upgini 1.2.81a3832.dev5__py3-none-any.whl → 1.2.81a3832.dev7__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.81a3832.dev5"
+__version__ = "1.2.81a3832.dev7"

upgini/features_enricher.py

@@ -1023,12 +1023,12 @@ class FeaturesEnricher(TransformerMixin):
                     self.__log_warning(self.bundle.get("metrics_no_important_free_features"))
                     return None
 
-                maybe_phone_column = self._get_phone_column(self.search_keys)
-                text_features = (
-                    [f for f in self.generate_features if f != maybe_phone_column]
-                    if self.generate_features is not None
-                    else None
-                )
+                text_features = self.generate_features.copy() if self.generate_features else None
+                if text_features:
+                    for renamed, original in columns_renaming.items():
+                        if original in text_features:
+                            text_features.remove(original)
+                            text_features.append(renamed)
 
                 print(self.bundle.get("metrics_start"))
                 with Spinner():
@@ -3092,7 +3092,7 @@ if response.status_code == 200:
             self.__show_selected_features(self.fit_search_keys)
 
             autofe_description = self.get_autofe_features_description()
-            if autofe_description is not None:
+            if autofe_description is not None and len(autofe_description) > 0:
                 self.logger.info(f"AutoFE descriptions: {autofe_description}")
                 self.autofe_features_display_handle = display_html_dataframe(
                     df=autofe_description,
@@ -3934,6 +3934,7 @@ if response.status_code == 200:
                 continue
 
             # Use only important features
+            # If select_features is False, we don't show etalon features in the report
             if (
                 # feature_meta.name in self.fit_generated_features or
                 feature_meta.name == COUNTRY  # constant synthetic column
@@ -4260,12 +4261,13 @@ if response.status_code == 200:
                     display_id=f"features_info_{uuid.uuid4()}",
                 )
 
-                self.data_sources_display_handle = display_html_dataframe(
-                    self.relevant_data_sources,
-                    self._relevant_data_sources_wo_links,
-                    self.bundle.get("relevant_data_sources_header"),
-                    display_id=f"data_sources_{uuid.uuid4()}",
-                )
+                if len(self.relevant_data_sources) > 0:
+                    self.data_sources_display_handle = display_html_dataframe(
+                        self.relevant_data_sources,
+                        self._relevant_data_sources_wo_links,
+                        self.bundle.get("relevant_data_sources_header"),
+                        display_id=f"data_sources_{uuid.uuid4()}",
+                    )
             else:
                 msg = self.bundle.get("features_info_zero_important_features")
                 self.__log_warning(msg, show_support_link=True)

upgini/metrics.py

@@ -18,7 +18,6 @@ from numpy import log1p
 from pandas.api.types import is_numeric_dtype
 from sklearn.metrics import check_scoring, get_scorer, make_scorer, roc_auc_score
 
-# from upgini.utils.blocked_time_series import BlockedTimeSeriesSplit
 from upgini.utils.features_validator import FeaturesValidator
 from upgini.utils.sklearn_ext import cross_validate
 
@@ -100,7 +99,6 @@ LIGHTGBM_REGRESSION_PARAMS = {
     "min_sum_hessian_in_leaf": 0.01,
     "objective": "huber",
     "deterministic": "true",
-    # "force_col_wise": "true",
     "verbosity": -1,
 }
 
@@ -115,12 +113,10 @@ LIGHTGBM_MULTICLASS_PARAMS = {
     "cat_smooth": 18,
     "cat_l2": 8,
     "objective": "multiclass",
-    # "class_weight": "balanced",
     "use_quantized_grad": "true",
     "num_grad_quant_bins": "8",
     "stochastic_rounding": "true",
     "deterministic": "true",
-    # "force_col_wise": "true",
     "verbosity": -1,
 }
 
