Making Predictions Using the ML UI

Follow the steps below to predict a set of values using a built model.

Start the WSO2 ML server. For instructions on starting, see Running the Product.
Access the ML UI from your Web browser using the following URL: https://<ML_HOST>:<ML_PORT>/ml

You can find the URL of the WSO2 ML UI in the server startup logs in the CLI as follows: INFO{org.wso2.carbon.ml.core.internal.MLCoreDS} - WSO2 Machine Learner UI : https://127.0.0.1:9446/ml
Log in to the ML UI as a user who is registered in WSO2 ML. For registering users, see User Management.
Log in to the WSO2 ML UI, if you are not already logged in.
Click PROJECTS in the top menu as shown below.
Click on the project which includes the analysis of the model on which you want to make the prediction.
Click MODELS as shown below.
Click the PREDICT option of the model on which you want to make the prediction as shown below.
Select File for the Prediction Source , and upload a CSV or TSV file containing feature values to predict data rows by specifying the data format as shown below.

Click Predict. This downloads the prediction result in a CSV file (e.g. Predictions_3_2015-08-12_19-33-08.csv file) as shown in the example below.
```
10,168,74,0,0,38.0,0.537,34,-9.538673375931532E64
10,139,80,0,0,27.1,1.441,57,-8.290788952350152E64
1,189,60,23,846,30.1,0.398,59,-5.103151579724951E65
5,166,72,19,175,25.8,0.587,51,-1.7860703345567017E65
7,100,0,0,0,30.0,0.484,32,-4.7180385980283585E64
0,118,84,47,230,45.8,0.551,31,-1.91437599142306E65
7,107,74,0,0,29.6,0.254,31,-6.772396075748577E64
1,103,30,38,83,43.3,0.183,33,-1.0016013750360163E65
1,115,70,30,96,34.6,0.529,32,-1.1953388291025707E65
3,126,88,41,235,39.3,0.704,27,-1.9712048264406836E65
```
Alternatively, select Feature values for the Prediction Source to predict a single data row by entering the value of each feature as shown below.

Click Predict. You view the predicted value at the bottom of the screen as shown below.

If you are using a deep learning model to make predictions without H2O runtime, see Using Deep Learning Models without H2O Runtime.