feat: ajout premier modele (1ere partie)

pyproject.toml

@@ -6,7 +6,8 @@ dependencies = [
     "beautifulsoup4==4.14.3",
     "pandas==2.3.3",
     "tqdm==4.67.3",
-    "scikit-learn==1.7.2"
+    "scikit-learn==1.7.2",
+    "matplotlib==3.10.8"
 ]
 
 [tool.pytest.ini_options]

src/learning.py

@@ -1,10 +1,14 @@
-#!/usr/bin/env python3
+
 
 from typing import Any, Callable
 from pandas import DataFrame
 from sklearn.linear_model import LinearRegression
+from sklearn.preprocessing import StandardScaler
 from sklearn.model_selection import train_test_split
 from sklearn.pipeline import make_pipeline
+import matplotlib.pyplot as plt
+
+from cleaning import Cleaning
 
 
 class Learning:
@@ -29,3 +33,61 @@ class Learning:
         prediction = pipeline.predict(self.X_test)
 
         return score, prediction
+
+    def draw(self, predictions, y_actual):
+        plt.figure(figsize=(8, 6))
+
+        plt.scatter(
+            predictions,
+            y_actual,
+            alpha=0.5,
+            c="royalblue",
+            edgecolors="k",
+            label="Vins",
+        )
+
+        mn = min(predictions.min(), y_actual.min())
+        mx = max(predictions.max(), y_actual.max())
+        plt.plot(
+            [mn, mx],
+            [mn, mx],
+            color="red",
+            linestyle="--",
+            lw=2,
+            label="Prédiction Parfaite",
+        )
+
+        plt.xlabel("Prix estimés (estim_LR)")
+        plt.ylabel("Prix réels (y_test)")
+        plt.title("titre")
+        plt.legend()
+        plt.grid(True, linestyle=":", alpha=0.6)
+
+        plt.show()
+
+
+df_vins = (
+    Cleaning("data.csv")
+    .drop_empty_appellation()
+    .fill_missing_scores()
+    .encode_appellation()
+    .drop_empty_price()
+    .getVins()
+)
+
+etude = Learning(df_vins, target="Prix")
+
+print("--- Question 16 & 17 ---")
+score_simple, estim_simple = etude.evaluate(LinearRegression())
+print(f"Score R² (LR Simple) : {score_simple:.4f}")
+
+etude.draw(estim_simple, etude.y_test)
+
+
+print("\n--- Question 18 ---")
+score_std, estim_std = etude.evaluate(
+    estimator=LinearRegression(), pretreatment=StandardScaler()
+)
+print(f"Score R² (Standardisation + LR) : {score_std:.4f}")
+
+etude.draw(estim_std, etude.y_test)