You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -41,7 +41,7 @@ At this point, you have a simple environment where any check-in to your source c
41
41
42
42
## Continuous deployment with the Azure SQL Data Warehouse (or Database) deployment task
43
43
44
-
1. Add a new task using the [Azure SQL Database deployment task](https://docs.microsoft.com/azure/devops/pipelines/tasks/deploy/sql-azure-dacpac-deployment?view=azure-devops) and fill in the required fields to connect to your target data warehouse. When this task runs, the DACPAC generated from the previous build process is deployed to the target data warehouse. You can also use the [Azure SQL Datawarehouse deployment task](https://marketplace.visualstudio.com/items?itemName=ms-sql-dw.SQLDWDeployment)
44
+
1. Add a new task using the [Azure SQL Database deployment task](https://docs.microsoft.com/azure/devops/pipelines/tasks/deploy/sql-azure-dacpac-deployment?view=azure-devops) and fill in the required fields to connect to your target data warehouse. When this task runs, the DACPAC generated from the previous build process is deployed to the target data warehouse. You can also use the [Azure SQL Data Warehouse deployment task](https://marketplace.visualstudio.com/items?itemName=ms-sql-dw.SQLDWDeployment).
Copy file name to clipboardExpand all lines: articles/sql-data-warehouse/sql-data-warehouse-get-started-analyze-with-azure-machine-learning.md
+27-37Lines changed: 27 additions & 37 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -32,12 +32,12 @@ This tutorial uses Azure Machine Learning to build a predictive machine learning
32
32
## Prerequisites
33
33
To step through this tutorial, you need:
34
34
35
-
* A SQL Data Warehouse pre-loaded with AdventureWorksDW sample data. To provision this, see [Create a SQL Data Warehouse][Create a SQL Data Warehouse]and choose to load the sample data. If you already have a data warehouse but do not have sample data, you can [load sample data manually][loadsample data manually].
35
+
* A SQL Data Warehouse pre-loaded with AdventureWorksDW sample data. To provision this, see [Create a SQL Data Warehouse](create-data-warehouse-portal.md)and choose to load the sample data. If you already have a data warehouse but do not have sample data, you can [load sample data manually](sql-data-warehouse-load-sample-databases.md).
36
36
37
37
## 1. Get the data
38
38
The data is in the dbo.vTargetMail view in the AdventureWorksDW database. To read this data:
39
39
40
-
1. Sign into [Azure Machine Learning studio][Azure Machine Learning studio] and click on my experiments.
40
+
1. Sign into [Azure Machine Learning studio](https://studio.azureml.net/) and click on my experiments.
41
41
2. Click **+NEW** on the bottom left of the screen and select **Blank Experiment**.
42
42
3. Enter a name for your experiment: Targeted Marketing.
43
43
4. Drag the **Import data** module under **Data Input and output** from the modules pane into the canvas.
@@ -65,75 +65,65 @@ FROM [dbo].[vTargetMail]
65
65
```
66
66
67
67
Run the experiment by clicking **Run** under the experiment canvas.
68
-
![Run the experiment][1]
68
+
69
+
69
70
70
71
After the experiment finishes running successfully, click the output port at the bottom of the Reader module and select **Visualize** to see the imported data.
To clean the data, drop some columns that are not relevant for the model. To do this:
75
77
76
78
1. Drag the **Select Columns in Dataset** module under **Data Transformation < Manipulation** into the canvas. Connect this module to the **Import Data** module.
77
79
2. Click **Launch column selector** in the Properties pane to specify which columns you wish to drop.
We will split the data 80-20: 80% to train a machine learning model and 20% to test the model. We will make use of the “Two-Class” algorithms for this binary classification problem.
84
88
85
89
1. Drag the **Split** module into the canvas.
86
90
2. In the properties pane, enter 0.8 for Fraction of rows in the first output dataset.
87
-
![Split data into training and test set][6]
91
+
92
+
88
93
3. Drag the **Two-Class Boosted Decision Tree** module into the canvas.
89
94
4. Drag the **Train Model** module into the canvas and specify inputs by connecting it to the **Two-Class Boosted Decision Tree** (ML algorithm) and **Split** (data to train the algorithm on) modules.
