Function to calclulation the distance between two points on a map used for NYC dataset

get_distance.py

import numpy as np
import pandas as pd

# Defining the function for distance calculation
def distance_calculation(df: pd.DataFrame) -> pd.DataFrame:
    """
    Calculates the distance between two points on the earth's surface.

    The distance is in meters
    """
    R = 6373.0

    lat1 = np.radians(df['pickup_latitude'])
    lon1 = np.radians(df['pickup_longitude'])
    lat2 = np.radians(df['dropoff_latitude'])
    lon2 = np.radians(df['dropoff_longitude'])

    dlon = lon2 - lon1
    dlat = lat2 - lat1

    a = np.sin(dlat / 2)**2 + np.cos(lat1) * np.cos(lat2) * np.sin(dlon / 2)**2
    c = 2 * np.arctan2(np.sqrt(a), np.sqrt(1 - a))

    distance = R * c

    # Saving the distance to the dataframe
    df['distance'] = distance * 1000 # Converting to meters
    return df