sparknlp_jsl.training_log_parser#
Module Contents#
Classes#
- class assertion_log_parser#
- get_best_f1_scores(log_path: str, labels: List[str])#
Returns the best Micro and Macro F1 Scores.
- Parameters:
log_path – path to the log file
labels – list of assertion labels
- get_charts(log_file: str, labels: List[str], threshold=0.0)#
Plots the figures of metrics ( precision, recall, f1) vs epochs.
- Parameters:
log_file – path to the log file
labels – list of assertion labels
- loss_plot(log_path: str)#
Plots the figure of loss vs epochs.
- Parameters:
log_path – path to the log file
- parse_logfile(path: str, labels: List[str])#
Returns metrics and avg-metrics dataframes, graph name and a boolean for whether test set is provided or not.
- Parameters:
path (str) – path to the log file
labels (list) – list of assertion labels
- class ner_log_parser#
- evaluate(true_seqs: List[str], pred_seqs: List[str], verbose=True)#
Evaluates the performance of the model.
if verbose, returns overall performance, as well as performance per chunk type; otherwise, simply returns overall precision, recall, f1 scores
- Parameters:
true_seqs (list) – a list of true tags
pred_seqs (list) – a list of predicted tags
verbose (bool) – whether to print the results or not
- evaluate_conll_file(fileIterator)#
prints overall performance, as well as performance per chunk type.
- get_best_f1_scores(log_path: str)#
Returns the best Micro and Macro F1 Scores.
- Parameters:
log_path – path to the log file
- get_charts(log_file: str, threshold: float = 0.0)#
Plots the figures of metrics ( precision, recall, f1) vs epochs.
- Parameters:
log_file – path to the log file
- loss_plot(log_path: str)#
Plots the figure of loss vs epochs.
- Parameters:
log_path – path to the log file
- parse_logfile(path: str)#
Returns metrics and avg-metrics dataframes, graph name and a boolean for whether test set is provided or not.
- Parameters:
path – path to the log file