# Read data
taxi_train = pd.read_csv('taxi_train.csv')
taxi_test = pd.read_csv('taxi_test.csv')
from sklearn.model_selection import train_test_split
# Create local validation
validation_train, validation_test = train_test_split(taxi_train,
test_size=0.3,
random_state=123)
बेसलाइन मॉडल I
import numpy as np
# Assign the mean fare amount to all the test observations
taxi_test['fare_amount'] = np.mean(taxi_train.fare_amount)
# Write predictions to the file
taxi_test[['id','fare_amount']].to_csv('mean_sub.csv', index=False)
वैलिडेशन RMSE
पब्लिक LB RMSE
पब्लिक LB पोज़ीशन
9.986
9.409
1449 / 1500
बेसलाइन मॉडल II
# Calculate the mean fare amount by group
naive_prediction_groups = taxi_train.groupby('passenger_count').fare_amount.mean()
# Make predictions on the test set
taxi_test['fare_amount'] = taxi_test.passenger_count.map(naive_prediction_groups)
# Write predictions to the file
taxi_test[['id','fare_amount']].to_csv('mean_group_sub.csv', index=False)
वैलिडेशन RMSE
पब्लिक LB RMSE
पब्लिक LB पोज़ीशन
9.978
9.407
1411 / 1500
बेसलाइन मॉडल III
# Select only numeric features
features = ['pickup_longitude', 'pickup_latitude',
'dropoff_longitude', 'dropoff_latitude', 'passenger_count']
from sklearn.ensemble import GradientBoostingRegressor
# Train a Gradient Boosting model
gb = GradientBoostingRegressor()
gb.fit(taxi_train[features], taxi_train.fare_amount)
# Make predictions on the test data
taxi_test['fare_amount'] = gb.predict(taxi_test[features])
बेसलाइन मॉडल III
# Write predictions to the file
taxi_test[['id','fare_amount']].to_csv('gb_sub.csv', index=False)
Preparing Video For Download...
