PrologMethods/Classification/softmax_regression.md

+# Softmax Regression
+
+An implementation of softmax regression for classification, which is a multiclass generalization of logistic regression.
+
+# Available Predicates
+
+* [initModelNoTrain/3](/PrologMethods/Classification/softmax_regression#initmodelnotrain3)
+* [initModelWithTrain/8](/PrologMethods/Classification/softmax_regression#initmodelwithtrain8)
+* [classifyPoint/3](/PrologMethods/Classification/softmax_regression#classifypoint3)
+* [classifyMatrix/8](/PrologMethods/Classification/softmax_regression#classifymatrix8)
+* [computeAccuracy/6](/PrologMethods/Classification/softmax_regression#computeaccuracy6)
+* [featureSize/1](/PrologMethods/Classification/softmax_regression#featuresize1)
+* [parameters/3](/PrologMethods/Classification/softmax_regression#parameters3)
+* [train/7](/PrologMethods/Classification/softmax_regression#train7)
+
+---
+
+[links/resources](/PrologMethods/Classification/softmax_regression#connected-linksresources)
+
+## **_initModelNoTrain/3_**
+
+Initializes the softmax_regression model without training.
+
+Be sure to use Train before calling Classif or ComputeAccuracy, otherwise the results may be meaningless.
+
+```prolog
+%% part of the predicate definition
+initModelNoTrain(  +integer, +integer, 
+                   +integer).
+```
+
+### Parameters
+| Name | Type | Description | Default |
+|------|------|-------------|---------|
+| inputSize | +integer | Size of the input feature vector. | 0 |
+| numClasses | +integer | Number of classes for classification. | 0 |
+| fitIntercept | +integer(bool) | add intercept term or not. | (0)false |
+
+---
+
+## **_initModelWithTrain/8_**
+
+Initializes the softmax_regression model and trains it.
+
+```prolog
+%% part of the predicate definition
+initModelWithTrain(  +pointer(float_array), +integer, +integer, 
+                     +pointer(float_array), +integer, 
+                     +integer, +float32, 
+                     +integer).
+```
+
+### Parameters
+| Name | Type | Description | Default |
+|------|------|-------------|---------|
+| data | +matrix | Input training features. Each column associate with one sample. | - |
+| labels | +vector | Labels associated with the feature data. | - |
+| numClasses | +integer | Number of classes for classification. | 0 |
+| lambda | +float | L2-regularization constant. | 0.0001 |
+| fitIntercept | +integer(bool) | add intercept term or not. | (0)false |
+
+---
+
+## **_classifyPoint/3_**
+
+Classify the given point.
+
+```prolog
+%% part of the predicate definition
+classifyPoint(  +pointer(float_array), +integer, 
+                [-integer]).
+```
+
+### Parameters
+| Name | Type | Description | Default |
+|------|------|-------------|---------|
+| point | +vector | Point to be classified. | - |
+| predictedLabel | -integer | Predicted class label of the point. | - |
+
+---
+
+## **_classifyMatrix/8_**
+
+Classify the given points, returning class probabilities and predicted class label for each point.
+
+```prolog
+%% part of the predicate definition
+classifyMatrix(  +pointer(float_array), +integer, +integer, 
+                 -pointer(float_array), -integer, 
+                 -pointer(float_array), -integer, -integer).
+```
+
+### Parameters
+| Name | Type | Description | Default |
+|------|------|-------------|---------|
+| data | +matrix | Matrix of data points to be classified. | - |
+| predictedLabels | -vector | Predicted labels for each point. | - |
+| probabilities | -matrix | Class probabilities for each point. | - |
+
+---
+
+## **_computeAccuracy/6_**
+
+Computes accuracy of the learned model given the feature data and the labels associated with each data point.
+
+Predictions are made using the provided data and are compared with the actual labels.
+
+```prolog
+%% part of the predicate definition
+computeAccuracy(  +pointer(float_array), +integer, +integer, 
+                  +pointer(float_array), +integer, 
+                  [-float32]).
+```
+
+### Parameters
+| Name | Type | Description | Default |
+|------|------|-------------|---------|
+| data | +matrix | Matrix of data points using which predictions are made. | - |
+| predictedLabels | -vector | Vector of labels associated with the data. | - |
+| accuracy | -float | - | - |
+
+---
+
+## **_featureSize/1_**
+
+Gets the features size of the training data.
+
+```prolog
+%% part of the predicate definition
+featureSize([-integer]).
+```
+
+### Parameters
+| Name | Type | Description | Default |
+|------|------|-------------|---------|
+| featureSize | -integer | Get the features size of the training data. | - |
+
+---
+
+## **_parameters/3_**
+
+Get the model parameters.
+
+```prolog
+%% part of the predicate definition
+parameters(-pointer(float_array), -integer, -integer).
+```
+
+### Parameters
+| Name | Type | Description | Default |
+|------|------|-------------|---------|
+| parameters | -matrix | Get the model parameters. | - |
+
+---
+
+## **_train/7_**
+
+Trains the softmax regression model with the given training data.
+
+```prolog
+%% part of the predicate definition
+train(  +pointer(float_array), +integer, +integer, 
+        +pointer(float_array), +integer, 
+        +integer, 
+        [-float32]).
+```
+
+### Parameters
+| Name | Type | Description | Default |
+|------|------|-------------|---------|
+| data | +matrix | Input training features. Each column associate with one sample. | - |
+| labels | +vector | Labels associated with the feature data. | - |
+| numClasses | +integer | Number of classes for classification. | 0 |
+| finalPointValue | -float | Objective value of final point | - |
+
+---
+
+# Connected Links/Resources
+
+If you want a more detailed explanation, then go to the python documentation. There is most of the time a good explanation on how the methods work and what the parameters do.
+
+* [MLpack::softmax_regression_C++\_documentation](https://www.mlpack.org/doc/stable/doxygen/classmlpack_1_1regression_1_1SoftmaxRegression.html)
+* [MLpack::softmax_regression_Python_documentation](https://www.mlpack.org/doc/stable/python_documentation.html#softmax_regression)
+
+added some of the links from the python documentation
+
+* logistic_regression
+* random_forest
+* [Multinomial logistic regression (softmax regression) on Wikipedia](https://en.wikipedia.org/wiki/Multinomial_logistic_regression)
\ No newline at end of file