upgini 1.2.118__py3-none-any.whl → 1.2.120a1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.118"
+__version__ = "1.2.120a1"

upgini/dataset.py

@@ -694,7 +694,9 @@ class Dataset:
 
     def prepare_uploading_file(self, base_path: str) -> str:
         parquet_file_path = f"{base_path}/{self.dataset_name}.parquet"
+        print("Before saving parquet file")
         self.data.to_parquet(path=parquet_file_path, index=False, compression="gzip", engine="fastparquet")
+        print("After saving parquet file")
         uploading_file_size = Path(parquet_file_path).stat().st_size
         self.logger.info(f"Size of prepared uploading file: {uploading_file_size}. {len(self.data)} rows")
         if uploading_file_size > self.MAX_UPLOADING_FILE_SIZE:

upgini/features_enricher.py

@@ -854,7 +854,7 @@ class FeaturesEnricher(TransformerMixin):
                     raise e
             finally:
                 self.logger.info(f"Transform elapsed time: {time.time() - start_time}")
-            
+
             return result
 
     def calculate_metrics(
@@ -1741,7 +1741,8 @@ class FeaturesEnricher(TransformerMixin):
             c
             for c in (validated_X.columns.to_list() + generated_features)
             if (not self.fit_select_features or c in set(self.feature_names_).union(self.id_columns or []))
-            and c not in (
+            and c
+            not in (
                 excluding_search_keys
                 + list(self.fit_dropped_features)
                 + [DateTimeSearchKeyConverter.DATETIME_COL, SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID]
@@ -2215,7 +2216,8 @@ class FeaturesEnricher(TransformerMixin):
             progress_callback=progress_callback,
             add_fit_system_record_id=True,
         )
-        if enriched_df is None:
+        if enriched_df is None or len(enriched_df) == 0 or len(enriched_df.columns) == 0:
+            self.logger.warning(f"Empty enriched dataframe returned: {enriched_df}, returning None")
             return None
 
         x_columns = [
@@ -2519,7 +2521,7 @@ if response.status_code == 200:
             if len(self.feature_names_) == 0:
                 msg = self.bundle.get("no_important_features_for_transform")
                 self.__log_warning(msg, show_support_link=True)
-                return X, {c: c for c in X.columns}, [], dict()
+                return None, {}, [], self.search_keys
 
             self.__validate_search_keys(self.search_keys, self.search_id)
 
@@ -2527,7 +2529,7 @@ if response.status_code == 200:
                 msg = self.bundle.get("transform_with_paid_features")
                 self.logger.warning(msg)
                 self.__display_support_link(msg)
-                return None, {c: c for c in X.columns}, [], {}
+                return None, {}, [], self.search_keys
 
             features_meta = self._search_task.get_all_features_metadata_v2()
             online_api_features = [fm.name for fm in features_meta if fm.from_online_api and fm.shap_value > 0]
@@ -2550,7 +2552,7 @@ if response.status_code == 200:
                         self.logger.warning(msg)
                         print(msg)
                         show_request_quote_button()
-                        return None, {c: c for c in X.columns}, [], {}
+                        return None, {}, [], {}
                     else:
                         msg = self.bundle.get("transform_usage_info").format(
                             transform_usage.limit, transform_usage.transformed_rows
@@ -2620,14 +2622,33 @@ if response.status_code == 200:
 
             # If there are no external features, we don't call backend on transform
             external_features = [fm for fm in features_meta if fm.shap_value > 0 and fm.source != "etalon"]
-            if not external_features:
+            if len(external_features) == 0:
                 self.logger.warning(
                     "No external features found, returning original dataframe"
                     f" with generated important features: {self.feature_names_}"
                 )
-                filtered_columns = [c for c in self.feature_names_ if c in df.columns]
-                self.logger.warning(f"Filtered columns by existance in dataframe: {filtered_columns}")
-                return df[filtered_columns], columns_renaming, generated_features, search_keys
+                df = df.rename(columns=columns_renaming)
+                generated_features = [columns_renaming.get(c, c) for c in generated_features]
+                search_keys = {columns_renaming.get(c, c): t for c, t in search_keys.items()}
+                selecting_columns = self._selecting_input_and_generated_columns(
+                    validated_Xy, generated_features, keep_input, trace_id
+                )
+                self.logger.warning(f"Filtered columns by existance in dataframe: {selecting_columns}")
+                if add_fit_system_record_id:
+                    df = self._add_fit_system_record_id(
+                        df,
+                        search_keys,
+                        SYSTEM_RECORD_ID,
+                        TARGET,
+                        columns_renaming,
+                        self.id_columns,
+                        self.cv,
+                        self.model_task_type,
+                        self.logger,
+                        self.bundle,
+                    )
+                    selecting_columns.append(SYSTEM_RECORD_ID)
+                return df[selecting_columns], columns_renaming, generated_features, search_keys
 
