upgini 1.1.244a24__py3-none-any.whl → 1.1.245a1__py3-none-any.whl

upgini/metrics.py

@@ -77,6 +77,7 @@ CATBOOST_MULTICLASS_PARAMS = {
     "verbose": False,
     "random_state": DEFAULT_RANDOM_STATE,
     "allow_writing_files": False,
+    "auto_class_weights": "Balanced",
 }
 
 LIGHTGBM_PARAMS = {

upgini/resource_bundle/__init__.py

@@ -8,7 +8,7 @@ import os
 import re
 from os import PathLike
 from pathlib import Path
-from typing import KeysView, Sequence
+from typing import KeysView, Optional, Sequence
 
 from .exceptions import MalformedResourceBundleError, NotInResourceBundleError
 
@@ -221,3 +221,16 @@ def get_bundle(bundle_name: str, locale: str | Sequence[str | str] = None, path:
 
 
 bundle = ResourceBundle("strings", None, path=os.path.dirname(os.path.realpath(__file__)))
+custom_bundles = dict()
+
+
+def get_custom_bundle(custom_cfg: Optional[str] = None) -> "ResourceBundle":
+    global custom_bundles
+    if custom_cfg is not None:
+        custom_bundle = custom_bundles.get(custom_cfg)
+        if custom_bundle is None:
+            custom_bundle = ResourceBundle("strings", custom_cfg, path=os.path.dirname(os.path.realpath(__file__)))
+            custom_bundles[custom_cfg] = custom_bundle
+        return custom_bundle
+    else:
+        return bundle

upgini/utils/target_utils.py

@@ -7,7 +7,7 @@ from pandas.api.types import is_numeric_dtype
 
 from upgini.errors import ValidationError
 from upgini.metadata import ModelTaskType
-from upgini.resource_bundle import bundle
+from upgini.resource_bundle import ResourceBundle, get_custom_bundle
 
 
 def correct_string_target(y: Union[pd.Series, np.ndarray]) -> Union[pd.Series, np.ndarray]:
@@ -18,8 +18,13 @@ def correct_string_target(y: Union[pd.Series, np.ndarray]) -> Union[pd.Series, n
 
 
 def define_task(
-    y: pd.Series, has_date: bool = False, logger: Optional[logging.Logger] = None, silent: bool = False
+    y: pd.Series,
+    has_date: bool = False,
+    logger: Optional[logging.Logger] = None,
+    silent: bool = False,
+    bundle: Optional[ResourceBundle] = None,
 ) -> ModelTaskType:
+    bundle = bundle or get_custom_bundle()
     if logger is None:
         logger = logging.getLogger()
     target = y.dropna()
@@ -61,6 +66,7 @@ def define_task(
                     task = ModelTaskType.REGRESSION
                 else:
                     task = ModelTaskType.MULTICLASS
+
     logger.info(f"Detected task type: {task}")
     if not silent:
         print(bundle.get("target_type_detected").format(task))

{upgini-1.1.244a24.dist-info → upgini-1.1.245a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.244a24
+Version: 1.1.245a1
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers
@@ -45,8 +45,8 @@ Requires-Dist: ipywidgets (>=8.1.0)
 <!-- <h2 align="center"> <a href="https://upgini.com/">Upgini</a> : low-code feature search and enrichment library for machine learning </h2> -->
 <!-- <h2 align="center"> <a href="https://upgini.com/">Upgini</a> : Free automated data enrichment library for machine learning: </br>only the accuracy improving features in 2 minutes </h2> -->
 <!-- <h2 align="center"> <a href="https://upgini.com/">Upgini</a> • Free production-ready automated data enrichment library for machine learning</h2>--> 
-<h2 align="center"> <a href="https://upgini.com/">Upgini • Intelligent data search & enrichment for Machine Learning</a></h2>
-<p align="center"> <b>Easily find and add relevant features to your ML pipeline from</br> hundreds of public, community and premium external data sources, </br>optimized for ML models with LLMs and other neural networks</b> </p>
+<h2 align="center"> <a href="https://upgini.com/">Upgini • Intelligent data search & enrichment for Machine Learning and AI</a></h2>
+<p align="center"> <b>Easily find and add relevant features to your ML & AI pipeline from</br> hundreds of public, community and premium external data sources, </br>including open & commercial LLMs</b> </p>
 <p align="center">
 	<br />
     <a href="https://colab.research.google.com/github/upgini/upgini/blob/main/notebooks/Upgini_Features_search%26generation.ipynb"><strong>Quick Start in Colab »</strong></a> |
@@ -70,7 +70,7 @@ Requires-Dist: ipywidgets (>=8.1.0)
 [![Gitter Сommunity](https://img.shields.io/badge/gitter-@upgini-teal.svg?logo=gitter)](https://gitter.im/upgini/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge) -->
 ## ❔ Overview
 
