upgini 1.1.197__py3-none-any.whl → 1.1.199__py3-none-any.whl

upgini/features_enricher.py

@@ -13,7 +13,7 @@ from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Union
 
 import numpy as np
 import pandas as pd
-from pandas.api.types import is_string_dtype
+from pandas.api.types import is_numeric_dtype, is_string_dtype
 from scipy.stats import ks_2samp
 from sklearn.base import TransformerMixin
 from sklearn.exceptions import NotFittedError
@@ -946,7 +946,9 @@ class FeaturesEnricher(TransformerMixin):
                         bundle.get("quality_metrics_rows_header"): _num_samples(fitting_X),
                         # bundle.get("quality_metrics_match_rate_header"): self._search_task.initial_max_hit_rate_v2(),
                     }
-                    if model_task_type in [ModelTaskType.BINARY, ModelTaskType.REGRESSION]:
+                    if model_task_type in [ModelTaskType.BINARY, ModelTaskType.REGRESSION] and is_numeric_dtype(
+                        y_sorted
+                    ):
                         train_metrics[bundle.get("quality_metrics_mean_target_header")] = round(y_sorted.mean(), 4)
                     if etalon_metric is not None:
                         train_metrics[bundle.get("quality_metrics_baseline_header").format(metric)] = etalon_metric
@@ -1008,7 +1010,9 @@ class FeaturesEnricher(TransformerMixin):
                                 bundle.get("quality_metrics_rows_header"): _num_samples(eval_X_sorted),
                                 # bundle.get("quality_metrics_match_rate_header"): eval_hit_rate,
                             }
-                            if model_task_type in [ModelTaskType.BINARY, ModelTaskType.REGRESSION]:
+                            if model_task_type in [ModelTaskType.BINARY, ModelTaskType.REGRESSION] and is_numeric_dtype(
+                                eval_y_sorted
+                            ):
                                 eval_metrics[bundle.get("quality_metrics_mean_target_header")] = round(
                                     eval_y_sorted.mean(), 4
                                 )
@@ -1204,7 +1208,7 @@ class FeaturesEnricher(TransformerMixin):
             self.logger.info("No external features selected. So use only input datasets for metrics calculation")
             X_sampled, search_keys = self._extend_x(validated_X, is_demo_dataset)
             y_sampled = validated_y
-            enriched_X = validated_X
+            enriched_X = X_sampled
             if eval_set is not None:
                 for idx in range(len(eval_set)):
                     eval_X_sampled, _ = self._extend_x(eval_set[idx][0], is_demo_dataset)
@@ -2315,7 +2319,7 @@ class FeaturesEnricher(TransformerMixin):
             do_without_pandas_limits(print_datasets_sample)
 
             maybe_date_col = self._get_date_column(self.search_keys)
-            if X is not None and maybe_date_col is not None:
+            if X is not None and maybe_date_col is not None and maybe_date_col in X.columns:
                 min_date = X[maybe_date_col].min()
                 max_date = X[maybe_date_col].max()
                 self.logger.info(f"Dates interval is ({min_date}, {max_date})")

{upgini-1.1.197.dist-info → upgini-1.1.199.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.197
+Version: 1.1.199
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers
@@ -109,7 +109,12 @@ Requires-Dist: ipywidgets (>=8.1.0)
     <td><a href="https://en.wikipedia.org/wiki/Regression_analysis">☑️ regression</a></td>
     <td><a href="https://en.wikipedia.org/wiki/Time_series#Prediction_and_forecasting">☑️ time series prediction</a></td>
   </tr>
-</table>
+</table>   
+
+⭐️ [Simple Drag & Drop Search UI](https://appwidget-uragwvgykrk4sbmropphpy.streamlit.app/~/+/):   
+<a href="https://appwidget-uragwvgykrk4sbmropphpy.streamlit.app/~/+/">
+<img width="710" alt="Drag & Drop Search UI" src="https://github.com/upgini/upgini/assets/95645411/36b6460c-51f3-400e-9f04-445b938bf45e">
+</a>
 
 
 ## 🌎 Connected data sources and coverage

{upgini-1.1.197.dist-info → upgini-1.1.199.dist-info}/RECORD

@@ -2,7 +2,7 @@ upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=mre6xn44wcC_fg63iLT_kTh4mViZqR9AKRJZAtpQz8Y,2592
 upgini/dataset.py,sha256=hqinFMd0x3hMgFqsRohb2GZvGmoEbdSEgvBjD5n5zaM,47346
 upgini/errors.py,sha256=BqpvfhW2jJW5fa5KXj0alhXatGl-WK4xTl309-QNLp8,959
-upgini/features_enricher.py,sha256=JqR2i8iTfd4IGC1vTt15TGeuUWi6MUlXWuXX9fyMIH0,146312
+upgini/features_enricher.py,sha256=b7yCgyyebhftP1D2Hf-XHSYmteJFniZpjqCTdvtUxuE,146535
 upgini/fingerprint.js,sha256=VygVIQlN1v4NGZfjHqtRogOw8zjTnnMNJg_f7M5iGQU,33442
 upgini/http.py,sha256=5t8t9KplLzZQhaoUbxVS-C0-Q78og-aAIUoAn_8dgdw,39538
 upgini/metadata.py,sha256=9Hm9L7efMGIRSfPUYZ_RUBW7_WMeeTL1fGhylMSvR7w,6135
@@ -45,8 +45,8 @@ upgini/utils/sklearn_ext.py,sha256=IMx2La70AXAggApVpT7sMEjWqVWon5AMZt4MARDsIMQ,4
 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-1.1.197.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.197.dist-info/METADATA,sha256=pqdXxn40GXMVJovcA94byupKZwkukr7Q9RpIQX0HEdk,47985
-upgini-1.1.197.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
-upgini-1.1.197.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.197.dist-info/RECORD,,
+upgini-1.1.199.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.199.dist-info/METADATA,sha256=BADcsoeqF6vs1TLz1FX1Q3f6ofqwq-tJqIUzrixJsVQ,48306
+upgini-1.1.199.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
+upgini-1.1.199.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.199.dist-info/RECORD,,