dggs_join (for benchmarking)

dggs_join.py

import os
import geopandas as gpd
import h3pandas


folder_path = 'E:/DGGS_Benchmark/vectors'

# Get a list of all GPKG files in the folder
v_files = [file for file in os.listdir(folder_path) if file.endswith('.gpkg')]
v_files = sorted(v_files)

# Specify the number of files to open (e.g., 5)
num_files_to_open = 10
h3_res=14   #Setting h3 resolution

# Initialize the first DataFrame to store the combined data
combined_df = gpd.read_file('E:/DGGS_Benchmark/vectors/vector_001.gpkg').to_crs(4326)
combined_df = combined_df.h3.polyfill(h3_res,explode=True).drop(columns=['geometry']) #polyfilling at resolution
combined_df.columns = ['001', *combined_df.columns[1:]]
combined_df = combined_df.set_index('h3_polyfill')  #setting index to h3 cells

# Loop through each CSV file and concatenate the data horizontally
for file in v_files[1:num_files_to_open]:
    file_path = os.path.join(folder_path, file)
    col_name = file.split('_')[1].split('.')[0]  # Extracting the column name from the file name
    df = gpd.read_file(file_path).to_crs(4326)
    df = df.h3.polyfill(h3_res,explode=True).drop(columns=['geometry'])
    df.columns = [col_name, *df.columns[1:]] #Setting the column to the file
    df = df.set_index('h3_polyfill')
    combined_df = combined_df.join(df)  #joining on index (h3 cell_id)