PyPI - upgini - Versions diffs - 1.2.80__py3-none-any.whl → 1.2.81__py3-none-any.whl - Mend

upgini 1.2.80py3-none-any.whl → 1.2.81py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (16) hide show

upgini/__about__.py +1 -1
upgini/autofe/binary.py +2 -2
upgini/autofe/timeseries/volatility.py +6 -4
upgini/features_enricher.py +155 -91
upgini/http.py +21 -21
upgini/mdc/__init__.py +1 -1
upgini/metadata.py +1 -1
upgini/metrics.py +289 -228
upgini/resource_bundle/strings.properties +1 -1
upgini/search_task.py +1 -0
upgini/utils/display_utils.py +12 -7
upgini/utils/target_utils.py +9 -6
{upgini-1.2.80.dist-info → upgini-1.2.81.dist-info}/METADATA +3 -1
{upgini-1.2.80.dist-info → upgini-1.2.81.dist-info}/RECORD +16 -16
{upgini-1.2.80.dist-info → upgini-1.2.81.dist-info}/WHEEL +0 -0
{upgini-1.2.80.dist-info → upgini-1.2.81.dist-info}/licenses/LICENSE +0 -0

upgini/resource_bundle/strings.properties CHANGED Viewed

@@ -140,7 +140,7 @@ baseline_score_column_not_exists=baseline_score_column {} doesn't exist in input
 baseline_score_column_has_na=baseline_score_column contains NaN. Clear it and and retry
 missing_features_for_transform=Missing some features for transform that were presented on fit: {}
 missing_target_for_transform=Search contains features on target. Please add y to the call and try again
-missing_id_column=Id column {} not found in X
+missing_id_column=Id column {} not found in X: {}
     # target validation
 empty_target=Target is empty in all rows
 # non_numeric_target=Binary target should be numerical type

upgini/search_task.py CHANGED Viewed

@@ -179,6 +179,7 @@ class SearchTask:
                     for f in meta.generated_features
                     for c in f.base_columns
                     if c.ads_definition_id is None
+                    and not c.original_name.endswith("_emb")  # embeddings already added
                 )
         return list(features_for_transform)

upgini/utils/display_utils.py CHANGED Viewed

@@ -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/utils/target_utils.py CHANGED Viewed

@@ -3,7 +3,7 @@ from typing import Callable, List, Optional, Union
 import numpy as np
 import pandas as pd
-from pandas.api.types import is_numeric_dtype, is_bool_dtype
+from pandas.api.types import is_bool_dtype, is_datetime64_any_dtype, is_numeric_dtype
 from upgini.errors import ValidationError
 from upgini.metadata import SYSTEM_RECORD_ID, CVType, ModelTaskType
@@ -14,11 +14,14 @@ from upgini.utils.ts_utils import get_most_frequent_time_unit, trunc_datetime
 TS_MIN_DIFFERENT_IDS_RATIO = 0.2
-def correct_string_target(y: Union[pd.Series, np.ndarray]) -> Union[pd.Series, np.ndarray]:
-    if isinstance(y, pd.Series):
-        return y.astype(str).astype("category").cat.codes
-    elif isinstance(y, np.ndarray):
-        return pd.Series(y).astype(str).astype("category").cat.codes.values
+def prepare_target(y: Union[pd.Series, np.ndarray], target_type: ModelTaskType) -> Union[pd.Series, np.ndarray]:
+    if target_type != ModelTaskType.REGRESSION or (not is_numeric_dtype(y) and not is_datetime64_any_dtype(y)):
+        if isinstance(y, pd.Series):
+            y = y.astype(str).astype("category").cat.codes
+        elif isinstance(y, np.ndarray):
+            y = pd.Series(y).astype(str).astype("category").cat.codes.values
+    return y
 def define_task(

{upgini-1.2.80.dist-info → upgini-1.2.81.dist-info}/METADATA RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.80
+Version: 1.2.81
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -22,6 +22,8 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
 Requires-Python: <3.12,>=3.10
+Requires-Dist: catboost>=1.0.3
+Requires-Dist: category-encoders>=2.8.1
 Requires-Dist: fastparquet>=0.8.1
 Requires-Dist: ipywidgets>=8.1.0
 Requires-Dist: jarowinkler>=2.0.0

