Added documentation for python scripts

scripts/legislation_info_generator.py

@@ -1,10 +1,29 @@
 import os
 import pyairtable
 import json
-LEGISLATION_INFO = os.environ['LEGISLATION_INFO']
-api = pyairtable.Api(LEGISLATION_INFO)
-table = api.table('apps7I6q0g9Hyb6j9','tblydWhHOZeqjzycO')
-legislation = table.all()
-legislation_list = [x['fields'] for x in legislation]
-with open("public/legislations_info.json", "w") as outfile: 
-    json.dump(legislation_list, fp = outfile,indent = 4)
+
+def generate_legislation_info(API_KEY, APP_KEY, TBL_KEY):
+    """
+    Generates legislation information and saves it to a JSON file.
+
+    This function retrieves legislation information from an Airtable database,
+    converts it to a list of dictionaries, and saves it to a JSON file for the front-end to access.
+
+    Args:
+        API_KEY (str): The API key for accessing the Airtable database.
+        APP_KEY (str): The application key for accessing the Airtable database.
+        TBL_KEY (str): The table key for accessing the specific table in the Airtable database.
+
+    Returns:
+        None
+    """
+    api = pyairtable.Api(API_KEY)
+    table = api.table(APP_KEY, TBL_KEY)
+    legislation = table.all()
+    legislation_list = [x['fields'] for x in legislation]
+    with open("public/legislations_info.json", "w") as outfile:
+        json.dump(legislation_list, fp=outfile, indent=4)
+
+if __name__ == '__main__':
+    API_KEY = os.environ['LEGISLATION_INFO']
+    generate_legislation_info(API_KEY, 'apps7I6q0g9Hyb6j9', 'tblydWhHOZeqjzycO')

scripts/legislation_votes_generator.py

@@ -2,28 +2,45 @@
 import pandas as pd
 import json
 
-senate_data = []
-with open("public/senate.geo.json", 'r') as f:
-  senate_data = json.load(f)
-assembly_data = []
-with open("public/assembly.geo.json", 'r') as f:
-  assembly_data = json.load(f)
-
-# Function to extract unique bill names from "HCMC support"
-def extract_unique_bills(features):
-    unique_bills = set()
-    for feature in features:
-        hcmc_support = feature['properties'].get('HCMC support', [])
-        unique_bills.update(hcmc_support)
-    return unique_bills
+def create_summary_data(counts, house):
+    """
+    Creates a summary of vote counts for each party in the given house.
+
+    Args:
+        counts (dict): A dictionary containing the vote counts for each party and bill.
+        house (str): The name of the house.
 
-# Extracting unique bills from Senate and Assembly
-unique_bills_senate = extract_unique_bills(senate_data['features'])
-unique_bills_assembly = extract_unique_bills(assembly_data['features'])
+    Returns:
+        list: A list of dictionaries, where each dictionary represents a party and its vote counts.
+              Each dictionary contains the following keys:
+              - "House": The name of the house.
+              - "Party": The name of the party.
+              - The bill names as keys, and the corresponding vote counts as string values.
+    """
+    summary = []
+    for party, bills in counts.items():
+        party_data = {"House": house, "Party": party}
+        party_data.update({bill: str(count) for bill, count in bills.items()})
+        summary.append(party_data)
+    return summary
 
-# Combining and sorting the unique bills
-all_unique_bills = sorted(unique_bills_senate.union(unique_bills_assembly))
 def count_bills_support(features, unique_bills):
+    """
+    Counts the number of bills supported by Democrats and Republicans.
+
+    Args:
+        features (list): A list of features containing information about each legislator.
+        unique_bills (list): A list of unique bill names.
+
+    Returns:
+        dict: A dictionary containing the counts of bills supported by Democrats and Republicans.
+            The dictionary has the following structure:
+            {
+                "Democrat": {bill: count},
+                "Republican": {bill: count}
+            }
+            where 'bill' is the name of the bill and 'count' is the number of occurrences.
+    """
     counts = {
         "Democrat": {bill: 0 for bill in unique_bills},
         "Republican": {bill: 0 for bill in unique_bills}
@@ -44,27 +61,71 @@ def count_bills_support(features, unique_bills):
 