             # Don't pass all features in backend on transform
             runtime_parameters = self._get_copy_of_runtime_parameters()
@@ -2845,29 +2866,12 @@ if response.status_code == 200:
                 how="left",
             )
 
-            fit_input_columns = [c.originalName for c in self._search_task.get_file_metadata(trace_id).columns]
-            new_columns_on_transform = [c for c in validated_Xy.columns if c not in fit_input_columns]
-
-            selected_generated_features = [
-                c for c in generated_features if not self.fit_select_features or c in self.feature_names_
-            ]
-            if keep_input is True:
-                selected_input_columns = [
-                    c
-                    for c in validated_Xy.columns
-                    if not self.fit_select_features
-                    or c in self.feature_names_
-                    or c in new_columns_on_transform
-                    or c in self.search_keys
-                    or c in (self.id_columns or [])
-                    or c in [EVAL_SET_INDEX, TARGET]  # transform for metrics calculation
-                ]
-            else:
-                selected_input_columns = []
-
-            selecting_columns = selected_input_columns + selected_generated_features
+            selecting_columns = self._selecting_input_and_generated_columns(
+                validated_Xy, generated_features, keep_input, trace_id
+            )
             selecting_columns.extend(
-                c for c in result.columns
+                c
+                for c in result.columns
                 if c in self.feature_names_ and c not in selecting_columns and c not in validated_Xy.columns
             )
             if add_fit_system_record_id:
@@ -2895,6 +2899,35 @@ if response.status_code == 200:
 
             return result, columns_renaming, generated_features, search_keys
 
+    def _selecting_input_and_generated_columns(
+        self,
+        validated_Xy: pd.DataFrame,
+        generated_features: list[str],
+        keep_input: bool,
+        trace_id: str,
+    ):
+        fit_input_columns = [c.originalName for c in self._search_task.get_file_metadata(trace_id).columns]
+        new_columns_on_transform = [c for c in validated_Xy.columns if c not in fit_input_columns]
+
+        selected_generated_features = [
+            c for c in generated_features if not self.fit_select_features or c in self.feature_names_
+        ]
+        if keep_input is True:
+            selected_input_columns = [
+                c
+                for c in validated_Xy.columns
+                if not self.fit_select_features
+                or c in self.feature_names_
+                or c in new_columns_on_transform
+                or c in self.search_keys
+                or c in (self.id_columns or [])
+                or c in [EVAL_SET_INDEX, TARGET]  # transform for metrics calculation
+            ]
+        else:
+            selected_input_columns = []
+
+        return selected_input_columns + selected_generated_features
+
     def __validate_search_keys(self, search_keys: dict[str, SearchKey], search_id: str | None = None):
         if (search_keys is None or len(search_keys) == 0) and self.country_code is None:
             if search_id:
@@ -3727,9 +3760,7 @@ if response.status_code == 200:
             eval_types = validated_eval_X.dtypes
             # Find columns with different types
             diff_cols = [
-                (col, x_types[col], eval_types[col])
-                for col in x_types.index
-                if x_types[col] != eval_types[col]
+                (col, x_types[col], eval_types[col]) for col in x_types.index if x_types[col] != eval_types[col]
             ]
             diff_col_names = [col for col, _, _ in diff_cols]
             # print columns with different types
@@ -3815,9 +3846,7 @@ if response.status_code == 200:
         return Xy[X.columns].copy(), Xy[TARGET].copy()
 
     @staticmethod
-    def _sort_by_system_record_id(
-        X: pd.DataFrame, y: pd.Series, cv: CVType | None
-    ) -> tuple[pd.DataFrame, pd.Series]:
+    def _sort_by_system_record_id(X: pd.DataFrame, y: pd.Series, cv: CVType | None) -> tuple[pd.DataFrame, pd.Series]:
         if cv not in [CVType.time_series, CVType.blocked_time_series]:
             record_id_column = ENTITY_SYSTEM_RECORD_ID if ENTITY_SYSTEM_RECORD_ID in X else SYSTEM_RECORD_ID
             Xy = X.copy()

upgini/http.py

@@ -426,19 +426,26 @@ class _RestClient:
     ) -> SearchTaskResponse:
         api_path = self.INITIAL_SEARCH_URI_FMT_V2
 
+        print("Before getting track metrics")
         track_metrics = get_track_metrics(self.client_ip, self.client_visitorid)
+        print("After getting track metrics")
 
         def open_and_send():
             md5_hash = hashlib.md5()
+            print("Before opening file to calculate hashes")
             with open(file_path, "rb") as file:
                 content = file.read()
                 md5_hash.update(content)
                 digest = md5_hash.hexdigest()
                 metadata_with_md5 = pydantic_copy_method(metadata)(update={"checksumMD5": digest})
+            print("After calculating md5")
 
+            print("Before calculating sha256")
             digest_sha256 = file_hash(file_path)
+            print("After calculating sha256")
             metadata_with_md5 = pydantic_copy_method(metadata_with_md5)(update={"digest": digest_sha256})
 
