factor_agent.exported.GraphFactor#
- class GraphFactor(config)[source]#
Bases:
DerivedColumnsFactorRecorded graphs, each ranked across the market, as one factor.
The graphs, name to
Graph.to_json(), are the class’sGRAPHS(an exported factor) or, when it has none,config.kwargs["graphs"]; the class path of each operator they record,CLASSESorconfig.kwargs["classes"](Vocabulary.class_paths); how each lag column they read is computed,PERIOD_LAGSorconfig.kwargs["period_lags"](period_lags), none when neither is set; each output’s direction,DIRECTIONSorconfig.kwargs["directions"](+1 when unset), turns it so a higher value means a higher return. A graph of an intraday family is its daily stage (staged): the intraday graph of each session column it reads is inSESSIONSorconfig.kwargs["sessions"], and the intraday dataset they run on, as aget_config()dict, inINTRADAYorconfig.kwargs["intraday"].config.data_columnsmust hold every dataset column the graphs and their lags read (data_columns).
Inherited methods and attributes are documented on the base classes linked above.
Methods#
The daily dataset columns the recorded graphs read, with the columns and keys of their |
|
The entries of |
|
Recorded graphs in their stages: each one's daily graph, by name, and every session column's intraday graph. |
Attributes#
- GraphFactor.CLASSES = {}#
Operator name -> class path, of every operator
GRAPHSrecords; set by an exported subclass.
- GraphFactor.DIRECTIONS = {}#
Output name -> its direction, +1 or -1; set by an exported subclass.
- GraphFactor.GRAPHS = {}#
Output name ->
Graph.to_json(); set by an exported subclass.
- GraphFactor.INTRADAY = {}#
The intraday dataset
SESSIONSruns on, as aget_config()dict; set by an exported subclass.
- GraphFactor.PERIOD_LAGS = {}#
Lag column -> how it is computed, of every lag column
GRAPHSreads; set by an exported subclass.
- GraphFactor.SESSIONS = {}#
Session column -> its intraday graph, of every session column
GRAPHSreads; set by an exported subclass.