upgini 1.1.261a3250.post2__tar.gz → 1.2.31a1__tar.gz

upgini-1.2.31a1/.gitignore

@@ -0,0 +1,157 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+env8/
+env9/
+env10/
+.env10/
+.env310/
+env11/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# IDE
+.vscode/
+.idea/
+
+# macOS
+.DS_Store
+
+# Other
+.cache/
+activate_venv.sh
+test-results/
+test_notebooks/
+publish.sh
+catboost_info/
+build/
+playgroung.ipynb
+fingerprint.js
+envVars.txt
+.ruff_cache
+.jupyter
+*.excalidraw

{upgini-1.1.261a3250.post2/src/upgini.egg-info → upgini-1.2.31a1}/PKG-INFO

@@ -1,14 +1,13 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.261a3250.post2
+Version: 1.2.31a1
 Summary: Intelligent data search & enrichment for Machine Learning
-Home-page: https://upgini.com/
-Author: Upgini Developers
-Author-email: madewithlove@upgini.com
-License: BSD 3-Clause License
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
+Project-URL: Homepage, https://upgini.com/
 Project-URL: Source, https://github.com/upgini/upgini
-Keywords: data science,machine learning,data mining,automl,data search
+Author-email: Upgini Developers <madewithlove@upgini.com>
+License-File: LICENSE
+Keywords: automl,data mining,data science,data search,machine learning
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Customer Service
 Classifier: Intended Audience :: Developers
@@ -23,22 +22,23 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Requires-Python: >=3.8,<3.11
-Description-Content-Type: text/markdown
-License-File: LICENSE
+Requires-Python: <3.12,>=3.8
+Requires-Dist: catboost>=1.0.3
+Requires-Dist: fastparquet>=0.8.1
+Requires-Dist: ipywidgets>=8.1.0
+Requires-Dist: jarowinkler>=2.0.0
+Requires-Dist: levenshtein>=0.25.1
+Requires-Dist: numpy<=1.26.4,>=1.19.0
+Requires-Dist: pandas<3.0.0,>=1.1.0
+Requires-Dist: pydantic<3.0.0,>1.0.0
+Requires-Dist: pyjwt>=2.8.0
+Requires-Dist: python-bidi==0.4.2
 Requires-Dist: python-dateutil>=2.8.0
+Requires-Dist: python-json-logger>=2.0.2
 Requires-Dist: requests>=2.8.0
-Requires-Dist: pandas<2.0.0,>=1.1.0
-Requires-Dist: numpy>=1.19.0
 Requires-Dist: scikit-learn>=1.3.0
-Requires-Dist: pydantic<2.0.0,>=1.8.2
-Requires-Dist: fastparquet>=0.8.1
-Requires-Dist: python-json-logger>=2.0.2
-Requires-Dist: catboost>=1.0.3
-Requires-Dist: lightgbm>=3.3.2
-Requires-Dist: pyjwt>=2.8.0
 Requires-Dist: xhtml2pdf==0.2.11
-Requires-Dist: ipywidgets>=8.1.0
+Description-Content-Type: text/markdown
 
 
 <!-- <h2 align="center"> <a href="https://upgini.com/">Upgini</a> : low-code feature search and enrichment library for machine learning </h2> -->
@@ -132,7 +132,7 @@ Requires-Dist: ipywidgets>=8.1.0
 |Consumer Confidence index| 44 |22|-|Monthly|date, country|No
 |World economic indicators|191 |41|-|Monthly|date, country|No
 |Markets data|-|17|-|Monthly|date, datetime|No
-|World mobile & fixed broadband network coverage and perfomance |167|-|3|Monthly|country, postal/ZIP code|No
+|World mobile & fixed broadband network coverage and performance |167|-|3|Monthly|country, postal/ZIP code|No
 |World demographic data |90|-|2|Annual|country, postal/ZIP code|No
 |World house prices |44|-|3|Annual|country, postal/ZIP code|No
 |Public social media profile data |104|-|-|Monthly|date, email/HEM, phone |Yes
@@ -145,7 +145,7 @@ Requires-Dist: ipywidgets>=8.1.0
 
 ## 💼 Tutorials
 
-###  [Search of relevant external features & Automated feature generation for Salary predicton task (use as a template)](https://github.com/upgini/upgini/blob/main/notebooks/Upgini_Features_search%26generation.ipynb)
+###  [Search of relevant external features & Automated feature generation for Salary prediction task (use as a template)](https://github.com/upgini/upgini/blob/main/notebooks/Upgini_Features_search%26generation.ipynb)
 
