in non_encode_features]
+    features_to_encode = list(set(x.select_dtypes(exclude=[np.number, np.datetime64, pd.CategoricalDtype()]).columns))
+    features_to_encode = [f for f in cat_features if f in features_to_encode]
 
     logger.info(f"Features to encode: {features_to_encode}")
 

{upgini-1.2.81a3832.dev7.dist-info → upgini-1.2.81a3832.dev9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.81a3832.dev7
+Version: 1.2.81a3832.dev9
 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-1.2.81a3832.dev7.dist-info → upgini-1.2.81a3832.dev9.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=RVMSywROOgx43djBaCB4g_TyIw1r_t2n34999sThuLw,33
+upgini/__about__.py,sha256=wEcwloV3XNyxWA40HLqEb4PIXttvc8pREucBfzAKW0c,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=aspri7ZAgwkNNUiIgQ1GRXvw8XQii3F4RfNXSrF4wrw,35365
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=WCX50iuq8_hf9AYuEfs_ZWNR7FbFc44zuXg27Z40r2s,210874
+upgini/features_enricher.py,sha256=ZSSukaq4_mngCkJyQe-XCssXbH8nOD7ByWfSHi9nypc,210847
 upgini/http.py,sha256=AfaJ3c8z_tK2hZFEehNybDKE0mp1tYcyAP_l0_p8bLQ,43933
 upgini/metadata.py,sha256=Yd6iW2f7Wz6vUkg5uvR4xylN16ANnCKVKqAsAkap7p8,12354
-upgini/metrics.py,sha256=lWFF_dQAWcgI7EOQlTXiLjsAEoPLxNv1PCp_egoKolc,38821
+upgini/metrics.py,sha256=4ehQO8VEebKLiCuBq2LRqC2QbPIqswoe7b1pnR_-zQA,39985
 upgini/search_task.py,sha256=RcvAE785yksWTsTNWuZFVNlk32jHElMoEna1T_C5N8Q,17823
 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=LRN840dzx78-wg7ftdxAkp2c1eu8-JDvkACiRThm4HE,
 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-1.2.81a3832.dev7.dist-info/METADATA,sha256=BrDfaRLGuSFtMudHxPC_sYI8_G9iWzidJO0vIihGtUE,49172
-upgini-1.2.81a3832.dev7.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.81a3832.dev7.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.81a3832.dev7.dist-info/RECORD,,
+upgini-1.2.81a3832.dev9.dist-info/METADATA,sha256=6jP4TJl2tN98P8wuWIBARzrPtZVRT48uPukgTvZOvlA,49172
+upgini-1.2.81a3832.dev9.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.81a3832.dev9.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.81a3832.dev9.dist-info/RECORD,,