upgini 1.2.121a2__py3-none-any.whl → 1.2.122a1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.121a2"
+__version__ = "1.2.122a1"

upgini/autofe/feature.py

@@ -42,6 +42,9 @@ class Column:
     def get_display_name(self, cache: bool = True, shorten: bool = False, **kwargs) -> str:
         return self.get_columns(**kwargs)[0]
 
+    def reset_display_indices(self) -> "Column":
+        return self
+
     def _unhash(self, feature_name: str) -> str:
         last_component_idx = feature_name.rfind("_")
         if not feature_name.startswith("f_"):
@@ -212,6 +215,13 @@ class Feature:
         self.cached_display_name = None
         return self
 
+    def reset_display_indices(self) -> "Feature":
+        for child in self.children:
+            child.reset_display_indices()
+        self.display_index = None
+        self.cached_display_name = None
+        return self
+
     def infer_type(self, data: pd.DataFrame) -> Union[str, DtypeObj]:
         if self.op.output_type:
             return self.op.output_type

upgini/features_enricher.py

@@ -1028,7 +1028,7 @@ class FeaturesEnricher(TransformerMixin):
                     columns_renaming,
                     _,
                 ) = prepared_data
-                
+
                 gc.collect()
 
                 if fitting_X.shape[1] == 0 and fitting_enriched_X.shape[1] == 0:
@@ -1406,7 +1406,7 @@ class FeaturesEnricher(TransformerMixin):
         self,
         X: pd.DataFrame,
         eval_set: list[tuple[pd.DataFrame, pd.Series]],
-        enriched_eval_set: dict,
+        enriched_eval_set: dict[int, tuple[pd.DataFrame, pd.Series, pd.DataFrame, pd.Series]],
         eval_set_dates: dict[int, pd.Series],
         search_keys: dict[str, SearchKey],
         stability_threshold: float,
@@ -1417,31 +1417,42 @@ class FeaturesEnricher(TransformerMixin):
         # Find latest eval set or earliest if all eval sets are before train set
         date_column = self._get_date_column(search_keys)
 
+        date_converter = DateTimeSearchKeyConverter(
+            date_column, self.date_format, self.logger, self.bundle, generate_cyclical_features=False
+        )
+
+        X = date_converter.convert(X)
+
         x_date = X[date_column].dropna()
-        if not is_numeric_dtype(x_date):
-            x_date = pd.to_datetime(x_date).dt.floor("D").astype(np.int64) / 10**6
-        main_min_date = x_date.min()
+        if len(x_date) == 0:
+            self.logger.warning("Empty date column in X")
+            return []
 
-        for eval_x, _ in eval_set:
-            eval_x_date = eval_x[date_column].dropna()
-            if not is_numeric_dtype(eval_x_date):
-                eval_x[date_column] = pd.to_datetime(eval_x_date).dt.floor("D").astype(np.int64) / 10**6
+        main_min_date = x_date.min()
 
         # Find minimum date for each eval_set and compare with main dataset
         eval_dates = []
         for i, (eval_x, _) in enumerate(eval_set):
-            if date_column in eval_x.columns:
-                if len(eval_x) < 1000:
-                    self.logger.warning(f"Eval_set {i} has less than 1000 rows. It will be ignored for stability check")
-                    continue
-                eval_x_date = eval_x[date_column].dropna()
-                if not is_numeric_dtype(eval_x_date):
-                    eval_x_date = pd.to_datetime(eval_x_date).dt.floor("D").astype(np.int64) / 10**6
-                eval_min_date = eval_x_date.min()
-                eval_max_date = eval_x_date.max()
-                eval_dates.append((i, eval_min_date, eval_max_date))
+            if date_column not in eval_x.columns:
+                self.logger.warning(f"Date column not found in eval_set {i + 1}")
+                continue
+            eval_x = date_converter.convert(eval_x)
+            eval_x_date = eval_x[date_column].dropna()
+            if len(eval_x_date) < 1000:
+                self.logger.warning(f"Eval_set {i} has less than 1000 rows. It will be ignored for stability check")
+                continue
+            if len(enriched_eval_set[i][2]) < 1000:
+                self.logger.warning(
+                    f"Enriched eval_set {i} has less than 1000 rows. It will be ignored for stability check"
+                )
+                continue
+
+            eval_min_date = eval_x_date.min()
+            eval_max_date = eval_x_date.max()
+            eval_dates.append((i, eval_min_date, eval_max_date))
 
         if not eval_dates:
+            self.logger.warning("There are no correct eval_sets for stability check")
             return []
 
