Train Classifier

Train a machine learning classifier on labeled imagery. Creates a model that can be used with classification_predict to classify new imagery. Supports Random Forest, SVM, Decision Trees, KNN, and Neural Networks.

ID	classification_train
Domain	geo
Category	classification
Type	raster-vector-to-model
Version	1.0.0

view yaml ◦view github ◦

Parameters

classifier: enum · default rf · Classifier algorithm: - rf: Random Forest (default) - robust, handles noise well - svm: Support Vector Machine - good for small training sets - dt: Decision Tree - fast, interpretable - knn: K-Nearest Neighbors - simple, no training phase - ann: Artificial Neural Network - complex patterns
label_field: string · default class · Field name in training_data containing class labels
rf_trees: integer · default 100 · Number of trees in the forest (rf only)
rf_max_depth: integer · default 25 · Maximum depth of each tree (rf only)
rf_min_samples: integer · default 5 · Minimum samples required at a leaf node (rf only)
svm_kernel: enum · default rbf · SVM kernel type (svm only)
svm_c: number · default 1 · SVM regularization parameter (svm only)
sample_strategy: enum · default smallest · How to balance samples across classes: - all: Use all available samples - smallest: Match the smallest class - constant: Fixed number per class - percent: Percentage of available samples
sample_count: integer · default 1000 · Samples per class (for constant/percent strategies)