- Trialling
`{roxytest}`

- Updated favicons
- Updated several vignettes
- Closed #154 by building out data vignette
- Updated centrality vignette with more modern plotting

- Added some more informative documentation families

- Folded
`m`

argument into`p`

for`generate_random()`

,`p`

can now be passed an integer to indicate the number of ties the network should have

- Refactored
`to_edges()`

to be ~26 times faster on average - Corrected edge labelling in
`to_edges()`

- Using
`to_subgraph()`

now instead of`dplyr::filter()`

or`strain()`

- Layouts now use
`times`

argument instead of`maxiter`

- Renamed
`"measure"`

class`"node_measure"`

and added`"graph_measure"`

class with print method - Overhaul of centrality measures
- Centrality and centralization measures now return normalized scores by default,
`normalized`

is now the second argument `directed`

and`weights`

arguments have been removed and are now imputed, if this is undesired please use`to_*()`

first`node_degree()`

now calculates strength centrality if network is weighted`node_eigenvector()`

and`graph_eigenvector()`

both work with two-mode networks- Added
`edge_degree()`

and`edge_eigenvector()`

, which both just apply the corresponding nodal measure to the edge graph

- Centrality and centralization measures now return normalized scores by default,
`edge_mutual()`

renamed to`edge_reciprocal()`

- Closed #225 by adding
`graph_assortativity()`

- Closed #151 with blockmodel coloring for signed graphs

- Dropped weight from
`mpn_elite_mex`

- Dropped direction from
`ison_brandes`

- Streamlined some examples to reduce testing time
- Fixed a DOI URL for Ortmann and Brandes reference

- Streamlined some tests to reduce testing time

`is_multiplex.igraph()`

and`is_multiplex.tbl_graph()`

now checks for multiple edge attributes- Added
`strain()`

as wrapper for`{dplyr}`

’s`filter()`

, renamed to avoid conflicts with`{stats}`

`ison_algebra`

now unlabelled

- Recognised contributors Henrique Sposito and Jael Tan
- Updated dependencies
`{readxl}`

is now*suggested*, but required if importing from an Excel sheet`{patchwork}`

replaces`{gridExtra}`

to make for more concise multiplot visualisations`{dplyr}`

also serves to export`{magrittr}`

’s pipe`{RColorBrewer}`

has been dropped and the`Dark2`

discrete set of colors is now internal

- README has been updated and now compiles from a .Rmd file
- Changed website theme to ‘superhero’
- All prior deprecated functions have been removed
- Increased testing to ~80% (closed #126, #212)
- CITATION has been updated too

- Moved to @describeIn documentation (closed #215)
- Distinguished
`directed`

and`direction`

arguments in some functions; whereas`directed`

is always logical (TRUE/FALSE),`direction`

expects a character string, e.g. “in”, “out”, or “undirected” `generate_permutation()`

now has an additional logical argument,`with_attr`

, that indicates whether any attributes from the original data should be passed to the permuted object- All
`create_*()`

functions now accept existing objects as their first argument and will create networks with the same dimensions `read_pajek()`

now imports nodal attributes alongside the main edges`read_ucinet()`

now enjoys clearer documentation

- All
`as_*()`

functions now retain weights where present; if you want an unweighted result, use`is_unweighted()`

afterwards`as_edgelist.network()`

now better handles edge weights`as_matrix.igraph()`

now better handles edge signs

- Pivoted to S3 methods for most manipulation functions for better dispatching and performance
- Added matrix, data.frame, network, igraph, and tbl_graph methods for
`is_twomode()`

,`is_directed()`

,`is_weighted()`

,`is_labelled()`

,`is_signed()`

,`is_multiplex()`

,`is_complex()`

, and`is_graph()`

- Added data.frame methods for
`as_edgelist()`

, and`to_unweighted()`

, and improved the data.frame method for`as_matrix()`

- Added data.frame and matrix methods for
`to_named()`

and`to_unsigned()`

- Added matrix, data.frame, network, igraph, and tbl_graph methods for
- Added
`to_edges()`

for creating adjacency matrices using a network’s edges as nodes - Renamed
`project_rows()`

and`project_cols()`

functions to`to_mode1()`

and`to_mode2()`

, which is both more consistent with other functions naming conventions and more generic by avoiding the matrix-based row/column distinction - Added
`node_mode()`

