upgini 1.1.166a2__py3-none-any.whl → 1.1.168__py3-none-any.whl

upgini/dataset.py

@@ -45,11 +45,11 @@ from upgini.utils.warning_counter import WarningCounter
 
 class Dataset:  # (pd.DataFrame):
     MIN_ROWS_COUNT = 100
-    MAX_ROWS = 300_000
+    MAX_ROWS = 200_000
     FIT_SAMPLE_ROWS = 200_000
     FIT_SAMPLE_THRESHOLD = 200_000
-    FIT_SAMPLE_WITH_EVAL_SET_ROWS = 300_000
-    FIT_SAMPLE_WITH_EVAL_SET_THRESHOLD = 300_000
+    FIT_SAMPLE_WITH_EVAL_SET_ROWS = 200_000
+    FIT_SAMPLE_WITH_EVAL_SET_THRESHOLD = 200_000
     MIN_SAMPLE_THRESHOLD = 20_000
     IMBALANCE_THESHOLD = 0.4
     MIN_TARGET_CLASS_ROWS = 100

upgini/features_enricher.py

@@ -111,6 +111,7 @@ class FeaturesEnricher(TransformerMixin):
     RANDOM_STATE = 42
     CALCULATE_METRICS_THRESHOLD = 50_000_000
     CALCULATE_METRICS_MIN_THRESHOLD = 500
+    GENERATE_FEATURES_LIMIT = 10
     EMPTY_FEATURES_INFO = pd.DataFrame(
         columns=[
             bundle.get("features_info_provider"),
@@ -211,8 +212,8 @@ class FeaturesEnricher(TransformerMixin):
         self.generate_features = generate_features
         self.round_embeddings = round_embeddings
         if generate_features is not None:
-            if len(generate_features) > 2:
-                msg = bundle.get("too_many_generate_features")
+            if len(generate_features) > self.GENERATE_FEATURES_LIMIT:
+                msg = bundle.get("too_many_generate_features").format(self.GENERATE_FEATURES_LIMIT)
                 self.logger.error(msg)
                 raise ValidationError(msg)
             self.runtime_parameters.properties["generate_features"] = ",".join(generate_features)
@@ -1755,7 +1756,7 @@ class FeaturesEnricher(TransformerMixin):
             and len(self._search_task.unused_features_for_generation) > 0
         ):
             unused_features_for_generation = [
-                dataset.columns_renaming.get(col) for col in self._search_task.unused_features_for_generation
+                dataset.columns_renaming.get(col) or col for col in self._search_task.unused_features_for_generation
             ]
             msg = bundle.get("features_not_generated").format(unused_features_for_generation)
             self.logger.warning(msg)

upgini/metrics.py

@@ -8,7 +8,15 @@ from catboost import CatBoostClassifier, CatBoostRegressor
 from lightgbm import LGBMClassifier, LGBMRegressor
 from numpy import log1p
 from pandas.api.types import is_numeric_dtype
-from sklearn.metrics import get_scorer_names, check_scoring, get_scorer, make_scorer
+from sklearn.metrics import check_scoring, get_scorer, make_scorer
+
+try:
+    from sklearn.metrics import get_scorer_names
+    available_scorers = get_scorer_names()
+except ImportError:
+    from sklearn.metrics._scorer import SCORERS
+    available_scorers = SCORERS
+
 from sklearn.metrics._regression import (
     _check_reg_targets,
     check_consistent_length,
@@ -385,7 +393,6 @@ def _get_scorer(target_type: ModelTaskType, scoring: Union[Callable, str, None])
 
     multiplier = 1
     if isinstance(scoring, str):
-        available_scorers = get_scorer_names()
         metric_name = scoring
         if "mean_squared_log_error" == metric_name or "MSLE" == metric_name or "msle" == metric_name:
             scoring = make_scorer(_ext_mean_squared_log_error, greater_is_better=False)

upgini/resource_bundle/strings.properties

@@ -59,7 +59,7 @@ no_connection_to_upgini=No connection to Upgini server https://search.upgini.com
 no_internet_connection=No internet connection from Jupyter server {} to initiate external data search with Upgini service, please try with Google Colab https://colab.research.google.com
 access_denied=Access denied
 unsupported_search_key=Search key {} not supported
-too_many_generate_features=Too many columns passed in `generate_features` argument. Only two columns supported to generate features now
+too_many_generate_features=Too many columns passed in `generate_features` argument. Only {} columns supported to generate features now
 invalid_round_embeddings=Argument `round_embeddings` should be non negative integer
 no_important_features_for_transform=There are no important features for transform. Return input as transformed
 

{upgini-1.1.166a2.dist-info → upgini-1.1.168.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.166a2
+Version: 1.1.168
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.166a2.dist-info → upgini-1.1.168.dist-info}/RECORD

