psifr.fr.lag_crp_compound#

psifr.fr.lag_crp_compound(df, lag_key='input', count_unique=False, item_query=None, test_key=None, test=None)#

Conditional response probability by lag of current and prior transitions.

Parameters:

df (pandas.DataFrame) – Merged study and recall data. See merge_lists. List length is assumed to be the same for all lists. Must have fields: subject, list, input, output, recalled. Input position must be defined such that the first serial position is 1, not 0.
lag_key (str, optional) – Name of column to use when calculating lag between recalled items. Default is to calculate lag based on input position.
count_unique (bool, optional) – If true, possible transitions of the same lag will only be incremented once per transition.
item_query (str, optional) – Query string to select items to include in the pool of possible recalls to be examined. See pandas.DataFrame.query for allowed format.
test_key (str, optional) – Name of column with labels to use when testing transitions for inclusion.
test (callable, optional) – Callable that takes in previous and current item values and returns True for transitions that should be included.

Returns:

results – Has fields:

subjecthashable: Results are separated by each subject.
previousint: Lag of the previous transition.
currentint: Lag of the current transition.
probfloat: Probability of each lag transition.
actualint: Total of actual made transitions at each lag.
possibleint: Total of times each lag was possible, given the prior input position and the remaining items to be recalled.

Return type:

pandas.DataFrame

See also

lag_crp: Conditional response probability by lag.

Examples

>>> from psifr import fr
>>> subjects = [1]
>>> study = [['absence', 'hollow', 'pupil', 'fountain']]
>>> recall = [['fountain', 'hollow', 'absence']]
>>> raw = fr.table_from_lists(subjects, study, recall)
>>> data = fr.merge_free_recall(raw)
>>> crp = fr.lag_crp_compound(data)
>>> crp.head(14)
    subject  previous  current  prob  actual  possible
0         1        -3       -3   NaN       0         0
1         1        -3       -2   NaN       0         0
2         1        -3       -1   NaN       0         0
3         1        -3        0   NaN       0         0
4         1        -3        1   NaN       0         0
5         1        -3        2   NaN       0         0
6         1        -3        3   NaN       0         0
7         1        -2       -3   NaN       0         0
8         1        -2       -2   NaN       0         0
9         1        -2       -1   1.0       1         1
10        1        -2        0   NaN       0         0
11        1        -2        1   0.0       0         1
12        1        -2        2   NaN       0         0
13        1        -2        3   NaN       0         0