ajout : aout des tests test_cleaning.py

cleaning.py

@@ -0,0 +1,106 @@
+#!/usr/bin/env python3
+from pandas import DataFrame, to_numeric
+import pandas as pd
+
+SCORE_COLS = ["Robert", "Robinson", "Suckling"]
+
+
+def display_info(df: DataFrame, name: str = "DataFrame") -> None:
+    """
+    Affiche un résumé du DataFrame
+        -la taille
+        -types des colonnes
+        -valeurs manquantes
+        -statistiques numériques
+    """
+    print(f"\n===== {name} =====")
+
+    print(f"Shape : {df.shape[0]} lignes × {df.shape[1]} colonnes")
+
+    print("\nTypes des colonnes :")
+    print(df.dtypes)
+
+    print("\nValeurs manquantes :")
+    print(df.isna().sum())
+
+    print("\nStatistiques numériques :")
+    print(df.describe().round(2))
+
+
+def drop_empty_appellation(df: DataFrame) -> DataFrame:
+
+    return df.dropna(subset=["Appellation"])
+
+
+def mean_score(df: DataFrame, col: str) -> DataFrame:
+    """
+    Calcule la moyenne d'une colonne de score par appellation.
+        - Convertit les valeurs en numériques, en remplaçant les non-convertibles par NaN
+        - Calcule la moyenne par appellation
+        - Remplace les NaN résultants par 0 
+
+    """
+    tmp = df[["Appellation", col]].copy()
+
+    tmp[col] = to_numeric(tmp[col], errors="coerce")
+
+    # moyenne par appellation
+    means = tmp.groupby("Appellation", as_index=False)[col].mean()
+    
+    means[col] = means[col].fillna(0)
+    
+    means = means.rename(columns={col: f"mean_{col}"})
+    
+    return means
+
+
+def mean_robert(df: DataFrame) -> DataFrame:
+    return mean_score(df, "Robert")
+
+
+def mean_robinson(df: DataFrame) -> DataFrame:
+    return mean_score(df, "Robinson")
+
+
+def mean_suckling(df: DataFrame) -> DataFrame:
+    return mean_score(df, "Suckling")
+
+
+def fill_missing_scores(df: DataFrame) -> DataFrame:
+    """
+    Remplacer les notes manquantes par la moyenne
+    des vins de la même appellation.
+    """
+    df_copy = df.copy()
+    df_copy["Appellation"] = df_copy["Appellation"].astype(str).str.strip()
+
+    for score in SCORE_COLS:
+        df_copy[score] = to_numeric(df_copy[score], errors="coerce")
+
+    temp_cols: list[str] = []
+
+    for score in SCORE_COLS:
+        mean_df = mean_score(df_copy, score)
+        mean_name = f"mean_{score}"
+        temp_cols.append(mean_name)
+
+        df_copy = df_copy.merge(mean_df, on="Appellation", how="left")
+        df_copy[score] = df_copy[score].fillna(df_copy[mean_name])
+
+    df_copy = df_copy.drop(columns=temp_cols)
+    return df_copy
+
+
+def encode_appellation(df: DataFrame, column: str = "Appellation") -> DataFrame:
+    """
+    Remplace la colonne 'Appellation' par des colonnes indicatrices
+    """
+    df_copy = df.copy()
+    
+    appellations = df_copy[column].astype(str).str.strip()
+
+    appellation_dummies = pd.get_dummies(appellations)
+
+    df_copy = df_copy.drop(columns=[column])
+
+    return df_copy.join(appellation_dummies)

main.py

@@ -5,13 +5,57 @@ from os.path import normpath, join
 from sys import argv
 from pandas import read_csv, DataFrame
 
