From 9a1db4002e2a5a569d63b5674c905fa41523b26d Mon Sep 17 00:00:00 2001 From: "Documenter.jl" Date: Mon, 26 Aug 2024 06:44:09 +0000 Subject: [PATCH] build based on e4be902 --- dev/.documenter-siteinfo.json | 2 +- dev/index.html | 2 +- dev/objects.inv | Bin 495 -> 495 bytes dev/reference/api/index.html | 8 ++++---- dev/usage/mlj/index.html | 2 +- dev/usage/quickstart/index.html | 2 +- 6 files changed, 8 insertions(+), 8 deletions(-) diff --git a/dev/.documenter-siteinfo.json b/dev/.documenter-siteinfo.json index 0e251e3..537f340 100644 --- a/dev/.documenter-siteinfo.json +++ b/dev/.documenter-siteinfo.json @@ -1 +1 @@ -{"documenter":{"julia_version":"1.10.4","generation_timestamp":"2024-08-25T13:08:26","documenter_version":"1.6.0"}} \ No newline at end of file +{"documenter":{"julia_version":"1.10.4","generation_timestamp":"2024-08-26T06:44:06","documenter_version":"1.6.0"}} \ No newline at end of file diff --git a/dev/index.html b/dev/index.html index 63a0501..ea564c1 100644 --- a/dev/index.html +++ b/dev/index.html @@ -1,2 +1,2 @@ -Home · Maxnet.jl

Maxnet

Stable Dev Build Status Coverage

This is a Julia implementation of the maxnet algorithm, with all core functionality in the original R package.

Maxnet transforms input data in various ways and then uses the GLMnet algorithm to fit a lasso path, selecting the best variables and transformations.

Maxnet is closely related to the Java MaxEnt application, which is widely used in species distribution modelling. It was developped by Steven Philips. See this publication for more details about maxnet.

Also see the Maxent page on the site of the American Museum for Natural History.

Documentation for Maxnet.

+Home · Maxnet.jl

Maxnet

Stable Dev Build Status Coverage

This is a Julia implementation of the maxnet algorithm, with all core functionality in the original R package.

Maxnet transforms input data in various ways and then uses the GLMnet algorithm to fit a lasso path, selecting the best variables and transformations.

Maxnet is closely related to the Java MaxEnt application, which is widely used in species distribution modelling. It was developped by Steven Philips. See this publication for more details about maxnet.

Also see the Maxent page on the site of the American Museum for Natural History.

Documentation for Maxnet.

diff --git a/dev/objects.inv b/dev/objects.inv index 3f34070adfc499eceb4dc6ed280584003ea65434..7abfd8d4ecc86ced2fabac2ec7b9300b7099c5f6 100644 GIT binary patch delta 12 TcmaFQ{GNG&Bcstqr?rd#ApQi3 delta 12 TcmaFQ{GNG&BctI)r?rd#Ao&D| diff --git a/dev/reference/api/index.html b/dev/reference/api/index.html index 64f827c..a40a284 100644 --- a/dev/reference/api/index.html +++ b/dev/reference/api/index.html @@ -1,5 +1,5 @@ -API reference · Maxnet.jl

API

Index

Functions

Maxnet.default_features — Method
default_features(np)

Takes the number of presences np and returns a Vector of AbstractFeatureClasss that are used my maxent as default.

If np is less than ten, then only LinearFeature and CategoricalFeature are used. If it is at least 10, then QuadraticFeature is additionally used. If it is at least 15, then HingeFeature is additionally used. If it is at least 80, then ProductFeature is additionally used.

