[pre-commit.ci] pre-commit autoupdate

.pre-commit-config.yaml

@@ -1,12 +1,12 @@
 ---
 repos:
   - repo: https://github.com/Lucas-C/pre-commit-hooks
-    rev: v1.2.0
+    rev: v1.5.5
     hooks:
       - id: remove-tabs
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.2.0
+    rev: v5.0.0
     hooks:
       - id: trailing-whitespace
       - id: check-merge-conflict
@@ -22,20 +22,20 @@ repos:
       - id: debug-statements
 
   - repo: https://github.com/pycqa/pydocstyle.git
-    rev: 6.1.1
+    rev: 6.3.0
     hooks:
       - id: pydocstyle
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.2.0
+    rev: v5.0.0
     hooks:
       - id: check-toml
       - id: check-yaml
       - id: end-of-file-fixer
       - id: trailing-whitespace
 
   - repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 24.10.0
     hooks:
       - id: black
 
@@ -46,7 +46,7 @@ repos:
   #     - id: check-manifest
 
   - repo: https://github.com/s-weigand/flake8-nb
-    rev: v0.4.0
+    rev: v0.5.3
     hooks:
       - id: flake8-nb
         additional_dependencies: ['pep8-naming']

notebooks/demo2/cascade_mask_rcnn_hrnetv2p_w32_20e_v2.py

@@ -1,4 +1,5 @@
 """Model settings."""
+
 model = dict(
     type="CascadeRCNN",
     # num_stages=3,

notebooks/demo2/config.py

@@ -1,4 +1,5 @@
 """Default runtime config."""
+
 import pathlib
 import os
 import yaml

notebooks/demo2/config_farm_train.py

@@ -1,6 +1,5 @@
 """Config FARM Training."""
 
-
 import pathlib
 import os
 from farm.modeling.prediction_head import TextClassificationHead

src/components/preprocessing/base_component.py

@@ -1,6 +1,5 @@
 """BaseComponent."""
 
-
 from abc import ABC, abstractmethod
 
 

src/components/preprocessing/base_curator.py

@@ -1,6 +1,5 @@
 """BaseCurator."""
 
-
 import re
 from abc import abstractmethod
 

src/components/preprocessing/base_kpi_inference_curator.py

@@ -197,7 +197,7 @@ def return_sliced_squad(self, squad_json, indices):
             return {}
 
         pdf2pars = defaultdict(list)
-        for (i1, i2) in indices:
+        for i1, i2 in indices:
             pdf2pars[i1].append(i2)
 
         data = []

src/components/preprocessing/curator.py

@@ -1,6 +1,5 @@
 """Curator."""
 
-
 import glob
 import logging
 

src/components/preprocessing/extractor.py

@@ -1,6 +1,5 @@
 """Extractor class."""
 
-
 from .pdf_table_extractor import PDFTableExtractor
 from .pdf_text_extractor import PDFTextExtractor
 import logging

src/components/preprocessing/kpi_inference_curator.py

@@ -103,6 +103,7 @@ def clean(self, df):
         Args:
             df (A pandas dataframe)
         """
+
         # map kpi to question
         def map_kpi(r):
             try:

src/components/preprocessing/nq_curator.py

@@ -1,6 +1,5 @@
 """Processing nq curator."""
 
-
 import logging
 import os
 from ast import literal_eval

src/components/preprocessing/nq_extractor.py

@@ -1,6 +1,5 @@
 """NQExtractor."""
 
-
 import json
 import logging
 import os

src/components/preprocessing/pdf_table_extractor.py

@@ -1,6 +1,5 @@
 """PDFTableExtractor."""
 
-
 from .base_component import BaseComponent
 import os
 from pdf2image import convert_from_path, pdfinfo_from_path

src/components/preprocessing/pdf_text_extractor.py

@@ -1,6 +1,5 @@
 """PDFTextExtractor."""
 
-
 import glob
 import io
 import json

src/components/preprocessing/text_curator.py

@@ -1,6 +1,5 @@
 """TextCurator."""
 
-
 import ast
 import json
 import logging

src/components/utils/cscdtabnet_checkpoint_url.py

@@ -1,6 +1,5 @@
 """Cscdtabnet checkpoint URLs."""
 
-
 checkpoint_url = {
     "general_model.pth": "https://drive.google.com/uc?id=1-xfq5hDmFdKgbY9FSFTmhSlcb2p13RPn",
     "icdar_13.pth": "https://drive.google.com/uc?id=1-mVr4UBicFk3mjUz5tsVPjQ4jzRtiT7V",

src/components/utils/nq_utils.py

@@ -1,6 +1,5 @@
 """NQ utils."""
 
-
 import re
 
 

src/components/utils/qa_metrics.py

@@ -1,6 +1,5 @@
 """QA metrics."""
 
-
 import numpy as np
 from farm.evaluation.metrics import squad_EM, squad_f1
 from sklearn.metrics import confusion_matrix

src/data/__init__.py

@@ -1,2 +1,3 @@
 """Data collection module."""
+
 from .s3_communication import S3FileType, S3Communication  # noqa F401

src/data/make_dataset.py

@@ -1,4 +1,5 @@
 """Data collection code."""
+
 import click
 import logging
 from pathlib import Path

src/data/s3_communication.py

@@ -1,4 +1,5 @@
 """S3 communication tools."""
+
 import os
 import pathlib
 import os.path as osp

src/models/__init__.py

@@ -1,4 +1,5 @@
 """Module for models."""
+
 from .farm_trainer import FARMTrainer
 from .qa_farm_trainer import QAFARMTrainer
 from .trainer_optuna import TrainerOptuna

src/models/farm_trainer.py

@@ -1,6 +1,5 @@
 """FARM Trainer."""
 
-
 import logging
 import os
 

src/models/qa_farm_trainer.py

@@ -1,6 +1,5 @@
 """QA Farm trainer."""
 
-
 import logging
 import json
 import os

src/models/relevance_infer.py

@@ -1,6 +1,5 @@
 """RelevanceInfer."""
 
-
 import json
 import logging
 import os

src/models/text_kpi_infer.py

@@ -1,6 +1,5 @@
 """Text KPI Inference."""
 
-
 import glob
 import logging
 import os
@@ -61,9 +60,9 @@ def __init__(self, infer_config, n_best_per_sample=1):
         self.model.model.prediction_heads[0].n_best_per_sample = n_best_per_sample
         # If positive, this will boost "No Answer" as prediction.
         # If negative, this will decrease the model from giving "No Answer" as prediction.
-        self.model.model.prediction_heads[
-            0
-        ].no_ans_boost = self.infer_config.no_ans_boost
+        self.model.model.prediction_heads[0].no_ans_boost = (
+            self.infer_config.no_ans_boost
+        )
         self.result_dir = self.infer_config.result_dir["Text"]
         if not os.path.exists(self.result_dir):
             os.makedirs(self.result_dir)