+from cleaning import (display_info,
+                      drop_empty_appellation,
+                      mean_robert,
+                      mean_robinson,
+                      mean_suckling,
+                      fill_missing_scores,
+                      encode_appellation)
+
+
+def load_csv(filename: str) -> DataFrame:
+    path: str = normpath(join(getcwd(), filename))
+    return read_csv(path)
+
+
+def save_csv(df: DataFrame, out_filename: str) -> None:
+    df.to_csv(out_filename, index=False)
+
+
 def main() -> None:
     if len(argv) != 2:
-        raise ValueError(f"{argv[0]} <filename.csv>")
+        raise ValueError(f"Usage: {argv[0]} <filename.csv>")
+
+    df = load_csv(argv[1])
+
+    display_info(df, "Avant le nettoyage")
+
+    df = drop_empty_appellation(df)
+    save_csv(df, "donnee_clean.csv")
+    display_info(df, "Après nettoyage d'appellations manquantes")
+    
+    #la moyenne des notes des vins pour chaque appellation
+    robert_means = mean_robert(df)
+    save_csv(robert_means, "mean_robert_by_appellation.csv")
+    display_info(robert_means, "Moyennes Robert par appellation")
+
+    robinson_means = mean_robinson(df)
+    save_csv(robinson_means, "mean_robinson_by_appellation.csv")
+    display_info(robinson_means, "Moyennes Robinson par appellation")
+  
+    suckling_means = mean_suckling(df)
+    save_csv(suckling_means, "mean_suckling_by_appellation.csv")
+    display_info(suckling_means, "Moyennes Suckling par appellation")
+    
+    df_missing_scores = fill_missing_scores(df)
+    save_csv(df_missing_scores, "donnee_filled.csv")
+    display_info(df_missing_scores, "Après remplissage des notes manquantes par la moyenne de l'appellation")
+     
+    df_ready = encode_appellation(df_missing_scores)
+    save_csv(df_ready, "donnee_ready.csv")
+    display_info(df_ready, "Après remplacer la colonne 'Appellation' par des colonnes indicatrices")
 
-    path: str = normpath(join(getcwd(), argv[1]))
-    db: DataFrame = read_csv(path)
-    print(db.all())
 
 if __name__ == "__main__":
     try:

scraper.py

@@ -3,9 +3,12 @@
 from sys import argv
 from typing import cast
 from requests import HTTPError, Response, Session
+from requests.exceptions import Timeout, ConnectionError
+import time
 from bs4 import BeautifulSoup, Tag
 from collections import OrderedDict
 from json import JSONDecodeError, loads
+from pathlib import Path
 
 
 class _ScraperData:
@@ -151,10 +154,7 @@ class _ScraperData:
         parker = self.parker()
         robinson = self.robinson()
         suckling = self.suckling()
-        try:
+        prix = self.prix()
-            prix = self.prix()
-        except ValueError:
-            prix = None
 
         return f"{appellation},{parker},{robinson},{suckling},{prix}"
 
@@ -174,6 +174,12 @@ class Scraper:
         # Très utile pour éviter de renvoyer toujours les mêmes handshake
         # TCP et d'avoir toujours une connexion constante avec le server
         self._session: Session = Session()
+        self._session.headers.update({
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+                        "AppleWebKit/537.36 (KHTML, like Gecko) "
+                        "Chrome/122.0.0.0 Safari/537.36",
+            "Accept-Language": "fr-FR,fr;q=0.9,en;q=0.8",
+        })
         # Système de cache pour éviter de solliciter le serveur inutilement
         self._latest_request: tuple[(str, Response)] | None = None
         self._latest_soups: OrderedDict[str, BeautifulSoup] = OrderedDict[
@@ -194,9 +200,20 @@ class Scraper:
             HTTPError: Si le serveur renvoie un code d'erreur (4xx, 5xx).
         """
         target_url: str = self._url + subdir.lstrip("/")
-        response: Response = self._session.get(url=target_url, timeout=10)
+        
-        response.raise_for_status()
+        last_exc: Exception | None = None
-        return response
+        for attempt in range(1, 4):
+            try:
+                response: Response = self._session.get(url=target_url, timeout=30)
+                response.raise_for_status()
+                return response
+            except (Timeout, ConnectionError) as e:
+                last_exc = e
+                print(f"Timeout/ConnectionError ({attempt}/3) sur {target_url}: {e}")
+                time.sleep(2 * attempt)  # 2s, 4s, 6s
+
+        # après 3 essais, on abandonne
+        raise last_exc if last_exc else RuntimeError("Request failed")
 
     def getresponse(self, subdir: str = "", use_cache: bool = True) -> Response:
         """
@@ -318,6 +335,27 @@ class Scraper:
         except (JSONDecodeError, HTTPError):
             return None
 
+    def _save_progress(self, page: int, i: int, last_link: str) -> None:
+        Path("progress.txt").write_text(f"{page},{i},{last_link}", encoding="utf-8")
+
+
+    def _load_progress(self) -> tuple[int, int, str | None]:
+        p = Path("progress.txt")
+        if not p.exists():
+            return (1, 0, None)
+
+        try:
+            parts = p.read_text(encoding="utf-8").strip().split(",", 2)
+
+            page = int(parts[0])
+            i = int(parts[1])
+
+            last_link = parts[2] if len(parts) == 3 and parts[2] != "" else None
+            return (page, i, last_link)
+
+        except Exception:
+            return (1, 0, None)
+        
     def getvins(self, subdir: str, filename: str):
         """_summary_
 
