upgini 1.2.71a3832.dev13__py3-none-any.whl → 1.2.72a3659.dev1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.71a3832.dev13"
+__version__ = "1.2.72a3659.dev1"

upgini/autofe/vector.py

@@ -1,4 +1,4 @@
-from typing import List, Optional
+from typing import Dict, List, Optional
 
 import pandas as pd
 
@@ -22,3 +22,25 @@ class Sum(PandasOperator, VectorizableMixin):
 
     def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
         return pd.DataFrame(data).T.fillna(0).sum(axis=1)
+
+
+class OnnxModel(PandasOperator):
+    name: str = "onnx"
+    is_vector: bool = True
+    output_type: Optional[str] = "float"
+    model_name: str
+
+    def get_params(self) -> Dict[str, Optional[str]]:
+        res = super().get_params()
+        res.update(
+            {
+                "model_name": self.model_name,
+            }
+        )
+        return res
+
+    # def load_model(self):
+    #     ...
+
+    # def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
+    #     ...

upgini/features_enricher.py

@@ -3250,8 +3250,7 @@ if response.status_code == 200:
     def _validate_eval_set_pair(self, X: pd.DataFrame, eval_pair: Tuple) -> Tuple[pd.DataFrame, pd.Series]:
         if len(eval_pair) != 2:
             raise ValidationError(self.bundle.get("eval_set_invalid_tuple_size").format(len(eval_pair)))
-        eval_X = eval_pair[0]
-        eval_y = eval_pair[1]
+        eval_X, eval_y = eval_pair
 
         if _num_samples(eval_X) == 0:
             raise ValidationError(self.bundle.get("eval_x_is_empty"))

upgini/metrics.py

@@ -8,13 +8,12 @@ from copy import deepcopy
 from dataclasses import dataclass
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
+import lightgbm as lgb
 import numpy as np
 import pandas as pd
 from lightgbm import LGBMClassifier, LGBMRegressor
-import lightgbm as lgb
 from numpy import log1p
 from pandas.api.types import is_numeric_dtype
-# from sklearn.calibration import LabelEncoder
 from sklearn.metrics import check_scoring, get_scorer, make_scorer, roc_auc_score
 from sklearn.preprocessing import OrdinalEncoder
 
@@ -127,7 +126,7 @@ LIGHTGBM_MULTICLASS_PARAMS = {
     "max_cat_threshold": 80,
     "min_data_per_group": 20,
     "cat_smooth": 18,
-    "cat_l2" : 8,
+    "cat_l2": 8,
     "objective": "multiclass",
     "class_weight": "balanced",
     "use_quantized_grad": "true",
@@ -148,7 +147,7 @@ LIGHTGBM_BINARY_PARAMS = {
     "max_cat_threshold": 80,
     "min_data_per_group": 20,
     "cat_smooth": 18,
-    "cat_l2" : 8,
+    "cat_l2": 8,
     "verbosity": -1,
 }
 
@@ -756,7 +755,6 @@ class LightGBMWrapper(EstimatorWrapper):
             logger=logger,
         )
         self.cat_features = None
-        # self.cat_features_encoders = dict()
         self.cat_encoder = None
         self.n_classes = None
 
@@ -768,23 +766,13 @@ class LightGBMWrapper(EstimatorWrapper):
             params["callbacks"] = [lgb.early_stopping(stopping_rounds=LIGHTGBM_EARLY_STOPPING_ROUNDS, verbose=False)]
         self.cat_features = _get_cat_features(x)
         if self.cat_features:
-            params["categorical_feature"] = self.cat_features
-            # params["categorical_feature"] = [x.columns.get_loc(c) for c in self.cat_features] Works
-            # params["categorical_feature"] = "notauto"
-            # params["categorical_feature"] = "name:" + ",".join(self.cat_features)  # Doesn't work
-            # cat_indices = [str(x.columns.get_loc(c)) for c in self.cat_features] Doesn't work
-            # params["categorical_feature"] = ",".join(cat_indices)
-            pass
             x = fill_na_cat_features(x, self.cat_features)
             encoder = OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1)
-            encoded = encoder.fit_transform(x[self.cat_features], y_numpy)
+            encoded = pd.DataFrame(
+                encoder.fit_transform(x[self.cat_features]), columns=self.cat_features, dtype="category"
+            )
             x[self.cat_features] = encoded
             self.cat_encoder = encoder
-        # for feature in self.cat_features:
-        #     encoder = OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1)
-        #     x[feature] = encoder.fit_transform(x[feature])
-        #     self.cat_features_encoders[feature] = encoder
-            # x[feature] = x[feature].astype("category").cat.codes
         if not is_numeric_dtype(y_numpy):
             y_numpy = correct_string_target(y_numpy)
 