-**Upgini** is an intelligent data search engine with a Python library that helps you find and add relevant features to your ML pipeline from hundreds of public, community, and premium external data sources. Under the hood, Upgini automatically optimizes all connected data sources by [generating an optimal set of machine ML features from the source data using large language models (LLMs), GraphNNs and recurrent neural networks (RNNs)](https://upgini.com/#optimized_external_data).   
+**Upgini** is an intelligent data search engine with a Python library that helps you find and add relevant features to your ML pipeline from hundreds of public, community, and premium external data sources. Under the hood, Upgini automatically optimizes all connected data sources by [generating an optimal set of machine ML features using large language models (LLMs), GraphNNs and recurrent neural networks (RNNs)](https://upgini.com/#optimized_external_data).   
 
 **Motivation:** for most supervised ML models external data & features boost accuracy significantly better than any hyperparameters tuning. But lack of automated and time-efficient enrichment tools for external data blocks massive adoption of external features in ML pipelines. We want radically simplify features search and enrichment to make external data a standard approach. Like a hyperparameter tuning for machine learning nowadays.  
 
@@ -78,9 +78,9 @@ Requires-Dist: ipywidgets (>=8.1.0)
 
 ## 🚀 Awesome features
 ⭐️ Automatically find only relevant features that *give accuracy improvement for ML model*. Not just correlated with target variable, what 9 out of 10 cases gives zero accuracy improvement  
-⭐️ Data source optimizations: automated feature generation with Large Language Models' data augmentation, RNNs, GraphNN; multiple data source ensembling  
-⭐️ *Automatic search key augmentation* from all connected sources. If you do not have all search keys in your search request, such as postal/zip code, Upgini will try to add those keys based on the provided set of search keys. This will broaden the search across all available data sources   
-⭐️ Calculate *accuracy metrics and uplifts* after enrichment existing ML model with external features   
+⭐️ Automated feature generation from the sources: feature generation with Large Language Models' data augmentation, RNNs, GraphNN; multiple data source ensembling  
+⭐️ Automatic search key augmentation from all connected sources. If you do not have all search keys in your search request, such as postal/zip code, Upgini will try to add those keys based on the provided set of search keys. This will broaden the search across all available data sources   
+⭐️ Calculate accuracy metrics and uplifts after enrichment existing ML model with external features   
 ⭐️ Check the stability of accuracy gain from external data on out-of-time intervals and verification datasets. Mitigate risks of unstable external data dependencies in ML pipeline   
 ⭐️ Easy to use - single request to enrich training dataset with [*all of the keys at once*](#-search-key-types-we-support-more-to-come):  
 <table>

