NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: fix or ignore runtime and deprecation warnings (#1660)

Browse Source 
* chore: fix or catch deprecation warnings

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

* chore: update poetry lock with latest docling-core

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

---------

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis
2025-05-28 17:55:31 +02:00
committed by GitHub
parent b3e0042813
commit 3942923125
7 changed files with 116 additions and 87 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
docling/models/layout_model.py
View File

@@ -185,13 +185,23 @@ class LayoutModel(BasePageModel):
).postprocess()
# processed_clusters, processed_cells = clusters, page.cells
conv_res.confidence.pages[page.page_no].layout_score = float(
np.mean([c.confidence for c in processed_clusters])
)
with warnings.catch_warnings():
warnings.filterwarnings(
"ignore",
"Mean of empty slice|invalid value encountered in scalar divide",
RuntimeWarning,
"numpy",
)
conv_res.confidence.pages[page.page_no].ocr_score = float(
np.mean([c.confidence for c in processed_cells if c.from_ocr])
)
conv_res.confidence.pages[page.page_no].layout_score = float(
np.mean([c.confidence for c in processed_clusters])
)
conv_res.confidence.pages[page.page_no].ocr_score = float(
np.mean(
[c.confidence for c in processed_cells if c.from_ocr]
)
)
page.cells = processed_cells
page.predictions.layout = LayoutPrediction(

17
docling/models/page_preprocessing_model.py
View File

@@ -1,4 +1,5 @@
import re
import warnings
from collections.abc import Iterable
from pathlib import Path
from typing import Optional
@@ -7,7 +8,7 @@ import numpy as np
from PIL import ImageDraw
from pydantic import BaseModel
from docling.datamodel.base_models import Page, ScoreValue
from docling.datamodel.base_models import Page
from docling.datamodel.document import ConversionResult
from docling.datamodel.settings import settings
from docling.models.base_model import BasePageModel
@@ -76,11 +77,15 @@ class PagePreprocessingModel(BasePageModel):
score = self.rate_text_quality(c.text)
text_scores.append(score)
conv_res.confidence.pages[page.page_no].parse_score = float(
np.nanquantile(
text_scores, q=0.10
) # To emphasise problems in the parse_score, we take the 10% percentile score of all text cells.
)
with warnings.catch_warnings():
warnings.filterwarnings(
"ignore", "Mean of empty slice", RuntimeWarning, "numpy"
)
conv_res.confidence.pages[page.page_no].parse_score = float(
np.nanquantile(
text_scores, q=0.10
) # To emphasise problems in the parse_score, we take the 10% percentile score of all text cells.
)
# DEBUG code:
def draw_text_boxes(image, cells, show: bool = False):