upgini 1.2.72a3659.dev1__py3-none-any.whl → 1.2.73a3659.dev1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.72a3659.dev1"
+__version__ = "1.2.73a3659.dev1"

upgini/autofe/vector.py

@@ -2,7 +2,7 @@ from typing import Dict, List, Optional
 
 import pandas as pd
 
-from upgini.autofe.operator import PandasOperator, VectorizableMixin
+from upgini.autofe.operator import OperatorRegistry, PandasOperator, VectorizableMixin
 
 
 class Mean(PandasOperator, VectorizableMixin):
@@ -24,11 +24,11 @@ class Sum(PandasOperator, VectorizableMixin):
         return pd.DataFrame(data).T.fillna(0).sum(axis=1)
 
 
-class OnnxModel(PandasOperator):
+class OnnxModel(PandasOperator, metaclass=OperatorRegistry):
     name: str = "onnx"
     is_vector: bool = True
     output_type: Optional[str] = "float"
-    model_name: str
+    model_name: str = ""
 
     def get_params(self) -> Dict[str, Optional[str]]:
         res = super().get_params()

upgini/metrics.py

@@ -19,6 +19,7 @@ from sklearn.preprocessing import OrdinalEncoder
 
 from upgini.utils.features_validator import FeaturesValidator
 from upgini.utils.sklearn_ext import cross_validate
+from upgini.utils.blocked_time_series import BlockedTimeSeriesSplit
 
 try:
     from sklearn.metrics import get_scorer_names
@@ -30,7 +31,7 @@ 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
+from sklearn.model_selection import BaseCrossValidator, TimeSeriesSplit
 
 from upgini.errors import ValidationError
 from upgini.metadata import ModelTaskType
@@ -84,22 +85,6 @@ CATBOOST_MULTICLASS_PARAMS = {
     "auto_class_weights": "Balanced",
 }
 
-LIGHTGBM_PARAMS = {
-    "random_state": DEFAULT_RANDOM_STATE,
-    # "num_leaves": 16,
-    # "n_estimators": 150,
-    # "min_child_weight": 1,
-    "max_depth": 4,
-    "max_cat_threshold": 80,
-    "min_data_per_group": 25,
-    "num_boost_round": 150,
-    "cat_l2": 10,
-    "cat_smooth": 12,
-    "learning_rate": 0.05,
-    "feature_fraction": 1.0,
-    "min_sum_hessian_in_leaf": 0.01,
-}
-
 LIGHTGBM_REGRESSION_PARAMS = {
     "random_state": DEFAULT_RANDOM_STATE,
     "deterministic": True,
@@ -128,7 +113,7 @@ LIGHTGBM_MULTICLASS_PARAMS = {
     "cat_smooth": 18,
     "cat_l2": 8,
     "objective": "multiclass",
-    "class_weight": "balanced",
+    # "class_weight": "balanced",
     "use_quantized_grad": "true",
     "num_grad_quant_bins": "8",
     "stochastic_rounding": "true",
@@ -142,7 +127,7 @@ LIGHTGBM_BINARY_PARAMS = {
     "max_depth": 5,
     "learning_rate": 0.05,
     "objective": "binary",
-    "class_weight": "balanced",
+    # "class_weight": "balanced",
     "deterministic": True,
     "max_cat_threshold": 80,
     "min_data_per_group": 20,
@@ -506,7 +491,8 @@ class EstimatorWrapper:
                 params = _get_add_params(params, add_params)
                 estimator = LightGBMWrapper(LGBMClassifier(**params), **kwargs)
             elif target_type == ModelTaskType.REGRESSION:
-                params = _get_add_params(params, LIGHTGBM_REGRESSION_PARAMS)
+                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:

upgini/utils/target_utils.py

@@ -297,9 +297,9 @@ def balance_undersample_time_series_trunc(
     time_unit_threshold: pd.Timedelta = DEFAULT_TIME_UNIT_THRESHOLD,
     **kwargs,
 ):
-    # Convert date column to datetime
     if id_columns is None:
-        id_columns = [date_column]
+        id_columns = []
+    # Convert date column to datetime
     dates_df = df[id_columns + [date_column]].copy()
     dates_df[date_column] = pd.to_datetime(dates_df[date_column], unit="ms")
 

