chore: Update dependencies and add utility functions for querying and aggregating data

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+# .env
+# .venv
+# env/
+# venv/
+# ENV/
+# env.bak/
+# venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

app.py

@@ -1,9 +1,11 @@
 import streamlit as st
 import pandas as pd
+import geopandas as gpd
 import folium
 from streamlit_folium import folium_static
 from pyeuropeana import apis
 from dotenv import load_dotenv
+from utils import get_provider_data, aggregate_location_counts
 import os
 
 # Load environment variables
@@ -14,25 +16,8 @@ if 'EUROPEANA_API_KEY' not in os.environ:
     st.error("EUROPEANA_API_KEY is not set in the environment variables. Please set it and restart the app.")
     st.stop()
 
-def get_provider_data(provider_name, rows=1000):
-    myquery = apis.search(
-        query='pl_wgs84_pos_lat:(*)',
-        qf=f'DATA_PROVIDER:"{provider_name}"',
-        rows=rows
-    )
-    
-    myquery_df = pd.DataFrame(myquery["items"], columns=['edmPlaceLatitude', 'edmPlaceLongitude', 'id', 'country', 'dataProvider', 'dcCreator'])
-    
-    def extract_single(x):
-        return x[0] if isinstance(x, list) and len(x) > 0 else x
-    
-    for col in ['edmPlaceLatitude', 'edmPlaceLongitude', 'country', 'dataProvider', 'dcCreator']:
-        myquery_df[col] = myquery_df[col].apply(extract_single)
-    
-    myquery_df['edmPlaceLatitude'] = pd.to_numeric(myquery_df['edmPlaceLatitude'], errors='coerce')
-    myquery_df['edmPlaceLongitude'] = pd.to_numeric(myquery_df['edmPlaceLongitude'], errors='coerce')
-    
-    return myquery_df
+# Load world map dataset
+world = gpd.read_file(gpd.datasets.get_path('naturalearth_lowres'))
 
 # Set up the Streamlit app
 st.title('Europeana Data Explorer')
@@ -46,7 +31,7 @@ if st.button('Fetch Data'):
         # Show loading message
         with st.spinner('Fetching data...'):
             # Get the data
-            df = get_provider_data(provider_name)
+            df = get_provider_data(provider_name, world)
         
         # Display the data
         st.subheader(f'Data from {provider_name}')

utils.py

@@ -0,0 +1,65 @@
+def get_provider_data(provider_name, world_gdf, rows=1000):
+    """
+    Query Europeana API for a specific data provider and return a processed DataFrame.
+    
+    Args:
+    provider_name (str): Name of the data provider to query
+    world_gdf (GeoDataFrame): World map GeoDataFrame for spatial join
+    rows (int): Number of rows to retrieve (default 1000)
+    
+    Returns:
+    pandas.DataFrame: Processed DataFrame with the queried data, including object location
+    """
+    # Query the Europeana API
+    myquery = apis.search(
+        query='pl_wgs84_pos_lat:(*)',
+        qf=f'DATA_PROVIDER:"{provider_name}"',
+        rows=rows
+    )
+    
+    # Create initial DataFrame
+    myquery_df = pd.DataFrame(myquery["items"], columns=['edmPlaceLatitude', 'edmPlaceLongitude', 'id', 'country', 'dataProvider', 'dcCreator'])
+    
+    # Function to extract single value from list or return original value
+    def extract_single(x):
+        return x[0] if isinstance(x, list) and len(x) > 0 else x
+    
+    # Apply extraction to relevant columns
+    for col in ['edmPlaceLatitude', 'edmPlaceLongitude', 'country', 'dataProvider', 'dcCreator']:
+        myquery_df[col] = myquery_df[col].apply(extract_single)
+    
+    # Convert latitude and longitude to float type
+    myquery_df['edmPlaceLatitude'] = pd.to_numeric(myquery_df['edmPlaceLatitude'], errors='coerce')
+    myquery_df['edmPlaceLongitude'] = pd.to_numeric(myquery_df['edmPlaceLongitude'], errors='coerce')
+    
+    # Create a GeoDataFrame from the DataFrame
+    gdf = gpd.GeoDataFrame(
+        myquery_df, 
+        geometry=gpd.points_from_xy(myquery_df.edmPlaceLongitude, myquery_df.edmPlaceLatitude), 
+        crs="EPSG:4326"
+    )
+
+    # Perform spatial join
+    gdf_with_country = gpd.sjoin(gdf, world_gdf[['geometry', 'name']], how='left', op='within')
+
+    # Add the new column to the original DataFrame
+    myquery_df['object_location'] = gdf_with_country['name']
+
+    # Fill NaN values (points that don't fall within any country) with "Unknown"
+    myquery_df['object_location'] = myquery_df['object_location'].fillna("Unknown")
+    
+    return myquery_df
+
+def aggregate_location_counts(df):
+    """
+    Aggregate the data by object_location and get counts.
+    
+    Args:
+    df (pandas.DataFrame): DataFrame containing 'object_location' column
+    
+    Returns:
+    pandas.DataFrame: DataFrame with object locations and their counts, sorted by count
+    """
+    location_counts = df['object_location'].value_counts().reset_index()
+    location_counts.columns = ['object_location', 'count']
+    return location_counts.sort_values('count', ascending=False)