 * The goal is to predict salary for data science job postning based on information about employer and job description.
 * Following this guide, you'll learn how to **search & auto generate new relevant features with Upgini library**
@@ -259,7 +259,9 @@ We do dataset verification and cleaning under the hood, but still there are some
 *Search keys* columns will be used to match records from all potential external data sources / features.   
 Define one or multiple columns as a search keys with `FeaturesEnricher` class initialization.  
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -345,7 +347,9 @@ enricher = FeaturesEnricher(
 
 For the meaning types <tt>SearchKey.DATE</tt>/<tt>SearchKey.DATETIME</tt> with dtypes <tt>object</tt> or <tt>string</tt> you have to clarify date/datetime format by passing <tt>date_format</tt> parameter to `FeaturesEnricher`. For example:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -366,7 +370,9 @@ df["date"] = df.date.astype("datetime64").dt.tz_localize("Europe/Warsaw")
 
 Single country for the whole training dataset can be passed with `country_code` parameter:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -385,7 +391,8 @@ Create instance of the `FeaturesEnricher` class and call:
 Let's try it out!
 ```python
 import pandas as pd
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
 
 # load labeled training dataset to initiate search
 train_df = pd.read_csv("customer_churn_prediction_train.csv")
@@ -476,7 +483,9 @@ We detect ML task under the hood based on label column values. Currently we supp
 
 But for certain search datasets you can pass parameter to `FeaturesEnricher` with correct ML taks type:
 ```python
-from upgini import ModelTaskType
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey, ModelTaskType
+
 enricher = FeaturesEnricher(
 	search_keys={"subscription_activation_date": SearchKey.DATE},
 	model_task_type=ModelTaskType.REGRESSION
@@ -489,7 +498,9 @@ enricher = FeaturesEnricher(
 
 To initiate feature search you can pass cross-validation type parameter to `FeaturesEnricher` with time series specific CV type:
 ```python
-from upgini.metadata import CVType
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey, CVType
+
 enricher = FeaturesEnricher(
 	search_keys={"sales_date": SearchKey.DATE},
 	cv=CVType.time_series
@@ -623,7 +634,9 @@ But you can easily define new split by passing child of BaseCrossValidator to pa
 
 Example with more tips-and-tricks:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(search_keys={"registration_date": SearchKey.DATE})
 
 # Fit with default setup for metrics calculation
@@ -796,7 +809,7 @@ You may publish ANY data which you consider as royalty / license free ([Open Dat
 2. Copy *Upgini API key* from profile and upload your data from Upgini python library with this key:
 ```python
 import pandas as pd
-from upgini import SearchKey
+from upgini.metadata import SearchKey
 from upgini.ads import upload_user_ads
 import os
 os.environ["UPGINI_API_KEY"] = "your_long_string_api_key_goes_here"
@@ -841,4 +854,4 @@ Some convenient ways to start contributing are:
 - [More perks for registered users](https://profile.upgini.com)
 
 <sup>😔 Found mistype or a bug in code snippet? Our bad! <a href="https://github.com/upgini/upgini/issues/new?assignees=&title=readme%2Fbug">
-Please report it here.</a></sup>
+Please report it here</a></sup>

{upgini-1.1.261a3250.post2 → upgini-1.2.31a1}/README.md

@@ -90,7 +90,7 @@
 |Consumer Confidence index| 44 |22|-|Monthly|date, country|No
 |World economic indicators|191 |41|-|Monthly|date, country|No
 |Markets data|-|17|-|Monthly|date, datetime|No
-|World mobile & fixed broadband network coverage and perfomance |167|-|3|Monthly|country, postal/ZIP code|No
+|World mobile & fixed broadband network coverage and performance |167|-|3|Monthly|country, postal/ZIP code|No
 |World demographic data |90|-|2|Annual|country, postal/ZIP code|No
 |World house prices |44|-|3|Annual|country, postal/ZIP code|No
 |Public social media profile data |104|-|-|Monthly|date, email/HEM, phone |Yes
@@ -103,7 +103,7 @@
 
 ## 💼 Tutorials
 
-###  [Search of relevant external features & Automated feature generation for Salary predicton task (use as a template)](https://github.com/upgini/upgini/blob/main/notebooks/Upgini_Features_search%26generation.ipynb)
+###  [Search of relevant external features & Automated feature generation for Salary prediction task (use as a template)](https://github.com/upgini/upgini/blob/main/notebooks/Upgini_Features_search%26generation.ipynb)
 
