SEQoutput

class pySEQTarget.SEQoutput

Collector class for results from SEQuential

Parameters:

  • options (SEQopts) – Options used in the SEQuential process

  • method (str) – Method of analysis [‘ITT’, ‘dose-response’, or ‘censoring’]

  • numerator_models (List[ResultsWrapper]) – Numerator models, if applicable, from the weighting process

  • denominator_models (List[ResultsWrapper]) – Denominator models, if applicable, from the weighting process

  • compevent_models (List[List[ResultsWrapper]]) – Competing event models, if applicable

  • weight_statistics (DataFrame) – Weight statistics once returned back to the expanded dataset

  • hazard (DataFrame) – Hazard ratio if applicable

  • km_data (DataFrame) – Dataframe of risk, survival, and incidence data if applicable at all followups

  • km_graph (Figure) – Figure of survival, risk, or incidence over followup times

  • risk_ratio (DataFrame) – Dataframe of risk ratios, compared between treatments and subgroups

  • risk_difference (DataFrame) – Dataframe of risk differences, compared between treatments and subgroups

  • time (dict) – Timings for every step of the process completed thus far

  • diagnostic_tables (dict) – Diagnostic tables (outcome, follow-up, switch, and competing-event counts where applicable), each split by baseline treatment arm. The “unique” tables count distinct subjects; the “nonunique” tables count rows: total outcome events for the outcome tables, and total person-time intervals (expanded follow-up rows) for the follow-up tables. For a one-time (terminal) outcome the unique and nonunique outcome counts coincide, since each subject contributes at most one event row.

__init__(options=None, method=None, numerator_models=None, denominator_models=None, outcome_models=None, compevent_models=None, weight_statistics=None, hazard=None, km_data=None, km_graph=None, risk_ratio=None, risk_difference=None, time=None, diagnostic_tables=None)
plot()

Displays the Kaplan-Meier graph

Return type:

None

retrieve_data(type=None)

Getter for data stored within SEQoutput

The diagnostic tables come in “unique” and “nonunique” variants that count different things, each broken down by baseline treatment arm:

  • unique_outcomes / nonunique_outcomes: distinct subjects who had the outcome vs. the total number of outcome events. These coincide for a one-time (terminal) outcome, since each subject contributes at most one event row.

  • unique_followup / nonunique_followup: distinct subjects contributing follow-up vs. the total number of person-time intervals (expanded rows). The nonunique count is much larger because each subject contributes one row per follow-up period; it is the denominator that, with nonunique_outcomes, gives the per-arm event rate.

Parameters:

type (Optional[Literal['km_data', 'hazard', 'risk_ratio', 'risk_difference', 'unique_outcomes', 'nonunique_outcomes', 'unique_followup', 'nonunique_followup', 'unique_compevent', 'nonunique_compevent', 'unique_switches', 'nonunique_switches']]) – Data which you would like to access, [‘km_data’, ‘hazard’, ‘risk_ratio’, ‘risk_difference’, ‘unique_outcomes’, ‘nonunique_outcomes’, ‘unique_followup’, ‘nonunique_followup’, ‘unique_compevent’, ‘nonunique_compevent’, ‘unique_switches’, ‘nonunique_switches’]

Return type:

DataFrame

summary(type=None)

Returns a list of model summaries of either the numerator, denominator, outcome, or competing event models

Parameters:

type (Optional[Literal['numerator', 'denominator', 'outcome', 'compevent']]) – Indicator for which model list you would like returned

Return type:

List

to_md(filename='SEQuential_results.md')

Generates a markdown report of the SEQuential analysis results.

Return type:

None

to_pdf(filename='SEQuential_results.pdf')

Generates a PDF report of the SEQuential analysis results.

Return type:

None