upgini 1.1.280.dev1__py3-none-any.whl → 1.1.281__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.280.dev1"
+__version__ = "1.1.281"

upgini/features_enricher.py

@@ -930,6 +930,7 @@ class FeaturesEnricher(TransformerMixin):
                         scoring,
                         groups=groups,
                         text_features=self.generate_features,
+                        has_date=has_date,
                     )
                     metric = wrapper.metric_name
                     multiplier = wrapper.multiplier
@@ -956,6 +957,7 @@ class FeaturesEnricher(TransformerMixin):
                             add_params=custom_loss_add_params,
                             groups=groups,
                             text_features=self.generate_features,
+                            has_date=has_date,
                         )
                         etalon_metric = baseline_estimator.cross_val_predict(
                             fitting_X, y_sorted, self.baseline_score_column
@@ -981,6 +983,7 @@ class FeaturesEnricher(TransformerMixin):
                             add_params=custom_loss_add_params,
                             groups=groups,
                             text_features=self.generate_features,
+                            has_date=has_date,
                         )
                         enriched_metric = enriched_estimator.cross_val_predict(fitting_enriched_X, enriched_y_sorted)
                         self.logger.info(f"Enriched {metric} on train combined features: {enriched_metric}")
@@ -1333,8 +1336,6 @@ class FeaturesEnricher(TransformerMixin):
         excluding_search_keys = list(search_keys.keys())
         if search_keys_for_metrics is not None and len(search_keys_for_metrics) > 0:
             excluding_search_keys = [sk for sk in excluding_search_keys if sk not in search_keys_for_metrics]
-        meta = self._search_task.get_all_features_metadata_v2()
-        zero_importance_client_features = [m.name for m in meta if m.source == "etalon" and m.shap_value == 0.0]
 
         client_features = [
             c
@@ -1344,7 +1345,6 @@ class FeaturesEnricher(TransformerMixin):
                 excluding_search_keys
                 + list(self.fit_dropped_features)
                 + [DateTimeSearchKeyConverter.DATETIME_COL, SYSTEM_RECORD_ID]
-                + zero_importance_client_features
             )
         ]
 
@@ -3720,7 +3720,7 @@ class FeaturesEnricher(TransformerMixin):
                     if y is not None:
                         with open(f"{tmp_dir}/y.pickle", "wb") as y_file:
                             pickle.dump(sample(y, xy_sample_index), y_file)
-                        if eval_set:
+                        if eval_set and _num_samples(eval_set[0][0]) > 0:
                             eval_xy_sample_index = rnd.randint(0, _num_samples(eval_set[0][0]), size=1000)
                             with open(f"{tmp_dir}/eval_x.pickle", "wb") as eval_x_file:
                                 pickle.dump(sample(eval_set[0][0], eval_xy_sample_index), eval_x_file)

upgini/metrics.py

@@ -314,9 +314,17 @@ class EstimatorWrapper:
             metrics_by_fold = cv_results["test_score"]
             self.cv_estimators = cv_results["estimator"]
 
+            self.check_fold_metrics(metrics_by_fold)
+
             metric = np.mean(metrics_by_fold) * self.multiplier
         return self.post_process_metric(metric)
 
+    def check_fold_metrics(self, metrics_by_fold: List[float]):
+        first_metric_sign = 1 if metrics_by_fold[0] >= 0 else -1
+        for metric in metrics_by_fold[1:]:
+            if first_metric_sign * metric < 0:
+                self.logger.warning(f"Sign of metrics differs between folds: {metrics_by_fold}")
+
     def post_process_metric(self, metric: float) -> float:
         if self.metric_name == "GINI":
             metric = 2 * metric - 1
@@ -346,6 +354,7 @@ class EstimatorWrapper:
         text_features: Optional[List[str]] = None,
         add_params: Optional[Dict[str, Any]] = None,
         groups: Optional[List[str]] = None,
+        has_date: Optional[bool] = None,
     ) -> EstimatorWrapper:
         scorer, metric_name, multiplier = _get_scorer(target_type, scoring)
         kwargs = {
@@ -360,6 +369,7 @@ class EstimatorWrapper:
         }
         if estimator is None:
             params = dict()
+            params["has_time"] = has_date
             # if metric_name.upper() in SUPPORTED_CATBOOST_METRICS:
             #     params["eval_metric"] = SUPPORTED_CATBOOST_METRICS[metric_name.upper()]
             if target_type == ModelTaskType.MULTICLASS:
@@ -475,7 +485,7 @@ class CatBoostWrapper(EstimatorWrapper):
 
         # Find rest categorical features
         self.cat_features = _get_cat_features(x, self.text_features, embedding_features)
-        x = fill_na_cat_features(x, self.cat_features)
+        # x = fill_na_cat_features(x, self.cat_features)
         unique_cat_features = []
         for name in self.cat_features:
             # Remove constant categorical features
@@ -525,7 +535,7 @@ class CatBoostWrapper(EstimatorWrapper):
             x, emb_columns = self.group_embeddings(x)
             params["embedding_features"] = emb_columns
         if self.cat_features:
-            x = fill_na_cat_features(x, self.cat_features)
+            # x = fill_na_cat_features(x, self.cat_features)
             params["cat_features"] = self.cat_features
 
         return x, y, params

upgini/utils/display_utils.py

@@ -9,6 +9,7 @@ from typing import Callable, List, Optional
 
 import pandas as pd
 from xhtml2pdf import pisa
+from upgini.__about__ import __version__
 
