github/sql-server-samples
1
0
Fork 0
mirror of https://github.com/Microsoft/sql-server-samples.git synced 2025-12-08 14:58:54 +00:00
Code Issues Releases Wiki Activity

PolyBase V1 samples & option to install AW/WWI dbs

Browse Source
This commit is contained in:
Umachandar Jayachandran
2019-03-19 17:26:09 -07:00
parent cf79ffdeb5
commit 6ddfd4d9b1
8 changed files with 337 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files
samples/features/sql-big-data-cluster/spark/spark-sql.ipynb
+17 -29
View File
@@ -25,9 +25,7 @@
{
"cell_type": "code",
"source": "# Read the clickstream CSV file(s) into a spark data frame, print schema & top rows\nresults = spark.read.option(\"inferSchema\", \"true\").csv('/clickstream_data').toDF(\n \"wcs_click_date_sk\", \"wcs_click_time_sk\", \"wcs_sales_sk\", \"wcs_item_sk\", \"wcs_web_page_sk\", \"wcs_user_sk\"\n )\nresults.printSchema()\nresults.show()",
"metadata": {
"language": "python"
},
"metadata": {},
"outputs": [
{
"name": "stdout",
@@ -35,14 +33,12 @@
"output_type": "stream"
}
],
"execution_count": 1
"execution_count": 3
},
{
"cell_type": "code",
"source": "# Disable saving SUCCESS file\r\nsc._jsc.hadoopConfiguration().set(\"mapreduce.fileoutputcommitter.marksuccessfuljobs\", \"false\") \r\n\r\n# Print the current warehouse directory where the parquet files will be stored\r\nprint(spark.conf.get(\"spark.sql.warehouse.dir\"))\r\n\r\n# Save results as parquet file and create hive table\r\nresults.write.format(\"parquet\").mode(\"overwrite\").saveAsTable(\"web_clickstreams\")\r\n",
"metadata": {
"language": "python"
},
"source": "# Disable saving SUCCESS file\r\nsc._jsc.hadoopConfiguration().set(\"mapreduce.fileoutputcommitter.marksuccessfuljobs\", \"false\") \r\n\r\n# Print the current warehouse directory where the parquet files will be stored\r\nprint(spark.conf.get(\"spark.sql.warehouse.dir\"))\r\n\r\n# Save results as parquet & orc file and create hive table\r\nresults.write.format(\"parquet\").mode(\"overwrite\").saveAsTable(\"web_clickstreams\")\r\nresults.write.format(\"orc\").mode(\"overwrite\").saveAsTable(\"web_clickstreams_orc\")",
"metadata": {},
"outputs": [
{
"name": "stdout",
@@ -50,29 +46,25 @@
"output_type": "stream"
}
],
"execution_count": 1
"execution_count": 4
},
{
"cell_type": "code",
"source": "# Execute Spark SQL commands\r\nsqlDF = spark.sql(\"SELECT * FROM web_clickstreams LIMIT 100\")\r\nsqlDF.show()\r\n\r\nsqlDF = spark.sql(\"SELECT wcs_user_sk, COUNT(*)\\\r\n FROM web_clickstreams\\\r\n WHERE wcs_user_sk IS NOT NULL\\\r\n GROUP BY wcs_user_sk\\\r\n ORDER BY COUNT(*) DESC LIMIT 100\")\r\nsqlDF.show()",
"metadata": {
"language": "python"
},
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": "+-----------------+-----------------+------------+-----------+---------------+-----------+\n|wcs_click_date_sk|wcs_click_time_sk|wcs_sales_sk|wcs_item_sk|wcs_web_page_sk|wcs_user_sk|\n+-----------------+-----------------+------------+-----------+---------------+-----------+\n| 36890| 40052| null| 4379| 34| null|\n| 36890| 41285| null| 6245| 34| null|\n| 36890| 23115| null| 13852| 34| null|\n| 36890| 17702| null| 15975| 34| null|\n| 36890| 62676| null| 2119| 34| null|\n| 36890| 34267| null| 10273| 34| null|\n| 36890| 8502| null| 17790| 34| null|\n| 36890| 54340| null| 3453| 34| null|\n| 36890| 54370| null| 6372| 34| null|\n| 36890| 6578| null| 17203| 34| null|\n| 36890| 75088| null| 4891| 34| null|\n| 36890| 23922| null| 11332| 34| null|\n| 36890| 28761| null| 4484| 34| null|\n| 36890| 21444| null| 5582| 34| null|\n| 36890| 58917| null| 8833| 34| null|\n| 36890| 27578| null| 8599| 34| null|\n| 36890| 8059| null| 6720| 34| null|\n| 36890| 43008| null| 17175| 34| null|\n| 36890| 4378| null| 10644| 34| null|\n| 36890| 55403| null| 8139| 34| null|\n+-----------------+-----------------+------------+-----------+---------------+-----------+\nonly showing top 20 rows\n\n+-----------+--------+\n|wcs_user_sk|count(1)|\n+-----------+--------+\n| 65042| 832|\n| 55928| 821|\n| 15570| 791|\n| 31138| 788|\n| 68188| 784|\n| 88205| 760|\n| 15678| 757|\n| 48063| 741|\n| 77518| 741|\n| 92978| 728|\n| 82129| 727|\n| 21700| 725|\n| 69707| 724|\n| 38895| 719|\n| 97643| 716|\n| 74426| 707|\n| 7813| 704|\n| 49528| 700|\n| 55766| 698|\n| 54355| 697|\n+-----------+--------+\nonly showing top 20 rows",
