feat: init Learning class and add drop_empty_price function

.github/workflows/python-app.yml

@@ -19,15 +19,15 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python 3.10
+      - name: Set up Python 3.x
         uses: actions/setup-python@v4
         with:
-          python-version: "3.10"
+          python-version: "3.x"
 
       - name: install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install ".[test,doc]"
+          pip install ".[test]"
 
       - name: Lint with flake8
         run: |

.github/workflows/static.yml

@@ -32,15 +32,14 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
 
-      - name: Set up Python 3.10
+      - name: Set up Python 3.x
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.x'
 
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          # Installe le projet en mode éditable avec les extras de doc
           pip install -e ".[doc]"
 
       - name: Setup Pages

pyproject.toml

@@ -6,6 +6,7 @@ dependencies = [
     "beautifulsoup4==4.14.3",
     "pandas==2.3.3",
     "tqdm==4.67.3",
+    "scikit-learn==1.7.2"
 ]
 
 [tool.pytest.ini_options]

src/cleaning.py

@@ -92,18 +92,24 @@ class Cleaning:
         self._vins = self._vins.join(appellation_dummies)
         return self
 
+    def drop_empty_price(self) -> "Cleaning":
+        self._vins = self._vins.dropna(subset=["Prix"])
+        return self
+
 
 def main() -> None:
     if len(argv) != 2:
         raise ValueError(f"Usage: {argv[0]} <filename.csv>")
 
     filename = argv[1]
-    cleaning: Cleaning = Cleaning(filename)
+    cleaning: Cleaning = (
-    cleaning.drop_empty_appellation()   \
+        Cleaning(filename)
-        .fill_missing_scores()          \
+        .drop_empty_appellation()
-        .encode_appellation()           \
+        .fill_missing_scores()
-        .getVins()                      \
+        .encode_appellation()
-        .to_csv("clean.csv", index=False)
+        .drop_empty_price()
+    )
+    cleaning.getVins().to_csv("clean.csv", index=False)
 
 
 if __name__ == "__main__":

src/learning.py

@@ -0,0 +1,31 @@
+#!/usr/bin/env python3
+
+from typing import Any, Callable
+from pandas import DataFrame
+from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import train_test_split
+from sklearn.pipeline import make_pipeline
+
+
+class Learning:
+    def __init__(self, vins: DataFrame, target: str) -> None:
+        self.X = vins.drop(target, axis=1)
+        self.y = vins[target]
+
+        self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(
+            self.X, self.y, test_size=0.25, random_state=49
+        )
+
+    def evaluate(
+        self,
+        estimator,
+        pretreatment=None,
+        fn_score=lambda m, xt, yt: m.score(xt, yt),
+    ):
+
+        pipeline = make_pipeline(pretreatment, estimator) if pretreatment else estimator
+        pipeline.fit(self.X_train, self.y_train)
+        score = fn_score(pipeline, self.X_test, self.y_test)
+        prediction = pipeline.predict(self.X_test)
+
+        return score, prediction