Predict Bike Trip Duration with a Regression Model in BQML Reviews

I'd add a step to compare predictions with real values: SELECT pred.*, src.duration FROM ML.PREDICT(MODEL bike_model.model_bucketized, ( SELECT start_station_name, start_date FROM `bigquery-public-data`.london_bicycles.cycle_hire LIMIT 100) ) as pred, `bigquery-public-data`.london_bicycles.cycle_hire as src WHERE pred.start_station_name = src.start_station_name and pred.start_date = src.start_date

Piotr K. · Reviewed about 5 years ago

jared j. · Reviewed about 5 years ago

ALEXANDRE MENEZES S. · Reviewed about 5 years ago

Teemu K. · Reviewed about 5 years ago

Very interresting. Unfortunately the time duration (1 hour) is not sufficient. It should be 2 hours.

Florian T. · Reviewed about 5 years ago

Giovanni B. · Reviewed about 5 years ago

Jair M. · Reviewed about 5 years ago

Harshita B. · Reviewed about 5 years ago

和美 井. · Reviewed about 5 years ago

ok

Marcos d. · Reviewed about 5 years ago

Timothy M. · Reviewed about 5 years ago

Thomas L. · Reviewed about 5 years ago

Christopher K. · Reviewed about 5 years ago

Karthik A. · Reviewed about 5 years ago

Thomas D. · Reviewed about 5 years ago

Armando F. · Reviewed about 5 years ago

Anirudh J. · Reviewed about 5 years ago

Itishree D. · Reviewed about 5 years ago

Kiran S. · Reviewed about 5 years ago

Guillaume G. · Reviewed about 5 years ago

Martino R. · Reviewed about 5 years ago

Alberto M. · Reviewed about 5 years ago

Stefan H. · Reviewed about 5 years ago

Zeyu Z. · Reviewed about 5 years ago

Zeyu Z. · Reviewed about 5 years ago