 
 def ipython_available() -> bool:
@@ -166,12 +167,12 @@ def make_html_report(
                         /*-pdf-frame-border: 1;*/
                     }}
                     @frame content_frame {{
-                        left: 10pt; width: 574pt; top: 50pt; height: 752pt;
+                        left: 10pt; width: 574pt; top: 50pt; height: 742pt;
                         /*-pdf-frame-border: 1;*/
                     }}
                     @frame footer_frame {{
                         -pdf-frame-content: footer_content;
-                        left: 10pt; width: 574pt; top: 802pt; height: 30pt;
+                        left: 10pt; width: 574pt; top: 802pt; height: 40pt;
                         /*-pdf-frame-border: 1;*/
                     }}
                 }}
@@ -234,7 +235,8 @@ def make_html_report(
             <div id="header_content">UPGINI</div>
             <div id="footer_content">
                 © Upgini</br>
-                sales@upgini.com
+                sales@upgini.com</br>
+                Launched by version {__version__}
             </div>
 
             <h1>Data search report</h1>
@@ -257,7 +259,7 @@ def make_html_report(
             }
             <h3>Relevant data sources</h3>
             {make_table(relevant_datasources_df)}
-            <h3>All relevant features. Listing</h3>
+            <h3>All relevant features. Listing ({len(relevant_features_df)} items)</h3>
             {make_table(relevant_features_df, wrap_long_string=25)}
             {"<h3>Description of AutoFE feature names</h3>" + make_table(autofe_descriptions_df, wrap_long_string=25)
              if autofe_descriptions_df is not None

{upgini-1.1.280.dev1.dist-info → upgini-1.1.281.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.280.dev1
+Version: 1.1.281
 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-1.1.280.dev1.dist-info → upgini-1.1.281.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=fqBvvVtpVdYqoxP5L8bSpUZgPbCyY2JajG5HQR_3yeI,29
+upgini/__about__.py,sha256=QXQ0qAoJaXwuS49QdPQRJ572R1Vxd94TndilBoFpK_s,24
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=7TLVVhGtjgx_9yaiaIUK3kZSe_R9wg5dY0d4F5qCGM4,45636
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=Nx5ZgUXvOh6HBuBWZt25kU0fqwG6955X8jSJkTxkq7A,176938
+upgini/features_enricher.py,sha256=J1x1YMoJBWMFWhdvP-_h7X67qEoTcLqkRRMrz8I1XKQ,176885
 upgini/http.py,sha256=khrYSldpY-HbVLCcApfV1BjBFK6Uyuatb4colKybxgY,42301
 upgini/metadata.py,sha256=CFJekYGD7Ep7pRFH7wCEcsXS4bz83do33FNmtcCY9P4,9729
-upgini/metrics.py,sha256=L4LKSMOK9iKFLaJvTBTKk2tQauMgiJqtfrBclM3fBjs,29670
+upgini/metrics.py,sha256=tTXAgjEuoo_vDe4n-R0AFK95IIx_7kugIJJJv2Hr_1o,30128
 upgini/search_task.py,sha256=LtRJ9bCPjMo1gJ-sUDKERhDwGcWKImrzwVFHjkMSQHQ,17071
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=RGg87VweujTNlibgsOuqPLIEiBgIOkuXNVTGuNCD234,1405
@@ -43,7 +43,7 @@ upgini/utils/custom_loss_utils.py,sha256=bLk3uygqkJBaGkyzfO032d72QASae-dDyEURfFe
 upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
 upgini/utils/datetime_utils.py,sha256=-LsDTThsGKsTZ57V1uNiHtLcoTtqktk5tui4WnqggJo,10673
 upgini/utils/deduplicate_utils.py,sha256=6AbARehUCghJZ4PppFtrej2s3gFRruh41MEm6mzakHs,8607
-upgini/utils/display_utils.py,sha256=LKoSwjrE0xgS5_cqVhc2og2CQ1UCZ1nTI2VKboIhoQA,10858
+upgini/utils/display_utils.py,sha256=A2ouB5eiZ-Kyt9ykYxkLQwyoRPrdYeJymwNTiajtFXs,10990
 upgini/utils/email_utils.py,sha256=PLufTO97Pg9PPsNqB9agcM6M98MIxKUgIgNn2mVwSQ0,3520
 upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
 upgini/utils/features_validator.py,sha256=PgKNt5dyqfErTvjtRNNUS9g7GFqHBtAtnsfA-V5UO1A,3307
@@ -56,7 +56,7 @@ upgini/utils/sklearn_ext.py,sha256=c23MGSUVfxLnaDWKAxavHgnOtm5dGKkF3YswdWQcFzs,4
 upgini/utils/target_utils.py,sha256=Y96_PJ5cC-WsEbeqg20v9uqywDQobLoTb-xoP7S3o4E,7807
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.280.dev1.dist-info/METADATA,sha256=PHXQUHQajqAckQJZe8k-vPW5Eq51hEzSfpUKOnctguc,48123
-upgini-1.1.280.dev1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.1.280.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.280.dev1.dist-info/RECORD,,
+upgini-1.1.281.dist-info/METADATA,sha256=l6PW4_vWrlqKTTbhXFb9Qsm9FIYMQH5BrU3Vca5WzKo,48118
+upgini-1.1.281.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.1.281.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.281.dist-info/RECORD,,