, which returns a vector of the mode assignments of the nodes in a network - Added
`edge_signs()`

, which returns a vector of the sign assignments of the edges in a network

- Added ‘visualization’ vignette that starts to introduce how
`autographr()`

works and how`{ggraph}`

extends this `autographr()`

now incorporates`ggidentify()`

functionality (closed #150)`{patchwork}`

is now used to assemble multiple plots together- Fixed #204 layout issues with
`ggatyear()`

- Added new
`measure`

class and directed most`node_*()`

functions to create objects of this class- A print method for this class prints an abbreviated vector (the full vector is always still contained within the object) and prints elements from both modes in the event that the original object was two-mode (closed #202)
- A plot method replaces
`ggdistrib()`

and offers “hist” and “dens” methods for histograms and density plots respectively

- Added some edge-based centrality measures (closed #165)
`edge_betweenness()`

wraps`{igraph}`

’s function of the same name`edge_closeness()`

measures the closeness centrality of nodes in an edge adjacency

- Added several more measures of connectedness
`node_cuts()`

identifies articulation points (nodes) in a network`edge_bridges()`

identifies edges that serve as bridges in a network`graph_cohesion()`

measures how many nodes would need to be removed to increase the number of components (closed #192)`graph_adhesion()`

measures how many edges would need to be removed to increase the number of components`graph_length()`

measures the average path length`graph_diameter()`

measures the longest path length

- Removed
`node_smallworld()`

and added`graph_smallworld()`

, which works with both one- and two-mode networks (fixed #214)

- Added some guidance to the naming convention used in
`node_quad_census()`

- Extended
`network_reg()`

’s formula-based system`network_reg()`

can now handle binary and multiple categorical variables (factors and characters, closed #211);`network_reg()`

can now manage interactions specified in the common syntax;`var1 * var2`

expands to`var1 + var2 + var1:var2`

(closed #163)`dist()`

and`sim()`

effects have been added (closed #207)

`network_reg()`

now employs logistic regression to estimate a binary outcome and linear regression to estimate a continuous outcome (closed #184)`network_reg()`

now uses Dekker et al’s semi-partialling procedure by default for multivariate specifications (closed #206), defaulting to*y*-permutations in the case of a single predictor (closed #208)- Added parallelisation to Monte Carlo based tests
- Refactored
`network_reg()`

, relying on`{furrr}`

for potential parallelisation and`{progressr}`

for progress reports (closed #185, #186) - Refactored
`test_random()`

and`test_permutation()`

, relying on`{furrr}`

for potential parallelisation and`{progressr}`

for progress reports; note that`nSim`

argument now`times`

(closed #199)

- Refactored
- Added
`{broom}`

S3 methods for`netlm`

and`netlogit`

class objects (closed #183)`tidy()`

extracts coefficients and related values`glance()`

extracts model-level values such as`R^2`

- Added plot method for
`netlm`

and`netlogit`

class objects (closed #216), which plots the empirical distribution for each test statistic, indicates percentiles relating to common critical values, and superimposes the observed coefficients - Added plot method for
`cug_test`

and`qap_test`

class objects, which plots the empirical distribution, highlighting tails beyond some critical value (closed #213), and superimposing the observed coefficient and, possibly, 0 - Relabelled some classes to avoid loading conflicts with
`{sna}`

`print.block_model()`

replaces`print.blockmodel()`

`plot.block_model()`

replaces`plot.blockmodel()`

- Reduced the number of simulations used in tests, examples, and vignettes to avoid CRAN warnings

- Updated several names of datasets for consistency and conciseness
`ison_southern_women`

instead of`southern_women`

`ison_brandes`

instead of`brandes`

`ison_networkers`

instead of`ison_eies`

`ison_algebra`

instead of`ison_m182`

`ison_adolescents`

instead of`ison_coleman`

- Extended several datasets
`mpn_elite_mex`

is extended with data from Pajek and with help from Frank Heber`ison_networkers`

becomes named with information from`{tnet}`

- Elaborated documentation of most
`mpn_*`

and`ison_*`

datasets, including references/sources

- Closed #149 by adding extra column to node_tie_census in
`cluster_structural_equivalence()`

for isolates- Note that this renders all isolates structurally equivalent

- Closed #168 by adding
`{patchwork}`

to suggested packages in DESCRIPTION - Updated function reference page on website

