casanovoutils.graphloss#

Plot Casanovo training and validation loss.

This script reads one or more Casanovo training logs (either a log file or a metrics.csv file) and produces a PNG plot of training and validation loss as a function of step/iteration.

Output is written to <root>.png.

Attributes#

`LossSeries`
`COMMANDS`

Functions#

`read_from_logfile`(→ tuple[LossSeries, LossSeries])	Read train/validation loss series from a Casanovo log file.
`read_from_csvfile`(→ tuple[LossSeries, LossSeries])	Read train/validation loss series from a Casanovo metrics.csv file.
`detect_input_format`(→ str)	Determine whether the input is a log file or a metrics CSV.
`read_from_file`(→ tuple[LossSeries, LossSeries])	Read losses from a Casanovo log file or metrics CSV.
`plot_losses`(→ None)	Create and save the loss plot.
`plot`(→ None)	Read Casanovo log and/or metrics.csv files and plot training/validation loss.
`main`(→ None)

Module Contents#

type casanovoutils.graphloss.LossSeries = list[tuple[int, float]]#

casanovoutils.graphloss.read_from_logfile(input_path: pathlib.Path) → tuple[LossSeries, LossSeries]#

Read train/validation loss series from a Casanovo log file.

Parameters:: input_path – Path to a text log file produced during Casanovo training.
Returns:: Two lists of (step, loss) tuples.
Return type:: (train_losses, val_losses)

casanovoutils.graphloss.read_from_csvfile(input_path: pathlib.Path) → tuple[LossSeries, LossSeries]#

Read train/validation loss series from a Casanovo metrics.csv file.

Parameters:: input_path – Path to a CSV file containing Casanovo metrics.
Returns:: Two lists of (step, loss) tuples.
Return type:: (train_losses, val_losses)

casanovoutils.graphloss.detect_input_format(input_path: pathlib.Path) → str#

Determine whether the input is a log file or a metrics CSV.

The detection is based on filename conventions and a quick header sniff.

Parameters:: input_path – Path to an input file.
Returns:: Either "csv" or "log".
Return type:: format

casanovoutils.graphloss.read_from_file(input_path: pathlib.Path) → tuple[LossSeries, LossSeries]#: Read losses from a Casanovo log file or metrics CSV.

casanovoutils.graphloss.plot_losses(root: str, train_loss_lists: list[LossSeries], val_loss_lists: list[LossSeries], max_y: float | None) → None#

Create and save the loss plot.

Parameters:

root – Output file root name. Output is written to {root}.png.
train_loss_lists – A sequence of training loss series.
val_loss_lists – A sequence of validation loss series.
max_y – Optional y-axis maximum.

casanovoutils.graphloss.plot(root: str, inputs: list[str], max_y: float | None = None) → None#

Read Casanovo log and/or metrics.csv files and plot training/validation loss.

Parameters:

root – Output file root; plot will be written to <root>.png and log to <root>.log.
inputs – One or more input files (Casanovo log files or metrics.csv files).
max_y – Optional y-axis maximum.

casanovoutils.graphloss.COMMANDS: casanovoutils.types.Commands#

casanovoutils.graphloss.main() → None#