upgini 1.1.278a1__tar.gz → 1.1.279__tar.gz

upgini-1.1.279/.gitignore

@@ -0,0 +1,156 @@
+# 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

{upgini-1.1.278a1/src/upgini.egg-info → upgini-1.1.279}/PKG-INFO

@@ -1,14 +1,13 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.278a1
+Version: 1.1.279
 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 +22,21 @@ 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-Dist: python-dateutil>=2.8.0
-Requires-Dist: requests>=2.8.0
-Requires-Dist: pandas<3.0.0,>=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-Python: <3.11,>=3.8
 Requires-Dist: catboost>=1.0.3
+Requires-Dist: fastparquet>=0.8.1
+Requires-Dist: ipywidgets>=8.1.0
 Requires-Dist: lightgbm>=3.3.2
+Requires-Dist: numpy>=1.19.0
+Requires-Dist: pandas<3.0.0,>=1.1.0
+Requires-Dist: pydantic<2.0.0,>=1.8.2
 Requires-Dist: pyjwt>=2.8.0
+Requires-Dist: python-dateutil>=2.8.0
+Requires-Dist: python-json-logger>=2.0.2
+Requires-Dist: requests>=2.8.0
+Requires-Dist: scikit-learn>=1.3.0
 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> -->
@@ -841,4 +839,4 @@ 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-1.1.279/pyproject.toml

@@ -0,0 +1,102 @@
+[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,<3.11"
+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",
+    "lightgbm>=3.3.2",
+    "numpy>=1.19.0",
+    "pandas>=1.1.0,<3.0.0",
+    "pydantic>=1.8.2,<2.0.0",
+    "pyjwt>=2.8.0",
+    "python-dateutil>=2.8.0",
+    "python-json-logger>=2.0.2",
+    "requests>=2.8.0",
+    "scikit-learn>=1.3.0",
+    "xhtml2pdf==0.2.11",
+]
+
+[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.envs.default]
+type = "virtual"
+python = "3.10"
+
+[tool.hatch.envs.test]
+dependencies = [
+  "coverage[toml]",
+  "pytest",
+  "pytest-cov",
+  "requests-mock",
+]
+
+[tool.hatch.envs.test.scripts]
+cov = 'pytest --cov-report=term-missing --cov-config=pyproject.toml --cov=upgini --cov=tests {args}'
+format = "black {args}"
+lint = "ruff check {args}"
+
+test_binary = 'pytest -s -vv tests/test_binary_dataset.py'
+
+[[tool.hatch.envs.test.matrix]]
+python = ["3.8", "3.9", "3.10"]
+
+[tool.black]
+line-length = 120
+
+[tool.isort]
+profile = "black"
+
+[tool.pytest.ini_options]
+pythonpath = [
+  "./src"
+]

upgini-1.1.279/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.279"

{upgini-1.1.278a1 → upgini-1.1.279}/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-1.1.278a1 → upgini-1.1.279}/src/upgini/autofe/all_operands.py

@@ -1,9 +1,10 @@
 from typing import Dict
+
+from upgini.autofe.binary import Add, Divide, Max, Min, Multiply, Sim, Subtract
 from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded
 from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
 from upgini.autofe.operand import Operand
-from upgini.autofe.unary import Abs, Log, Residual, Sqrt, Square, Sigmoid, Floor, Freq
-from upgini.autofe.binary import Min, Max, Add, Subtract, Multiply, Divide, Sim
+from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Sigmoid, Sqrt, Square
 from upgini.autofe.vector import Mean, Sum
 
 ALL_OPERANDS: Dict[str, Operand] = {

{upgini-1.1.278a1 → upgini-1.1.279}/src/upgini/autofe/binary.py

@@ -1,9 +1,10 @@
-from upgini.autofe.operand import PandasOperand, VectorizableMixin
 import numpy as np
 import pandas as pd
 from numpy import dot
 from numpy.linalg import norm
 
+from upgini.autofe.operand import PandasOperand, VectorizableMixin
+
 
 class Min(PandasOperand):
     name = "min"

{upgini-1.1.278a1 → upgini-1.1.279}/src/upgini/autofe/date.py

@@ -1,8 +1,9 @@
 from typing import Any, Optional, Union
+
 import numpy as np
 import pandas as pd
-from pydantic import BaseModel
 from pandas.core.arrays.timedeltas import TimedeltaArray
+from pydantic import BaseModel
 
 from upgini.autofe.operand import PandasOperand
 

{upgini-1.1.278a1 → upgini-1.1.279}/src/upgini/autofe/feature.py

@@ -215,7 +215,7 @@ class Feature:
             return Column(string)
 
         def is_trivial_char(c: str) -> bool:
-            return not (c in "()+-*/,")
+            return c not in "()+-*/,"
 
         def find_prev(string: str) -> int:
             if string[-1] != ")":

{upgini-1.1.278a1 → upgini-1.1.279}/src/upgini/autofe/groupby.py

@@ -1,7 +1,9 @@
-from upgini.autofe.operand import PandasOperand, VectorizableMixin
 from typing import Optional
+
 import pandas as pd
 
+from upgini.autofe.operand import PandasOperand, VectorizableMixin
+
 
 class GroupByThenAgg(PandasOperand, VectorizableMixin):
     agg: Optional[str]

{upgini-1.1.278a1 → upgini-1.1.279}/src/upgini/autofe/operand.py

@@ -1,8 +1,9 @@
-from pydantic import BaseModel
-from typing import Dict, List, Optional, Tuple, Union
 import abc
-import pandas as pd
+from typing import Dict, List, Optional, Tuple, Union
+
 import numpy as np
+import pandas as pd
+from pydantic import BaseModel
 
 
 class Operand(BaseModel):