- Updated
`add_`

functions- Closed #178 by adding name to existing edges when further edges added in
`mutate_edges()`

- Closed #179 by inferring an attribute vector is for one of the two modes where possible in
`add_node_attributes()`

- Closed #178 by adding name to existing edges when further edges added in
- Added
`is_`

methods:`is_multiplex()`

,`is_uniplex()`

,`is_acyclic()`

- Added
`edge_`

functions to identify edges by properties:`edge_mutual()`

,`edge_multiple()`

,`edge_loop()`

- Fixed #172 by removing redundant header argument in
`read_nodelist()`

and`read_edgelist()`

- Fixed #173 by extending
`as_network()`

method to convert correctly form an`{igraph}`

to a`{network}`

object. - Removed
`ggraphgrid()`

documentation

- Replaced xlsx dependency in
`read_edgelist()`

and`read_nodelist()`

to readxl to avoid Java dependency - Replaced xlsx dependency in
`write_edgelist()`

and`write_nodelist()`

to avoid Java dependency- Note that these functions will now export to .csv rather than .xlsx

- Fixed direction recognition bug in
`as_network()`

,`as_igraph()`

, and`is_directed()`

- Closed #139 by adding vignette on importing and connecting data

- Added
`read_`

and`write_`

functions and updated documentation- Closed #137 by adding
`read_edgelist()`

for importing edgelists from Excel and csv files - Closed #170 by adding
`read_pajek()`

for importing .net and .paj files - Added
`write_edgelist()`

,`write_nodelist`

,`write_pajek()`

, and`write_ucinet()`

for exporting into various file formats (Excel, csv, Pajek, and UCINET) - Closed #140 by adding links to further data resources

- Closed #137 by adding

- Added
`is_graph()`

to check if an object is a graph or not - Extended
`as_network()`

to retain attributes - Fixed bugs in
`as_`

and`to_`

functions- Fixed bug in
`as_`

functions to convert from dataframes instead of tibbles - Fixed bug in conversion from network to igraph object in
`as_igraph()`

function - Fixed bug in
`to_undirected()`

function to work with network objects - Fixed bug in
`to_main_component()`

function so that it retains vertex attributes in network objects

- Fixed bug in
- Added
`edge_attribute()`

to grab a named edge attribute from a graph/network - Updated
`to_unweighted()`

to prevent conversion of network object into igraph object when deleting weights

- Closed #143 by adding nodal summary by cluster function
`summarise_statistics()`

- Fixed
`network_reg()`

example

- Closed #117 by updating the node/edge/arrow size limits in
`autographr()`

- Added start to network linear model part of practical 7 vignette
- Thanks to @BBieri for adding many tests and working on igraph<->network interchange

- Added
`ison_eies`

dataset for use in practical 7 vignette

- The
`as_matrix()`

method for networks now works with two-mode and weighted networks - The
`as_igraph()`

method for matrices now checks for weights independently of coercion - The
`as_igraph()`

method for networks now works with two-mode and weighted networks - The
`as_network()`

method for matrices now works with two-mode and weighted networks - The
`as_network()`

method for edgelists, igraph, and tidygraphs now works with weighted networks - Added
`to_unnamed()`

method for edge lists - Added
`to_simplex()`

method for matrices - Added
`to_main_component()`

method for networks - Added
`to_multilevel()`

method for matrices `mutate_edges()`

now coalesces rows of edges

- Fixed bug where clusters were not being reported in the correct order in
`graph_blau_index()`

- Fixed one-mode bug with
`generate_permutation()`

and thus`test_permutation()`

- Renamed
`netlm()`

to`network_reg()`

to avoid frustrating conflicts`network_reg()`

now accepts migraph-consistent objects`network_reg()`

now accepts formula terms such as`ego()`

,`alter()`

, and`same()`

- Added new issue templates and refined the wording in existing templates
- Improved documentation across many help pages
- Closed #146 by adding vignette on homophily

- Added
`generate_permutation()`

which takes an object and returns an object with the edges permuted, but retaining all nodal attributes - Made
`generate_random()`

also work with an existing object as input, in which it will return a random graph with the same dimensions and density - Consolidated data scripts

