Update query-parquet-files.md

Author: jovanpop-msft

articles/synapse-analytics/sql/query-parquet-files.md

@@ -21,52 +21,35 @@ Your first step is to **create a database** where the tables will be created. Th
 
 ## Dataset
 
-You can query Parquet files the same way you read CSV files. The only difference is that the FILEFORMAT parameter should be set to PARQUET. Examples in this article show the specifics of reading Parquet files.
+[NYC Yellow Taxi](https://azure.microsoft.com/services/open-datasets/catalog/nyc-taxi-limousine-commission-yellow-taxi-trip-records/) dataset i used in this sample isYou can query Parquet files the same way you read CSV files. The only difference is that the FILEFORMAT parameter should be set to PARQUET. Examples in this article show the specifics of reading Parquet files.
 
 > [!NOTE]
 > You do not have to specify columns in the OPENROWSET WITH clause when reading parquet files. SQL on-demand will utilize metadata in the Parquet file and bind columns by name.
 
-You'll use the folder *parquet/taxi* for the sample queries. It contains NYC Taxi - Yellow Taxi Trip Records data from July 2016. to June 2018.
-
-Data is partitioned by year and month and the folder structure is as follows:
-
-- year=2016
-  - month=6
-  - ...
-  - month=12
-- year=2017
-  - month=1
-  - ...
-  - month=12
-- year=2018
-  - month=1
-  - ...
-  - month=6
-
 ## Query set of parquet files
 
 You can specify only the columns of interest when you query Parquet files.
 
 ```sql
 SELECT
-        YEAR(pickup_datetime),
-        passenger_count,
+        YEAR(tpepPickupDateTime),
+        passengerCount,
         COUNT(*) AS cnt
 FROM  
     OPENROWSET(
-        BULK 'parquet/taxi/*/*/*',
-        DATA_SOURCE = 'SqlOnDemandDemo',
+        BULK 'puYear=2018/puMonth=*/*.snappy.parquet',
+        DATA_SOURCE = 'YellowTaxi',
         FORMAT='PARQUET'
     ) WITH (
-        pickup_datetime DATETIME2,
-        passenger_count INT
+        tpepPickupDateTime DATETIME2,
+        passengerCount INT
     ) AS nyc
 GROUP BY
-    passenger_count,
-    YEAR(pickup_datetime)
+    passengerCount,
+    YEAR(tpepPickupDateTime)
 ORDER BY
-    YEAR(pickup_datetime),
-    passenger_count;
+    YEAR(tpepPickupDateTime),
+    passengerCount;
 ```
 
 ## Automatic schema inference
@@ -79,14 +62,13 @@ The sample below shows the automatic schema inference capabilities for Parquet f
 > You don't have to specify columns in the OPENROWSET WITH clause when reading Parquet files. In that case, SQL on-demand Query service will utilize metadata in the Parquet file and bind columns by name.
 
 ```sql
-SELECT
-    COUNT_BIG(*)
-FROM
+SELECT TOP 10 *
+FROM  
     OPENROWSET(
-        BULK 'parquet/taxi/year=2017/month=9/*.parquet',
-        DATA_SOURCE = 'SqlOnDemandDemo',
+        BULK 'puYear=2018/puMonth=*/*.snappy.parquet',
+        DATA_SOURCE = 'YellowTaxi',
         FORMAT='PARQUET'
-    ) AS nyc;
+    ) AS nyc
 ```
 
 ### Query partitioned data
@@ -98,28 +80,25 @@ The data set provided in this sample is divided (partitioned) into separate subf
 
 ```sql
 SELECT
-    nyc.filepath(1) AS [year],
-    nyc.filepath(2) AS [month],
-    payment_type,
-    SUM(fare_amount) AS fare_total
-FROM
+        YEAR(tpepPickupDateTime),
+        passengerCount,
+        COUNT(*) AS cnt
+FROM  
     OPENROWSET(
-        BULK 'parquet/taxi/year=*/month=*/*.parquet',
-        DATA_SOURCE = 'SqlOnDemandDemo',
+        BULK 'puYear=*/puMonth=*/*.snappy.parquet',
+        DATA_SOURCE = 'YellowTaxi',
         FORMAT='PARQUET'
-    ) AS nyc
+    ) nyc
 WHERE
     nyc.filepath(1) = 2017
     AND nyc.filepath(2) IN (1, 2, 3)
-    AND pickup_datetime BETWEEN CAST('1/1/2017' AS datetime) AND CAST('3/31/2017' AS datetime)
+    AND tpepPickupDateTime BETWEEN CAST('1/1/2017' AS datetime) AND CAST('3/31/2017' AS datetime)
 GROUP BY
-    nyc.filepath(1),
-    nyc.filepath(2),
-    payment_type
+    passengerCount,
+    YEAR(tpepPickupDateTime)
 ORDER BY
-    nyc.filepath(1),
-    nyc.filepath(2),
-    payment_type;
+    YEAR(tpepPickupDateTime),
+    passengerCount;
 ```
 
 ## Type mapping