{upgini-1.1.244a24.dist-info → upgini-1.1.245a1.dist-info}/RECORD

@@ -1,12 +1,12 @@
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=mre6xn44wcC_fg63iLT_kTh4mViZqR9AKRJZAtpQz8Y,2592
-upgini/dataset.py,sha256=_k0J-YcXt-wsihv9WRWUE6tb_h6bbwELauJnp_A1an4,49697
+upgini/dataset.py,sha256=AsDJmEfVvdnBrIXQ2DSjitnTQ-5uu1H59YkhjhBRXcw,50424
 upgini/errors.py,sha256=pdzQl3MKuK52yvncxMWMRWeSIOGhUFzpQoszoRFBOk0,958
-upgini/features_enricher.py,sha256=Z9PaDRGEFJUYzxd0VIPYH1N7I1EiCGkQLu0mRP98lOI,166504
+upgini/features_enricher.py,sha256=DpSKMU9cyDWAn494MF_7WYl4uTWh3_g410n205WYh58,167803
 upgini/fingerprint.js,sha256=VygVIQlN1v4NGZfjHqtRogOw8zjTnnMNJg_f7M5iGQU,33442
 upgini/http.py,sha256=eSG4gOpmCGlXmB6KIPNzAG8tRZNUjyYpMeUeHw_2li4,42264
 upgini/metadata.py,sha256=55t0uQI910tzTcnwxZCUL1413BhTiSm8oqiwp-94NyA,9613
-upgini/metrics.py,sha256=WL0-JSJXjl8jTdEzPDhXUeyd_QQtB09gNOltZDLuWTI,26689
+upgini/metrics.py,sha256=LS2MgEKgmn9VEXsKzxv3pBZ-q71mTnpWu6vL8fYgpo4,26727
 upgini/search_task.py,sha256=5n4qGJmtu48s0-FHAtF3L5qVLMd1JVW3FJlM8dFbh-s,17063
 upgini/spinner.py,sha256=Dm1dQ5F_z_Ua2odLxZX7OypcOX9tSx_vE5MGaKtUmfw,1118
 upgini/version_validator.py,sha256=rDIncP6BEko4J2F2hUcMOtKm_vZbI4ICWcNcw8hrwM4,1400
@@ -26,7 +26,7 @@ upgini/mdc/__init__.py,sha256=ETDh3JKbrDdPMOECiYLAa8lvKYe68mv4IY6fZa9FimA,1126
 upgini/mdc/context.py,sha256=Sl1S_InKlzzRxYqwJ2k24lawJdCKWgGJ-RIRfvzWJrk,1468
 upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/normalizer/phone_normalizer.py,sha256=lhwsPEnfyjeIsndW2EcQGZksXYsfxaQ1ghAzVYoDRKM,9927
-upgini/resource_bundle/__init__.py,sha256=M7GtS7KPQw9pinz8P2aQWXpSkD2YFwUPVGk1w92Pn84,7888
+upgini/resource_bundle/__init__.py,sha256=hdvbqL0b0xMWbY6-kiYGsW1ro2GMiWpxxsO9uCv-h9Q,8379
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
 upgini/resource_bundle/strings.properties,sha256=0qDpfZBMU4moFXKzb11ALwk5N8FdgyJYzI0wRTvFJbI,25008
 upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -51,11 +51,11 @@ upgini/utils/phone_utils.py,sha256=JNSkF8G6mgsN8Czy11pamaJdsY6rBINEMpi7jbVt_RA,4
 upgini/utils/postal_code_utils.py,sha256=_8CR9tBqsPptQsmMUvnrCAmBaMIQSWH3JfJ4ly3x_zs,409
 upgini/utils/progress_bar.py,sha256=iNXyqT3vKCeHpfiG5HHwr7Lk2cTtKViM93Fl8iZnjGc,1564
 upgini/utils/sklearn_ext.py,sha256=fvuTWJ5AnT3ED9KSaQu_yIgW2JR19hFlaGDoVP3k60g,44027
-upgini/utils/target_utils.py,sha256=VgEGA4v5soWE9H5mQUPUEg8fnIXXWXDVHDBjq2oPDCk,2562
+upgini/utils/target_utils.py,sha256=tZoSdrn74xzFOX-AO3KxEd_6utCNGp6DUciWhjlsFV0,2691
 upgini/utils/track_info.py,sha256=EPcJ13Jqa17_T0JjM37Ac9kWDz5Zk0GVsIZKutOb8aU,5207
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.244a24.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.244a24.dist-info/METADATA,sha256=w0-iq4DCF3wHO8QBf20W3EHMhNdjrKJRN9IakMZYAcs,48265
-upgini-1.1.244a24.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
-upgini-1.1.244a24.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.244a24.dist-info/RECORD,,
+upgini-1.1.245a1.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.245a1.dist-info/METADATA,sha256=0zG-bWLQ9yLlpGZrFgQCiPtQvVj_G7HbNJQpFfh4pj0,48234
+upgini-1.1.245a1.dist-info/WHEEL,sha256=pkctZYzUS4AYVn6dJ-7367OJZivF2e8RA9b_ZBjif18,92
+upgini-1.1.245a1.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.245a1.dist-info/RECORD,,

{upgini-1.1.244a24.dist-info → upgini-1.1.245a1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.37.1)
+Generator: bdist_wheel (0.40.0)
 Root-Is-Purelib: true
 Tag: py3-none-any