- Added
`mutate_edges()`

for adding new edges as attributes to existing edges in an object

- Closed #159 by fixing bug in
`graph_blau_index()`

- Closed #157 by fixing bug in
`graph_ei_index()`

- Closed #156 and #158 by fixing bugs with
`test_random()`

(defunct`test_cug()`

)

- Closed #148 and #153 by making all
`autographr()`

arguments take variable names in quotation marks

- Closed #75 by updating the README

- Added some functions for grabbing key information from objects
`node_names()`

for quickly accessing node labels`node_attribute()`

for quickly accessing a certain nodal attribute`edge_weights()`

for quickly accessing edge weights`graph_nodes()`

for quickly accessing a count of nodes in the graph, note that for two-mode networks this will be a vector of length 2`graph_edges()`

for quickly accessing a count of edges in the graph`graph_dimensions()`

is currently a copy of`graph_nodes()`

- Added some functions for adding key information to objects
`add_node_attributes()`

for adding particular nodal attributes`add_edge_attributes()`

for adding edges from another graph`copy_edge_attributes()`

for copying all nodal attributes from another graph

- Improved twomode and weighted handling of several functions

- Added diversity functions
`graph_blau_index()`

for summarising diversity of an attribute in a network or group`graph_ei_index()`

for summarising diversity of an attribute over a network’s ties

- Closed #119 by adding
`node_quad_census()`

, especially useful for two-mode blockmodelling - Closed #95 and #120 by adding
`graph_mixed_census()`

- Closed #97 by adding test functions
`test_random()`

carries out a conditional uniform graph (CUG) test`test_permutation()`

carries out a quadratic assignment procedure (QAP) test

- Closed #135 by reexporting
`aes()`

from`{ggplot2}`

- Added
`node_shape`

option to`autographr()`

- Updated various URLs in the vignettes to pass CRAN tests
- Reduce number of layout examples to avoid examples taking too long to run

- Closed #128 by adding
`as_edgelist()`

methods for converting other objects into edgelists- Note that this currently returns a tibble

- Using
`to_unnamed()`

on ‘network’ objects now operates on them directly - Elaborated
`to_`

documentation significantly - Fixed bug in
`to_onemode()`

that was tripping`blockmodel()`

on networks that are already one-mode - Added
`is_connected()`

to test whether network is connected,`method =`

argument can be specified as`weak`

or`strong`

- Added
`create_tree()`

and`create_lattice()`

, and made`create_star()`

a bit faster for one-mode networks - Added
`generate_smallworld()`

and`generate_scalefree()`

, though only for one-mode networks currently

- Added rounding to centralization measures, by default
`=2`

- Closed #109 by adding centrality vignette

- Added
`graph_dyad_census()`

for more graph profile options - Fixed bug with
`blockmodel_concor()`

when an object was of class ‘igraph’ but not ‘tbl_graph’ - Fixed bug in how
`blockmodel()`

was treating two-mode networks - Closed #116 by offering both
`"elbow"`

and`"strict"`

methods for*k*-identification- Fixed bug in elbow method that biased heavily bipartitioned data

- Closed #131 by refactoring
`ggidentify_clusters()`

for speed- Takes now roughly half the time (see issue for details)

- Added
`ggdistrib()`

for easy plotting of degree and other node score distributions - Reexported
`ggsave()`

,`xlab()`

and`ylab()`

from`{ggplot2}`

for easier plot annotation

- Closed #108 by adding cohesion and community vignette

- Fixed #122 by retaining edge weights from igraph in
`as_matrix()`

where available

- Split
`graph_equivalency()`

into the same for two-mode networks and`graph_congruency()`

for three-mode (two two-mode) networks - Added option for
`graph_reciprocity()`

method - Added
`graph_components()`

and`node_components()`

- Fixed #113 by retaining node labels through census functions
- Closed #114 by transposing
`node_tie_census()`

output so that it’s consistent with`node_triad_census()`

and future node_census functions - Closed #121 by renaming
`cluster_triad_census()`