@@ -793,19 +781,11 @@ class LightGBMWrapper(EstimatorWrapper):
     def _prepare_to_calculate(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, np.ndarray, dict]:
         x, y_numpy, params = super()._prepare_to_calculate(x, y)
         if self.cat_features is not None:
-            params["categorical_feature"] = self.cat_features
-            # params["categorical_feature"] = [x.columns.get_loc(c) for c in self.cat_features]
-            # params["categorical_feature"] = "notauto"
-            # params["categorical_feature"] = "name:" + ",".join(self.cat_features)  # Doesn't work
-            # cat_indices = [str(x.columns.get_loc(c)) for c in self.cat_features]
-            # params["categorical_feature"] = ",".join(cat_indices)
             x = fill_na_cat_features(x, self.cat_features)
             if self.cat_encoder is not None:
-                x[self.cat_features] = self.cat_encoder.transform(x[self.cat_features])
-            # for feature in self.cat_features:
-            #     encoder = self.cat_features_encoders[feature]
-            #     x[feature] = encoder.transform(x[feature])
-                # x[feature] = x[feature].astype("category").cat.codes
+                x[self.cat_features] = pd.DataFrame(
+                    self.cat_encoder.transform(x[self.cat_features]), columns=self.cat_features, dtype="category"
+                )
         if not is_numeric_dtype(y):
             y_numpy = correct_string_target(y_numpy)
         return x, y_numpy, params

{upgini-1.2.71a3832.dev13.dist-info → upgini-1.2.72a3659.dev1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.71a3832.dev13
+Version: 1.2.72a3659.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-1.2.71a3832.dev13.dist-info → upgini-1.2.72a3659.dev1.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=buorll9F2OX4EgV8VmlIrj09nqmsSmqAG8T8p6hRCls,34
+upgini/__about__.py,sha256=n3Di7UqdUYABUquK0tXIme5xiFjO7fpJ3AKGXnT-Jec,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=lk80Bx9U36lva6T4lPHBFk88ivrpZ-2uwwMwQg0LglE,207023
+upgini/features_enricher.py,sha256=Li1sPihWVkPUPcma8HRbPFwpCqd9V9d2p5zQUgkpdpU,206998
 upgini/http.py,sha256=RvzcShpDXssLs6ycGN8xilkKi8ZV9XGUrrk8bwdUzbw,43607
 upgini/metadata.py,sha256=Yd6iW2f7Wz6vUkg5uvR4xylN16ANnCKVKqAsAkap7p8,12354
-upgini/metrics.py,sha256=ot6AhxfRRTzM-dNApWTvmteLBAmGjD9OyAuKmtUTprE,40630
+upgini/metrics.py,sha256=jobZL_Hg7guufDYH2XdanxgbyJTuC9ZAMZodeptE3I4,39177
 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=l0KdKg-txlZxDSE4hPPfCtfGQofYbl7oaABPr830sPI,667
+upgini/autofe/vector.py,sha256=-aLI4cA5HI2p42Skj4Sfb3XAPAFfbcu7FjukWsxVFdM,1161
 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
@@ -70,7 +70,7 @@ upgini/utils/target_utils.py,sha256=KNFzJta1SpGU4sp07dHKSeVJlDs_9qgD2wcw5YuJfOc,
 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-1.2.71a3832.dev13.dist-info/METADATA,sha256=JdRugxJAMW4KLyRuz7yIX_PqSz_nObynmhkW5-g_lVs,49102
-upgini-1.2.71a3832.dev13.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.71a3832.dev13.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.71a3832.dev13.dist-info/RECORD,,
+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,,