upgini 1.2.24a1__py3-none-any.whl → 1.2.25__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.24a1"
+__version__ = "1.2.25"

upgini/features_enricher.py

@@ -3194,9 +3194,8 @@ class FeaturesEnricher(TransformerMixin):
 
         return df
 
-    @staticmethod
     def _add_current_date_as_key(
-        df: pd.DataFrame, search_keys: Dict[str, SearchKey], logger: logging.Logger, bundle: ResourceBundle
+        self, df: pd.DataFrame, search_keys: Dict[str, SearchKey], logger: logging.Logger, bundle: ResourceBundle
     ) -> pd.DataFrame:
         if (
             set(search_keys.values()) == {SearchKey.PHONE}
@@ -3204,9 +3203,7 @@ class FeaturesEnricher(TransformerMixin):
             or set(search_keys.values()) == {SearchKey.HEM}
             or set(search_keys.values()) == {SearchKey.COUNTRY, SearchKey.POSTAL_CODE}
         ):
-            msg = bundle.get("current_date_added")
-            print(msg)
-            logger.warning(msg)
+            self.__log_warning(bundle.get("current_date_added"))
             df[FeaturesEnricher.CURRENT_DATE] = datetime.date.today()
             search_keys[FeaturesEnricher.CURRENT_DATE] = SearchKey.DATE
             converter = DateTimeSearchKeyConverter(FeaturesEnricher.CURRENT_DATE)

upgini/metrics.py

@@ -437,7 +437,8 @@ class EstimatorWrapper:
                                 f"Client cat_feature `{cat_feature}` not found in x columns: {x.columns.to_list()}"
                             )
                     estimator_copy.set_params(
-                        cat_features=[x.columns.get_loc(cat_feature) for cat_feature in cat_features]
+                        # cat_features=[x.columns.get_loc(cat_feature) for cat_feature in cat_features]
+                        cat_features=cat_features
                     )
                 estimator = CatBoostWrapper(**kwargs)
             else:

upgini/resource_bundle/strings.properties

@@ -9,7 +9,7 @@ search_stopped=Search request stopped
 polling_search_task=\nRunning search request, search_id={}
 polling_unregister_information=We'll send email notification once it's completed, just use your personal api_key from profile.upgini.com
 ads_upload_finish=Thank you for your submission!\nWe'll check your data sharing proposal and get back to you
-demo_dataset_info=Demo training dataset detected. Registration for an API key is not required.
+demo_dataset_info=Demo training dataset detected. Registration for an API key is not required.\n
 transform_usage_info=You use Trial access to Upgini data enrichment. Limit for Trial: {} rows. You have already enriched: {} rows.
 transform_usage_warning=You are trying to launch enrichment for {} rows, which will exceed the rest limit {}.
 

upgini/utils/deduplicate_utils.py

@@ -24,7 +24,7 @@ def remove_fintech_duplicates(
     date_format: Optional[str] = None,
     logger: Optional[Logger] = None,
     bundle: ResourceBundle = None,
-) -> tuple[pd.DataFrame, Optional[List[str]]]:
+) -> Tuple[pd.DataFrame, Optional[List[str]]]:
     # Initial checks for target type and date column
     bundle = bundle or get_custom_bundle()
     if logger is None:
@@ -60,7 +60,7 @@ def remove_fintech_duplicates(
 
     warning_messages = []
 
-    def process_df(segment_df: pd.DataFrame, eval_index=0) -> tuple[pd.DataFrame, Optional[str]]:
+    def process_df(segment_df: pd.DataFrame, eval_index=0) -> Tuple[pd.DataFrame, Optional[str]]:
         """Process a subset of the dataset to remove duplicates based on personal keys."""
         # Fast check for duplicates based on personal keys
         if not segment_df[personal_cols].duplicated().any():

upgini/utils/display_utils.py

@@ -4,7 +4,7 @@ import textwrap
 import urllib.parse
 import uuid
 from datetime import datetime, timezone
-from io import BytesIO
+from io import StringIO
 from typing import Callable, List, Optional
 
