titanic dataset is not downloaded

Author: Julien Roussel

.github/workflows/publish.yml

@@ -11,9 +11,9 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Set up Python
-      uses: actions/setup-python@v3
+      uses: actions/setup-python@v3.12.0
       with:
         python-version: '3.10'
     - name: Install dependencies

AUTHORS.rst

@@ -5,10 +5,10 @@ Credits
 Development Team
 ----------------
 
-* Julien Roussel <jroussel@quantmetry.com>
-* Anh Khoa Ngo Ho <angoho@quantmetry.com>
-* Charles-Henri Prat <chprat@quantmetry.com>
-* Guillaume Saës <gsaes@quantmetry.com>
+* Julien Roussel <julien.a.roussel@capgemini.com>
+* Anh Khoa Ngo Ho <anh-khoa.ngo-ho@capgemini.com>
+* Guillaume Saës <guillaume.saes@capgemini.com>
+* Yasser Zidani <yasser.zidani@capgemini.com>
 
 Past Contributors
 -----------------
@@ -19,3 +19,4 @@ Past Contributors
 * Mikaïl Duran
 * Rima Hajou
 * Thomas Morzadec
+* Charles-Henri Prat

qolmat/imputations/preprocessing.py

@@ -320,7 +320,6 @@ def make_pipeline_mixte_preprocessing(
 
     if avoid_new:
         preprocessor.steps.append(("bins", BinTransformer()))
-    print(preprocessor)
     return preprocessor
 
 

qolmat/utils/data.py

@@ -119,21 +119,25 @@ def get_data(
         df = read_csv_local("conductors")
         return df
     elif name_data == "Titanic":
-        df = read_csv_local("titanic", sep=";")
-        df = df.dropna(how="all")
-        df = df.drop(
-            columns=[
-                "pclass",
-                "name",
-                "home.dest",
-                "cabin",
-                "ticket",
-                "boat",
-                "body",
-            ]
-        )
-        df["age"] = pd.to_numeric(df["age"], errors="coerce")
-        df["fare"] = pd.to_numeric(df["fare"].str.replace(",", ""), errors="coerce")
+        # df = read_csv_local("titanic", sep=";")
+        path = "https://gist.githubusercontent.com/fyyying/4aa5b471860321d7b47fd881898162b7/raw/"
+        "6907bb3a38bfbb6fccf3a8b1edfb90e39714d14f/titanic_dataset.csv"
+        df = pd.read_csv(path)
+        # df = df.dropna(how="all")
+        # df = df.drop(
+        #     columns=[
+        #         "pclass",
+        #         "name",
+        #         "home.dest",
+        #         "cabin",
+        #         "ticket",
+        #         "boat",
+        #         "body",
+        #     ]
+        # )
+        df = df[["Survived", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked"]]
+        df["Age"] = pd.to_numeric(df["Age"], errors="coerce")
+        df["Fare"] = pd.to_numeric(df["Fare"], errors="coerce")
         return df
     elif name_data == "Artificial":
         city = "Wonderland"