         # Check if any eval_set has minimum date >= main dataset minimum date
@@ -1464,10 +1475,7 @@ class FeaturesEnricher(TransformerMixin):
         checking_eval_set_df = checking_eval_set_df.copy()
 
         checking_eval_set_df[date_column] = eval_set_dates[selected_eval_set_idx]
-        if not is_numeric_dtype(checking_eval_set_df[date_column]):
-            checking_eval_set_df[date_column] = (
-                pd.to_datetime(checking_eval_set_df[date_column]).dt.floor("D").astype(np.int64) / 10**6
-            )
+        checking_eval_set_df = date_converter.convert(checking_eval_set_df)
 
         psi_values_sparse = calculate_sparsity_psi(
             checking_eval_set_df, cat_features, date_column, self.logger, model_task_type

upgini/resource_bundle/strings.properties

@@ -155,7 +155,7 @@ target_outliers_warning=We detected {} outliers in your sample.\nExamples of out
     # features validation
 empty_or_contant_features=Columns {} has value with frequency more than 99%, removed from X
 high_cardinality_features=Columns {} has high cardinality (>90% unique values), removed from X
-one_hot_encoded_features=One hot encoded features detected: {}
+one_hot_encoded_features=One hot encoded features detected. Use int encoding for correct results of fit.\n{}
 
     # Dataset validation
 dataset_too_few_rows=X size should be at least {} rows after validation

upgini/utils/features_validator.py

@@ -46,7 +46,7 @@ class FeaturesValidator:
 
         if one_hot_encoded_features:
             msg = bundle.get("one_hot_encoded_features").format(one_hot_encoded_features)
-            self.logger.info(msg)
+            warnings.append(msg)
 
         columns_renaming = columns_renaming or {}
 
@@ -100,18 +100,29 @@ class FeaturesValidator:
     @staticmethod
     def is_one_hot_encoded(series: pd.Series) -> bool:
         try:
-            # Column contains only 0 and 1 (as strings or numbers)
-            series = series.astype(float)
-            if set(series.unique()) != {0.0, 1.0}:
+            # All rows should be the same type
+            if series.apply(lambda x: type(x)).nunique() != 1:
+                return False
+
+            # First, handle string representations of True/False
+            series_copy = series.copy()
+            if series_copy.dtype == "object" or series_copy.dtype == "string":
+                # Convert string representations of boolean values to numeric
+                series_copy = series_copy.astype(str).str.strip().str.lower()
+                series_copy = series_copy.replace({"true": "1", "false": "0"})
+
+            # Column contains only 0 and 1 (as strings or numbers or booleans)
+            series_copy = series_copy.astype(float)
+            if set(series_copy.unique()) != {0.0, 1.0}:
                 return False
 
-            series = series.astype(int)
+            series_copy = series_copy.astype(int)
 
             # Column doesn't contain any NaN, np.NaN, space, null, etc.
-            if not (series.isin([0, 1])).all():
+            if not (series_copy.isin([0, 1])).all():
                 return False
 
-            vc = series.value_counts()
+            vc = series_copy.value_counts()
             # Column should contain both 0 and 1
             if len(vc) != 2:
                 return False

upgini/utils/psi.py

@@ -7,7 +7,6 @@ from typing import Callable, Dict, Optional
 import more_itertools
 import numpy as np
 import pandas as pd
-from pandas.api.types import is_numeric_dtype
 from pydantic import BaseModel
 