 import pandas as pd
@@ -150,7 +150,7 @@ def make_html_report(
     search_id: str,
     email: Optional[str] = None,
     search_keys: Optional[List[str]] = None,
-):
+) -> str:
     # relevant_features_df = relevant_features_df.copy()
     # relevant_features_df["Feature name"] = relevant_features_df["Feature name"].apply(
     #     lambda x: "*" + x if x.contains("_autofe_") else x
@@ -161,9 +161,18 @@ def make_html_report(
         """<button type="button">Request a quote</button></a>"""
     )
     relevant_datasources_df.rename(columns={"action": "&nbsp;"}, inplace=True)
+
+    try:
+        from importlib.resources import files
+        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')
+
     return f"""<html>
         <head>
             <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+            <meta charset="UTF-8">
             <style>
                 @page {{
                     size: a4 portrait;
@@ -184,12 +193,14 @@ def make_html_report(
                 }}
 
                 @font-face {{
-                    font-family: "Alice-Regular";
-                    src: url("/fonts/Alice-Regular.ttf") format("truetype");
+                    font-family: "Roboto";
+                    src: url("{font_path}") format("truetype");
                 }}
 
                 body {{
-                    font-family: "Alice-Regular", Arial, sans-serif;
+                    font-family: "Roboto", sans-serif;
+                    font-weight: 400;
+                    font-style: normal;
                 }}
 
                 #header_content {{
@@ -305,8 +316,13 @@ def show_button_download_pdf(
     from IPython.display import HTML, display
 
     file_name = f"upgini-report-{uuid.uuid4()}.pdf"
+
+    # from weasyprint import HTML
+
+    # html = HTML(string=source)
+    # html.write_pdf(file_name)
     with open(file_name, "wb") as output:
-        pisa.CreatePDF(src=BytesIO(source.encode("UTF-8")), dest=output)
+        pisa.CreatePDF(src=StringIO(source), dest=output, encoding="UTF-8")
 
     with open(file_name, "rb") as f:
         b64 = base64.b64encode(f.read())

{upgini-1.2.24a1.dist-info → upgini-1.2.25.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.24a1
+Version: 1.2.25
 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-1.2.24a1.dist-info → upgini-1.2.25.dist-info}/RECORD

