Modules

Learn

Classify

Design

Predict

class caspo.predict.Predictor(networks, setup)

Predictor of all possible experimental conditions over a given experimental setup using a given list of logical networks.

Parameters:

• networks (caspo.core.logicalnetwork.LogicalNetworkList) – The list of logical networks used to generate the ensemble of predictions
• setup (caspo.core.setup.Setup) – The experimental setup to generate possible experimental conditions

networks

Type:caspo.core.logicalnetwork.LogicalNetworkList

setup

Type:caspo.core.setup.Setup

predict()

Computes all possible weighted average predictions and their variances

Example:

>>> from caspo import core, predict

>>> networks = core.LogicalNetworkList.from_csv('behaviors.csv')
>>> setup = core.Setup.from_json('setup.json')

>>> predictor = predict.Predictor(networks, setup)
>>> df = predictor.predict()

>>> df.to_csv('predictions.csv'), index=False)

Returns:DataFrame with the weighted average predictions and variance of all readouts for each possible clamping Return type:pandas.DataFrame

Control

Visualize

caspo.visualize.behaviors_distribution(df, filepath=None)

Plots the distribution of logical networks across input-output behaviors. Optionally, input-output behaviors can be grouped by MSE.

Parameters:

• df (pandas.DataFrame) – DataFrame with columns networks and optionally mse
• filepath (str) – Absolute path to a folder where to write the plot

Returns:

Generated plot

Return type:

plot

caspo.visualize.coloured_network(network, setup, filename)

Plots a coloured (hyper-)graph to a dot file

Parameters:

• network (object) – An object implementing a method __plot__ which must return the networkx.MultiDiGraph instance to be coloured. Typically, it will be an instance of either caspo.core.graph.Graph, caspo.core.logicalnetwork.LogicalNetwork or caspo.core.logicalnetwork.LogicalNetworkList
• setup (caspo.core.setup.Setup) – Experimental setup to be coloured in the network

caspo.visualize.differences_distribution(df, filepath=None)

For each experimental design it plot all the corresponding generated differences in different plots

Parameters:

• df (pandas.DataFrame) – DataFrame with columns id, pairs, and starting with DIF:
• filepath (str) – Absolute path to a folder where to write the plots

Returns:

Generated plots

Return type:

list

caspo.visualize.experimental_designs(df, filepath=None)

For each experimental design it plot all the corresponding experimental conditions in a different plot

Parameters:

• df (pandas.DataFrame) – DataFrame with columns id and starting with TR:
• filepath (str) – Absolute path to a folder where to write the plot

Returns:

Generated plots

Return type:

list

caspo.visualize.intervention_strategies(df, filepath=None)

Plots all intervention strategies

Parameters:

• df (pandas.DataFrame) – DataFrame with columns starting with TR:
• filepath (str) – Absolute path to a folder where to write the plot

Returns:

Generated plot

Return type:

plot

caspo.visualize.interventions_frequency(df, filepath=None)

Plots the frequency of occurrence for each intervention

Parameters:

• df (pandas.DataFrame) – DataFrame with columns frequency and intervention
• filepath (str) – Absolute path to a folder where to write the plot

Returns:

Generated plot

Return type:

plot

caspo.visualize.mappings_frequency(df, filepath=None)

Plots the frequency of logical conjunction mappings

Parameters:

• df (pandas.DataFrame) – DataFrame with columns frequency and mapping
• filepath (str) – Absolute path to a folder where to write the plot

Returns:

Generated plot

Return type:

plot

caspo.visualize.networks_distribution(df, filepath=None)

Generates two alternative plots describing the distribution of variables mse and size. It is intended to be used over a list of logical networks.

Parameters:

• df (pandas.DataFrame) – DataFrame with columns mse and size
• filepath (str) – Absolute path to a folder where to write the plots

Returns:

Generated plots

Return type:

tuple

caspo.visualize.predictions_variance(df, filepath=None)

Plots the mean variance prediction for each readout

Parameters:

• df (pandas.DataFrame) – DataFrame with columns starting with VAR:
• filepath (str) – Absolute path to a folder where to write the plots

Returns:

Generated plot

Return type:

plot