upgini 1.1.279a2__tar.gz → 1.1.279a2.dev1__tar.gz

upgini-1.1.279a2.dev1/.gitignore

@@ -0,0 +1,154 @@
+# 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

{upgini-1.1.279a2/src/upgini.egg-info → upgini-1.1.279a2.dev1}/PKG-INFO

@@ -1,14 +1,13 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.279a2
+Version: 1.1.279a2.dev1
 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-1.1.279a2.dev1/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-1.1.279a2.dev1/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.279a2.dev1"

{upgini-1.1.279a2 → upgini-1.1.279a2.dev1}/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-1.1.279a2 → upgini-1.1.279a2.dev1}/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-1.1.279a2 → upgini-1.1.279a2.dev1}/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-1.1.279a2 → upgini-1.1.279a2.dev1}/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-1.1.279a2 → upgini-1.1.279a2.dev1}/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-1.1.279a2 → upgini-1.1.279a2.dev1}/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-1.1.279a2 → upgini-1.1.279a2.dev1}/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-1.1.279a2 → upgini-1.1.279a2.dev1}/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-1.1.279a2 → upgini-1.1.279a2.dev1}/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-1.1.279a2 → upgini-1.1.279a2.dev1}/src/upgini/dataset.py

@@ -15,9 +15,9 @@ 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
@@ -95,7 +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)
@@ -251,7 +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
@@ -259,7 +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

{upgini-1.1.279a2 → upgini-1.1.279a2.dev1}/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)
 
 

{upgini-1.1.279a2 → upgini-1.1.279a2.dev1}/src/upgini/features_enricher.py

@@ -2548,7 +2548,7 @@ class FeaturesEnricher(TransformerMixin):
             validated_X = X.copy()
         elif isinstance(X, pd.Series):
             validated_X = X.to_frame()
-        elif isinstance(X, np.ndarray) or isinstance(X, list):
+        elif isinstance(X, (list, np.ndarray)):
             validated_X = pd.DataFrame(X)
             renaming = {c: str(c) for c in validated_X.columns}
             validated_X = validated_X.rename(columns=renaming)
@@ -2637,7 +2637,7 @@ class FeaturesEnricher(TransformerMixin):
             validated_eval_X = eval_X.copy()
         elif isinstance(eval_X, pd.Series):
             validated_eval_X = eval_X.to_frame()
-        elif isinstance(eval_X, np.ndarray) or isinstance(eval_X, list):
+        elif isinstance(eval_X, (list, np.ndarray)):
             validated_eval_X = pd.DataFrame(eval_X)
             renaming = {c: str(c) for c in validated_eval_X.columns}
             validated_eval_X = validated_eval_X.rename(columns=renaming)
@@ -2819,7 +2819,7 @@ class FeaturesEnricher(TransformerMixin):
             )
 
             def sample(df):
-                if isinstance(df, pd.Series) or isinstance(df, pd.DataFrame):
+                if isinstance(df, (pd.DataFrame, pd.Series)):
                     return df.head(10)
                 else:
                     return df[:10]
@@ -3693,7 +3693,7 @@ class FeaturesEnricher(TransformerMixin):
                 def sample(inp, sample_index):
                     if _num_samples(inp) <= 1000:
                         return inp
-                    if isinstance(inp, pd.DataFrame) or isinstance(inp, pd.Series):
+                    if isinstance(inp, (pd.DataFrame, pd.Series)):
                         return inp.sample(n=1000, random_state=random_state)
                     if isinstance(inp, np.ndarray):
                         return inp[sample_index]

{upgini-1.1.279a2 → upgini-1.1.279a2.dev1}/src/upgini/http.py

@@ -22,6 +22,7 @@ from pydantic import BaseModel
 from pythonjsonlogger import jsonlogger
 from requests.exceptions import RequestException
 
+from upgini.__about__ import __version__
 from upgini.errors import (
     HttpError,
     UnauthorizedError,
@@ -38,17 +39,17 @@ from upgini.metadata import (
 from upgini.resource_bundle import bundle
 from upgini.utils.track_info import get_track_metrics
 
-try:
-    from importlib_metadata import version  # type: ignore
+# try:
+#     from importlib.metadata import version  # type: ignore
 
-    __version__ = version("upgini")
-except ImportError:
-    try:
-        from importlib.metadata import version  # type: ignore
+#     __version__ = version("upgini")
+# except ImportError:
+#     try:
+#         from importlib_metadata import version  # type: ignore
 
-        __version__ = version("upgini")
-    except ImportError:
-        __version__ = "Upgini wasn't installed"
+#         __version__ = version("upgini")
+#     except ImportError:
+#         __version__ = "Upgini wasn't installed"
 
 UPGINI_URL: str = "UPGINI_URL"
 UPGINI_API_KEY: str = "UPGINI_API_KEY"
@@ -925,7 +926,7 @@ def is_demo_api_key(api_token: Optional[str]) -> bool:
     return api_token is None or api_token == "" or api_token == DEMO_API_KEY
 
 
-@lru_cache()
+@lru_cache
 def _get_rest_client(
     backend_url: str, api_token: str, client_ip: Optional[str] = None, client_visitorid: Optional[str] = None
 ) -> _RestClient:

{upgini-1.1.279a2 → upgini-1.1.279a2.dev1}/src/upgini/mdc/__init__.py

@@ -1,15 +1,13 @@
-# -*- coding: utf-8 -*-
 """
 .. module: mdc
 .. moduleauthor:: Aljosha Friemann a.friemann@automate.wtf
 """
-from __future__ import absolute_import, division, print_function, unicode_literals
 
 import logging
 
-from upgini.mdc.context import new_log_context, get_mdc_fields
 from pythonjsonlogger import jsonlogger
 
+from upgini.mdc.context import get_mdc_fields, new_log_context
 
 MDContext = new_log_context
 MDC = new_log_context

{upgini-1.1.279a2 → upgini-1.1.279a2.dev1}/src/upgini/mdc/context.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """
 .. module: TODO
     :platform: TODO
@@ -7,12 +6,11 @@
 .. moduleauthor:: Aljosha Friemann a.friemann@automate.wtf
 """
 
-import time
-import uuid
+import collections
 import logging
 import threading
-import collections
-
+import time
+import uuid
 from contextlib import contextmanager
 
 LOGGER = logging.getLogger(__name__)
@@ -32,7 +30,7 @@ def get_mdc_fields():
 
 @contextmanager
 def new_log_context(**kwargs):
-    context_id = "mdc-{thread}-{context}".format(thread=threading.current_thread().ident, context=uuid.uuid4())
+    context_id = f"mdc-{threading.current_thread().ident}-{uuid.uuid4()}"
 
     LOGGER.debug("creating context %s", context_id)
 

{upgini-1.1.279a2 → upgini-1.1.279a2.dev1}/src/upgini/metadata.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 from enum import Enum
 from typing import Dict, List, Optional, Set
 
@@ -201,6 +203,7 @@ class FileMetadata(BaseModel):
         for c in self.columns:
             if c.name == name:
                 return c
+        return None
 
     def search_types(self) -> Set[SearchKey]:
         search_keys = set()