90
-
![Connect the Train Model module][7]
95
+
96
+
91
97
5. Then, click **Launch column selector** in the Properties pane. Select the **BikeBuyer** column as the column to predict.
92
-
![Select Column to predict][8]
98
+
99
+
93
100
94
101
## 4. Score the model
95
102
Now, we will test how the model performs on test data. We will compare the algorithm of our choice with a different algorithm to see which performs better.
96
103
97
104
1. Drag **Score Model** module into the canvas and connect it to **Train Model** and **Split Data** modules.
98
-
![Score the model][9]
105
+
106
+
99
107
2. Drag the **Two-Class Bayes Point Machine** into the experiment canvas. We will compare how this algorithm performs in comparison to the Two-Class Boosted Decision Tree.
100
108
3. Copy and Paste the modules Train Model and Score Model in the canvas.
101
109
4. Drag the **Evaluate Model** module into the canvas to compare the two algorithms.
102
110
5.**Run** the experiment.
103
-
![Run the experiment][10]
111
+
112
+
104
113
6. Click the output port at the bottom of the Evaluate Model module and click Visualize.
105
-
![Visualize evaluation results][11]
106
114
107
-
The metrics provided are the ROC curve, precision-recall diagram and lift curve. Looking at these metrics, we can see that the first model performed better than the second one. To look at the what the first model predicted, click on output port of the Score Model and click Visualize.
The metrics provided are the ROC curve, precision-recall diagram, and lift curve. Looking at these metrics, we can see that the first model performed better than the second one. To look at what the first model predicted, click on output port of the Score Model and click Visualize.
You will see two more columns added to your test dataset.
111
122
112
123
* Scored Probabilities: the likelihood that a customer is a bike buyer.
113
124
* Scored Labels: the classification done by the model – bike buyer (1) or not (0). This probability threshold for labeling is set to 50% and can be adjusted.
114
125
115
-
Comparing the column BikeBuyer (actual) with the Scored Labels (prediction), you can see how well the model has performed. As next steps, you can use this model to make predictions for new customers and publish this model as a web service or write results back to SQL Data Warehouse.
126
+
Comparing the column BikeBuyer (actual) with the Scored Labels (prediction), you can see how well the model has performed. Next, you can use this model to make predictions for new customers and publish this model as a web service or write results back to SQL Data Warehouse.
116
127
117
128
## Next steps
118
-
To learn more about building predictive machine learning models, refer to [Introduction to Machine Learning on Azure][Introduction to Machine Learning on Azure].
[Introduction to Machine Learning on Azure]:https://azure.microsoft.com/documentation/articles/machine-learning-what-is-machine-learning/
138
-
[load sample data manually]: sql-data-warehouse-load-sample-databases.md
139
-
[Create a SQL Data Warehouse]: sql-data-warehouse-get-started-provision.md
129
+
To learn more about building predictive machine learning models, refer to [Introduction to Machine Learning on Azure](https://azure.microsoft.com/documentation/articles/machine-learning-what-is-machine-learning/).
3. On the Help + Support blade, click **New support request** and fill out the **Basics** blade.
25
25
26
-
Select your [Azure support plan][Azure support plan].
26
+
Select your [Azure support plan](https://azure.microsoft.com/support/plans/?WT.mc_id=Support_Plan_510979/).
27
27
28
28
***Billing, quota, and subscription management** support are available at all support levels.
29
-
***Break-fix** support is provided through [Developer][Developer], [Standard][Standard], [Professional Direct][Professional Direct], or [Premier][Premier] support. Break-fix issues are problems experienced by customers while using Azure where there is a reasonable expectation that Microsoft caused the problem.
30
-
***Developer mentoring** and **advisory services** are available at the [Professional Direct][Professional Direct]and [Premier][Premier] support levels.
