Merge pull request #201 from MindSetLib/dev

Switch to poetry packaging & adding more tests

.github/workflows/insolver-pypi-release.yaml

@@ -17,14 +17,15 @@ jobs:
       uses: actions/setup-python@v5
       with:
         python-version: "3.10"
+    - name: Install Poetry
+      uses: snok/install-poetry@v1
     - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip setuptools wheel
-        pip install build
+      shell: bash
+      run: poetry self add poetry-version-plugin
     - name: Build a binary wheel and a source tarball
-      run: python -m build --sdist --wheel --outdir dist/ .
+      run: poetry build
     - name: Publish package to PyPI
       uses: pypa/gh-action-pypi-publish@release/v1
       with:
         user: __token__
-        password: ${{ secrets.PYPI_API_TOKEN }}
+        password: ${{ secrets.PYPI_API_TOKEN }}

.github/workflows/insolver-tests.yaml

@@ -31,25 +31,25 @@ jobs:
     - name: Install libomp for lightgbm (macOS)
       if: matrix.os == 'macos-latest'
       run: brew install libomp
+    - name: Install Poetry
+      uses: snok/install-poetry@v1
     - name: Install dependencies
       shell: bash
       run: |
-        python -m pip install --upgrade pip setuptools wheel
-        pip install wheel ruff pytest pytest-cov black[jupyter]
-        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+        poetry install --with dev --no-interaction
     - name: Lint with black
       shell: bash
       run: |
-        black . --check --line-length 120
+        poetry run black . --check --line-length 120
     - name: Lint with ruff
       shell: bash
       run: |
-        ruff check . --select=E9,F63,F7,F82 --show-source
-        ruff check . --exit-zero --statistics
+        poetry run ruff check . --select=E9,F63,F7,F82 --show-source
+        poetry run ruff check . --exit-zero --statistics
     - name: Test with pytest
       shell: bash
       run: |
-        python -m pytest --cov=insolver --cov-report xml
+        poetry run pytest --cov=insolver --cov-report xml
     - name: Code coverage with codecov on (ubuntu-latest & Python 3.10 & master)
       if: |
         (matrix.os == 'ubuntu-latest' && matrix.python-version == '3.10' && github.ref == 'refs/heads/master')

.pre-commit-config.yaml

@@ -1,17 +1,18 @@
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
+    rev: v4.5.0
     hooks:
     -   id: check-added-large-files
+        args: ['--maxkb=800']
     -   id: check-yaml
     -   id: check-toml
     -   id: end-of-file-fixer
     -   id: trailing-whitespace
 -   repo: https://github.com/psf/black
-    rev: 23.7.0
+    rev: 24.4.2
     hooks:
     -   id: black-jupyter
 -   repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: 'v0.0.246'
+    rev: 'v0.4.4'
     hooks:
     -   id: ruff

README.md

@@ -68,7 +68,7 @@ python -m pytest
 
 tests with coverage:
 ```shell
-python -m pytest --cov=insolver; coverage html; xdg-open htmlcov/index.html
+python -m pytest . --cov=insolver --cov-report html
 ```
 
 

insolver/feature_engineering/feature_engineering.py

@@ -132,7 +132,7 @@ def preprocess(self, df, target=None, drop_target=True):
         # create a copy of the DataFrame if inplace=False
         df = df.copy()
 
-        if drop_target:
+        if drop_target and not (self.smoothing or self.sampling or self.dim_red):
             # if target is str add to lists
             if isinstance(target, str):
                 self.normalization_drop.append(target)

insolver/feature_monitoring/homogeneity_report.py

@@ -1,13 +1,13 @@
 import os
 import inspect
 import numpy as np
-import pandas as pd
 import plotly as py
-import jinja2
 from os.path import dirname
 from typing import List, Sequence, Dict, Union
-from plotly.figure_factory import create_distplot
+from pandas import DataFrame
 from plotly import express as px
+from plotly.figure_factory import create_distplot
+from jinja2 import Environment, FileSystemLoader
 
 from .homogeneity_tests import ContinuousHomogeneityTests, DiscreteHomogeneityTests, fillna_cont, fillna_discr
 
@@ -176,8 +176,8 @@ def config_dict(self, config_dict_inp: Dict) -> None:
 
     def build_report(
         self,
-        df1: pd.DataFrame,
-        df2: pd.DataFrame,
+        df1: DataFrame,
+        df2: DataFrame,
         dropna: bool = False,
         name1: str = 'Base subset',
         name2: str = 'Current subset',
@@ -218,9 +218,9 @@ def build_report(
         """
 
         # checking error situations
-        if not isinstance(df1, pd.DataFrame):
+        if not isinstance(df1, DataFrame):
             raise TypeError("df1 must be a pandas DataFrame.")
-        if not isinstance(df2, pd.DataFrame):
+        if not isinstance(df2, DataFrame):
             raise TypeError("df2 must be a pandas DataFrame.")
         features = self.features
         if not (set(features) <= set(df1.columns)):
@@ -368,7 +368,7 @@ def render_report(report_data: list, report_path: str = 'homogeneity_report.html
             raise KeyError("Missing information in nan gap dict.")
 
     # render report
-    env = jinja2.Environment(loader=jinja2.FileSystemLoader(curr_folder))
+    env = Environment(loader=FileSystemLoader(curr_folder))
     template = env.get_template("report_template.html")
     output = template.render(sets=report_data)