{upgini-1.2.80.dist-info → upgini-1.2.81.dist-info}/RECORD RENAMED Viewed

@@ -1,20 +1,20 @@
-upgini/__about__.py,sha256=CoguueQtsTfVbd91MeGXrmsF-vGq7K1xnwf9nFL4qz0,23
+upgini/__about__.py,sha256=Yiy3WTZ3aZz8a-WWP0GOQrsX6GQJWYTfOAenVKHKVFA,23
 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=MQZ01u-7jR8nSTlsyvMzUt-FvsbsBjds2TvQZG5F4vM,208296
-upgini/http.py,sha256=UH7nswcZ221un3O_VW9limCBO5oRsyg1eKUHiVslRPs,43737
-upgini/metadata.py,sha256=Yd6iW2f7Wz6vUkg5uvR4xylN16ANnCKVKqAsAkap7p8,12354
-upgini/metrics.py,sha256=pv3LELb8QObiaKcUco5YUfM_rP2c7hseK2qtjKmjBGk,39378
-upgini/search_task.py,sha256=RcvAE785yksWTsTNWuZFVNlk32jHElMoEna1T_C5N8Q,17823
+upgini/features_enricher.py,sha256=cWbEA2lOt51x62NrLkyxu1G8I4KQo_2aOgqt3Ypyr1M,212819
+upgini/http.py,sha256=AfaJ3c8z_tK2hZFEehNybDKE0mp1tYcyAP_l0_p8bLQ,43933
+upgini/metadata.py,sha256=zt_9k0iQbWXuiRZcel4ORNPdQKt6Ou69ucZD_E1Q46o,12341
+upgini/metrics.py,sha256=3cip0_L6-OFew74KsRwzxJDU6UFq05h2v7IsyHLcMRc,43164
+upgini/search_task.py,sha256=Q5HjBpLIB3OCxAD1zNv5yQ3ZNJx696WCK_-H35_y7Rs,17912
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
 upgini/ads_management/__init__.py,sha256=qzyisOToVRP-tquAJD1PblZhNtMrOB8FiyF9JvfkvgE,50
 upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo-R-nGdw,2648
 upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/autofe/all_operators.py,sha256=rdjF5eaE4bC6Q4eu_el5Z7ekYt8DjOFermz2bePPbUc,333
-upgini/autofe/binary.py,sha256=MnQuFiERpocjCPQUjOljlsq5FE-04GPfwtNjzvfNMyU,7671
+upgini/autofe/binary.py,sha256=oOEECc4nRzZN2tYaiqx8F2XHnfWpk1bVvb7ZkZJ0lO8,7709
 upgini/autofe/date.py,sha256=MM1S-6imNSzCDOhbNnmsc_bwSqUWBcS8vWAdHF8j1kY,11134
 upgini/autofe/feature.py,sha256=G_YgnsauIoaMgByx9JXDPiKc4nqs0pwWZUfvoIGMKxY,15305
 upgini/autofe/groupby.py,sha256=IYmQV9uoCdRcpkeWZj_kI3ObzoNCNx3ff3h8sTL01tk,3603
@@ -29,16 +29,16 @@ upgini/autofe/timeseries/delta.py,sha256=h0YhmI1TlPJnjwFpN_GQxLb6r59DQuucnG5tQAX
 upgini/autofe/timeseries/lag.py,sha256=LfQtg484vuqM0mgY4Wft1swHX_Srq7OKKgZswCXoiXI,1882
 upgini/autofe/timeseries/roll.py,sha256=zADKXU-eYWQnQ5R3am1yEal8uU6Tm0jLAixwPb_aCHg,2794
 upgini/autofe/timeseries/trend.py,sha256=K1_iw2ko_LIUU8YCUgrvN3n0MkHtsi7-63-8x9er1k4,2129
-upgini/autofe/timeseries/volatility.py,sha256=9shUmIKjpWTHVYjj80YBsk0XheBJ9uBuLv5NW9Mchnk,7953
+upgini/autofe/timeseries/volatility.py,sha256=SvZfhM_ZAWCNpTf87WjSnZsnlblARgruDlu4By4Zvhc,8078
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/data_source/data_source_publisher.py,sha256=4S9qwlAklD8vg9tUU_c1pHE2_glUHAh15-wr5hMwKFw,22879
-upgini/mdc/__init__.py,sha256=aM08nIWFc2gWdWUa3_IuEnNND0cQPkBGnYpRMnfFN8k,1019
+upgini/mdc/__init__.py,sha256=iHJlXQg6xRM1-ZOUtaPSJqw5SpQDszvxp4LyqviNLIQ,1027
 upgini/mdc/context.py,sha256=3u1B-jXt7tXEvNcV3qmR9SDCseudnY7KYsLclBdwVLk,1405
 upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 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=o9iLgAJSxXm6mkQgtNwBVQKIRVwLF1__Dn9gSXb1kLY,27953
+upgini/resource_bundle/strings.properties,sha256=GmkTgxowpykuuviubVH5cMF_lNFQJEqfRoBJaj3c72E,27957
 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
@@ -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
@@ -66,11 +66,11 @@ upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
 upgini/utils/sklearn_ext.py,sha256=HpaNQaKJisgNE7IZ71n7uswxTj7kbPglU2G3s1sORAc,45042
 upgini/utils/sort.py,sha256=8uuHs2nfSMVnz8GgvbOmgMB1PgEIZP1uhmeRFxcwnYw,7039
-upgini/utils/target_utils.py,sha256=P0cCVRaakWLydYwFjk3TEaQfr0p0hfsJCvKRD8qcxiE,16650
+upgini/utils/target_utils.py,sha256=LRN840dzx78-wg7ftdxAkp2c1eu8-JDvkACiRThm4HE,16832
 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-1.2.80.dist-info/METADATA,sha256=szsz09LH3Kv4SMNG8Ogut33IDG0Tzqln2JsrLiEXPBc,49091
-upgini-1.2.80.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.80.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.80.dist-info/RECORD,,
+upgini-1.2.81.dist-info/METADATA,sha256=hmVcLcbz9e9wFcV2LkMYnocAlnwAiy6VQKUMxn5IUyE,49162
+upgini-1.2.81.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.81.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.81.dist-info/RECORD,,

{upgini-1.2.80.dist-info → upgini-1.2.81.dist-info}/WHEEL RENAMED Viewed

File without changes

{upgini-1.2.80.dist-info → upgini-1.2.81.dist-info}/licenses/LICENSE RENAMED Viewed

File without changes

upgini 1.2.80__py3-none-any.whl → 1.2.81__py3-none-any.whl

upgini 1.2.80py3-none-any.whl → 1.2.81py3-none-any.whl