From 7799b94cc843a88045840b6c797e6df99e43a46a Mon Sep 17 00:00:00 2001
From: Alice BRENON <alice.brenon@ens-lyon.fr>
Date: Mon, 20 Nov 2023 18:38:52 +0100
Subject: [PATCH] Add predictor for MultiBERT model, improve the trainer for
the same model and expose the predicted score in the model's output
---
scripts/ML/BERT/Classifier.py | 12 ++++------
scripts/ML/Corpus.py | 21 ++++++-----------
scripts/ML/predictMulti.py | 26 +++++++++++++++++++++
scripts/ML/{predict.py => predictSimple.py} | 2 +-
scripts/ML/prodigy-multi-jsonl-to-tsv.py | 2 +-
scripts/ML/trainMultiBERT.py | 20 ++++++----------
6 files changed, 47 insertions(+), 36 deletions(-)
create mode 100755 scripts/ML/predictMulti.py
rename scripts/ML/{predict.py => predictSimple.py} (92%)
diff --git a/scripts/ML/BERT/Classifier.py b/scripts/ML/BERT/Classifier.py
index 04bcffa..d5c1b50 100644
--- a/scripts/ML/BERT/Classifier.py
+++ b/scripts/ML/BERT/Classifier.py
@@ -24,16 +24,14 @@ class Classifier(BERT):
self.pipe = TextClassificationPipeline(
model=self.model,
tokenizer=self.tokenizer,
- return_all_scores=True,
+ top_k=1,
device=self.device)
def __call__(self, text_generator):
tokenizer_kwargs = {'padding':True, 'truncation':True, 'max_length':512}
- predictions = []
+ labels, scores = [], []
for output in tqdm(self.pipe(text_generator, **tokenizer_kwargs)):
byScoreDesc = sorted(output, key=lambda d: d['score'], reverse=True)
- predictions.append([int(byScoreDesc[0]['label'][6:]),
- byScoreDesc[0]['score'],
- int(byScoreDesc[1]['label'][6:])])
- return self.encoder.inverse_transform(
- numpy.array(predictions)[:,0].astype(int))
+ labels.append(int(byScoreDesc[0]['label'][6:]))
+ scores.append(byScoreDesc[0]['score'])
+ return self.encoder.inverse_transform(labels), numpy.array(scores)
diff --git a/scripts/ML/Corpus.py b/scripts/ML/Corpus.py
index 159092b..00d5d9f 100644
--- a/scripts/ML/Corpus.py
+++ b/scripts/ML/Corpus.py
@@ -1,3 +1,4 @@
+from GEODE import fromKey, relativePath
import pandas
from os import makedirs
from os.path import dirname, isdir
@@ -103,34 +104,26 @@ class Directory(TSVIndexed):
A class to handle the normalised path used in the project and loading the
actual text input as a generator from records when they are needed
"""
- def __init__(self, root_path, column_name='content'):
+ def __init__(self, root_path, tsv_filename="files", column_name='content'):
"""
Positional arguments
:param root_path: the path to a GÉODE-style folder containing the text
version of the corpus on which to predict the classes
"""
self.text_path = f"{root_path}/Text"
- TSVIndexed.__init__(self, f"{root_path}/files.tsv", column_name)
+ TSVIndexed.__init__(self, f"{root_path}/{tsv_filename}.tsv", column_name)
def path_to(self, primary_key):
record = self.dict_primary_key(primary_key)
- article_relative_path = "{work}/T{volume}/{article}".format(**record)
- prefix = f"{self.text_path}/{article_relative_path}"
- if 'paragraph' in record:
- return f"{prefix}/{record['paragraph']}.txt"
- else:
- return f"{prefix}.txt"
+ return f"{self.text_path}/{relativePath(record, 'txt')}"
def dict_primary_key(self, primary_key):
if type(primary_key) == pandas.core.series.Series:
return dict(primary_key)
- elif type(primary_key) != dict:
- keys = self.default_keys.copy()
- if len(primary_key) == 4:
- keys.append('paragraph')
- return dict(zip(keys, primary_key))
- else:
+ elif type(primary_key) == dict:
