fix: banking example dataset's link dead, replaced with original source

Author: sbrugman

examples/bank_marketing_data/banking_data.py

@@ -5,12 +5,12 @@
 import pandas as pd
 
 from pandas_profiling import ProfileReport
-from pandas_profiling.utils.cache import cache_file
+from pandas_profiling.utils.cache import cache_zipped_file
 
 if __name__ == "__main__":
-    file_name = cache_file(
+    file_name = cache_zipped_file(
         "bank-full.csv",
-        "https://storage.googleapis.com/erwinh-public-data/bankingdata/bank-full.csv",
+        "https://archive.ics.uci.edu/ml/machine-learning-databases/00222/bank.zip",
     )
 
     # Download the UCI Bank Marketing Dataset

src/pandas_profiling/utils/cache.py

@@ -1,4 +1,5 @@
 """Dataset cache utility functions"""
+import zipfile
 from pathlib import Path
 
 import requests
@@ -20,9 +21,41 @@ def cache_file(file_name: str, url: str) -> Path:
     data_path = get_data_path()
     data_path.mkdir(exist_ok=True)
 
+    file_path = data_path / file_name
+
     # If not exists, download and create file
-    if not (data_path / file_name).exists():
-        data = requests.get(url)
-        (data_path / file_name).write_bytes(data.content)
+    if not file_path.exists():
+        response = requests.get(url)
+        file_path.write_bytes(response.content)
+
+    return file_path
+
+
+def cache_zipped_file(file_name: str, url: str) -> Path:
+    """Check if file_name already is in the data path, otherwise download it from url.
+
+    Args:
+        file_name: the file name
+        url: the URL of the dataset
+
+    Returns:
+        The relative path to the dataset
+    """
+
+    data_path = get_data_path()
+    data_path.mkdir(exist_ok=True)
+
+    file_path = data_path / file_name
+
+    # If not exists, download and create file
+    if not file_path.exists():
+        response = requests.get(url)
+        tmp_path = data_path / "tmp.zip"
+        tmp_path.write_bytes(response.content)
+
+        with zipfile.ZipFile(tmp_path, "r") as zip_file:
+            zip_file.extract(file_path.name, data_path)
+
+        tmp_path.unlink()
 
-    return data_path / file_name
+    return file_path

tests/issues/test_issue377.py

@@ -8,14 +8,14 @@
 import pytest
 
 import pandas_profiling
-from pandas_profiling.utils.cache import cache_file
+from pandas_profiling.utils.cache import cache_zipped_file
 
 
 @pytest.mark.skipif(sys.version_info < (3, 6), reason="requires python3.6 or higher")
 def test_issue377():
-    file_name = cache_file(
+    file_name = cache_zipped_file(
         "bank-full.csv",
-        "https://storage.googleapis.com/erwinh-public-data/bankingdata/bank-full.csv",
+        "https://archive.ics.uci.edu/ml/machine-learning-databases/00222/bank.zip",
     )
 
     # Download the UCI Bank Marketing Dataset