bob.ip.binseg.utils.plot¶
Functions
|
Creates a loss curve in a Matplotlib figure. |
|
Creates a precision-recall plot with confidence intervals |
-
bob.ip.binseg.utils.plot.precision_recall_f1iso(data, confidence=True)[source]¶ Creates a precision-recall plot with confidence intervals
This function creates and returns a Matplotlib figure with a precision-recall plot containing shaded confidence intervals (standard deviation on the precision-recall measurements). The plot will be annotated with F1-score iso-lines (in which the F1-score maintains the same value).
This function specially supports “second-annotator” entries by plotting a line showing the comparison between the default annotator being analyzed and a second “opinion”. Second annotator dataframes contain a single entry (threshold=0.5), given the nature of the binary map comparisons.
- Parameters
data (dict) –
A dictionary in which keys are strings defining plot labels and values are dictionaries with two entries:
df:pandas.DataFrameA dataframe that is produced by our evaluator engine, indexed by integer “thresholds”, containing the following columns:
threshold(sorted ascending),precision,recall,pr_upper(upper precision bounds),pr_lower(lower precision bounds),re_upper(upper recall bounds),re_lower(lower recall bounds).threshold:listA threshold to graph with a dot for each set. Specific threshold values do not affect “second-annotator” dataframes.
confidence (
bool, Optional) – If set, draw confidence intervals for each line, using*_upperand*_lowerentries.
- Returns
figure – A matplotlib figure you can save or display (uses an
aggbackend)- Return type
-
bob.ip.binseg.utils.plot.loss_curve(df)[source]¶ Creates a loss curve in a Matplotlib figure.
- Parameters
df (
pandas.DataFrame) – A dataframe containing, at least, “epoch”, “median-loss” and “learning-rate” columns, that will be plotted.- Returns
figure – A figure, that may be saved or displayed
- Return type