Functions — github.com/al-jshen/compute

hub / github.com/al-jshen/compute / functions

Functions442 in github.com/al-jshen/compute

⨍ Functions 442◇ Types & classes 42

↓ 65 callersMethodsample_n

Generates a vector of `n` randomly sampled values from the given probability distribution.

src/distributions/mod.rs:32

↓ 28 callersMethodto_vec

Converts the matrix to a Vector.

src/linalg/array/matrix.rs:436

↓ 21 callersMethodinto_iter

(self)

src/linalg/array/vec.rs:139

↓ 15 callersFunctionis_matrix

(m: &[f64], nrows: usize)

src/linalg/utils.rs:47

↓ 15 callersFunctionmatmul

( a: &[f64], b: &[f64], rows_a: usize, rows_b: usize, transpose_a: bool, transpose_b:

src/linalg/utils.rs:362

↓ 15 callersFunctionmean

Calculates the mean of an array of data points.

src/statistics/moments.rs:37

↓ 13 callersFunctiongamma

Calculates the [Gamma function](https://en.wikipedia.org/wiki/Gamma_function) using the [Lanczos approximation](https://en.wikipedia.org/wiki/Lanczos_

src/functions/gamma.rs:31

↓ 13 callersMethodsample

Samples from the given T distribution.

src/distributions/t.rs:38

↓ 11 callersMethodt

Transpose the matrix.

src/linalg/array/matrix.rs:412

↓ 11 callersFunctiontranspose

Transpose a matrix.

src/linalg/utils.rs:158

↓ 10 callersFunctiondot

(x: &[f64], y: &[f64])

src/linalg/utils.rs:570

↓ 10 callersFunctionis_square

(m: &[f64])

src/linalg/utils.rs:58

↓ 8 callersMethodshape

Get the number of rows and columns in the matrix.

src/linalg/array/matrix.rs:282

↓ 7 callersFunctioninvert_matrix

Given an n by n matrix, invert it. The resulting matrix is returned as a flattened array.

src/linalg/utils.rs:183

↓ 7 callersFunctionmatmul_blocked

Performs blocked matrix multiplication with block size `bsize`. See the API for the [matmul](crate::linalg::matmul).

src/linalg/utils.rs:314

↓ 6 callersFunctioncholesky

Computes the Cholesky decomposition of the matrix `a` using the Cholesky-Banachiewicz algorithm.

src/linalg/decomposition/cholesky.rs:9

↓ 6 callersMethodextend

(&mut self, iter: T)

src/linalg/array/vec.rs:183

↓ 6 callersFunctionlinspace

Generates evenly spaced values within a given interval, with a set number of points. Both the start and stop points are included.

src/linalg/utils.rs:38

↓ 6 callersFunctionmax

Returns the largest element in the array.

src/statistics/order.rs:9

↓ 6 callersMethodsize

Get the total number of elements in the matrix.

src/linalg/array/matrix.rs:287

↓ 6 callersMethodto_matrix

(self)

src/linalg/array/vec.rs:66

↓ 5 callersFunctionarange

Generates evenly spaced values within a given interval. Values generated in the half-open interval [start, stop). That is, the stop point is not inclu

src/linalg/utils.rs:29

↓ 5 callersMethoddeviance

Return the deviance of the model.

src/predict/glms/glm.rs:247

↓ 5 callersFunctionlu

Computes the pivoted LU decomposition of a square matrix. For some matrix A, this decomposition is A = PLU. The resulting matrix has U in its upper tr

src/linalg/decomposition/lu.rs:14

↓ 5 callersMethodreshape

(&self, nrows: i32, ncols: i32)

src/linalg/array/vec.rs:71

↓ 5 callersFunctionsolve

Solve the linear system Ax = b.

src/linalg/utils.rs:274

↓ 5 callersFunctionvar

Calculates the population variance from an array of data points in a numerically stable manner using the Welford algorithm.