 * The goal is to predict salary for data science job postning based on information about employer and job description.
 * Following this guide, you'll learn how to **search & auto generate new relevant features with Upgini library**
@@ -217,7 +217,9 @@ We do dataset verification and cleaning under the hood, but still there are some
 *Search keys* columns will be used to match records from all potential external data sources / features.   
 Define one or multiple columns as a search keys with `FeaturesEnricher` class initialization.  
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -303,7 +305,9 @@ enricher = FeaturesEnricher(
 
 For the meaning types <tt>SearchKey.DATE</tt>/<tt>SearchKey.DATETIME</tt> with dtypes <tt>object</tt> or <tt>string</tt> you have to clarify date/datetime format by passing <tt>date_format</tt> parameter to `FeaturesEnricher`. For example:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -324,7 +328,9 @@ df["date"] = df.date.astype("datetime64").dt.tz_localize("Europe/Warsaw")
 
 Single country for the whole training dataset can be passed with `country_code` parameter:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -343,7 +349,8 @@ Create instance of the `FeaturesEnricher` class and call:
 Let's try it out!
 ```python
 import pandas as pd
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
 
 # load labeled training dataset to initiate search
 train_df = pd.read_csv("customer_churn_prediction_train.csv")
@@ -434,7 +441,9 @@ We detect ML task under the hood based on label column values. Currently we supp
 
 But for certain search datasets you can pass parameter to `FeaturesEnricher` with correct ML taks type:
 ```python
-from upgini import ModelTaskType
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey, ModelTaskType
+
 enricher = FeaturesEnricher(
 	search_keys={"subscription_activation_date": SearchKey.DATE},
 	model_task_type=ModelTaskType.REGRESSION
@@ -447,7 +456,9 @@ enricher = FeaturesEnricher(
 
 To initiate feature search you can pass cross-validation type parameter to `FeaturesEnricher` with time series specific CV type:
 ```python
-from upgini.metadata import CVType
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey, CVType
+
 enricher = FeaturesEnricher(
 	search_keys={"sales_date": SearchKey.DATE},
 	cv=CVType.time_series
@@ -581,7 +592,9 @@ But you can easily define new split by passing child of BaseCrossValidator to pa
 
 Example with more tips-and-tricks:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(search_keys={"registration_date": SearchKey.DATE})
 
 # Fit with default setup for metrics calculation
@@ -754,7 +767,7 @@ You may publish ANY data which you consider as royalty / license free ([Open Dat
 2. Copy *Upgini API key* from profile and upload your data from Upgini python library with this key:
 ```python
 import pandas as pd
-from upgini import SearchKey
+from upgini.metadata import SearchKey
 from upgini.ads import upload_user_ads
 import os
 os.environ["UPGINI_API_KEY"] = "your_long_string_api_key_goes_here"
@@ -799,4 +812,4 @@ Some convenient ways to start contributing are:
 - [More perks for registered users](https://profile.upgini.com)
 
 <sup>😔 Found mistype or a bug in code snippet? Our bad! <a href="https://github.com/upgini/upgini/issues/new?assignees=&title=readme%2Fbug">
-Please report it here.</a></sup>
+Please report it here</a></sup>