to`group_triad_census()`

- Added
`group_tie_census()`

- Added option to
`autographr()`

for plotting convex/concave hulls - Closed #124 by making
`ggraphgrid()`

a set of layout functions:`layout_tbl_graph_frgrid()`

or`autographr(object, "frgrid")`

for snapping Fruchterman-Reingold to a grid`layout_tbl_graph_kkgrid()`

or`autographr(object, "kkgrid")`

for snapping Kamada-Kawai to a grid`layout_tbl_graph_gogrid()`

or`autographr(object, "gogrid")`

for snapping graph optimisation to a grid`ggraphgrid()`

has been deprecated

- Fixed some
`ison_m182`

documentation

- Fixed CRAN package check dependencies bug where ‘knitr’ and ‘rmarkdown’ were listed as Imports without being used in the package

- Fixed bug where bipartite edge lists were not being recognised as a twomode network by
`as_igraph()`

- Fixed bug where
`to_uniplex()`

was not returning a weighted graph

- Fixed bug where
`blockmodel()`

was not retaining node names in all parts of the object structure

- Closed #107 by choosing better brewer pallette (though note this is not a very deep pallette with only 9 colors)

- Expanded on the blockmodelling vignette with more intro, discussion, interpretation clues

- Fixed codecov url bug
- Removed several package dependencies by moving
`plot_releases()`

to another package - Made many dependencies more explicit
- Entire package ‘linted’

- Added
`is_signed()`

to logically test whether the network is a signed network - Added
`to_unsigned()`

for extracting networks of either “positive” or “negative” ties from a signed network - Added
`tbl_graph`

methods for all other`to_`

functions - Reexported
`activate()`

from`{tidygraph}`

- Added sensible plotting defaults for signed networks in
`autographr()`

- Removed
`plot_releases()`

from this package

- Refactored
`graph_balance()`

to be much faster, following David Schoch’s`{signnet}`

package (see that package for further extensions)

- Updated the edge ‘sign’ attribute of
`ison_marvel_relationships`

to be a double (`-1`

/`1`

) to be compatible with the new`graph_balance()`

and`{signnet}`

- Fixed coercion to
`{igraph}`

from data frames and updated read script - Added
`to_main_component()`

to extract the main component of a network - Added
`to_onemode()`

for moving to multimodal igraph objects - Added
`to_uniplex()`

method to delete edge types and their edges from multiplex networks - Added
`to_simplex()`

method to delete loops from a network - Added
`to_named()`

method for randomly naming unlabeled networks

- Added
`ison_mm`

,`ison_mb`

,`ison_bm`

, and`ison_bb`

projection illustration data - Added
`ison_karateka`

community detection illustration data - Added
`ison_marvel_teams`

and`ison_marvel_relationships`

datasets - Added
`ison_m182`

dataset of friends, social and task ties between 16 anonymous students - Renamed
`adolescent_society`

dataset to`ison_coleman`

for consistency - Data now listed at the bottom of the website References page

- Added
`graph_eigenvector()`

for one mode networks - Added
`graph_balance()`

for measuring structural balance - Added
`node_tie_census()`

,`node_triad_census()`

,`cluster_triad_census()`

, and`graph_triad_census()`

- Separated out
`graph_clustering()`

into the cohesion measures`graph_density()`

,`graph_reciprocity()`

,`graph_transitivity()`

, and`graph_equivalence()`

- Fixed
`node_smallworld()`

to use separated cohesion measures

- Added
`blockmodel()`

which masks its`{sna}`

namesake but has the advantages of working with two-mode networks and retaining node names where available- Added
`cluster_structural_equivalence()`

and`cluster_regular_equivalence()`

as bases for blockmodelling - Added
`reduce_graph()`

for creating a network from a blockmodel

- Added
- Added first vignette on structural holes, structural equivalence and regular equivalence blockmodelling

- Added
`autographr()`

for plotting graphs with sensible defaults- Uses a more contrastive discrete palette when some nodal attribute is given
- Uses an alpha for edges, and edges will now be sized by edge weight, where available
- Uses node labels, sans borders, where available
- Uses different shaped nodes, and different fonts, for different node sets
- Removed
`ggraphlabel()`

since core functionality now provided by autographr

- Added ability for
`ggidentify()`

to identify the node with the highest value of a specified node-level measure - Added a couple of more specific visualization functions
- Added
`ggatyear()`

for subsetting and plotting edgelists at year - Updated
`gglineage()`

to return a graph colored according to lineage- Added tick marks

- Added
- Added several more specific functions for diagnosing and visualising blockmodels
- Added
`ggtree()`

for neatly visualising hierarchical clusters - Added
`ggidentify_clusters()`

for identifying which number of clusters is most appropriate following the elbow method