{upgini-1.2.72a3659.dev1.dist-info → upgini-1.2.73a3659.dev1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.72a3659.dev1
+Version: 1.2.73a3659.dev1
 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-1.2.72a3659.dev1.dist-info → upgini-1.2.73a3659.dev1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=n3Di7UqdUYABUquK0tXIme5xiFjO7fpJ3AKGXnT-Jec,33
+upgini/__about__.py,sha256=P0-IBesoAL5QOV1IF6-YzKS7yS-wDwGyoE_mzzIQ6Lo,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=aspri7ZAgwkNNUiIgQ1GRXvw8XQii3F4RfNXSrF4wrw,35365
@@ -6,7 +6,7 @@ upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
 upgini/features_enricher.py,sha256=Li1sPihWVkPUPcma8HRbPFwpCqd9V9d2p5zQUgkpdpU,206998
 upgini/http.py,sha256=RvzcShpDXssLs6ycGN8xilkKi8ZV9XGUrrk8bwdUzbw,43607
 upgini/metadata.py,sha256=Yd6iW2f7Wz6vUkg5uvR4xylN16ANnCKVKqAsAkap7p8,12354
-upgini/metrics.py,sha256=jobZL_Hg7guufDYH2XdanxgbyJTuC9ZAMZodeptE3I4,39177
+upgini/metrics.py,sha256=a0bY4oTMb-MgB1yC1IuTcEtotKZxAxjgV_QV2Z4V8u4,38988
 upgini/search_task.py,sha256=EuCGp0iCWz2fpuJgN6M47aP_CtIi3Oq9zw78w0mkKiU,17595
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -21,7 +21,7 @@ upgini/autofe/groupby.py,sha256=IYmQV9uoCdRcpkeWZj_kI3ObzoNCNx3ff3h8sTL01tk,3603
 upgini/autofe/operator.py,sha256=EOffJw6vKXpEh5yymqb1RFNJPxGxmnHdFRo9dB5SCFo,4969
 upgini/autofe/unary.py,sha256=yVgPvtfnPSOhrii0YgezddmgWPwyOBCR0JutaIkdTTc,4658
 upgini/autofe/utils.py,sha256=fK1am2_tQj3fL2vDslblye8lmyfWgGIUOX1beYVBz4k,2420
-upgini/autofe/vector.py,sha256=-aLI4cA5HI2p42Skj4Sfb3XAPAFfbcu7FjukWsxVFdM,1161
+upgini/autofe/vector.py,sha256=w7ipoFRvR0BcTYcvJR9EbKc_ycIn9cJ94RLgrgIi4Uc,1212
 upgini/autofe/timeseries/__init__.py,sha256=PGwwDAMwvkXl3el12tXVEmZUgDUvlmIPlXtROm6bD18,738
 upgini/autofe/timeseries/base.py,sha256=rWJqRuFAzTZEsUdWG5s1Vhif9zzRRmalASXvarufRxI,3610
 upgini/autofe/timeseries/cross.py,sha256=BTINVwuZSbm_4NKkVm0FGM68SrvZLENZKXN7-UyvhYI,5319
@@ -66,11 +66,11 @@ upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
 upgini/utils/sklearn_ext.py,sha256=HpaNQaKJisgNE7IZ71n7uswxTj7kbPglU2G3s1sORAc,45042
 upgini/utils/sort.py,sha256=8uuHs2nfSMVnz8GgvbOmgMB1PgEIZP1uhmeRFxcwnYw,7039
-upgini/utils/target_utils.py,sha256=KNFzJta1SpGU4sp07dHKSeVJlDs_9qgD2wcw5YuJfOc,16661
+upgini/utils/target_utils.py,sha256=P0cCVRaakWLydYwFjk3TEaQfr0p0hfsJCvKRD8qcxiE,16650
 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-1.2.72a3659.dev1.dist-info/METADATA,sha256=tuv9DtWEtwHVjoIMPK4LKOvrmaQ3suMZS43JeEcEDiY,49101
-upgini-1.2.72a3659.dev1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.72a3659.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.72a3659.dev1.dist-info/RECORD,,
+upgini-1.2.73a3659.dev1.dist-info/METADATA,sha256=fcp9DYpvz_dYwW0eBieEbIXL40Smn9toZbeACzNdC68,49101
+upgini-1.2.73a3659.dev1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.73a3659.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.73a3659.dev1.dist-info/RECORD,,