     return counts
 
-# Counting bills for Senate and Assembly
-senate_bills_counts = count_bills_support(senate_data['features'], all_unique_bills)
-assembly_bills_counts = count_bills_support(assembly_data['features'], all_unique_bills)
-def create_summary_data(counts, house):
-    summary = []
-    for party, bills in counts.items():
-        party_data = {"House": house, "Party": party}
-        party_data.update({bill: str(count) for bill, count in bills.items()})
-        summary.append(party_data)
-    return summary
+def extract_unique_bills(features):
+    """
+    Extracts unique bills from a list of features.
+
+    Args:
+        features (list): A list of features.
+
+    Returns:
+        set: A set of unique bills.
+    """
+    unique_bills = set()
+    for feature in features:
+        hcmc_support = feature['properties'].get('HCMC support', [])
+        unique_bills.update(hcmc_support)
+    return unique_bills
+
+import json
+
+def generate_legislation_votes():
+    """
+    Generates a JSON file containing the summary data of legislation votes for the Senate and Assembly.
+
+    This function reads the Senate and Assembly data from the 'public' directory, extracts unique bills,
+    counts the support for each bill in the Senate and Assembly, creates summary data for each chamber,
+    combines the summaries, and writes the final summary data to a new JSON file.
+
+    Args:
+        None
+
+    Returns:
+        None
+    """
+
+    senate_data = []
+    with open("public/senate.geo.json", 'r') as f:
+        senate_data = json.load(f)
+    assembly_data = []
+    with open("public/assembly.geo.json", 'r') as f:
+        assembly_data = json.load(f)
+
+    # Extracting unique bills from Senate and Assembly
+    unique_bills_senate = extract_unique_bills(senate_data['features'])
+    unique_bills_assembly = extract_unique_bills(assembly_data['features'])
+
+    # Combining and sorting the unique bills
+    all_unique_bills = sorted(unique_bills_senate.union(unique_bills_assembly))
+
+    # Counting bills for Senate and Assembly
+    senate_bills_counts = count_bills_support(senate_data['features'], all_unique_bills)
+    assembly_bills_counts = count_bills_support(assembly_data['features'], all_unique_bills)
+
+    # Creating the summary data for Senate and Assembly
+    summary_data_senate = create_summary_data(senate_bills_counts, "Senate")
+    summary_data_assembly = create_summary_data(assembly_bills_counts, "Assembly")
+
+    # Combining both summaries
+    final_summary_data = summary_data_senate + summary_data_assembly
 
-# Creating the summary data for Senate and Assembly
-summary_data_senate = create_summary_data(senate_bills_counts, "Senate")
-summary_data_assembly = create_summary_data(assembly_bills_counts, "Assembly")
+    # Path for the new JSON file
+    output_file_path_dynamic = "public/legislations_votes.json"
 
-# Combining both summaries
-final_summary_data = summary_data_senate + summary_data_assembly
+    # Writing the data to a new JSON file
+    with open(output_file_path_dynamic, 'w') as file:
+        json.dump(final_summary_data, file, indent=4)
 
-# Path for the new JSON file
-output_file_path_dynamic = "public/legislations_votes.json"
 
-# Writing the data to a new JSON file
-with open(output_file_path_dynamic, 'w') as file:
-    json.dump(final_summary_data, file, indent=4)
+if __name__ == '__main__':
+    generate_legislation_votes()

scripts/legislative_support_generator.py

@@ -3,40 +3,67 @@
 import pandas as pd
 import geopandas as gpd
 
-LEGISLATIVE_SUPPORT = os.environ['LEGISLATIVE_SUPPORT']
+def generate_legislative_support_geojson(API_KEY, APP_KEY, TBL_KEY):
+    """
+    Generates GeoJSON files for New York State Assembly and Senate districts
+    with legislative support data.
 
-api = pyairtable.Api(LEGISLATIVE_SUPPORT)
+    The function retrieves data from an Airtable database using the pyairtable library,
+    merges it with GeoJSON files for district boundaries, and exports the merged data
+    as separate GeoJSON files for Assembly and Senate districts.
 
-table = api.table('appD3YhFHjmqJKtZ6','tblgyOlrTfYRaodyb')
+    Args:
+        API_KEY (str): The API key for accessing the Airtable database.
+        APP_KEY (str): The application key for accessing the Airtable database.
+        TBL_KEY (str): The table key for accessing the Airtable database.
 