@@ -1,13 +1,13 @@
-upgini/__about__.py,sha256=TCYncqb9tQ1P6IPCnFvo0uTWg2scIXJ42Ey9L3G22qo,25
+upgini/__about__.py,sha256=9j001fhDZzLSWs6YCbGQFuK5ERX5EUWz3RKLN8l5JS8,23
 upgini/__init__.py,sha256=M64LwQTBa-5Jz24Zm2h8rWwlKQQ1J8nP7gGgIciS0WU,589
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=iPFiMJtk4HF1ytw9wCQr8H9RfoOKj_TIo8XYZKWgcMc,31331
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=rctS3kRWwTJmU5X203t7sUZ_B40XYVBPeXy_0hPw2Ec,193667
+upgini/features_enricher.py,sha256=V1zzUHYzmhdouZVdoFBbMH1OIqUCqV1p0mIXfcTvj6Y,193614
 upgini/http.py,sha256=21asexflvavydzCOONJDGQBtQanCElrbnqLXakJ9Cu8,42880
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=osmzdNESeh7yP3BZday6N9Q3eaIHfzhhRM1d6NSgcf0,11223
-upgini/metrics.py,sha256=SRTtQyrX_yIlOO1wSfq8R1FFTVABnl0FOYKqlmQEZGo,34536
+upgini/metrics.py,sha256=PoY1fq6XYAHNzn-rmnwRQZjCoVYP5bJNmKhR0ST2Txk,34588
 upgini/search_task.py,sha256=qxUxAD-bed-FpZYmTB_4orW7YJsW_O6a1TcgnZIRFr4,17307
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=h1GViOWzULy5vf6M4dpTJuIk-4V38UCrTY1sb9yLa5I,1594
@@ -30,12 +30,13 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 upgini/normalizer/normalize_utils.py,sha256=Ft2MwSgVoBilXAORAOYAuwPD79GOLfwn4qQE3IUFzzg,7218
 upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=ikL5KvPcJz9fGyVK-xOvvo6LyRfeOey8xXjoq5nnWqU,26667
+upgini/resource_bundle/strings.properties,sha256=l3yg9H17NwCwvfZQyOYTvXbPP6mwdXH_CGlqyxOQVFY,26669
 upgini/resource_bundle/strings_widget.properties,sha256=gOdqvZWntP2LCza_tyVk1_yRYcG4c04K9sQOAVhF_gw,1577
 upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/sampler/base.py,sha256=7GpjYqjOp58vYcJLiX__1R5wjUlyQbxvHJ2klFnup_M,6389
 upgini/sampler/random_under_sampler.py,sha256=TIbm7ATo-bCMF-IiS5sZeDC1ad1SYg0eY_rRmg84yIQ,4024
 upgini/sampler/utils.py,sha256=PYOk3kKSnFlyxcpdtDNLBEEhTB4lO_iP7pQHqeUcmAc,20211
+upgini/utils/Roboto-Regular.ttf,sha256=kqYnZjMRQMpbyLulIChCLSdgYa1XF8GsUIoRi2Gcauw,168260
 upgini/utils/__init__.py,sha256=O_KgzKiJjW3g4NoqZ7lAxUpoHcBi_gze6r3ndEjCH74,842
 upgini/utils/base_search_key_detector.py,sha256=Inc6iGG-VXQdejWFfbekIkZk2ahC4k7CdGqzOkie6Bs,1021
 upgini/utils/blocked_time_series.py,sha256=Uqr3vp4YqNclj2-PzEYqVy763GSXHn86sbpIl1UOB4s,3382
@@ -43,8 +44,8 @@ upgini/utils/country_utils.py,sha256=lY-eXWwFVegdVENFttbvLcgGDjFO17Sex8hd2PyJaRk
 upgini/utils/custom_loss_utils.py,sha256=kieNZYBYZm5ZGBltF1F_jOSF4ea6C29rYuCyiDcqVNY,3857
 upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
 upgini/utils/datetime_utils.py,sha256=a8X4jX2y3-6E7ZNZIG5z61qfzCvsvaNEjR1Bi5KUqfM,11279
-upgini/utils/deduplicate_utils.py,sha256=kINO1KoH8kPRA3JSYogzv4jaUP1Ceguv5etBPtLcsSw,8855
-upgini/utils/display_utils.py,sha256=NGhki1aGMsS8OeI69eLXEpmS_s41k8ojKHQxacJaXiU,11493
+upgini/utils/deduplicate_utils.py,sha256=SMZx9IKIhWI5HqXepfKiQb3uDJrogQZtG6jcWuMo5Z4,8855
+upgini/utils/display_utils.py,sha256=DsBjJ8jEYAh8BPgfAbzq5imoGFV6IACP20PQ78BQCX0,11964
 upgini/utils/email_utils.py,sha256=j0Ug1R_0AnCg1Y92zIZ4XMwvKo3G5_pcOlBN1OH_gZs,5191
 upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
 upgini/utils/features_validator.py,sha256=1Xj2ir5LzzYiX3NH8o88c2J6RTTetaTwu0MhjLTyuvM,3378
@@ -57,7 +58,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=qHzZRmICFbLNCrmVqGkaBcjm91L2ERRZMppci36acV4,10085
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.24a1.dist-info/METADATA,sha256=EUaoN3ViaM5Al2JbZCmR_pZAjslGQQy4Q5IngbvOD3Q,48580
-upgini-1.2.24a1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.24a1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.24a1.dist-info/RECORD,,
+upgini-1.2.25.dist-info/METADATA,sha256=EeYzVMje4sNfeZjoeYf5mF7Y-O8ig75asLBQFWnDI_E,48578
+upgini-1.2.25.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.25.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.25.dist-info/RECORD,,