ppforest2::stats Namespace Reference

Statistical infrastructure for training and evaluation. More...

Classes
struct	ConfusionMatrix
	A confusion matrix comparing predicted vs actual group labels. More...
struct	DataPacket
	Bundled dataset: features, responses, and group labels. More...
class	GroupPartition
	Contiguous-block representation of grouped observations. More...
class	Normal
	Normal (Gaussian) random number generator. More...
struct	SimulationParams
	Parameters for generating simulated classification data. More...
struct	Split
	Indices for a train/test split. More...
class	Uniform
	Discrete uniform random integer generator over [min, max]. More...

Typedefs
using	RNG = pcg32

Functions
float	accuracy (types::ResponseVector const &predictions, types::ResponseVector const &actual)
	Accuracy of a prediction.
double	error_rate (types::ResponseVector const &predictions, types::ResponseVector const &actual)
	Error rate of a prediction.
std::map< int, int >	get_labels_map (types::ResponseVector const &groups)
	Build a sorted mapping from unique group labels to contiguous indices.
types::FeatureVector	sd (types::FeatureMatrix const &data)
	Column-wise sample standard deviation of a matrix.
double	sd (types::FeatureVector const &data)
	Sample standard deviation of a vector.
DataPacket	simulate (int n, int p, int G, RNG &rng, SimulationParams const &params=SimulationParams{})
	Generate a simulated dataset with G groups, n rows, and p features.
void	sort (types::FeatureMatrix &x, types::ResponseVector &y)
	Sort a feature matrix and a response vector by the response values.
Split	split (DataPacket const &data, float train_ratio, RNG &rng)
	Perform a stratified random train/test split on a DataPacket.
std::set< types::Response >	unique (types::ResponseVector const &column)
	Unique values of a response vector.

Detailed Description

Statistical infrastructure for training and evaluation.

Provides the random number generator (pcg32), discrete uniform sampling (Lemire's method), grouped-observation bookkeeping (GroupPartition), confusion matrices, data simulation, and basic descriptive statistics used throughout the training pipeline.

Typedef Documentation

RNG

using ppforest2::stats::RNG = pcg32

Function Documentation

accuracy()

float ppforest2::stats::accuracy	(	types::ResponseVector const &	predictions,
		types::ResponseVector const &	actual )

Accuracy of a prediction.

Parameters

predictions	Predicted response vector.
actual	Actual response vector.

Returns

Accuracy (0 to 1).

error_rate()

double ppforest2::stats::error_rate	(	types::ResponseVector const &	predictions,
		types::ResponseVector const &	actual )

Error rate of a prediction.

Parameters

predictions	Predicted response vector.
actual	Actual response vector.

Returns

Error rate (0 to 1).

get_labels_map()

std::map< int, int > ppforest2::stats::get_labels_map

(

types::ResponseVector const &

groups

)

Build a sorted mapping from unique group labels to contiguous indices.

Parameters

groups

A response vector containing group labels.

Returns

A map from label value to its 0-based index.

sd() [1/2]

types::FeatureVector ppforest2::stats::sd

(

types::FeatureMatrix const &

data

)

Column-wise sample standard deviation of a matrix.

Parameters

data	Feature matrix with at least 2 rows.

Returns

FeatureVector of size p (one σ per column).

sd() [2/2]

double ppforest2::stats::sd

(

types::FeatureVector const &

data

)

Sample standard deviation of a vector.

Parameters

data	Feature vector with at least one row.

Returns

Sample standard deviation.

simulate()

DataPacket ppforest2::stats::simulate	(	int	n,
		int	p,
		int	G,
		RNG &	rng,
		SimulationParams const &	params = SimulationParams{} )

Generate a simulated dataset with G groups, n rows, and p features.

Each group is drawn from a normal distribution with a shifted mean. The resulting data is sorted by group label.

Parameters

n	Number of rows (observations).
p	Number of feature columns.
G	Number of groups (must be > 1).
rng	Random number generator.
params	Simulation parameters (mean, separation, sd).

Returns

A DataPacket with the simulated feature matrix and response vector.

sort()

void ppforest2::stats::sort	(	types::FeatureMatrix &	x,
		types::ResponseVector &	y )

Sort a feature matrix and a response vector by the response values.

Parameters

x	Feature matrix.
y	Response vector.

split()

Split ppforest2::stats::split	(	DataPacket const &	data,
		float	train_ratio,
		RNG &	rng )

Perform a stratified random train/test split on a DataPacket.

Samples indices within each group proportional to train_ratio so that group balance is preserved in both train and test sets.

Parameters

data	The full dataset.
train_ratio	Proportion of data to use for training (0, 1).
rng	Random number generator.

Returns

A Split containing train and test index vectors.

unique()

std::set< types::Response > ppforest2::stats::unique

(

types::ResponseVector const &

column

)

Unique values of a response vector.

Parameters

column

Response vector.

Returns

Set of unique response values.