bigquery_ml_0003.sql

CREATE MODEL `kaggle_talkingdata_adtracking.talkingdata_logreg_0001`
OPTIONS (
  model_type='logistic_reg',
  input_label_cols=['is_attributed'],
  data_split_method='seq',
  data_split_col='click_time'
) AS
SELECT CAST(ip AS STRING) as ip,
  CAST(app AS STRING) as app,
  CAST(device AS STRING) as device,
  CAST(os AS STRING) as os,
  CAST(channel AS STRING) as channel,
  CAST(EXTRACT(hour from click_time) AS STRING) as hod,
  CONCAT('app_', CAST(app AS STRING), '_device_', CAST(device AS STRING)) app_x_device,
  CONCAT('os_', CAST(os AS STRING), '_channel_', CAST(channel AS STRING)) os_x_channel,
  click_time,
  is_attributed                                                     
FROM `kaggle_talkingdata_adtracking.dataset_train` ;