-table_dict = table.all()
+    Returns:
+    None
+    """
 
-rows = []
+    # Initialize pyairtable API
+    api = pyairtable.Api(API_KEY)
 
-for row in table_dict:
-    rows.append(row['fields'])
-df = pd.DataFrame(rows)
-# Load GeoJSONs
-gdf_assembly = gpd.read_file("public/NYS_Assembly_Districts.geojson").to_crs("EPSG:4326")
-gdf_senate = gpd.read_file("public/NYS_Senate_Districts.geojson").rename(columns={'DISTRICT':'District'}).to_crs("EPSG:4326")
+    # Get table from Airtable
+    table = api.table(APP_KEY,TBL_KEY)
 
-# Split your dataframe by house
-df_assembly = df[df['House'] == 'Assembly']
-df_senate = df[df['House'] == 'Senate']
+    # Retrieve all records from the table
+    table_dict = table.all()
 
-# Merge DataFrames with GeoDataFrames
-gdf_assembly = gdf_assembly.merge(df_assembly, on='District')
-gdf_senate = gdf_senate.merge(df_senate, on='District')
-gdf_assembly['Which HCMC legislation do they support?'] = gdf_assembly['Which HCMC legislation do they support?'].fillna('[]')
-gdf_senate['Which HCMC legislation do they support?'] = gdf_senate['Which HCMC legislation do they support?'].fillna('[]')
+    # Extract fields from the records and create a DataFrame
+    rows = []
+    for row in table_dict:
+        rows.append(row['fields'])
+    df = pd.DataFrame(rows)
 
+    # Load GeoJSONs for Assembly and Senate districts
+    gdf_assembly = gpd.read_file("public/NYS_Assembly_Districts.geojson").to_crs("EPSG:4326")
+    gdf_senate = gpd.read_file("public/NYS_Senate_Districts.geojson").rename(columns={'DISTRICT':'District'}).to_crs("EPSG:4326")
 
-gdf_assembly['Which HCMC legislation do they support?'] = gdf_assembly['Which HCMC legislation do they support?'].apply(lambda x: str(x))
-gdf_senate['Which HCMC legislation do they support?'] = gdf_senate['Which HCMC legislation do they support?'].apply(lambda x: str(x))
+    # Split the DataFrame by house (Assembly and Senate)
+    df_assembly = df[df['House'] == 'Assembly']
+    df_senate = df[df['House'] == 'Senate']
 
-gdf_senate = gdf_senate.rename(columns = {'Which HCMC legislation do they support?':'HCMC support'})
-gdf_assembly = gdf_assembly.rename(columns = {'Which HCMC legislation do they support?':'HCMC support'})
+    # Merge DataFrames with GeoDataFrames based on district
+    gdf_assembly = gdf_assembly.merge(df_assembly, on='District')
+    gdf_senate = gdf_senate.merge(df_senate, on='District')
 
-# Export the new GeoJSONs
-gdf_assembly.to_file('public/assembly.geo.json', driver='GeoJSON')
-gdf_senate.to_file('public/senate.geo.json', driver='GeoJSON')
+    # Fill missing values in the 'Which HCMC legislation do they support?' column with empty lists
+    gdf_assembly['Which HCMC legislation do they support?'] = gdf_assembly['Which HCMC legislation do they support?'].fillna('[]')
+    gdf_senate['Which HCMC legislation do they support?'] = gdf_senate['Which HCMC legislation do they support?'].fillna('[]')
+
+    # Convert the 'Which HCMC legislation do they support?' column to string type
+    gdf_assembly['Which HCMC legislation do they support?'] = gdf_assembly['Which HCMC legislation do they support?'].apply(lambda x: str(x))
+    gdf_senate['Which HCMC legislation do they support?'] = gdf_senate['Which HCMC legislation do they support?'].apply(lambda x: str(x))
+
+    # Rename columns for clarity
+    gdf_senate = gdf_senate.rename(columns = {'Which HCMC legislation do they support?':'HCMC support'})
+    gdf_assembly = gdf_assembly.rename(columns = {'Which HCMC legislation do they support?':'HCMC support'})
+
+    # Export the new GeoJSONs for Assembly and Senate districts
+    gdf_assembly.to_file('public/assembly.geo.json', driver='GeoJSON')    
+    gdf_senate.to_file('public/senate.geo.json', driver='GeoJSON')
+
+if __name__ == '__main__':
+    API_KEY = os.environ['LEGISLATIVE_SUPPORT']
+    generate_legislative_support_geojson(API_KEY, 'appD3YhFHjmqJKtZ6', 'tblgyOlrTfYRaodyb')