Merge pull request #153870 from saveenr/patch-105

Update get-started-analyze-sql-pool.md

Author: PMEds28

articles/synapse-analytics/get-started-analyze-sql-pool.md

@@ -38,49 +38,54 @@ A dedicated SQL pool consumes billable resources as long as it's active. You can
 1. Select the pool 'SQLPOOL1' (pool created in [STEP 1](./get-started-create-workspace.md) of this tutorial) in 'Connect to' drop down list above the script.
 1. Enter the following code:
     ```
-    CREATE TABLE [dbo].[Trip]
-    (
-        [DateID] int NOT NULL,
-        [MedallionID] int NOT NULL,
-        [HackneyLicenseID] int NOT NULL,
-        [PickupTimeID] int NOT NULL,
-        [DropoffTimeID] int NOT NULL,
-        [PickupGeographyID] int NULL,
-        [DropoffGeographyID] int NULL,
-        [PickupLatitude] float NULL,
-        [PickupLongitude] float NULL,
-        [PickupLatLong] varchar(50) COLLATE SQL_Latin1_General_CP1_CI_AS NULL,
-        [DropoffLatitude] float NULL,
-        [DropoffLongitude] float NULL,
-        [DropoffLatLong] varchar(50) COLLATE SQL_Latin1_General_CP1_CI_AS NULL,
-        [PassengerCount] int NULL,
-        [TripDurationSeconds] int NULL,
-        [TripDistanceMiles] float NULL,
-        [PaymentType] varchar(50) COLLATE SQL_Latin1_General_CP1_CI_AS NULL,
-        [FareAmount] money NULL,
-        [SurchargeAmount] money NULL,
-        [TaxAmount] money NULL,
-        [TipAmount] money NULL,
-        [TollsAmount] money NULL,
-        [TotalAmount] money NULL
-    )
-    WITH
-    (
-        DISTRIBUTION = ROUND_ROBIN,
-        CLUSTERED COLUMNSTORE INDEX
-    );
+	IF NOT EXISTS (SELECT * FROM sys.objects O JOIN sys.schemas S ON O.schema_id = S.schema_id WHERE O.NAME = 'NYCTaxiTripSmall' AND O.TYPE = 'U' AND S.NAME = 'dbo')
+	CREATE TABLE dbo.NYCTaxiTripSmall
+		(
+		 [DateID] int,
+		 [MedallionID] int,
+		 [HackneyLicenseID] int,
+		 [PickupTimeID] int,
+		 [DropoffTimeID] int,
+		 [PickupGeographyID] int,
+		 [DropoffGeographyID] int,
+		 [PickupLatitude] float,
+		 [PickupLongitude] float,
+		 [PickupLatLong] nvarchar(4000),
+		 [DropoffLatitude] float,
+		 [DropoffLongitude] float,
+		 [DropoffLatLong] nvarchar(4000),
+		 [PassengerCount] int,
+		 [TripDurationSeconds] int,
+		 [TripDistanceMiles] float,
+		 [PaymentType] nvarchar(4000),
+		 [FareAmount] numeric(19,4),
+		 [SurchargeAmount] numeric(19,4),
+		 [TaxAmount] numeric(19,4),
+		 [TipAmount] numeric(19,4),
+		 [TollsAmount] numeric(19,4),
+		 [TotalAmount] numeric(19,4)
+		)
+	WITH
+		(
+		DISTRIBUTION = ROUND_ROBIN,
+		 CLUSTERED COLUMNSTORE INDEX
+		 -- HEAP
+		)
+	GO
 
-    COPY INTO [dbo].[Trip]
-    FROM 'https://nytaxiblob.blob.core.windows.net/2013/Trip2013/QID6392_20171107_05910_0.txt.gz'
-    WITH
-    (
-        FILE_TYPE = 'CSV',
-        FIELDTERMINATOR = '|',
-        FIELDQUOTE = '',
-        ROWTERMINATOR='0X0A',
-        COMPRESSION = 'GZIP'
-    )
-    OPTION (LABEL = 'COPY : Load [dbo].[Trip] - Taxi dataset');
+	--Uncomment the 4 lines below to create a stored procedure for data pipeline orchestration​
+	--CREATE PROC bulk_load_NYCTaxiTripSmall
+	--AS
+	--BEGIN
+	COPY INTO dbo.NYCTaxiTripSmall
+	(DateID 1, MedallionID 2, HackneyLicenseID 3, PickupTimeID 4, DropoffTimeID 5, PickupGeographyID 6, DropoffGeographyID 7, PickupLatitude 8, PickupLongitude 9, PickupLatLong 10, DropoffLatitude 11, DropoffLongitude 12, DropoffLatLong 13, PassengerCount 14, TripDurationSeconds 15, TripDistanceMiles 16, PaymentType 17, FareAmount 18, SurchargeAmount 19, TaxAmount 20, TipAmount 21, TollsAmount 22, TotalAmount 23)
+	FROM 'https://contosolake.dfs.core.windows.net/users/NYCTripSmall.parquet'
+	WITH
+	(
+		FILE_TYPE = 'PARQUET'
+		,MAXERRORS = 0
+		,IDENTITY_INSERT = 'OFF'
+	)
     ```
 1. Click the Run button to execute the script.
 1. This script will finish in less than 60 seconds. It loads 2 million rows of NYC Taxi data into a table called **dbo.Trip**.