6.5 Visualizing Fusions

After creating your fusion, you will be able to analyze the results with BigML’s unique visualization: a Partial Dependence Plot (PDP) to examine how the input fields impact the Objective Field (see subsection 6.5.1 ). You will also be able to find the models composing the fusion under the model list tab (see subsection 6.5.2 ).

Switch from the PDP view to the model list view by clicking on the icons in the top bar menu of the fusion view (see Figure 6.21 ).

6.5.1 Fusion Partial Dependence Plot

The chart view is composed of three main parts: the CHART itself, the PREDICTION legend and the INPUT FIELDS form. (See Figure 6.22 .) You can find a detailed explanation of each one below.

• The CHART allows you to view the impact of the input fields on the objective field predictions. You can select a different input field for each axis and the predictions are represented in different colors on the heat map. You can select numeric or categorical fields for the axis and inspect the axis values in the grey area next to the selector. You can switch the axis by clicking on the option on top of the chart area (see Figure 6.23 ).

  

  You can freeze the view by pressing Shift and release it again by pressing Escape from your keyboard. When the view is frozen, an edition icon will appear so you can edit the axis values and obtain a prediction for another desired value. You can see the predictions in the legend to the right.

• The PREDICTION legend allows you to visualize the objective field classes (classification fusions) or the predicted value (regression fusions). For classification, each class is represented by a color, the main probability color bar at the top is the probability for the predicted class. By default, colors are shaded according to the prediction range shown in the chart area. That way, smaller differences in predictions are easier to perceive. However, you can choose to see the color shading according to the total range of possible values for the objective field by clicking on the icon next to the prediction bar Total (see Figure 6.24 ). You can also select to see only one of the classes using the class selector at the bottom of the legend.

  

  Freeze this view by pressing Shift , and release it again by pressing Escape from your keyboard.

• Below the chart legend, you can find the INPUT FIELDS form (see Figure 6.25 ). You can configure the values for any numeric, categorical, text or items field. By changing their values, you can see the predictions changing in real-time. You can also select or disable your input fields, so they will be treated as missing values. If your fusion contains models, ensembles or deepnets, you will be able to see each field importance and order the fields from the highest to lowest importance. If your fusion only contains logistic regressions, the fields will not have importances.

  

Note: if any of the models composing the fusion fail to calculate the prediction (e.g., if a logistic regression is trained without missing numerics it will fail for predictions that have missing numeric values). BigML will use the other models to return a result instead of returning an error.

Moreover, the chart includes a reset option for your input fields values, and an export option to download your chart in PNG format explained below:

• After selecting the fields for the axis or configuring the input fields values, you can set them again to the default view by clicking the reset icon highlighted in Figure 6.26 .

  

• You can also export your chart in PNG format with or without legends. Freeze the view by pressing Shift from your keyboard and export the chart to get the prediction values in the legend. Release the view by pressing Escape .

  

Note: there are some limitations for the number of classes of the objective field and the number of input fields to visualize your fusion in the chart (explained in section 6.8 ).

6.5.2 Fusion Model List

The model list contains all the models composing the fusion. You can see the model number (this is the order in which you selected the models to create the fusion), the model type icon, the model name, the model configuration options, and the model weights (see subsection 6.4.3 for an explanation about the weights). If you click on the model name, you will be taken to that model view. You can filter this list by model type by clicking on the icons shown in Figure 6.28 .