@@ -131,13 +127,11 @@ LIGHTGBM_BINARY_PARAMS = {
     "max_depth": 5,
     "learning_rate": 0.05,
     "objective": "binary",
-    # "class_weight": "balanced",
     "max_cat_threshold": 80,
     "min_data_per_group": 20,
     "cat_smooth": 18,
     "cat_l2": 8,
     "deterministic": "true",
-    # "force_col_wise": "true",
     "verbosity": -1,
 }
 
@@ -146,34 +140,6 @@ LIGHTGBM_EARLY_STOPPING_ROUNDS = 20
 N_FOLDS = 5
 BLOCKED_TS_TEST_SIZE = 0.2
 
-# NA_VALUES = [
-#     "",
-#     " ",
-#     "   ",
-#     "#n/a",
-#     "#n/a n/a",
-#     "#na",
-#     "-1.#ind",
-#     "-1.#qnan",
-#     "-nan",
-#     "1.#ind",
-#     "1.#qnan",
-#     "n/a",
-#     "na",
-#     "null",
-#     "nan",
-#     "n/a",
-#     "nan",
-#     "none",
-#     "-",
-#     "undefined",
-#     "[[unknown]]",
-#     "[not provided]",
-#     "[unknown]",
-# ]
-
-# NA_REPLACEMENT = "NA"
-
 SUPPORTED_CATBOOST_METRICS = {
     s.upper(): s
     for s in (
@@ -975,7 +941,8 @@ def _get_cat_features(
 
     logger.info(f"Selected categorical features: {cat_features}")
 
-    features_to_encode = list(set(x.select_dtypes(exclude=[np.number, np.datetime64, pd.CategoricalDtype()]).columns))
+    non_encode_features = list(set(x.select_dtypes(exclude=[np.number, np.datetime64, pd.CategoricalDtype()]).columns))
+    features_to_encode = [f for f in cat_features if f not in non_encode_features]
 
     logger.info(f"Features to encode: {features_to_encode}")
 
@@ -1067,12 +1034,3 @@ def _ext_mean_squared_log_error(y_true, y_pred, *, sample_weight=None, multioutp
         multioutput=multioutput,
     )
     return mse if squared else np.sqrt(mse)
-
-
-# def fill_na_cat_features(df: pd.DataFrame, cat_features: List[str]) -> pd.DataFrame:
-#     for c in cat_features:
-#         if c in df.columns:
-#             df[c] = df[c].astype("string").fillna(NA_REPLACEMENT).astype(str)
-#             na_filter = df[c].str.lower().isin(NA_VALUES)
-#             df.loc[na_filter, c] = NA_REPLACEMENT
-#     return df

upgini/utils/display_utils.py

@@ -92,9 +92,9 @@ def display_html_dataframe(
     if table_tsv is not None:
         copy_and_share = f"""
             <div style="text-align: right">
-                <button onclick=navigator.clipboard.writeText(decodeURI('{table_tsv}'))>\U0001F4C2 Copy</button>
+                <button onclick=navigator.clipboard.writeText(decodeURI('{table_tsv}'))>\U0001f4c2 Copy</button>
                 <a href='mailto:<Share with...>?subject={email_subject}&body={table_tsv}'>
-                    <button>\U0001F4E8 Share</button>
+                    <button>\U0001f4e8 Share</button>
                 </a>
             </div>"""
     else:
@@ -112,6 +112,7 @@ def display_html_dataframe(
 
             .upgini-df tbody td {{
                 padding: 0.5em;
+                color: black;
             }}
 
             .upgini-df tbody tr:nth-child(odd) {{
@@ -164,10 +165,12 @@ def make_html_report(
 
     try:
         from importlib.resources import files
-        font_path = files('upgini.utils').joinpath('Roboto-Regular.ttf')
+
+        font_path = files("upgini.utils").joinpath("Roboto-Regular.ttf")
     except Exception:
         from pkg_resources import resource_filename
-        font_path = resource_filename('upgini.utils', 'Roboto-Regular.ttf')
+
+        font_path = resource_filename("upgini.utils", "Roboto-Regular.ttf")
 
     return f"""<html>
         <head>
@@ -274,8 +277,10 @@ def make_html_report(
              if metrics_df is not None
              else ""
             }
-            <h3>Relevant data sources</h3>
-            {make_table(relevant_datasources_df)}
+            {"<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)
@@ -311,7 +316,7 @@ def prepare_and_show_report(
 
 
 def show_button_download_pdf(
-    source: str, title="\U0001F4CA Download PDF report", display_id: Optional[str] = None, display_handle=None
+    source: str, title="\U0001f4ca Download PDF report", display_id: Optional[str] = None, display_handle=None
 ):
     from IPython.display import HTML, display
 

