First commit with setup and DVC files

.dvc/.gitignore

@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache

.dvc/config

@@ -0,0 +1,6 @@
+[core]
+    remote = remote_storage
+['remote "remote_storage"']
+    url = ../../dvc_remote
+['remote "remote_gdrive"']
+    url = gdrive://1IDOqFaErwMk0BnK2_W2bYrodEE-mCVnN

.dvcignore

@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore

.gitignore

@@ -79,7 +79,7 @@ target/
 .ipynb_checkpoints/
 
 # exclude data from source control by default
-/data/
+#/data/
 
 # Mac OS-specific storage files
 .DS_Store

data/.gitignore

@@ -0,0 +1 @@
+/raw

data/raw.dvc

@@ -0,0 +1,6 @@
+outs:
+- md5: 90c3e04bb8fa1558eb70f9096b5b6010.dir
+  size: 31082914
+  nfiles: 4
+  hash: md5
+  path: raw

src/data/make_dataset.py

@@ -21,10 +21,10 @@ def main(input_filepath, output_filepath):
 
     # Prompt the user for input file paths
     input_filepath= click.prompt('Enter the file path for the input data', type=click.Path(exists=True))
-    input_filepath_users = f"{input_filepath}\\usagers-2021.csv"
-    input_filepath_caract = f"{input_filepath}\\caracteristiques-2021.csv"
-    input_filepath_places = f"{input_filepath}\\lieux-2021.csv"
-    input_filepath_veh = f"{input_filepath}\\vehicules-2021.csv"
+    input_filepath_users = f"{input_filepath}/usagers-2021.csv"
+    input_filepath_caract = f"{input_filepath}/caracteristiques-2021.csv"
+    input_filepath_places = f"{input_filepath}/lieux-2021.csv"
+    input_filepath_veh = f"{input_filepath}/vehicules-2021.csv"
     output_filepath = click.prompt('Enter the file path for the output preprocessed data (e.g., output/preprocessed_data.csv)', type=click.Path())
 
     # Call the main data processing function with the provided file paths