source
Maxnet.maxnet — Method
maxnet(
+API reference · Maxnet.jl
API
Index
Functions
Maxnet.default_features — Method
default_features(np)
Takes the number of presences np and returns a Vector of AbstractFeatureClasss that are used my maxent as default.
If np is less than ten, then only LinearFeature and CategoricalFeature are used. If it is at least 10, then QuadraticFeature is additionally used. If it is at least 15, then HingeFeature is additionally used. If it is at least 80, then ProductFeature is additionally used.
source
Maxnet.maxnet — Method
maxnet(
     p_a, X; 
     features, regularization_multiplier, regularization_function,
     addsamplestobackground, weight_factor, 
@@ -14,12 +14,12 @@
 Features classes: Maxnet.AbstractFeatureClass[LinearFeature(), CategoricalFeature(), QuadraticFeature()]
 Entropy: 6.114650341746531
 Model complexity: 21
-Variables selected: [:frs6190_ann, :h_dem, :pre6190_l1, :pre6190_l10, :pre6190_l4, :pre6190_l7, :tmn6190_ann, :vap6190_ann, :ecoreg, :cld6190_ann, :dtr6190_ann, :tmx6190_ann]
source
StatsAPI.predict — Method
predict(m, X; link, clamp)
+Variables selected: [:frs6190_ann, :h_dem, :pre6190_l1, :pre6190_l10, :pre6190_l4, :pre6190_l7, :tmn6190_ann, :vap6190_ann, :ecoreg, :cld6190_ann, :dtr6190_ann, :tmx6190_ann]
source
StatsAPI.predict — Method
predict(m, X; link, clamp)
 
 Use a maxnet model to predict on new data.
Arguments
  • m: a MaxnetModel as returned by maxnet
  • X: a Tables.jl-compatible table of predictors. All columns that were used to fit m should be present in X
Keywords
  • link: the link function used. Defaults to CloglogLink(), which is the default on the Maxent Java appliation since version 4.3.   Alternatively, LogitLink() was the Maxent default on earlier versions.    To get exponential output, which can be interpreted as predicted abundance, use LogLink()   IdentityLink() returns the exponent without any transformation.
  • clamp: If true, values in x will be clamped to the range the model was trained on. Defaults to false.
Returns
A Vector with the resulting predictions.
Example
using Maxnet
 p_a, env = Maxnet.bradypus();
 bradypus_model = maxnet(p_a, env; features = "lq")
-prediction = predict(bradypus_model, env)
source
Types
Types
Maxnet.MaxnetBinaryClassifier — Type
MaxnetBinaryClassifier
 
 A model type for fitting a maxnet model using `MLJ`.
     
@@ -37,4 +37,4 @@
 fit!(mach)
 yhat = MLJBase.predict(mach, env)
 # output
-```
source

+```
source
diff --git a/dev/usage/mlj/index.html b/dev/usage/mlj/index.html index 7ab3e64..df386f9 100644 --- a/dev/usage/mlj/index.html +++ b/dev/usage/mlj/index.html @@ -21,4 +21,4 @@ pred_test = predict(mach; rows = test) # predict on some new dataset -pred = predict(mach, X) +pred = predict(mach, X) diff --git a/dev/usage/quickstart/index.html b/dev/usage/quickstart/index.html index d46402b..a1ff3dc 100644 --- a/dev/usage/quickstart/index.html +++ b/dev/usage/quickstart/index.html @@ -4,4 +4,4 @@ p_a, env = Maxnet.bradypus() bradypus_model = maxnet(p_a, env) prediction = predict(bradypus_model, env)

There are numerous settings that can be tweaked to change the model fit. These are documentated in the documentation for the maxnet and predict functions.

Model settings

The two most important settings to change when running Maxnet is the feature classes selected and the regularization factor.

By default, the feature classes selected depends on the number of presence points, see Maxnet.default_features. To set them manually, specify the features keyword using either a Vector of AbstractFeatureClass, or a string, where l represents LinearFeature and CategoricalFeature, q represents QuadraticFeature, p represents ProductFeature, t represents ThresholdFeature and h represents HingeFeature.

For example:

model1 = maxnet(p_a, env; features = [LinearFeature(), CategoricalFeature(), QuadraticFeature()])
-model2 = maxnet(p_a, env; features = "lqph")

The regularization multiplier controls how much the algorithms penalizes complex models. A higher regularization multiplier will result in a simpler model with fewer features.

model3 = maxnet(p_a, env; features = "lqph", regularization_multiplier = 10.0)

The number of features selected is shown when a model is printed in the REPL and can be accessed using complexity. Here complexity(model2) gives 48 and complexity(model3) gives 13.

+model2 = maxnet(p_a, env; features = "lqph")

The regularization multiplier controls how much the algorithms penalizes complex models. A higher regularization multiplier will result in a simpler model with fewer features.

model3 = maxnet(p_a, env; features = "lqph", regularization_multiplier = 10.0)

The number of features selected is shown when a model is printed in the REPL and can be accessed using complexity. Here complexity(model2) gives 48 and complexity(model3) gives 13.