Package: netOP 0.1.2

netOP: Network Data Operations and Overlapping Partitions Based Methods for Large Networks

Implements methods for generating, embedding, and clustering random networks and for estimating and selecting statistical network models. Provides SONNET (Subsampling ON NETwork), a scalable subsampling-based divide-and-conquer method for community detection described by Chakrabarty, Sengupta and Chen (2025) <doi:10.5705/ss.202022.0108>, and NETCROP (NETwork CRoss-validation using Overlapping Partitions), an overlapping-partition framework for network cross-validation, model selection, and regularization tuning described by Chakrabarty, Sengupta and Chen (2026) <doi:10.48550/arXiv.2504.06903>. Also includes spectral and latent-space methods, loss functions, and helper functions for statistical analysis of network data.

Authors:Sayan Chakrabarty [aut, cre]

netOP_0.1.2.tar.gz
netOP_0.1.2.zip(r-4.7-x86_64)netOP_0.1.2.zip(r-4.7-arm64)netOP_0.1.2.zip(r-4.6-x86_64)netOP_0.1.2.zip(r-4.6-arm64)netOP_0.1.2.zip(r-4.5-x86_64)
netOP_0.1.2.tgz(r-4.6-x86_64)netOP_0.1.2.tgz(r-4.6-arm64)netOP_0.1.2.tgz(r-4.5-x86_64)netOP_0.1.2.tgz(r-4.5-arm64)
netOP_0.1.2.tar.gz(r-4.7-arm64)netOP_0.1.2.tar.gz(r-4.7-x86_64)netOP_0.1.2.tar.gz(r-4.6-arm64)netOP_0.1.2.tar.gz(r-4.6-x86_64)
netOP_0.1.2.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
netOP/json (API)

# Install 'netOP' in R:
install.packages('netOP', repos = c('https://sayan-ch.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/sayan-ch/netop/issues

Uses libs:
  • c++– GNU Standard C++ Library v3

On CRAN:

Conda:

cpp

4.48 score 93 exports 17 dependencies

Last updated from:fb5a91eac4. Checks:15 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-arm64OK183
linux-devel-x86_64OK219
source / vignettesOK265
linux-release-arm64OK168
linux-release-x86_64OK216
macos-release-arm64OK274
macos-release-x86_64OK498
macos-oldrel-arm64OK298
macos-oldrel-x86_64OK530
windows-devel-arm64OK423
windows-devel-x86_64OK232
windows-release-arm64OK421
windows-release-x86_64OK193
windows-oldrel-x86_64OK194
wasm-releaseOK142

Exports:adjacency_neighborsadjacency_weighted_neighborsapply_average_degree_scalingaseaucauc_as_lossbin_devbin_dev_meanclip_probabilitiesclip_valuescolMeanscolSumsconnected_componentsdiagdkest_tune_regularizerecv_stability_blockmodelecv_stability_rdpgeig_decompestimate_dcbmestimate_dcbm_P_hatestimate_sbmestimate_sbm_P_hatgenerate_adjacencygenerate_community_labelsgenerate_dcbmgenerate_degree_parametersgenerate_ergenerate_inverse_beta_degree_parametersgenerate_latent_positionsgenerate_lsmgenerate_lsm_alphagenerate_lsm_positionsgenerate_rdpggenerate_sbmgenerate_truncated_normalget_generator_parametersgraph_laplacianhardmaxhardminlabel_match_brute_forcelabel_match_greedylargest_connected_componentlsm_pgdmaematrix_densitymeanmeasure_peak_rammodalmsemult_reg_sonnetmult_reg_spectral_clusterncv_stability_blockmodelnetcrop_blockmodelnetcrop_lsmnetcrop_param_selectnetcrop_rdpgnetcrop_tune_regularizernminormalize_lsm_positionsoracle_plotterouter_addpair_hamming_losspair_nmi_lossprocrustesread_networkrowMeansrowSumsrun_simulationssaescale_lsm_to_average_degreescale_to_average_degreescale_to_average_degree_naiveshortest_path_distancessigmoidsingular_decompsoftmaxsoftminsoftplussonnetsonnet_independent_overlapsonnet_param_selectsonnet_shared_overlapspectral_clusterssesumtruncated_svd_reconstructuni_mclapplyusvtwhich_hardmaxwhich_hardminwhich_softmaxwhich_softminwrite_network

Dependencies:cliclusterglueirlbalatticelifecyclemagrittrMatrixpillarpkgconfigRcppRcppEigenrlangRSpectratibbleutf8vctrs

Choosing a Method
At a glance | A common block-model setup | Candidate sets and entry points | Reproducibility | Glossary | References and disclosures

Last update: 2026-09-04
Started: 2026-09-04

Getting Started with netOP
Generate and inspect a network | Embed and cluster | Select a model | Results and plotting