@@ -1,12 +1,12 @@
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=mre6xn44wcC_fg63iLT_kTh4mViZqR9AKRJZAtpQz8Y,2592
-upgini/dataset.py,sha256=ke0Gg-AqmC8GCwKcvAdOZP58Fa5ruAa5rjXyihF-Jqc,45054
+upgini/dataset.py,sha256=GMIebWv9FNFnlLs2XwVzKnQQAaU5VqTKIptCzZUAgBg,45054
 upgini/errors.py,sha256=BqpvfhW2jJW5fa5KXj0alhXatGl-WK4xTl309-QNLp8,959
-upgini/features_enricher.py,sha256=RIAnqg8P_F6T-HY-SunuAJE_heZQLHCHZMUJzEnqdv8,128425
+upgini/features_enricher.py,sha256=ISbksk_4HEGYMQPVbdXz4hujSCEFy4p2ofJZaCaldbU,128529
 upgini/fingerprint.js,sha256=VygVIQlN1v4NGZfjHqtRogOw8zjTnnMNJg_f7M5iGQU,33442
 upgini/http.py,sha256=3gVHdNEYmZfegpImHLN7u5wHoqftqcFEdXxdLonREGE,36326
 upgini/metadata.py,sha256=Oefg-rkA4PsZUHIho_clZcnyZwdtVJ1gXPvEY6oBmpg,5969
-upgini/metrics.py,sha256=KUCl6PK5IGcRbBZUs1drjAYvSubRTMpCQVvyj_SAXxQ,19519
+upgini/metrics.py,sha256=4h6gkfYUdOOJADhMzxGq_yfkF750MTwbcE1xcwEIXAs,19653
 upgini/search_task.py,sha256=-csRukeVPH04f7RLbHHAtxHGOi9_z_2Cf5kIuyTATUY,16434
 upgini/spinner.py,sha256=yhakBaydMNS8E8TRAwTdCMdnWrHeWT0cR1M8c9hP6jA,1157
 upgini/version_validator.py,sha256=rDIncP6BEko4J2F2hUcMOtKm_vZbI4ICWcNcw8hrwM4,1400
@@ -20,7 +20,7 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 upgini/normalizer/phone_normalizer.py,sha256=VIgLXuDuzzjPEXiy_LyDVLZKGaS7-le6Fh6T4D-TQDU,9930
 upgini/resource_bundle/__init__.py,sha256=M7GtS7KPQw9pinz8P2aQWXpSkD2YFwUPVGk1w92Pn84,7888
 upgini/resource_bundle/exceptions.py,sha256=KT-OnqA2J4OTfLjhbEl3KFZM2ci7EOPjqJuY_rXp3vs,622
-upgini/resource_bundle/strings.properties,sha256=z8yGmNCysutwPDOn3azhur_POfrYzDQi9EaV1oC0vV0,22854
+upgini/resource_bundle/strings.properties,sha256=K3EdTMYl-OlXI8LHA4wYi9SOufX9Pwj7XUBMEapA_fk,22853
 upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/sampler/base.py,sha256=X2PVsfZ3Rl7twpFDh5UWyxqY2K_jcMGxZ2NcHLwFRj4,6489
 upgini/sampler/random_under_sampler.py,sha256=whX_f_TtalHH8Seyn_7n3sX_TSiDHeYfALmme9saqDg,4082
@@ -42,8 +42,8 @@ upgini/utils/postal_code_utils.py,sha256=_8CR9tBqsPptQsmMUvnrCAmBaMIQSWH3JfJ4ly3
 upgini/utils/target_utils.py,sha256=cu52icjhDIPpEStHYMXrD2hIl9gzvfnxZr0Ra5osV0k,1616
 upgini/utils/track_info.py,sha256=2IGGyHPXBLhWcLO8-Q-5qir52k_kD6DtdU-sv_Z2hHY,5325
 upgini/utils/warning_counter.py,sha256=vnmdFo5-7GBkU2bK9h_uC0K0Y_wtfcYstxOdeRfacO0,228
-upgini-1.1.166a2.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.166a2.dist-info/METADATA,sha256=guklS-j9m4XFDmc7ep0h2LKTtDeLkVaXW5L2IGiRP6M,47897
-upgini-1.1.166a2.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
-upgini-1.1.166a2.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.166a2.dist-info/RECORD,,
+upgini-1.1.168.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.168.dist-info/METADATA,sha256=ZLuxZdDftGNXmRwHJD-FuTq3D9wGmVP2mCoDEkqo9bE,47895
+upgini-1.1.168.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
+upgini-1.1.168.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.168.dist-info/RECORD,,