src/statistics/moments.rs:49

↓ 4 callersMethoddiag

Get the diagonal elements of the matrix.

src/linalg/array/matrix.rs:243

↓ 4 callersMethodlu

(&self)

src/linalg/array/matrix.rs:163

↓ 4 callersMethodlu_solve

Solve the linear system Ax = b given a LU decomposed matrix A. The first argument should be a tuple, where the first element is the LU decomposed matr

src/linalg/array/matrix.rs:526

↓ 4 callersFunctionrow_to_col_major

Convert a 1D matrix from row-major ordering into column-major ordering.

src/linalg/utils.rs:134

↓ 3 callersMethodcholesky

Return the Cholesky decomposition of the matrix. Resulting matrix is lower triangular.

src/linalg/array/matrix.rs:143

↓ 3 callersFunctioncholesky_solve

Solves the system Lx=b, where L is a lower triangular matrix (e.g., a Cholesky decomposed matrix), and b is a one dimensional vector.

src/linalg/decomposition/cholesky.rs:32

↓ 3 callersFunctioncol_to_row_major

Convert a 1D matrix from column-major ordering into row-major ordering.

src/linalg/utils.rs:146

↓ 3 callersMethodinv_link

(&self, eta: &[f64])

src/predict/glms/families.rs:43

↓ 3 callersFunctionlu_solve

Solve the linear system Ax = b given a LU decomposed matrix A. The first argument should be a tuple, where the first element is the LU decomposed matr

src/linalg/decomposition/lu.rs:56

↓ 3 callersFunctionmin

A module for computing order statistics. This includes medians, quantiles, and extrema. Returns the smallest element in the array.

src/statistics/order.rs:4

↓ 3 callersFunctionnorm

Calculates the norm of a vector.

src/linalg/utils.rs:609

↓ 3 callersFunctionrbfkernel

(a: &Matrix, b: &Matrix, var: f64, lengthsq: f64)

examples/gp_regression/src/main.rs:81

↓ 3 callersMethodupdate

Update the coefficients of the polynomial regressor.

src/predict/polynomial.rs:21

↓ 3 callersFunctionwelford_statistics

Uses the Welford online algorithm to calculate the count, mean, and m2 of an array of data points. This is the driver for the `mean`, `variance`, and

src/statistics/moments.rs:23

↓ 2 callersFunctionacf

Calculates the autocorrelation of lag (-)k of a vector of time series data, assuming that the points are equally spaced in time.

src/timeseries/functions.rs:17

↓ 2 callersFunctionbinom_coeff

Calculates the [binomial coefficient](https://en.wikipedia.org/wiki/Binomial_coefficient) nCk for two integers `n` and `k`, with `n >= k`.

src/functions/combinatorial.rs:7

↓ 2 callersFunctionbootstrap

Given an array of data, returns `n_bootstrap` vectors, where each has elements that are drawn from the original array with replacement, and the length

src/validation/resample.rs:8

↓ 2 callersMethodcoef

Return the maximum likelihood estimates for the parameters.

src/predict/glms/glm.rs:238

↓ 2 callersMethodcompute_ddbeta

(&self, x: &[f64], dmu: &[f64], var: &[f64], weights: &[f64])

src/predict/glms/glm.rs:113

↓ 2 callersMethoddata

(&self)

src/linalg/array/vec.rs:30

↓ 2 callersFunctiondesign

Create a design matrix from a given matrix.

src/linalg/utils.rs:465

↓ 2 callersMethodget_col_as_vector

Return a copy of the column of the matrix as a Vector.

src/linalg/array/matrix.rs:362

↓ 2 callersMethodget_dim

(&self)

src/distributions/multivariatenormal.rs:61

↓ 2 callersMethodget_row_as_vector

Return a copy of the row of the matrix as a Vector.

src/linalg/array/matrix.rs:356

↓ 2 callersFunctionhist_bin_centers

Given the edges of some intervals, return the centers of the intervals. If `edges` is length n, then the resulting vector will be length n - 1.