upgini-1.2.31a1/pyproject.toml

@@ -0,0 +1,124 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "upgini"
+dynamic = ["version"]
+description = "Intelligent data search & enrichment for Machine Learning"
+readme = "README.md"
+requires-python = ">=3.8,<3.12"
+authors = [
+    { name = "Upgini Developers", email = "madewithlove@upgini.com" },
+]
+keywords = [
+    "automl",
+    "data mining",
+    "data science",
+    "data search",
+    "machine learning",
+]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Customer Service",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Financial and Insurance Industry",
+    "Intended Audience :: Information Technology",
+    "Intended Audience :: Science/Research",
+    "Intended Audience :: Telecommunications Industry",
+    "License :: OSI Approved :: BSD License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+]
+dependencies = [
+    "catboost>=1.0.3",
+    "fastparquet>=0.8.1",
+    "ipywidgets>=8.1.0",
+    "numpy>=1.19.0,<=1.26.4",
+    "pandas>=1.1.0,<3.0.0",
+    "pydantic>1.0.0,<3.0.0",
+    "pyjwt>=2.8.0",
+    "python-dateutil>=2.8.0",
+    "python-json-logger>=2.0.2",
+    "requests>=2.8.0",
+    "scikit-learn>=1.3.0",
+    "python-bidi==0.4.2",
+    "xhtml2pdf==0.2.11",
+    "jarowinkler>=2.0.0",
+    "levenshtein>=0.25.1",
+]
+
+[project.urls]
+"Bug Reports" = "https://github.com/upgini/upgini/issues"
+Homepage = "https://upgini.com/"
+Source = "https://github.com/upgini/upgini"
+
+[tool.hatch.version]
+path = "src/upgini/__about__.py"
+
+[tool.hatch.build.targets.sdist]
+include = [
+    "src"
+]
+
+[tool.hatch.build.targets.wheel]
+packages = [
+    "src/upgini"
+]
+
+[tool.hatch.build]
+include = [
+  "/src/utils/Roboto-Regular.ttf",
+]
+
+[tool.hatch.envs.default]
+type = "virtual"
+python = "3.10"
+
+[tool.hatch.envs.test.scripts]
+cov = 'pytest --cov-report=term-missing --cov-config=pyproject.toml --cov=upgini --cov=tests'
+format = "black {args}"
+lint = "ruff check {args}"
+test_all = 'pytest -s -vv tests'
+
+[[tool.hatch.envs.test.matrix]]
+python = ["3.8"]
+pandas = ["1.1.0"]
+
+[[tool.hatch.envs.test.matrix]]
+python = ["3.8", "3.9", "3.10"]
+pandas = ["1.2.0", "1.3.0", "1.4.0", "1.5.0", "2.0.0"]
+
+[[tool.hatch.envs.test.matrix]]
+python = ["3.9", "3.10"]
+pandas = ["2.1.0", "2.2.0"]
+
+# from versions: 0.1, 0.2, 0.3.0, 0.4.0, 0.4.1, 0.4.2, 0.4.3, 0.5.0, 0.6.0, 0.6.1, 0.7.0, 0.7.1, 0.7.2, 0.7.3, 0.8.0, 0.8.1, 0.9.0, 0.9.1, 0.10.0, 0.10.1, 0.11.0, 0.12.0, 0.13.0, 0.13.1, 0.14.0, 0.14.1, 0.15.0, 0.15.1, 0.15.2, 0.16.0, 0.16.1, 0.16.2, 0.17.0, 0.17.1, 0.18.0, 0.18.1, 0.19.0, 0.19.1, 0.19.2, 0.20.0, 0.20.1, 0.20.2, 0.20.3, 0.21.0, 0.21.1, 0.22.0, 0.23.0, 0.23.1, 0.23.2, 0.23.3, 0.23.4, 0.24.0, 0.24.1, 0.24.2, 0.25.0, 0.25.1, 0.25.2, 0.25.3, 1.0.0, 1.0.1, 1.0.2, 1.0.3, 1.0.4, 1.0.5, 1.1.0, 1.1.1, 1.1.2, 1.1.3, 1.1.4, 1.1.5, 1.2.0, 1.2.1, 1.2.2, 1.2.3, 1.2.4, 1.2.5, 1.3.0, 1.3.1, 1.3.2, 1.3.3, 1.3.4, 1.3.5, 1.4.0rc0, 1.4.0, 1.4.1, 1.4.2, 1.4.3, 1.4.4, 1.5.0rc0, 1.5.0, 1.5.1, 1.5.2, 1.5.3, 2.0.0rc0, 2.0.0rc1, 2.0.0, 2.0.1, 2.0.2, 2.0.3
+
+[tool.hatch.envs.test]
+dependencies = [
+  "coverage[toml]",
+  "pytest",
+  "pytest-cov",
+#  "pytest-timeout",
+  "requests-mock",
+  "pytest-datafiles",
+  "pytest-xdist",
+  "pandas~={matrix:pandas}",
+]
+
+[tool.black]
+line-length = 120
+
+[tool.isort]
+profile = "black"
+
+[tool.pytest.ini_options]
+pythonpath = [
+  "./src"
+]
+addopts="-n 4"

upgini-1.2.31a1/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.31a1"

upgini-1.2.31a1/src/upgini/__init__.py

@@ -0,0 +1,5 @@
+from upgini.features_enricher import FeaturesEnricher  # noqa: F401
+from upgini.metadata import SearchKey, CVType, RuntimeParameters, ModelTaskType  # noqa: F401
+import warnings
+
+warnings.filterwarnings("ignore", category=UserWarning, module="_distutils_hack")

