Organize repo, create tests, add CI support

.github/workflows/pytest.yml

@@ -0,0 +1,29 @@
+name: Run Pytest on Push
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2 # Checks out your repository code
+      - name: Set up Python
+        uses: actions/setup-python@v2
+
+        # Specify your Python version here
+        with:
+          python-version: "3.10.10"
+
+      # Install all modules used in code
+      - name: Install Dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+
+      # Run your pytest tests
+      - name: Run Pytest
+        run: |
+          pytest

requirements.txt

@@ -1,3 +1,5 @@
+# PYTHON VERSION: 3.10.10
+
 numpy==1.24.2
 pytest==7.4.2
 pandas==2.0.0

site_slotting_new/data_cleaning.py

@@ -0,0 +1,36 @@
+import pandas as pd
+
+
+def preprocess_df(file_path: str) -> pd.DataFrame:
+    df = pd.read_csv(file_path)
+    relevant_features = [
+        "Email Address",
+        "Name",
+        "Castlemont",
+        "Montera",
+        "DeJean",
+        "DCA",
+        "Rudsdale",
+        "Longfellow",
+        "SquashDrive",
+        "John Henry",
+        "Life Academy",
+        "CC Member",
+        "Exec",
+        "Spanish Speaker",
+        "Can Drive",
+        "Has Car",
+        "Gender",
+        "Site Leader",
+    ]
+    # Select columns that contain a feature
+    relevant_columns = [
+        col
+        for col in df.columns
+        if any(feature in col for feature in relevant_features)
+    ]
+
+    # Create a new DataFrame with only the relevant columns
+    pre_processed_df = df[relevant_columns]
+
+    return pre_processed_df

tests/algorithm_test.py

@@ -0,0 +1,18 @@
+import pytest
+import pandas as pd
+
+from site_slotting_new import algorithm
+from site_slotting_new import data_cleaning
+
+
+def test_preprocess_df1():
+    file = "data/anonymized_spring24_sites_data.csv"
+    cleaned_data = data_cleaning.preprocess_df(file)
+    print(cleaned_data.columns)
+    assert cleaned_data.shape[1] <= 18
+
+
+def test_preprocess_df2():
+    file = "data/anonymized_spring24_sites_data.csv"
+    cleaned_data = data_cleaning.preprocess_df(file)
+    assert cleaned_data.shape[1] == 18