"text": "+-----------------+-----------------+------------+-----------+---------------+-----------+\n|wcs_click_date_sk|wcs_click_time_sk|wcs_sales_sk|wcs_item_sk|wcs_web_page_sk|wcs_user_sk|\n+-----------------+-----------------+------------+-----------+---------------+-----------+\n| 37506| 7933| null| 1384| 2| 39437|\n| 37506| 56044| null| 14689| 2| 26419|\n| 37506| 52706| null| 8541| 2| 44016|\n| 37506| 67325| null| 16129| 2| 83371|\n| 37506| 84857| null| 1869| 2| 13090|\n| 37506| 49599| null| 2994| 2| 8940|\n| 37506| 78150| null| 11392| 2| 65633|\n| 37506| 38720| null| 14366| 2| 22281|\n| 37506| 79915| null| 11102| 2| 81755|\n| 37506| 67253| null| 5380| 2| 46868|\n| 37506| 6507| null| 6813| 2| 49363|\n| 37506| 18280| null| 1458| 2| 49363|\n| 37506| 72258| null| 2869| 2| 67756|\n| 37506| 8045| null| 615| 2| 86035|\n| 37506| 86164| null| 7000| 2| 94821|\n| 37506| 29724| null| 2767| 2| 94821|\n| 37506| 55471| null| 3584| 2| 62792|\n| 37506| 677| null| 1720| 2| 27212|\n| 37506| 66638| null| 9898| 2| 20370|\n| 37506| 48515| null| 9394| 2| 17157|\n+-----------------+-----------------+------------+-----------+---------------+-----------+\nonly showing top 20 rows\n\n+-----------+--------+\n|wcs_user_sk|count(1)|\n+-----------+--------+\n| 65042| 832|\n| 55928| 821|\n| 15570| 791|\n| 31138| 788|\n| 68188| 784|\n| 88205| 760|\n| 15678| 757|\n| 48063| 741|\n| 77518| 741|\n| 92978| 728|\n| 82129| 727|\n| 21700| 725|\n| 69707| 724|\n| 38895| 719|\n| 97643| 716|\n| 74426| 707|\n| 7813| 704|\n| 49528| 700|\n| 55766| 698|\n| 54355| 697|\n+-----------+--------+\nonly showing top 20 rows",
"output_type": "stream"
}
],
"execution_count": 1
"execution_count": 5
},
{
"cell_type": "code",
"source": "# Read the product reviews CSV files into a spark data frame, print schema & top rows\r\nresults = spark.read.option(\"inferSchema\", \"true\").csv('/product_review_data').toDF(\r\n \"pr_review_sk\", \"pr_review_content\"\r\n )\r\nresults.printSchema()\r\nresults.show()",
"metadata": {
"language": "python"
},
"metadata": {},
"outputs": [
{
"name": "stdout",
@@ -80,31 +72,27 @@
"output_type": "stream"
}
],
"execution_count": 1
"execution_count": 6
},
{
"cell_type": "code",
"source": "# Save results as parquet file and create hive table\r\nresults.write.format(\"parquet\").mode(\"overwrite\").saveAsTable(\"product_reviews\")\r\n",
"metadata": {
"language": "python"
},
"source": "# Save results as parquet, and orc formats and create hive table\r\nresults.write.format(\"parquet\").mode(\"overwrite\").saveAsTable(\"product_reviews\")\r\nresults.write.format(\"orc\").mode(\"overwrite\").saveAsTable(\"product_reviews_orc\")\r\n",
"metadata": {},
"outputs": [],
"execution_count": 1
"execution_count": 7
},
{
"cell_type": "code",
"source": "# Execute Spark SQL commands\r\nsqlDF = spark.sql(\"SELECT pr_review_sk, CHAR_LENGTH(pr_review_content) as len FROM product_reviews LIMIT 100\")\r\nsqlDF.show()",
"metadata": {
"language": "python"
},
"metadata": {},
"outputs": [
{
"name": "stdout",
"text": "+------------+----+\n|pr_review_sk| len|\n+------------+----+\n| 14868| 985|\n| 14869|1601|\n| 14875|1221|\n| 14880| 665|\n| 14886| 91|\n| 14894| 697|\n| 14899| 356|\n| 14903|2361|\n| 14908| 872|\n| 14909| 74|\n| 14917| 908|\n| 14918| 50|\n| 14919| 256|\n| 14921| 723|\n| 14925| 313|\n| 14931|1304|\n| 14939|1023|\n| 14949| 552|\n| 14954|2144|\n| 14955| 123|\n+------------+----+\nonly showing top 20 rows",
"text": "+------------+----+\n|pr_review_sk| len|\n+------------+----+\n| 26035| 876|\n| 26037| 109|\n| 26038| 478|\n| 26041| 106|\n| 26043| 332|\n| 26044| 487|\n| 26045| 428|\n| 26048| 87|\n| 26049| 118|\n| 26051|2906|\n| 26053| 464|\n| 26054| 212|\n| 26059| 191|\n| 26060| 207|\n| 26061| 515|\n| 26063| 59|\n| 26069| 487|\n| 26070| 160|\n| 26071| 380|\n| 26072| 234|\n+------------+----+\nonly showing top 20 rows",
"output_type": "stream"
}
],
"execution_count": 1
"execution_count": 8
}
]
}
}}