Challenge Lab Link: https://google.qwiklabs.com/focuses/14294?parent=catalog
With BigQueryML the goal of the lab was making two Machine Learning Models with diffrent features and evaluating them to see the better model and using the better model to predict. The Model eventually should predict the average trip duration for all trips from the busiest bike sharing station in 2019 where the subscriber type is 'Single Trip' using one of google's dataset.
Model 1.sql: This file is the first machine learning model which uses the starting station name, the hour the trip started, the weekday of the trip, and the address of the start station as features and was trained by the 2018 data. (Task2)
Model 2.sql: This file is the second machine learning model which uses the starting station name, the bike share subscriber type and the start time for the trip as features and was trained by the 2018 data. (Task 3)
Evaluate Model 1.sql and Evaluate Model 2.sql : These two files evaluate both model 1 and 2 using 2019 data and reporting both the Mean Absolute Error and the Root Mean Square Error. (Task 4)
Query.sql This SQL file was used to query Google's dataset to check the busiest station to complete task 4.
Predict with Model 2.sql This file predicts the average rip length for trips from the busiest bike sharing station in 2019 where the subscriber type is Single Trip. (Task 4)
After finishing the Lab with a perfect score I got a badge from google to regonize my achievement.
The Bage: https://google.qwiklabs.com/public_profiles/3f648623-1064-4781-9988-2df7708d937e/badges/1169968
Note: I know this isn't the best way to make a machine learning model but it is definitely the start of my Machine Learning learning path and possibly carrer 😉.