- Added
- Fixed bug related to
`ggraph::theme_graph()`

present in a few different visualisation functions

- Added
`brandes`

dataset for teaching centrality measures - Added
`adolescent_society`

dataset for teaching friendship paradox - Added
`read_edgelist()`

for importing Excel-created edgelists directly

- Added
`ggraphlabel()`

for one-function (1F) plotting label-based network graphs - Added
`ggevolution()`

for 1F-plotting begin/end graph comparisons - Added
`ggraphgrid()`

for 1F snap-to-grid graph layouts based on Fruchterman-Reingold or Kamada-Kawai - Added
`ggidentify()`

for 1F identifying nodes with maximum scores based on some arbitrary function

- Added
`to_undirected()`

for symmetrising networks of all types - Made existing
`to_`

functions S3 methods

- Fixed Unicode char bug in coercion documentation

Closed #100 by converting

`as_`

coercion functions to S3 methods- Added a little more readable documentation
- Fixed bug with
`as_matrix()`

weighting - Fixed bug with
`as_tidygraph()`

- Closed #92 by adding
`gglineage()`

for graphing a citation network through time - Closed #99 by adding
`ggevolution()`

for graphing two timepoints of the same network side by side - Closed #102 by adding
`ggraphgrid()`

for locking a graph to a grid - Slight improvements to
`plot.igraph()`

defaults

- Added tidygraph lookups to
`node_`

functions

Fixed bug in

`as_matrix()`

with frame matrix by dropping (rarely necessary) functionality- Improved handling of weights column in three-column edgelists
- Improved documentation of
`as_`

functions

Fixed bugs in

`plot_releases()`

with more graceful handling of http errors- Added online condition to example in documentation
- Specified encoding for more silent operation

- Removed unused package dependencies (
`{R6}`

,`{ggraph}`

) - Avoided M1mac check issue by dropping sensitive
`netlm()`

test - Added some tests

- Renamed
`binarise()`

to`to_unweighted()`

- Added
`to_unnamed()`

for unlabelling networks

- Extended R version dependence back to 3.6.*

- Added
`binarise()`

for unweighting networks - Fixed bug in
`as_tidygraph()`

when passed a tbl_graph directly

- Added
`plot_releases()`

for more general use - Fixed bug in
`plot.igraph()`

with layouts and one-mode graphs

Updated README

- Updated installation instructions for CRAN
- Added package functions overview

Added

`CITATION`

details

Separated coercion (previously conversion) and manipulation

Added some more inter-class coercion tests

Fixed bug in how

`as_network()`

sometimes coerced two-mode networks into much larger dimension matricesAdded more

`is_`

tests for class-independent property tests- Added
`is_weighted()`

- Added
`is_directed()`

- Added
`is_labelled()`

- Added

Added @csteglich ’s

`read_ucinet()`

and`write_ucinet()`

functions`read_ucinet()`

offers a file-picker when file path unknown`read_ucinet()`

now imports to an igraph-class object by default, with an argument to allow other alternatives`write_ucinet()`

works with all migraph-compatible objects

Updated

`mpn_bristol`

documentationAdded

`create_star()`

function- Added in-star/out-star option via
`directed =`

argument - Updated
`create_`

documentation

- Added in-star/out-star option via
Renamed

`sample_affiliation()`

to`generate_random()`

- Rewrote
`generate_random()`

to be able to generate random one- or two-mode networks - Updated documentation

- Rewrote

- Added test for
`print.blockmodel()`

2021-04-13

- Reran
`usethis::use_mit_license("James Hollway")`

. MIT License file now contains only the standard two lines. - Removed
`\dontrun`

from examples.`netlm()`

now runs in <5 seconds. - Fixed missing website item

2021-04-11

- Closed #21 by elaborating DESCRIPTION file in preparation for CRAN submission
- Updated several old URLs in documentation

