graphy.qualityfuncs - Module defining quality functions

Module implements quality functions for graph decompositions.

class graphy.qualityfuncs.QualityFunction[source]

Bases: object

quality(membership)[source]

Returns a quality score corresponding to membership vector.

Parameters:
membershipnp.array

Membership vector

Returns:
float

Quality

find_optimal(initial_membership=None, num_runs=1, debug_level=0)[source]

Find optimal decomposition.

Parameters:
initial_membershipnp.array, optional

Initial membership assignment. If None specified, each component is assigned to separate subsystem.

num_runsint, optional

Number of runs to try, can improve quality of decompositions. Default is 1.

debug_levelint, optional

Amount of debugging information to display, from 0 (no debugging information) to 3 (maximal debugging information)

Returns:
np.array

Optimal membership array

float

Q value corresponding to optimal membership

class graphy.qualityfuncs.Modularity(mx)[source]

Bases: QualityFunction

quality(membership)[source]

Returns a quality score corresponding to membership vector.

Parameters:
membershipnp.array

Membership vector

Returns:
float

Quality

find_optimal(initial_membership=None, num_runs=1, debug_level=0)

Find optimal decomposition.

Parameters:
initial_membershipnp.array, optional

Initial membership assignment. If None specified, each component is assigned to separate subsystem.

num_runsint, optional

Number of runs to try, can improve quality of decompositions. Default is 1.

debug_levelint, optional

Amount of debugging information to display, from 0 (no debugging information) to 3 (maximal debugging information)

Returns:
np.array

Optimal membership array

float

Q value corresponding to optimal membership

class graphy.qualityfuncs.DirectedModularity(mx)[source]

Bases: Modularity

quality(membership)[source]

Returns a quality score corresponding to membership vector.

Parameters:
membershipnp.array

Membership vector

Returns:
float

Quality

find_optimal(initial_membership=None, num_runs=1, debug_level=0)

Find optimal decomposition.

Parameters:
initial_membershipnp.array, optional

Initial membership assignment. If None specified, each component is assigned to separate subsystem.

num_runsint, optional

Number of runs to try, can improve quality of decompositions. Default is 1.

debug_levelint, optional

Amount of debugging information to display, from 0 (no debugging information) to 3 (maximal debugging information)

Returns:
np.array

Optimal membership array

float

Q value corresponding to optimal membership

class graphy.qualityfuncs.InfoMapCodeLength(mx, teleportation_prob=0.0)[source]

Bases: QualityFunction

static normed_entropy(probs)[source]
find_optimal(initial_membership=None, num_runs=1, debug_level=0)

Find optimal decomposition.

Parameters:
initial_membershipnp.array, optional

Initial membership assignment. If None specified, each component is assigned to separate subsystem.

num_runsint, optional

Number of runs to try, can improve quality of decompositions. Default is 1.

debug_levelint, optional

Amount of debugging information to display, from 0 (no debugging information) to 3 (maximal debugging information)

Returns:
np.array

Optimal membership array

float

Q value corresponding to optimal membership

quality(membership, extrainfo=False)[source]

Returns a quality score corresponding to membership vector.

Parameters:
membershipnp.array

Membership vector

Returns:
float

Quality