return primary_key
+ else:
+ return fromKey(primary_key)
def get_text(self, primary_key):
with open(self.path_to(primary_key), 'r') as file:
diff --git a/scripts/ML/predictMulti.py b/scripts/ML/predictMulti.py
new file mode 100755
index 0000000..80d7eaa
--- /dev/null
+++ b/scripts/ML/predictMulti.py
@@ -0,0 +1,26 @@
+#!/usr/bin/env python3
+from BERT import Classifier
+from Corpus import corpus
+import GEODE.discursive as discursive
+import pandas
+from sys import argv
+
+def rateClass(name, answer, score):
+ return (1, score) if answer == 'accept' else (0, -score)
+
+def combine(row):
+ classes = [(name, row[name], row[name + 'Score'])
+ for name in discursive.functions]
+ return max(classes, key=lambda c: rateClass(*c))[0]
+
+def label(modelsRoot, source):
+ records = pandas.DataFrame(source.get_all('key'))
+ for name in discursive.functions:
+ classify = Classifier(f"{modelsRoot}/{name}")
+ content = source.get_all('content')
+ records[name], records[name + 'Score'] = classify(content)
+ records['label'] = records.apply(combine, axis=1)
+ return records
+
+if __name__ == '__main__':
+ label(argv[1], corpus(argv[2])).to_csv(argv[3], sep='\t', index=False)
diff --git a/scripts/ML/predict.py b/scripts/ML/predictSimple.py
similarity index 92%
rename from scripts/ML/predict.py
rename to scripts/ML/predictSimple.py
index 2dfa3e8..5ba28ad 100755
--- a/scripts/ML/predict.py
+++ b/scripts/ML/predictSimple.py
@@ -22,7 +22,7 @@ def label(classify, source, name='label'):
an additional column
"""
records = pandas.DataFrame(source.get_all('key'))
- records[name] = classify(source.get_all('content'))
+ records[name], records['score'] = classify(source.get_all('content'))
return records
if __name__ == '__main__':
diff --git a/scripts/ML/prodigy-multi-jsonl-to-tsv.py b/scripts/ML/prodigy-multi-jsonl-to-tsv.py
index c4b3c17..d555e74 100755
--- a/scripts/ML/prodigy-multi-jsonl-to-tsv.py
+++ b/scripts/ML/prodigy-multi-jsonl-to-tsv.py
@@ -22,7 +22,7 @@ def initialiseTexts(texts, key, annotation):
{'accept': None,
'reject': set(),
'row': dict(**annotation['meta'],
- content=annotation['text'])})
+ content=annotation['text'].strip()+'\n')})
def byLabel(annotations):
labels = {}
diff --git a/scripts/ML/trainMultiBERT.py b/scripts/ML/trainMultiBERT.py
index 637ad29..43cc10b 100755
--- a/scripts/ML/trainMultiBERT.py
+++ b/scripts/ML/trainMultiBERT.py
@@ -6,24 +6,18 @@ from LabeledData import LabeledData
import os
import sys
-def split(columnName):
- return {}
-
-def load(rootPath):
- classes = {}
- for f in os.listdir(rootPath):
- if f[-4:] == '.tsv':
- classes[f[:-4]] = f"{rootPath}/{f}"
- return classes
-
def trainSubClassifier(trainRoot, modelRoot, className):
trainData = Directory(trainRoot, tsv_filename=className)
labeled_data = LabeledData(trainData, "answer")
subModelPath = f"{modelRoot}/{className}"
os.makedirs(subModelPath, exist_ok=True)
- os.symlink(f"../{BERT.encoder_file}", f"{subModelPath}/{BERT.encoder_file}")
- trainer = Trainer(subModelPath, labeled_data)
- trainer()
+ encoderLink = f"{subModelPath}/{BERT.encoder_file}"
+ if not os.path.islink(encoderLink):
+ os.symlink(f"../{BERT.encoder_file}", encoderLink)
+ if not os.path.exists(f"{subModelPath}/pytorch_model.bin"):
+ trainer = Trainer(subModelPath, labeled_data)
+ print(f"Training {className} to {subModelPath}")
+ trainer()
if __name__ == '__main__':
for className in discursive.functions:
--
GitLab