Last update: 2026-09-04
Started: 2026-09-04

Readme and manuals

Help Manual

Help pageTopics
Compute absolute-error lossesabsolute_error_losses mae sae
Find adjacent nodesadjacency_neighbors adjacency_weighted_neighbors
Apply the selected average-degree scaling methodapply_average_degree_scaling
Compute an adjacency spectral embeddingase
Compute AUC scores and lossesauc auc_as_loss auc_losses
Compute binary deviance lossesbinary_deviance_losses bin_dev bin_dev_mean
Clip probability values safelyclip_probabilities
Clip numeric values to an intervalclip_values
Find connected componentsconnected_components largest_connected_component
Tune a degree-regularized spectral modeldkest_tune_regularizer
Edge cross-validation stability selectionecv_stability
Select block-model size with edge cross-validationecv_stability_blockmodel
Select RDPG dimension with edge cross-validationecv_stability_rdpg
Compute an eigendecompositioneig_decomp
Network embedding, clustering, estimation, and label alignmentembedding_estimating
Estimate stochastic block modelsestimate_dcbm estimate_sbm
Reconstruct block-model probability matricesestimate_dcbm_P_hat estimate_sbm_P_hat
Compute hard and soft extremaextrema_selectors hardmax hardmin softmax softmin which_hardmax which_hardmin which_softmax which_softmin
Sample a network from edge probabilitiesgenerate_adjacency
Generate or validate community labelsgenerate_community_labels
Generate block-model networksgenerate_dcbm generate_sbm
Generate or validate DCBM degree parametersgenerate_degree_parameters
Generate an Erdos-Renyi networkgenerate_er
Generate inverse-beta degree parametersgenerate_inverse_beta_degree_parameters
Generate or validate latent positionsgenerate_latent_positions
Generate a latent-space-model networkgenerate_lsm
Generate latent-space-model interceptsgenerate_lsm_alpha
Generate latent-space-model positionsgenerate_lsm_positions
Generate a random dot product graphgenerate_rdpg
Generate truncated standard-normal valuesgenerate_truncated_normal
Retrieve parameters attached by a network generatorget_generator_parameters
Construct a graph Laplaciangraph_laplacian
Check whether a network matrix is symmetricis_symmetric_network_matrix
Match community labelslabel_match_brute_force label_match_greedy
Fit a latent-space model by projected gradient descentlsm_pgd
Compute matrix densitymatrix_density
Matrix summary genericscolMeans colSums diag matrix-generics mean rowMeans rowSums sum
Measure peak memory usemeasure_peak_ram
Compute the statistical modemodal
Fit SONNET over multiple regularizersmult_reg_sonnet
Fit spectral clusterings over multiple regularizersmult_reg_spectral_cluster
Node cross-validation stability selectionncv_stability
Select block-model size with node cross-validationncv_stability_blockmodel
Select a block model with NETCROPnetcrop_blockmodel plot.netcrop_blockmodel print.netcrop_blockmodel print.summary.netcrop_blockmodel summary.netcrop_blockmodel
Select latent-space dimension with NETCROPnetcrop_lsm plot.netcrop_lsm print.netcrop_lsm print.summary.netcrop_lsm summary.netcrop_lsm
Select NETCROP partition parametersnetcrop_param_select
Select RDPG dimension with NETCROPnetcrop_rdpg plot.netcrop_rdpg print.netcrop_rdpg print.summary.netcrop_rdpg summary.netcrop_rdpg
Tune a network regularizer with NETCROPnetcrop_tune_regularizer plot.netcrop_regularizer print.netcrop_regularizer print.summary.netcrop_regularizer summary.netcrop_regularizer
Network input, generation, and probability calibrationnetwork_generators
Compute normalized mutual informationnmi
Normalize latent-space positionsnormalize_lsm_positions
Compare clustering methods with known labelsoracle_plotter
Add vectors by outer expansionouter_add
Compare pairs of clusteringspair_hamming_loss pair_nmi_loss
Align point configurations by Procrustes transformationprocrustes
Run reproducible simulation jobsrun_simulations
Scale latent-space logits to a target average degreescale_lsm_to_average_degree
Scale probabilities to a target average degreescale_to_average_degree scale_to_average_degree_naive
Compute shortest-path distancesshortest_path_distances
Compute the sigmoid transformsigmoid
Compute a singular-value decompositionsingular_decomp
Compute the softplus transformsoftplus
Fit a SONNET network clusteringprint.sonnet print.summary.sonnet sonnet summary.sonnet
Select SONNET partition parameterssonnet_param_select
Fit SONNET overlap variantssonnet_independent_overlap sonnet_shared_overlap
Cluster a network spectrallyspectral_cluster
Compute squared-error lossesmse squared_error_losses sse
Reconstruct a truncated singular-value approximationtruncated_svd_reconstruct
Apply a function consistently across platformsuni_mclapply
Estimate a matrix with universal singular-value thresholdingusvt
Read and write network edge listsread_network write_network