src/statistics/hist.rs:5

↓ 2 callersMethodinf_norm

Calculates the infinity norm of the matrix.

src/linalg/array/matrix.rs:396

↓ 2 callersFunctioninterp1d_linear

( x: &[f64], y: &[f64], tgt: &[f64], extrapolate: ExtrapolationMode, )

src/functions/interpolate.rs:9

↓ 2 callersMethodinv

Invert the matrix.

src/linalg/array/matrix.rs:73

↓ 2 callersFunctionipiv_parity

Calculates the parity of a swap permutation array ipiv (e.g. that you get as an output from Lapack).

src/linalg/utils.rs:111

↓ 2 callersFunctionis_positive_definite

(m: &[f64])

src/linalg/utils.rs:96

↓ 2 callersFunctionjackknife

Given a length-n array of data, returns all leave-one-out length n-1 vectors. See <https://en.wikipedia.org/wiki/Jackknife_resampling>

src/validation/resample.rs:23

↓ 2 callersMethodoptimize

Run the optimization algorithm, given a vector of parameters to optimize and a function which calculates the residuals.

src/optimize/adam.rs:84

↓ 2 callersMethodpredict

Use the fitted model to make predictions on some new data.

src/predict/glms/glm.rs:300

↓ 2 callersMethodpredict

Predict n values ahead. For forecasts after the first forecast, uses previous forecasts as "data" to create subsequent forecasts.

src/timeseries/autoregressive.rs:58

↓ 2 callersMethodreshape_mut

Reshape the matrix in-place. A size of `-1` in either the rows or the columns means that the size for that dimension will be automatically determined

src/linalg/array/matrix.rs:293

↓ 2 callersMethodsample

Samples from the given Binomial distribution. For `np <= 30`, this is done with an inversion algorithm. Otherwise, this is done with the BTPE algorith

src/distributions/binomial.rs:46

↓ 2 callersMethodsample_matrix

Generates a matrix of size `n x m` with values randomly sampled from the given distribution.

src/distributions/mod.rs:37

↓ 2 callersMethodset_stepsize

(&mut self, stepsize: f64)

src/optimize/adam.rs:64

↓ 2 callersMethodsolve

Solve the linear system Ax = b using LU decomposition.

src/linalg/array/matrix.rs:553

↓ 2 callersFunctionsum

(x: &[f64])

src/linalg/utils.rs:501

↓ 2 callersMethodsum_cols

Sum the matrix down the columns.

src/linalg/array/matrix.rs:384

↓ 2 callersMethodsum_rows

Sum the matrix across the rows.

src/linalg/array/matrix.rs:375

↓ 2 callersFunctiontrapezoid

Integrate samples from a function

src/integrate/samples.rs:4

↓ 2 callersFunctionxtx

Given a matrix X with k rows, return X transpose times X, which is a symmetric matrix.

src/linalg/utils.rs:217

↓ 1 callersFunctionacovf

Calculates the autocovariance of lag (-)k of a vector of time series data, assuming that the points are equally spaced in time.

src/timeseries/functions.rs:5

↓ 1 callersMethodapply_dbeta_penalty

(&self, dbeta: &mut [f64], coef: &[f64])

src/predict/glms/glm.rs:129

↓ 1 callersMethodapply_ddbeta_penalty

(&self, ddbeta: &mut [f64], n_predictors: usize)

src/predict/glms/glm.rs:135

↓ 1 callersMethodargmax

Find the position of the largest element in the matrix. Returns (row, column).

src/linalg/array/matrix.rs:498

↓ 1 callersMethodargmin

Find the position of the smallest element in the matrix. Returns (row, column).

