baseline_model

from sklearn.model_selection import train_test_split

train, test = train_test_split(taxi, test_size=0.3, random_state=42)
import numpy as np
import shutil

def distance_between(lat1, lon1, lat2, lon2):
  # Haversine formula to compute distance 
  dist = np.degrees(np.arccos(np.sin(np.radians(lat1)) * np.sin(np.radians(lat2)) + np.cos(np.radians(lat1)) * np.cos(np.radians(lat2)) * np.cos(np.radians(lon2 - lon1)))) * 60 * 1.515 * 1.609344
  return dist

def estimate_distance(df):
  return distance_between(df['pickup_latitude'], df['pickup_longitude'], df['dropoff_latitude'], df['dropoff_longitude'])

def compute_rmse(actual, predicted):
  return np.sqrt(np.mean((actual - predicted)**2))

def print_rmse(df, rate, name):
  print("{1} RMSE = {0}".format(compute_rmse(df['fare_amount'], rate * estimate_distance(df)), name))
  
rate = train['fare_amount'].mean() / estimate_distance(train).mean()

print("Rate = ${0}/km".format(rate))
print_rmse(train, rate, 'Train')
print_rmse(test, rate, 'Test')