- Closed #85 by adding
`as_network()`

to coerce objects into network class - Modified other coercion functions to also work with network class objects

2021-03-03

- Moved package’s Github repository from
`jhollway/`

to`snlab-ch/`

organisation - Trimmed some package dependencies and added others

Elaborated documentation for the remainder of the datasets

- Now all datasets in this package are titled with whether they are one-mode, two-mode, or three-mode

- Fixed bug in
`graph_degree()`

where data was hard-coded in

Closed #18 by adding

`blockmodel_concor()`

for employing the CONCOR algorithm to blockmodel both one-mode and two-mode networks- Added a new print method for “blockmodel”-class objects based on the
`print.blockmodel()`

method in the`{sna}`

package that also prints blockmodel results for two-mode networks consistently - Added a new plot method for “blockmodel”-class objects that leverages
`{ggplot2}`

for pretty plotting and that better inherits names from the underlying object

- Added a new print method for “blockmodel”-class objects based on the

2021-02-06

- Closed #81 by making
`{migraph}`

depend on R versions 4.0 or above - Updated PR template

- Added functions for class conversion between migraph-consistent graph formats
`as_matrix()`

function to coerce objects into an adjacency or incidence matrix class`as_igraph()`

function to coerce objects into an`{igraph}`

graph class`as_tidygraph()`

function to coerce objects into an`{tidygraph}`

tbl_graph class- Closed #79 by adding
`is_twomode()`

function to check whether network is two-mode on all object types

Renamed several datasets and elaborated their documentation

`mpn_mexicanpower`

was renamed to`mpn_elite_mex`

`mpn_powerelite`

was renamed to`mpn_elite_usa_advice`

`mpn_opensecrets`

was renamed to`mpn_elite_usa_money`

Reconstructed several creation functions to take universal (one-mode/two-mode) input: specifying

`n = 5`

creates a one-mode network, while specifying`n = c(5, 5)`

creates a two-mode network- Added
`create_empty()`

- Added
`create_complete()`

- Closed #65 by extending
`create_ring()`

to create rings of varying breadth - Closed #66 by extending
`create_components()`

(renamed from`create_silos()`

) to create networks with varying numbers of components - Added
`sample_affiliation()`

for random two-mode networks - Removed
`create_match()`

and`create_nest()`

- Added

Renamed

`centrality_`

functions with`node_`

prefix and ensured they all also wrapped one-mode measures`centrality_degree()`

renamed to`node_degree()`

`centrality_closeness()`

renamed to`node_closeness()`

`centrality_betweenness()`

renamed to`node_betweenness()`

- Closed #31 by adding
`node_eigenvector()`

Re-added

`node_constraint()`

for calculating Burt’s constraint measure for one- and two-mode networksRe-added

`node_smallworld()`

for calculating Watts-Strogatz measure of small-worldness for two-mode networksClosed #32 by re-adding centralization functions for one- and two-mode networks

`graph_degree()`

for degree centralization`graph_closeness()`

for closeness centralization`graph_betweenness()`

for betweenness centralization

Re-added

`graph_clustering()`

for calculating (see Knoke et al 2021):- transitivity on one-mode networks
- shared four-cycles on two-mode networks
- congruent four-cycles on three-mode networks

Re-added

`netlm()`

for performing linear regression for multimodal network data- Closed #76 by changing
`netlm()`

to accept a formula-based input - Closed #77 by adding
`print.summary.netlm()`

for`netlm()`

regressions

- Closed #76 by changing

- Closed #82 by re-adding a version
`plot.igraph()`

with sensible defaults for two-mode networks

2021-01-11

- pkgdown now deploys after release
- Reexported a number of
`{igraph}`

and`{tidygraph}`

functions for internal use - Completed some
`convert_`

and`project_`

documentation

- Updated mpn_ data source references

Added centrality measures that take (and if necessary return) matrix, igraph, or tidygraph objects, and offer a correct normalization for two-mode networks

- Added
`centrality_degree()`

- Added
`centrality_closeness()`

- Added
`centrality_betweenness()`

- Added

2021-01-08

Package name change from roctopus to

`{migraph}`

- Closed #50 with new logo

Now builds Linux binary too

- Added
`project_rows()`

and`project_cols()`

to make it easier to project two-mode networks in different formats (matrix, igraph, tidygraph) into projected versions in the same format - Closed #30 with conversion from different data frame formats, e.g. weighted and unweighted edgelists, into an incidence matrix with
`as_incidence_matrix()`

