Wolfram Language & System 10.3 (2015)|Legacy Documentation

This is documentation for an earlier version of the Wolfram Language.View current documentation (Version 11.2)

IndeterminateThreshold

IndeterminateThreshold
is an option for Classify, Predict, and related functions that specifies below what probability or probability density a result should be considered indeterminate.

DetailsDetails

  • With , Indeterminate will be returned if the probability or probability density of the predicted value is less than .

ExamplesExamplesopen allclose all

Basic Examples  (3)Basic Examples  (3)

Train a logistic classifier:

In[1]:=
Click for copyable input
In[2]:=
Click for copyable input
Out[2]=

Obtain class probabilities for a new example:

In[3]:=
Click for copyable input
Out[3]=

The most probable class is predicted:

In[4]:=
Click for copyable input
Out[4]=

If no probability is above the probability threshold, no class is predicted:

In[5]:=
Click for copyable input
Out[5]=

The probability threshold can be set in the classifier:

In[6]:=
Click for copyable input
Out[6]=
In[7]:=
Click for copyable input
Out[7]=

Train a linear predictor:

In[1]:=
Click for copyable input
Out[1]=

Visualize the probability density for a given example:

In[2]:=
Click for copyable input
Out[2]=
In[3]:=
Click for copyable input
Out[3]=

For this example, the predicted value and its corresponding probability density are as follows:

In[4]:=
Click for copyable input
Out[4]=
In[5]:=
Click for copyable input
Out[5]=

If the threshold is higher than the probability density, no value is predicted:

In[6]:=
Click for copyable input
Out[6]=

Change the value of IndeterminateThreshold in a built-in classifier:

In[1]:=
Click for copyable input
Out[1]=
In[2]:=
Click for copyable input
Out[2]=
Introduced in 2014
(10.0)