src/linalg/array/matrix.rs:492

↓ 1 callersMethodas_ref

(&self)

src/linalg/array/vec.rs:124

↓ 1 callersFunctionbackward_substitution

Solve a matrix equation of the form Ux=b, where U is an upper triangular matrix. See the [Wikipedia page](https://en.wikipedia.org/wiki/Triangular_mat

src/linalg/decomposition/substitution.rs:23

↓ 1 callersMethodbackward_substitution

Solve a matrix equation of the form Ux=b, where U is an upper triangular matrix. See the [Wikipedia page](https://en.wikipedia.org/wiki/Triangular_mat

src/linalg/array/matrix.rs:132

↓ 1 callersFunctionbeta

Calculates the [beta function](https://en.wikipedia.org/wiki/Beta_function) using the relationship between the beta function and the gamma function.

src/functions/gamma.rs:46

↓ 1 callersFunctionbinomial_btpe

(n: u64, p: f64)

src/distributions/binomial.rs:91

↓ 1 callersFunctionbinomial_inversion

(n: u64, p: f64)

src/distributions/binomial.rs:77

↓ 1 callersMethodcholesky_solve

(&self, system: &Vector)

src/linalg/array/matrix.rs:511

↓ 1 callersMethodcoef_covariance_matrix

Returns the fitted covariance for the estimated parameters.

src/predict/glms/glm.rs:283

↓ 1 callersMethodcoef_standard_error

Returns the estimated standard errors on the estimated parameters. This is equivalent to the square root of the diagonals of the covariance matrix.

src/predict/glms/glm.rs:293

↓ 1 callersMethodcompute_dbeta

( &self, x: &[f64], y: &[f64], mu: &[f64], dmu: &[f64], var: &

src/predict/glms/glm.rs:86

↓ 1 callersMethodd_inv_link

(&self, eta: &[f64], mu: &[f64])

src/predict/glms/families.rs:57

↓ 1 callersMethoddet

Calculates the determinant of the matrix using the LU decomposition.

src/linalg/array/matrix.rs:205

↓ 1 callersMethoddeviance

(&self, y: &[f64], mu: &[f64])

src/predict/glms/families.rs:71

↓ 1 callersFunctiondiag

(a: &[f64])

src/linalg/utils.rs:124

↓ 1 callersFunctiondiag_matrix

Create a diagonal matrix with the given elements along the elements.

src/linalg/utils.rs:173

↓ 1 callersMethoddiff

(&self)

src/linalg/array/vec.rs:87

↓ 1 callersFunctiondigamma

Calculates the [digamma function](https://en.wikipedia.org/wiki/Digamma_function), which is the logarithmic derivative of the gamma function. It obeys

src/functions/gamma.rs:54

↓ 1 callersMethoddispersion

Calculates the dispersion of the model.

src/predict/glms/glm.rs:269

↓ 1 callersFunctionerf

Calculates the [error function](https://en.wikipedia.org/wiki/Error_function) erf(x). # Remarks Uses Equation 7.1.26 in Stegun in combination with Ho

src/functions/statistical.rs:59

↓ 1 callersMethodfit

Fit the polynomial regressor to some observed data `y` given some explanatory variables `x`. Uses least squares fitting.

src/predict/polynomial.rs:42

↓ 1 callersMethodfit

Fit the GLM using the [scoring algorithm](https://en.wikipedia.org/wiki/Score_(statistics)#Scoring_algorithm), which gives the maximumum likelihood es

src/predict/glms/glm.rs:144

↓ 1 callersMethodfit

Fit the AR(p) model to the data using the Yule-Walker equations.

src/timeseries/autoregressive.rs:27

↓ 1 callersFunctionforward_substitution

Solve a matrix equation of the form Lx=b, where L is a lower triangular matrix. See the [Wikipedia page](https://en.wikipedia.org/wiki/Triangular_matr

src/linalg/decomposition/substitution.rs:7

↓ 1 callersMethodforward_substitution

Solve a matrix equation of the form Lx=b, where L is a lower triangular matrix. See the [Wikipedia page](https://en.wikipedia.org/wiki/Triangular_matr

src/linalg/array/matrix.rs:120

next →1–100 of 442, ranked by callers