rm -r dp-203 -f

git clone https://github.com/MicrosoftLearning/dp-203-azure-data-engineer dp-203

cd dp-203/Allfiles/labs/01

./setup.ps1

-- This is auto-generated code
SELECT
    TOP 100 *
FROM
    OPENROWSET(
        BULK 'https://datalakexxxxxxx.dfs.core.windows.net/files/product_data/products.csv',
        FORMAT = 'CSV',
        PARSER_VERSION='2.0'
    ) AS [result]

SELECT
    TOP 100 *
FROM
    OPENROWSET(
        BULK 'https://datalakexxxxxxx.dfs.core.windows.net/files/product_data/products.csv',
        FORMAT = 'CSV',
        PARSER_VERSION='2.0',
        HEADER_ROW = TRUE
    ) AS [result]

SELECT
    Category, COUNT(*) AS ProductCount
FROM
    OPENROWSET(
        BULK 'https://datalakexxxxxxx.dfs.core.windows.net/files/product_data/products.csv',
        FORMAT = 'CSV',
        PARSER_VERSION='2.0',
        HEADER_ROW = TRUE
    ) AS [result]
GROUP BY Category;

%%pyspark
df = spark.read.load('abfss://files@datalakexxxxxxx.dfs.core.windows.net/product_data/products.csv', format='csv'
## If header exists uncomment line below
##, header=True
)
display(df.limit(10))

%%pyspark
df = spark.read.load('abfss://files@datalakexxxxxxx.dfs.core.windows.net/product_data/products.csv', format='csv'
## If header exists uncomment line below
, header=True
)
display(df.limit(10))

df_counts = df.groupby(df.Category).count()
display(df_counts)

SELECT d.CalendarYear, d.MonthNumberOfYear, d.EnglishMonthName,
       p.EnglishProductName AS Product, SUM(o.OrderQuantity) AS UnitsSold
FROM dbo.FactInternetSales AS o
JOIN dbo.DimDate AS d ON o.OrderDateKey = d.DateKey
JOIN dbo.DimProduct AS p ON o.ProductKey = p.ProductKey
GROUP BY d.CalendarYear, d.MonthNumberOfYear, d.EnglishMonthName, p.EnglishProductName
ORDER BY d.MonthNumberOfYear