@@ -325,11 +363,17 @@ class Scraper:
             subdir (str): _description_
             filename (str): _description_
         """
-        with open(filename, "a") as f:
+        start_page, start_i, last_link = self._load_progress()
+        print(f"__INFO__ Reprise à page={start_page}, index={start_i}, last_link={last_link}")
+        
+        with open(filename, "a", encoding="utf-8") as f:
             cache: set[str] = set[str]()
-            page = 0
+            
-            _ = f.write("Appellation,Robert,Robinson,Suckling,Prix\n")
+            if f.tell() == 0:
-
+                _ = f.write("Appellation,Robert,Robinson,Suckling,Prix\n")
+                
+            page = start_page - 1
+            
             while True:
                 page += 1
                 products_list = self._geturlproductslist(f"{subdir}?page={page}")
@@ -338,24 +382,40 @@ class Scraper:
                     break
 
                 products_list_length = len(products_list)
-                for i, product in enumerate(products_list):
+                start_at = start_i if page == start_page else 0
+
+                for i in range(start_at, products_list_length):
+                    product = products_list[i]
                     if not isinstance(product, dict):
                         continue
 
                     link = product.get("seoKeyword")
+                    if not link:
+                        continue
+
+                    # pour eviter les doublons :
+                    if (page == start_page) and (last_link is not None) and (link == last_link):
+                        self._save_progress(page, + 1, link)
+                        continue
+
+                    self._save_progress(page, i + 1, link)
+
+                    if link in cache:
+                        continue
+
+                    try:
+                        infos = self.getjsondata(link).informations()
+                        _ = f.write(infos + "\n")
+                        print(f"page: {page} | {i + 1}/{products_list_length} {link}")
+                        cache.add(link)
+
+                    except (JSONDecodeError, HTTPError) as e:
+                        print(f"Erreur sur le produit {link}: {e}")
 
-                    if link and link not in cache:
-                        try:
-                            infos = self.getjsondata(link).informations()
-                            _ = f.write(infos + "\n")
-                            print(
-                                f"page: {page} | {i + 1}/{products_list_length} {link}"
-                            )
-                            cache.add(link)
-                        except (JSONDecodeError, HTTPError) as e:
-                            print(f"Erreur sur le produit {link}: {e}")
                 f.flush()
 
+        Path("progress.txt").unlink(missing_ok=True)
+
 
 def main() -> None:
     if len(argv) != 2:

test_cleaning.py

@@ -0,0 +1,64 @@
+import pandas as pd
+import pytest
+from pandas import DataFrame
+
+from cleaning import (
+    SCORE_COLS,
+    drop_empty_appellation,
+    mean_score,
+    fill_missing_scores,
+    encode_appellation,
+)
+
+
+@pytest.fixture
+def df_raw() -> DataFrame:
+    return pd.DataFrame({
+        "Appellation": ["Pauillac", "Pauillac ", "Margaux", None, "Pomerol", "Pomerol"],
+        "Robert":      ["95", None, "bad", 90, None, None],
+        "Robinson":    [None, "93", 18, None, None, None],
+        "Suckling":    [96, None, None, None, 91, None],
+        "Prix":        ["10.0", "11.0", "20.0", "30.0", "40.0", "50.0"],
+    })
+
+
+def test_drop_empty_appellation(df_raw: DataFrame):
+    out = drop_empty_appellation(df_raw)
+    assert out["Appellation"].isna().sum() == 0
+    assert len(out) == 5 
+
+
+def test_mean_score_zero_when_no_scores(df_raw: DataFrame):
+    out = drop_empty_appellation(df_raw)
+    m = mean_score(out, "Robert")
+    assert list(m.columns) == ["Appellation", "mean_Robert"]
+
+    # Pomerol n'a aucune note Robert => moyenne doit être 0
+    pomerol_mean = m.loc[m["Appellation"].str.strip() == "Pomerol", "mean_Robert"].iloc[0]
+    assert pomerol_mean == 0
+
+
+def test_fill_missing_scores(df_raw: DataFrame):
+    out = drop_empty_appellation(df_raw)
+    filled = fill_missing_scores(out)
+
+    # plus de NaN dans les colonnes de scores
+    for col in SCORE_COLS:
+        assert filled[col].isna().sum() == 0
+
+    assert filled.loc[1, "Robert"] == 95.0
+
+    # pas de colonnes temporaires mean_*
+    for col in SCORE_COLS:
+        assert f"mean_{col}" not in filled.columns
+
+
+def test_encode_appellation(df_raw: DataFrame):
+    out = drop_empty_appellation(df_raw)
+    filled = fill_missing_scores(out)
+    encoded = encode_appellation(filled)
+
+    # la colonne texte disparaît
+    assert "Appellation" not in encoded.columns
+    assert "Pauillac" in encoded.columns
+    assert encoded.loc[0, "Pauillac"] == 1