Create ML Models with BigQuery ML: Challenge Lab

 bq mk austin
 
 


Task 2
 
 CREATE OR REPLACE MODEL austin.location_model
OPTIONS
  (model_type='linear_reg', labels=['duration_minutes']) AS
SELECT
    start_station_name,
    EXTRACT(HOUR FROM start_time) AS start_hour,
    EXTRACT(DAYOFWEEK FROM start_time) AS day_of_week,
    duration_minutes,
    address as location
FROM
    `bigquery-public-data.austin_bikeshare.bikeshare_trips` AS trips
JOIN
    `bigquery-public-data.austin_bikeshare.bikeshare_stations` AS stations
ON
    trips.start_station_name = stations.name
WHERE
    EXTRACT(YEAR FROM start_time) = <replace year>
    AND duration_minutes > 0
    
 

 
Task 3

CREATE OR REPLACE MODEL austin.subscriber_model
OPTIONS
  (model_type='linear_reg', labels=['duration_minutes']) AS
SELECT
    start_station_name,
    EXTRACT(HOUR FROM start_time) AS start_hour,
    subscriber_type,
    duration_minutes
FROM `bigquery-public-data.austin_bikeshare.bikeshare_trips` AS trips
WHERE EXTRACT(YEAR FROM start_time) = <replace year>




CREATE OR REPLACE MODEL austin.subscriber_model
OPTIONS
  (model_type='linear_reg', labels=['duration_minutes']) AS
SELECT
    start_station_name,
    EXTRACT(HOUR FROM start_time) AS start_hour,
    subscriber_type,
    duration_minutes
FROM `bigquery-public-data.austin_bikeshare.bikeshare_trips` AS trips
WHERE EXTRACT(YEAR FROM start_time) = <replace year>






Task 4 

SELECT
  SQRT(mean_squared_error) AS rmse,
  mean_absolute_error
FROM
  ML.EVALUATE(MODEL austin.location_model, (
  SELECT
    start_station_name,
    EXTRACT(HOUR FROM start_time) AS start_hour,
    EXTRACT(DAYOFWEEK FROM start_time) AS day_of_week,
    duration_minutes,
    address as location
  FROM
    `bigquery-public-data.austin_bikeshare.bikeshare_trips` AS trips
  JOIN
   `bigquery-public-data.austin_bikeshare.bikeshare_stations` AS stations
  ON
    trips.start_station_name = stations.name
  WHERE EXTRACT(YEAR FROM start_time) = <replace year> )
)





SELECT
  SQRT(mean_squared_error) AS rmse,
  mean_absolute_error
FROM
  ML.EVALUATE(MODEL austin.subscriber_model, (
  SELECT
    start_station_name,
    EXTRACT(HOUR FROM start_time) AS start_hour,
    subscriber_type,
    duration_minutes
  FROM
    `bigquery-public-data.austin_bikeshare.bikeshare_trips` AS trips
  WHERE
    EXTRACT(YEAR FROM start_time) = <replace year>)
)



Task 5


SELECT
  start_station_name,
  COUNT(*) AS trips
FROM
  `bigquery-public-data.austin_bikeshare.bikeshare_trips`
WHERE
  EXTRACT(YEAR FROM start_time) = <replace year>
GROUP BY
  start_station_name
ORDER BY
  trips DESC
  







  SELECT AVG(predicted_duration_minutes) AS average_predicted_trip_length
FROM ML.predict(MODEL austin.subscriber_model, (
SELECT
    start_station_name,
    EXTRACT(HOUR FROM start_time) AS start_hour,
    subscriber_type,
    duration_minutes
FROM
  `bigquery-public-data.austin_bikeshare.bikeshare_trips`
WHERE 
  EXTRACT(YEAR FROM start_time) = <replace year>
  AND subscriber_type = 'Single Trip'
  AND start_station_name = '21st & Speedway @PCL'))