+            print("Before opening file to send")
             with open(file_path, "rb") as file:
                 files = {
                     "metadata": (
@@ -466,9 +473,12 @@ class _RestClient:
                     )
                 additional_headers = {self.SEARCH_KEYS_HEADER_NAME: ",".join(self.search_keys_meaning_types(metadata))}
 
-                return self._send_post_file_req_v2(
+                print("Before sending request for initial search")
+                response = self._send_post_file_req_v2(
                     api_path, files, trace_id=trace_id, additional_headers=additional_headers
                 )
+                print("After sending request")
+                return response
 
         response = self._with_unauth_retry(open_and_send)
         return SearchTaskResponse(response)

upgini/utils/display_utils.py

@@ -269,19 +269,22 @@ def make_html_report(
                 if search_keys is not None
                 else ""
             }
-            {"<h3>All relevant features. Accuracy after enrichment</h3>" + make_table(metrics_df)
-             if metrics_df is not None
-             else ""
+            {
+                "<h3>All relevant features. Accuracy after enrichment</h3>" + make_table(metrics_df)
+                if metrics_df is not None
+                else ""
             }
-            {"<h3>Relevant data sources</h3>" + make_table(relevant_datasources_df)
-             if len(relevant_datasources_df) > 0
-             else ""
+            {
+                "<h3>Relevant data sources</h3>" + make_table(relevant_datasources_df)
+                if len(relevant_datasources_df) > 0
+                else ""
             }
             <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
-             else ""
+            {
+                "<h3>Description of AutoFE feature names</h3>" + make_table(autofe_descriptions_df, wrap_long_string=25)
+                if autofe_descriptions_df is not None and len(autofe_descriptions_df) > 0
+                else ""
             }
             <p>To buy found data sources, please contact: <a href='mailto:sales@upgini.com'>sales@upgini.com</a></p>
             <p>Best regards, </br><b>Upgini Team</b></p>

{upgini-1.2.118.dist-info → upgini-1.2.120a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.118
+Version: 1.2.120a1
 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-1.2.118.dist-info → upgini-1.2.120a1.dist-info}/RECORD

@@ -1,10 +1,10 @@
-upgini/__about__.py,sha256=q02CtZPV2DVtBrD7C_RFfsbI15l7QGmxfUzcCx5UykM,24
+upgini/__about__.py,sha256=J4ou6xfTwIgzTXi7mnxG9WD4vn49_cFGZVdB8RZEIPM,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/dataset.py,sha256=9xYeqp-Ti3-QcsucyxlDFOHQef6ZQsBX7bOZMCyT2rM,31665
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=zGWU8l6dWZwV1fsQD-j9tTKP9X6mUO9HPnwcGrJFS8o,230596
-upgini/http.py,sha256=-J_wOpnwVnT0ebPC6sOs6fN3AWtCD0LJLu6nlYmxaqk,44348
+upgini/features_enricher.py,sha256=C9pZKusj_QnG9coPVAa1a_88VC-lLR4Tre4uC10yt04,231852
+upgini/http.py,sha256=CzDgSrYH6-R14G0d8xPyLalb-w42fjj9XOHVXh7leyM,44835
 upgini/metadata.py,sha256=VzgtgEbPPtNxTrj9LM5qSDP3DujHwAXqbUSKBjPcb9c,12477
 upgini/metrics.py,sha256=KCPE_apPN-9BIdv6GqASbJVaB_gBcy8wzNApAcyaGo4,46020
 upgini/search_task.py,sha256=SAiUd1AytbA2Q6PSnnztr7oTRKpud1wQZ5YtKjsmQHU,18256
@@ -54,7 +54,7 @@ upgini/utils/custom_loss_utils.py,sha256=kieNZYBYZm5ZGBltF1F_jOSF4ea6C29rYuCyiDc
 upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
 upgini/utils/datetime_utils.py,sha256=UL1ernnawW0LV9mPDpCIc6sFy0HUhFscWVNwfH4V7rI,14366
 upgini/utils/deduplicate_utils.py,sha256=oZEiZeN-A92zwAPysV4OP9hO-niC2RLt-Dhc_hynBTU,11273
-upgini/utils/display_utils.py,sha256=Quzl9hBOruLEMaSkeNKWwI5qrd9Hc5MeGiYG3cOqCzk,11868
+upgini/utils/display_utils.py,sha256=uSG3JwpwCIgRJXsp-8ktuJ0Dh-WFti7IrRLMUfHfoDc,11973
 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
@@ -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-1.2.118.dist-info/METADATA,sha256=fEdGQaho0hyf9dXC_fL1AxuJFI46-zCMvm_U_O6hOec,50743
-upgini-1.2.118.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.118.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.118.dist-info/RECORD,,
+upgini-1.2.120a1.dist-info/METADATA,sha256=Ai4c0bpRvXFgEYB78zVltQNbWv6HpPdc96IAw85kPJI,50745
+upgini-1.2.120a1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.120a1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.120a1.dist-info/RECORD,,