{upgini-1.2.81a3832.dev5.dist-info → upgini-1.2.81a3832.dev7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.81a3832.dev5
+Version: 1.2.81a3832.dev7
 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-1.2.81a3832.dev5.dist-info → upgini-1.2.81a3832.dev7.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=ixqR9YBpWXVR7UIN7EjNA5u0StPom5moacbDEkTJTUs,33
+upgini/__about__.py,sha256=RVMSywROOgx43djBaCB4g_TyIw1r_t2n34999sThuLw,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=aspri7ZAgwkNNUiIgQ1GRXvw8XQii3F4RfNXSrF4wrw,35365
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=JYMZG712gAJbk1iymcm_JB5VaXADtKhI_IuTUdMlmvM,210602
+upgini/features_enricher.py,sha256=WCX50iuq8_hf9AYuEfs_ZWNR7FbFc44zuXg27Z40r2s,210874
 upgini/http.py,sha256=AfaJ3c8z_tK2hZFEehNybDKE0mp1tYcyAP_l0_p8bLQ,43933
 upgini/metadata.py,sha256=Yd6iW2f7Wz6vUkg5uvR4xylN16ANnCKVKqAsAkap7p8,12354
-upgini/metrics.py,sha256=I3ad9pcB2ODf4HNETXtVeM6YA8aymUamWtYA0nvIt7Y,39720
+upgini/metrics.py,sha256=lWFF_dQAWcgI7EOQlTXiLjsAEoPLxNv1PCp_egoKolc,38821
 upgini/search_task.py,sha256=RcvAE785yksWTsTNWuZFVNlk32jHElMoEna1T_C5N8Q,17823
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -53,7 +53,7 @@ upgini/utils/custom_loss_utils.py,sha256=kieNZYBYZm5ZGBltF1F_jOSF4ea6C29rYuCyiDc
 upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
 upgini/utils/datetime_utils.py,sha256=_jq-kn_dGNFfs-DGXcWCGzy9bkplfAjrZ8SsmN28zXc,13535
 upgini/utils/deduplicate_utils.py,sha256=AcMLoObMjhOTQ_fMS1LWy0GKp6WXnZ-FNux_8V3nbZU,8914
-upgini/utils/display_utils.py,sha256=DsBjJ8jEYAh8BPgfAbzq5imoGFV6IACP20PQ78BQCX0,11964
+upgini/utils/display_utils.py,sha256=hAeWEcJtPDg8fAVcMNrNB-azFD2WJp1nvbPAhR7SeP4,12071
 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=Q9HN6A-fvfVD-irFWrmOqqZG9RsUSvh5MTY_k0xu-tE,7287
@@ -70,7 +70,7 @@ upgini/utils/target_utils.py,sha256=LRN840dzx78-wg7ftdxAkp2c1eu8-JDvkACiRThm4HE,
 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-1.2.81a3832.dev5.dist-info/METADATA,sha256=etw4taZHb8GlFA_w6POAXt0Wracb4cM4WNYE0SW6tI8,49172
-upgini-1.2.81a3832.dev5.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.81a3832.dev5.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.81a3832.dev5.dist-info/RECORD,,
+upgini-1.2.81a3832.dev7.dist-info/METADATA,sha256=BrDfaRLGuSFtMudHxPC_sYI8_G9iWzidJO0vIihGtUE,49172
+upgini-1.2.81a3832.dev7.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.81a3832.dev7.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.81a3832.dev7.dist-info/RECORD,,