 from upgini.metadata import TARGET, ModelTaskType

{upgini-1.2.121a2.dist-info → upgini-1.2.122a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.121a2
+Version: 1.2.122a1
 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-1.2.121a2.dist-info → upgini-1.2.122a1.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=Dv8DzHbPAHs_fY_MACW4HNqnYW7CilejShdVPFkTaYM,26
+upgini/__about__.py,sha256=hzzmPAt8OZIX5YRwSKl5dj9LWowWDEnOpFN5Xq2xARQ,26
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=pQ8JQe0cdygD-W9GefJmfE6bnj4EYzXsjlgWdIS9nS8,31578
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=Du1S72F55cqyKbHT3VGSPnJO3XicWABFVkA2-G3chdA,231696
+upgini/features_enricher.py,sha256=lBaecwDHkKpYWTz8fxs5Q12bDJGPLcDOesCPh0xX96s,231839
 upgini/http.py,sha256=-J_wOpnwVnT0ebPC6sOs6fN3AWtCD0LJLu6nlYmxaqk,44348
 upgini/metadata.py,sha256=VzgtgEbPPtNxTrj9LM5qSDP3DujHwAXqbUSKBjPcb9c,12477
 upgini/metrics.py,sha256=KCPE_apPN-9BIdv6GqASbJVaB_gBcy8wzNApAcyaGo4,46020
@@ -16,7 +16,7 @@ upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/autofe/all_operators.py,sha256=rdjF5eaE4bC6Q4eu_el5Z7ekYt8DjOFermz2bePPbUc,333
 upgini/autofe/binary.py,sha256=oOEECc4nRzZN2tYaiqx8F2XHnfWpk1bVvb7ZkZJ0lO8,7709
 upgini/autofe/date.py,sha256=RvexgrL1_6ISYPVrl9HUQmPgpVSGQsTNv8YhNQWs-5M,11329
-upgini/autofe/feature.py,sha256=b4Ps_sCPui9b4h0K3ya85cfL1SWpLVrlHc40zkKVfAY,16329
+upgini/autofe/feature.py,sha256=2jOdTTnUqdUewznxsveuTLgKcPLPNtFWS0YQsYYBbPk,16622
 upgini/autofe/groupby.py,sha256=IYmQV9uoCdRcpkeWZj_kI3ObzoNCNx3ff3h8sTL01tk,3603
 upgini/autofe/operator.py,sha256=RB3rKMjFi5Cx81RiYXN3OTCuXjmvzmFKQrxn4h0Oclo,5219
 upgini/autofe/unary.py,sha256=FFtvkQaT0cu_zPZ1jCLcsjik-UUh12qQFF3tUW8NqsE,6675
@@ -38,7 +38,7 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 upgini/normalizer/normalize_utils.py,sha256=mDh2mBW3aQMB4EFP2aHbf2dGMVkOcWnp4sKKvKDBh8w,8511
 upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=Kmc6ZHpo0hK-bEQuoQkU0SPIQCnIDYRKqkfN3a_gvRU,29237
+upgini/resource_bundle/strings.properties,sha256=KcXm1Nl6c3zswL91tIbG0DjuuNpzxUdCg1cY9f2-9cg,29283
 upgini/resource_bundle/strings_widget.properties,sha256=gOdqvZWntP2LCza_tyVk1_yRYcG4c04K9sQOAVhF_gw,1577
 upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/sampler/base.py,sha256=Fva2FEhLiNRPZ9Q6uOtJRtRzwsayjv7aphalAZO_4lc,6452
@@ -58,7 +58,7 @@ upgini/utils/display_utils.py,sha256=uSG3JwpwCIgRJXsp-8ktuJ0Dh-WFti7IrRLMUfHfoDc
 upgini/utils/email_utils.py,sha256=pZ2vCfNxLIPUhxr0-OlABNXm12jjU44isBk8kGmqQzA,5277
 upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
 upgini/utils/feature_info.py,sha256=6vihytwKma_TlXtTn4l6Aj4kqlOj0ouLy-yWVV6VUw8,7551
-upgini/utils/features_validator.py,sha256=RAnfX80GBFcz6-SlTSR0DF6BZzf7A7IL8dlIqEoSz_s,4265
+upgini/utils/features_validator.py,sha256=A_3AX7X5u5AH7RLgkTiS6dHxaOiq5vm8w4ijQWLGcMY,4871
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
 upgini/utils/hash_utils.py,sha256=mP2yHyzvDNdpa5g3B4MHzulxBeEz_ZSoGl1YF_VnAyE,5538
 upgini/utils/ip_utils.py,sha256=wmnnwVQdjX9o1cNQw6VQMk6maHhvsq6hNsZBYf9knrw,6585
@@ -66,7 +66,7 @@ upgini/utils/mstats.py,sha256=u3gQVUtDRbyrOQK6V1UJ2Rx1QbkSNYGjXa6m3Z_dPVs,6286
 upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,10432
 upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml6ZcU,1716
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
-upgini/utils/psi.py,sha256=vw8QEktXSx29IiMJMxmDeFU_4lJInJBXt_XL5Muekzo,11114
+upgini/utils/psi.py,sha256=D_DMMBVkU4nwMospTwdMpYzNFACDxhqTuNesDngPwyY,11068
 upgini/utils/sample_utils.py,sha256=xpfYaZ2cYP7I2JrcooVc13QNBFawB81cJRuh38451Q4,15123
 upgini/utils/sklearn_ext.py,sha256=Pcy8sWD6f4YcE5Bu0UmXD4j0ICmXtrT8DJlTArM-_a0,49356
 upgini/utils/sort.py,sha256=8uuHs2nfSMVnz8GgvbOmgMB1PgEIZP1uhmeRFxcwnYw,7039
@@ -74,7 +74,7 @@ upgini/utils/target_utils.py,sha256=GCPn4QeJ83JJ_vyBJ3IhY5fyIRkLC9q9BE59S2FRO1I,
 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-1.2.121a2.dist-info/METADATA,sha256=1XVh2jWKC2I3ElN4ftyEveTny9C1pU5z69Osnp6q7_s,50745
-upgini-1.2.121a2.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.121a2.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.121a2.dist-info/RECORD,,
+upgini-1.2.122a1.dist-info/METADATA,sha256=3pPdEVaYucgJB5Klks339i5-JTM7hJpEZUmZS7dEWi8,50745
+upgini-1.2.122a1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.122a1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.122a1.dist-info/RECORD,,