{upgini-1.1.278a1 → upgini-1.1.279}/src/upgini/autofe/unary.py

@@ -1,7 +1,8 @@
-from upgini.autofe.operand import PandasOperand, VectorizableMixin
 import numpy as np
 import pandas as pd
 
+from upgini.autofe.operand import PandasOperand, VectorizableMixin
+
 
 class Abs(PandasOperand, VectorizableMixin):
     name = "abs"

{upgini-1.1.278a1 → upgini-1.1.279}/src/upgini/autofe/vector.py

@@ -1,5 +1,7 @@
 from typing import List
+
 import pandas as pd
+
 from upgini.autofe.operand import PandasOperand, VectorizableMixin
 
 

{upgini-1.1.278a1 → upgini-1.1.279}/src/upgini/dataset.py

@@ -15,17 +15,15 @@ from pandas.api.types import (
     is_float_dtype,
     is_integer_dtype,
     is_numeric_dtype,
+    is_object_dtype,
     is_period_dtype,
     is_string_dtype,
-    is_object_dtype,
 )
 
 from upgini.errors import ValidationError
 from upgini.http import ProgressStage, SearchProgress, _RestClient
 from upgini.metadata import (
-    ENTITY_SYSTEM_RECORD_ID,
     EVAL_SET_INDEX,
-    SEARCH_KEY_UNNEST,
     SYSTEM_COLUMNS,
     SYSTEM_RECORD_ID,
     TARGET,
@@ -81,7 +79,6 @@ class Dataset:  # (pd.DataFrame):
         path: Optional[str] = None,
         meaning_types: Optional[Dict[str, FileColumnMeaningType]] = None,
         search_keys: Optional[List[Tuple[str, ...]]] = None,
-        unnest_search_keys: Optional[Dict[str, str]] = None,
         model_task_type: Optional[ModelTaskType] = None,
         random_state: Optional[int] = None,
         rest_client: Optional[_RestClient] = None,
@@ -98,7 +95,7 @@ class Dataset:  # (pd.DataFrame):
                 data = pd.read_csv(path, **kwargs)
             else:
                 # try different separators: , ; \t ...
-                with open(path, mode="r") as csvfile:
+                with open(path) as csvfile:
                     sep = csv.Sniffer().sniff(csvfile.read(2048)).delimiter
                 kwargs["sep"] = sep
                 data = pd.read_csv(path, **kwargs)
@@ -116,7 +113,6 @@ class Dataset:  # (pd.DataFrame):
         self.description = description
         self.meaning_types = meaning_types
         self.search_keys = search_keys
-        self.unnest_search_keys = unnest_search_keys
         self.ignore_columns = []
         self.hierarchical_group_keys = []
         self.hierarchical_subgroup_keys = []
@@ -176,7 +172,7 @@ class Dataset:  # (pd.DataFrame):
         new_columns = []
         dup_counter = 0
         for column in self.data.columns:
-            if column in [TARGET, EVAL_SET_INDEX, SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID, SEARCH_KEY_UNNEST]:
+            if column in [TARGET, EVAL_SET_INDEX, SYSTEM_RECORD_ID]:
                 self.columns_renaming[column] = column
                 new_columns.append(column)
                 continue
@@ -255,7 +251,7 @@ class Dataset:  # (pd.DataFrame):
     @staticmethod
     def _ip_to_int(ip: Optional[_BaseAddress]) -> Optional[int]:
         try:
-            if isinstance(ip, IPv4Address) or isinstance(ip, IPv6Address):
+            if isinstance(ip, (IPv4Address, IPv6Address)):
                 return int(ip)
         except Exception:
             pass
@@ -263,7 +259,7 @@ class Dataset:  # (pd.DataFrame):
     @staticmethod
     def _ip_to_int_str(ip: Optional[_BaseAddress]) -> Optional[str]:
         try:
-            if isinstance(ip, IPv4Address) or isinstance(ip, IPv6Address):
+            if isinstance(ip, (IPv4Address, IPv6Address)):
                 return str(int(ip))
         except Exception:
             pass
@@ -357,9 +353,7 @@ class Dataset:  # (pd.DataFrame):
 
             if is_string_dtype(self.data[postal_code]) or is_object_dtype(self.data[postal_code]):
                 try:
-                    self.data[postal_code] = (
-                        self.data[postal_code].astype("string").astype("Float64").astype("Int64").astype("string")
-                    )
+                    self.data[postal_code] = self.data[postal_code].astype("float64").astype("Int64").astype("string")
                 except Exception:
                     pass
             elif is_float_dtype(self.data[postal_code]):
@@ -809,9 +803,6 @@ class Dataset:  # (pd.DataFrame):
                     meaningType=meaning_type,
                     minMaxValues=min_max_values,
                 )
-                if self.unnest_search_keys and column_meta.originalName in self.unnest_search_keys:
-                    column_meta.isUnnest = True
-                    column_meta.unnestKeyNames = self.unnest_search_keys[column_meta.originalName]
 
                 columns.append(column_meta)
 

{upgini-1.1.278a1 → upgini-1.1.279}/src/upgini/errors.py

@@ -16,7 +16,7 @@ class UnauthorizedError(HttpError):
     """Unauthorized error from REST API."""
 
     def __init__(self, message, status_code):
-        message = "Unauthorized, please check your authorization token ({})".format(message)
+        message = f"Unauthorized, please check your authorization token ({message})"
         super(UnauthorizedError, self).__init__(message, status_code)