29
+
***Break-fix** support is provided through [Developer](https://azure.microsoft.com/support/plans/developer/), [Standard](https://azure.microsoft.com/support/plans/standard/), [Professional Direct](https://azure.microsoft.com/support/plans/prodirect/), or [Premier](https://azure.microsoft.com/support/plans/premier/) support. Break-fix issues are problems experienced by customers while using Azure where there is a reasonable expectation that Microsoft caused the problem.
30
+
***Developer mentoring** and **advisory services** are available at the [Professional Direct](https://azure.microsoft.com/support/plans/prodirect/)and [Premier](https://azure.microsoft.com/support/plans/premier/) support levels.
31
31
32
-
If you have a Premier support plan, you can also report SQL Data Warehouse related issues on the [Microsoft Premier online portal][Microsoft Premier online portal]. See [Azure support plans][Azure support plan]to learn more about the various support plans, including scope, response times, pricing, etc. For frequently asked questions about Azure support, see [Azure support FAQs][Azure support FAQs].
32
+
If you have a Premier support plan, you can also report SQL Data Warehouse related issues on the [Microsoft Premier online portal](https://premier.microsoft.com/). See [Azure support plans](https://azure.microsoft.com/support/plans/?WT.mc_id=Support_Plan_510979/)to learn more about the various support plans, including scope, response times, pricing, etc. For frequently asked questions about Azure support, see [Azure support FAQs](https://azure.microsoft.com/support/faq/).
> By default, each SQL server (for example, myserver.database.windows.net) has a **DTU Quota** of 45,000. This quota is simply a safety limit. You can increase your quota by creating a support ticket and selecting *Quota* as the request type. To calculate your DTU needs, multiply 7.5 by the total [DWU][DWU] needed. For example, you would like to host two DW6000s on one SQL server, then you should request a DTU quota of 90,000. You can view your current DTU consumption from the SQL server blade in the portal. Both paused and unpaused databases count toward the DTU quota.
41
+
> By default, each SQL server (for example, myserver.database.windows.net) has a **DTU Quota** of 45,000. This quota is simply a safety limit. You can increase your quota by creating a support ticket and selecting *Quota* as the request type. To calculate your DTU needs, multiply 7.5 by the total [DWU](sql-data-warehouse-overview-what-is.md) needed. For example, you would like to host two DW6000s on one SQL server, then you should request a DTU quota of 90,000. You can view your current DTU consumption from the SQL server blade in the portal. Both paused and unpaused databases count toward the DTU quota.
6. Click **Create** to submit the support request.
49
51
50
52
## Monitor a support ticket
51
-
After you have submitted the support request, the Azure support team will contact you. To check your request status and details, click **All support requests** on the dashboard.
53
+
After you've submitted the support request, the Azure support team will contact you. To check your request status and details, click **All support requests** on the dashboard.
Additionally, you can connect with the SQL Data Warehouse community on [Stack Overflow][Stack Overflow] or on the [Azure SQL Data Warehouse MSDN forum][Azure SQL Data Warehouse MSDN forum].
57
-
58
-
<!--Image references-->
59
-
60
-
<!--Article references-->
61
-
[DWU]: ./sql-data-warehouse-overview-what-is.md
62
-
63
-
<!--MSDN references-->
64
-
65
-
<!--Other web references-->
66
-
[Azure portal]: https://portal.azure.com/
67
-
[Azure support plan]: https://azure.microsoft.com/support/plans/?WT.mc_id=Support_Plan_510979/
[Azure SQL Data Warehouse MSDN forum]: https://social.msdn.microsoft.com/Forums/home?forum=AzureSQLDataWarehouse/
58
+
You can also connect with the SQL Data Warehouse community on [Stack Overflow](https://stackoverflow.com/questions/tagged/azure-sqldw/) or through the [Azure SQL Data Warehouse MSDN forum](https://social.msdn.microsoft.com/Forums/home?forum=AzureSQLDataWarehouse/).
0 commit comments