ReverseGeocoder

import os
import pandas as pd
import reverse_geocoder as rg

# --- 1. Load your CSV data ---
input_file_path = "../content/gdrive/My Drive/Colab_Notebooks/5G_coverage/Simplified_Rand_Real.csv"
df = pd.read_csv(input_file_path)

#Get output directory and create if not exist
output_dir = "../content/gdrive/My Drive/Colab_Notebooks/5GCoverageResults/"
os.makedirs(output_dir, exist_ok=True) # Create the output directory if it doesn't exist

# --- 2. Prepare coordinates for batch geocoding ---
coordinates = list(zip(df['SiteLatitude_decDeg'], df['SiteLongitude_decDeg']))

# --- 3. Perform batch reverse geocoding ---
results = rg.search(coordinates)

# --- 4. Extract state information and add to DataFrame ---
states = []
for result in results:
    state = result.get('admin1')  # First try admin1
    if state is None or state == "":
        state = result.get('admin2')  # If admin1 is missing, try admin2
        if state is None or state == "":
            state = result.get('name', 'Not Found')  # If both are missing, use 'name' or 'Not Found'
    states.append(state)

df['State'] = states

# --- 5. Separate into files by state ---
for state in df['State'].unique():
    if state != "Not Found":  # Skip 'Not Found' entries
        state_df = df[df['State'] == state]
        output_file_path = os.path.join(output_dir, f"{state}_sites.csv")
        state_df.to_csv(output_file_path, index=False)
        print(f"Created {output_file_path}")
    else:
        not_found_df = df[df['State'] == "Not Found"]
        output_file_path = os.path.join(output_dir, "sites_not_found.csv")
        not_found_df.to_csv(output_file_path, index=False)
        print(f"Created {output_file_path}")

# --- 6. (Optional) Display the first few rows with the new State column ---
print(df.head())