Query.txt

# Here there are some queries for validation of the dataset and get more info about the data : 

SELECT COUNT(*) FROM `retail_data_pipeline_dataset.retail_raw_data`;

SELECT 
  COUNTIF(Transaction_ID IS NULL) AS null_transactions,
  COUNTIF(Customer_ID IS NULL) AS null_customer,
  COUNTIF(Date IS NULL) AS null_date,
  COUNTIF(products IS NULL) AS null_product
FROM `retail-data-pipeline-453817.retail_data_pipeline_dataset.retail_raw_data`;  


SELECT
  MIN(Date) AS earliest_date,
  MAX(Date) AS latest_date,
FROM `retail-data-pipeline-453817.retail_data_pipeline_dataset.retail_raw_data`;


SELECT * 
FROM `retail-data-pipeline-453817.retail_data_pipeline_dataset.retail_raw_data`
WHERE Date > CURRENT_DATE();

SELECT Transaction_ID,COUNT(*) AS count
FROM `retail-data-pipeline-453817.retail_data_pipeline_dataset.retail_raw_data`
GROUP BY(Transaction_ID)
HAVING count > 1;



SELECT *
FROM `retail-data-pipeline-453817.retail_data_pipeline_dataset.retail_raw_data`
WHERE Total_Purchases < 0;


SELECT DISTINCT Payment_Method
FROM `retail-data-pipeline-453817.retail_data_pipeline_dataset.retail_raw_data`;