- Renamed data related to the book “Multimodal Political Networks” with “mpn_” prefix

2020-11-06

Data creation updated for

`{tidygraph}`

defaults- Renamed
`create_lattice()`

to`create_chain()`

to avoid conflicts with`tidygraph::create_lattice()`

- Renamed
`create_poles()`

to`create_silos()`

- Renamed
`create_random()`

to`play_twomode()`

to avoid conflicts with`tidygraph::play_bipartite()`

- Added export options for all
`create_`

and`play_`

functions as`tbl_graph`

(default),`igraph`

, and base matrix - Updated tests for new
`create_`

and`play_`

function names

- Renamed
Packaged data updated for

`{tidygraph}`

defaults- Renamed packaged data from book to
`mpn_`

- Renamed packaged data from book to

2020-08-18

- Renamed
`twomode_netlm()`

to`netlm2()`

- Fixed various printing issues with
`netlm2()`

- Added tests for
`netlm2()`

- Added tests for
`create_random()`

- Added
`opensecrets`

data - Added
`powerelite`

data

2020-07-21

- Renamed data documentation scripts
- Added tests for most
`create_()`

functions - Renamed test scripts and removed
`context()`

declaration `create_nest()`

now exports matrix object

2020-07-20

- Added
`row_project()`

and`col_project()`

functions to make it easier to remember project directions

2020-07-19

- Added
`mexicanpower`

dataset - Added
`senate112`

datasets - Updated
`evs`

datasets to matrices

- Added
`df_to_mat()`

function for converting regular adjacency and incidence data frames into matrices

2020-07-17

- Added
`ryanair`

dataset from Christopoulos 2006

- Split workflow into pull-request and merge/push prompted actions
- Added codecov calculation to workflows

2020-07-03

- Added
`evs`

datasets from Knoke et al 2020

2020-06-30

- Added
`bristol`

dataset from Knoke et al 2020

2018-12-20

- Added hex sticker
- Updated README with more detailed installation information
- Pkgdown exports to https://jhollway.bitbucket.io/roctopus/

- Added
`twomode_modularity()`

to calculate modularity in two-mode networks

- Added
`plot_multilevel()`

that rotates a force-directed`igraph`

plot in three dimensions to reveal multilevel structure - Added
`plot_globalnet()`

to map a multilevel network on to a javascript, rotatable global

2018-08-25

- Added
`twomode_smallworld()`

to calculate observed/expected clustering, observed/expected path-length, and the observed/expected clustering ratio - Added
`twomode_2x2()`

to identify dominance and coherence values for networks over time - Updated
`twomode_coherence()`

to allow for introduction of second-mode attributes - Renamed
`twomode_fragmentation()`

to`twomode_components()`

- Added
`plot_2x2()`

to plot values through a two-by-two matrix

2018-08-14

- Renamed package to
`roctopus`

- Added two-mode @family tag to documentation

- Added
`twomode_fragmentation()`

to calculate number of components in two-mode networks and identify their membership - Added
`twomode_dominance()`

to allow an nodal attribute to be passed to the function to weight the centralization measure - Added
`twomode_coherence()`

to calculate Jaccard similarity

Added

`plot_twomode()`

, which wraps`plot(igraph::graph_from_incidence_matrix())`

with some useful defaults- coloured grayscale by default, with green/blue option
- shaped circles and squares by default

2018-07-30

- Initialised package
- Added
`README.md`

file with instructions on how to install package - Added
`LICENSE`

file and pointed to bug/issue tracker - Added a
`NEWS.md`

file to track changes to the package

- Added
`twomode_clustering()`

to calculate percentage of three-paths closed by four-paths - Added
`twomode_lattice()`

to create two-mode lattices - Added
`twomode_centralization_degree()`

to calculate degree centralization in two-mode networks, for rows, columns, or both - Added
`twomode_centralization_between()`

to calculate betweenness centralization in two-mode networks - Added
`twomode_constraint()`

to calculate network constraint in two-mode networks - Added
`arrange.vars()`

to rearrange variables by position