{upgini-1.1.261a3250.post2 → upgini-1.2.31a1}/src/upgini/ads.py

@@ -5,7 +5,7 @@ from typing import Dict, Optional
 
 import numpy as np
 import pandas as pd
-from pandas.api.types import is_string_dtype
+from pandas.api.types import is_object_dtype, is_string_dtype
 
 from upgini import SearchKey
 from upgini.http import get_rest_client
@@ -34,7 +34,11 @@ def upload_user_ads(name: str, df: pd.DataFrame, search_keys: Dict[str, SearchKe
             if df[column_name].notnull().sum() < min_valid_rows_count:
                 raise ValueError(bundle.get("ads_upload_to_many_empty_rows"))
             meaning_type = search_keys[column_name].value
-            if meaning_type == FileColumnMeaningType.MSISDN and not is_string_dtype(df[column_name]):
+            if (
+                meaning_type == FileColumnMeaningType.MSISDN
+                and not is_string_dtype(df[column_name])
+                and not is_object_dtype(df[column_name])
+            ):
                 df[column_name] = df[column_name].values.astype(np.int64).astype("string")  # type: ignore
         else:
             meaning_type = FileColumnMeaningType.FEATURE

{upgini-1.1.261a3250.post2 → upgini-1.2.31a1}/src/upgini/ads_management/ads_manager.py

@@ -1,9 +1,11 @@
 import time
-from typing import Dict, Optional
 import uuid
+from typing import Dict, Optional
+
+import pandas as pd
+
 from upgini.http import get_rest_client
 from upgini.spinner import Spinner
-import pandas as pd
 
 
 class AdsManager:

upgini-1.2.31a1/src/upgini/autofe/all_operands.py

@@ -0,0 +1,87 @@
+from copy import deepcopy
+from typing import Dict
+
+from upgini.autofe.binary import (
+    Add,
+    Combine,
+    CombineThenFreq,
+    Distance,
+    Divide,
+    JaroWinklerSim1,
+    JaroWinklerSim2,
+    LevenshteinSim,
+    Max,
+    Min,
+    Multiply,
+    Sim,
+    Subtract,
+)
+from upgini.autofe.date import (
+    DateDiff,
+    DateDiffType2,
+    DateListDiff,
+    DateListDiffBounded,
+    DatePercentile,
+    DatePercentileMethod2,
+)
+from upgini.autofe.groupby import GroupByThenAgg, GroupByThenFreq, GroupByThenNUnique, GroupByThenRank
+from upgini.autofe.operand import Operand
+from upgini.autofe.unary import Abs, Embeddings, Floor, Freq, Log, Residual, Norm, Sigmoid, Sqrt, Square
+from upgini.autofe.vector import Mean, Sum
+
+ALL_OPERANDS: Dict[str, Operand] = {
+    op.name: op
+    for op in [
+        Freq(),
+        Mean(),
+        Sum(),
+        Abs(),
+        Log(),
+        Sqrt(),
+        Square(),
+        Sigmoid(),
+        Floor(),
+        Residual(),
+        Min(),
+        Max(),
+        Add(),
+        Subtract(),
+        Multiply(),
+        Divide(),
+        GroupByThenAgg(name="GroupByThenMin", agg="min"),
+        GroupByThenAgg(name="GroupByThenMax", agg="max"),
+        GroupByThenAgg(name="GroupByThenMean", agg="mean"),
+        GroupByThenAgg(name="GroupByThenMedian", agg="median"),
+        GroupByThenAgg(name="GroupByThenStd", output_type="float", agg="std"),
+        GroupByThenRank(),
+        Combine(),
+        CombineThenFreq(),
+        GroupByThenNUnique(),
+        GroupByThenFreq(),
+        Sim(),
+        DateDiff(),
+        DateDiffType2(),
+        DateListDiff(aggregation="min"),
+        DateListDiff(aggregation="max"),
+        DateListDiff(aggregation="mean"),
+        DateListDiff(aggregation="nunique"),
+        DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=0, upper_bound=18),
+        DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=18, upper_bound=23),
+        DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=23, upper_bound=30),
+        DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=30, upper_bound=45),
+        DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=45, upper_bound=60),
+        DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=60),
+        DatePercentile(),
+        DatePercentileMethod2(),
+        Norm(),
+        JaroWinklerSim1(),
+        JaroWinklerSim2(),
+        LevenshteinSim(),
+        Distance(),
+        Embeddings(),
+    ]
+}
+
+
+def find_op(name):
+    return deepcopy(ALL_OPERANDS.get(name))