Merge pull request databricks#48 from austinyoung123/master

Adding 9/24 Data Collab Lab notebook + data
Amrit-Hub · Sep 28, 2020 · 75dcbee · 75dcbee
2 parents 17bb5a5 + 702fefb
commit 75dcbee
Show file tree

Hide file tree

Showing 5 changed files with 84 additions and 0 deletions.
diff --git a/2020-09-24 | Automate Data Pipelines with PySpark SQL/FINAL IoT Machine Stream PySpark.dbc b/2020-09-24 | Automate Data Pipelines with PySpark SQL/FINAL IoT Machine Stream PySpark.dbc
diff --git a/2020-09-24 | Automate Data Pipelines with PySpark SQL/average_heart_rate.json b/2020-09-24 | Automate Data Pipelines with PySpark SQL/average_heart_rate.json
@@ -0,0 +1,41 @@
+{
+	"data": {
+		"results": [{
+				"user_id": 24,
+				"average_heart_rate": 75,
+				"num_steps": 5014,
+				"miles_walked": 2.506999969482422,
+				"time_stamp": "2018-07-21 13:53:32.530695",
+				"device_id": 5
+			},
+
+			{
+				"user_id": 4,
+				"average_heart_rate": 92,
+				"num_steps": 7314,
+				"miles_walked": 3.6570000648498535,
+				"time_stamp": "2018-07-24 02:37:36.530805",
+				"device_id": 5
+			},
+
+			{
+				"user_id": 24,
+				"average_heart_rate": 111,
+				"num_steps": 2536,
+				"miles_walked": 1.2680000066757202,
+				"time_stamp": "2018-07-22 14:24:34.530772",
+				"device_id": 13
+			},
+
+			{
+				"user_id": 4,
+				"average_heart_rate": 92,
+				"num_steps": 7314,
+				"miles_walked": 3.6570000648498535,
+				"time_stamp": "2018-07-24 02:37:36.530805",
+				"device_id": 5
+			}
+
+		]
+	}
+}
diff --git a/2020-09-24 | Automate Data Pipelines with PySpark SQL/average_heart_rate.txt b/2020-09-24 | Automate Data Pipelines with PySpark SQL/average_heart_rate.txt
@@ -0,0 +1 @@
+CREATE EXTERNAL TABLE `final_average_heart_rate`(`average_heart_rate` bigint, `device_id` bigint, `miles_walked` double, `num_steps` bigint, `time_stamp` timestamp, `sample_new_field` string)  PARTITIONED BY (`user_id` bigint)
diff --git a/2020-09-24 | Automate Data Pipelines with PySpark SQL/calories_burnt.json b/2020-09-24 | Automate Data Pipelines with PySpark SQL/calories_burnt.json
@@ -0,0 +1,41 @@
+{
+	"data": {
+		"results": [{
+				"user_id": 24,
+				"calories_burnt": 250.6999969482422,
+				"num_steps": 5014,
+				"miles_walked": 2.506999969482422,
+				"time_stamp": "2018-07-21 13:53:32.530695",
+				"device_id": 5
+			},
+
+			{
+				"user_id": 4,
+				"calories_burnt": 365.70001220703125,
+				"num_steps": 7314,
+				"miles_walked": 3.6570000648498535,
+				"time_stamp": "2018-07-24 02:37:36.530805",
+				"device_id": 5
+			},
+
+			{
+				"user_id": 24,
+				"calories_burnt": 126.80000305175781,
+				"num_steps": 2536,
+				"miles_walked": 1.2680000066757202,
+				"time_stamp": "2018-07-22 14:24:34.530772",
+				"device_id": 13
+			},
+
+			{
+				"user_id": 4,
+				"calories_burnt": 365.70001220703125,
+				"num_steps": 7314,
+				"miles_walked": 3.6570000648498535,
+				"time_stamp": "2018-07-24 02:37:36.530805",
+				"device_id": 5
+			}
+
+		]
+	}
+}
diff --git a/2020-09-24 | Automate Data Pipelines with PySpark SQL/calories_burnt.txt b/2020-09-24 | Automate Data Pipelines with PySpark SQL/calories_burnt.txt
@@ -0,0 +1 @@
+CREATE EXTERNAL TABLE `final_{table_name}`(`calories_burnt` double, `device_id` bigint, `miles_walked` double, `num_steps` bigint, `time_stamp` timestamp, `sample_new_field` string)  PARTITIONED BY (`user_id` bigint)
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		CREATE EXTERNAL TABLE `final_average_heart_rate`(`average_heart_rate` bigint, `device_id` bigint, `miles_walked` double, `num_steps` bigint, `time_stamp` timestamp, `sample_new_field` string) PARTITIONED BY (`user_id` bigint)
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		CREATE EXTERNAL TABLE `final_{table_name}`(`calories_burnt` double, `device_id` bigint, `miles_walked` double, `num_steps` bigint, `time_stamp` timestamp, `sample_new_field` string) PARTITIONED BY (`user_id` bigint)