ajout: learning.ipnyb dans mkdocs et finission du modele 1

mkdocs.yml

@@ -7,6 +7,7 @@ theme:
 plugins:
   - search
   - mkdocstrings
+  - mkdocs-jupyter
 
 extra:
   generator: false

pyproject.toml

@@ -7,7 +7,7 @@ dependencies = [
     "pandas==2.3.3",
     "tqdm==4.67.3",
     "scikit-learn==1.7.2",
-    "matplotlib==3.10.8"
+    "matplotlib==3.10.8",
 ]
 
 [tool.pytest.ini_options]
@@ -16,7 +16,12 @@ testpaths = ["tests"]
 
 [project.optional-dependencies]
 test = ["pytest==8.4.2", "requests-mock==1.12.1", "flake8==7.3.0"]
-doc = ["mkdocs<2.0.0", "mkdocs-material==9.6.23", "mkdocstrings[python]"]
+doc = [
+    "mkdocs<2.0.0",
+    "mkdocs-material==9.6.23",
+    "mkdocstrings[python]",
+    "mkdocs-jupyter==0.26.1",
+]
 
 [build-system]
 requires = ["setuptools", "wheel"]

src/cleaning.py

@@ -97,11 +97,12 @@ class Cleaning:
         return self
 
 
-def main() -> None:
+def main(filename: str | None = None) -> None:
+    if not filename:
         if len(argv) != 2:
             raise ValueError(f"Usage: {argv[0]} <filename.csv>")
-
         filename = argv[1]
+        
     cleaning: Cleaning = (
         Cleaning(filename)
         .drop_empty_appellation()

src/learning.py

@@ -1,93 +1,65 @@
+# 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
 
 
-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
+# class Learning:
+#     def __init__(self, vins: DataFrame, target: str) -> None:
+#         self.X = vins.drop(target, axis=1)
+#         self.y = vins[target]
 
-from cleaning import Cleaning
+#         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),
+#     ):
 
-class Learning:
-    def __init__(self, vins: DataFrame, target: str) -> None:
-        self.X = vins.drop(target, axis=1)
-        self.y = vins[target]
+#         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)
 
-        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
-        )
+#         return score, prediction
 
-    def evaluate(
-        self,
-        estimator,
-        pretreatment=None,
-        fn_score=lambda m, xt, yt: m.score(xt, yt),
-    ):
+#     def draw(self, predictions, y_actual):
+#         plt.figure(figsize=(8, 6))
 
-        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)
+#         plt.scatter(
+#             predictions,
+#             y_actual,
+#             alpha=0.5,
+#             c="royalblue",
+#             edgecolors="k",
+#             label="Vins",
+#         )
 
-        return score, prediction
+#         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",
+#         )
 
-    def draw(self, predictions, y_actual):
-        plt.figure(figsize=(8, 6))
+#         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.scatter(
-            predictions,
-            y_actual,
-            alpha=0.5,
-            c="royalblue",
-            edgecolors="k",
-            label="Vins",
-        )
+#         plt.show()
 
-        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)

src/scraper.py

@@ -490,9 +490,10 @@ class Scraper:
                 savestate((page, cache))
 
 
-def main() -> None:
+def main(filename: str | None = None, suburl: str | None = None) -> None:
+    if filename is None or suburl is None:
         if len(argv) != 3:
-        raise ValueError(f"{argv[0]} <filename> <sous-url>")
+            raise ValueError(f"Usage: python {argv[0]} <filename> <sous-url>")
         filename = argv[1]
         suburl = argv[2]