Charles Kabui
commited on
Commit
•
810a7a1
1
Parent(s):
dec87ec
read zip files
Browse files- data/preview.ipynb +87 -0
- data/raw/README.md +0 -33
- data/raw/preview.ipynb +0 -0
- utils/read_zip_file.py +15 -0
data/preview.ipynb
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "markdown",
|
5 |
+
"metadata": {},
|
6 |
+
"source": [
|
7 |
+
"### Details"
|
8 |
+
]
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"cell_type": "markdown",
|
12 |
+
"metadata": {},
|
13 |
+
"source": [
|
14 |
+
"`/raw/DocLayNet_core.zip` downloaded from [DocLayNet_core.zip dataset](https://codait-cos-dax.s3.us.cloud-object-storage.appdomain.cloud/dax-doclaynet/1.0.0/DocLayNet_core.zip)\n",
|
15 |
+
"\n",
|
16 |
+
"`/raw/RVL-CDIP-invoice.zip` downloaded from [chainyo/rvl-cdip-invoice](https://huggingface.co/datasets/chainyo/rvl-cdip-invoice). It can also be downloaded from [aharley/rvl_cdip](https://huggingface.co/datasets/aharley/rvl_cdip).\n",
|
17 |
+
"\n",
|
18 |
+
"`/processed/vectors/RVL-CDIP-invoice.json.zip` generated using `/raw/RVL-CDIP-invoice.zip`, and the model to create the following features."
|
19 |
+
]
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"cell_type": "markdown",
|
23 |
+
"metadata": {},
|
24 |
+
"source": [
|
25 |
+
"### Preview"
|
26 |
+
]
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"cell_type": "code",
|
30 |
+
"execution_count": 3,
|
31 |
+
"metadata": {},
|
32 |
+
"outputs": [
|
33 |
+
{
|
34 |
+
"ename": "BadZipFile",
|
35 |
+
"evalue": "File is not a zip file",
|
36 |
+
"output_type": "error",
|
37 |
+
"traceback": [
|
38 |
+
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
39 |
+
"\u001b[0;31mBadZipFile\u001b[0m Traceback (most recent call last)",
|
40 |
+
"Cell \u001b[0;32mIn[3], line 3\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mzipfile\u001b[39;00m\n\u001b[0;32m----> 3\u001b[0m filelist \u001b[38;5;241m=\u001b[39m \u001b[43mzipfile\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mZipFile\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43m./raw/DocLayNet_core.zip\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mr\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mfilelist\n\u001b[1;32m 4\u001b[0m filelist\n",
|
41 |
+
"File \u001b[0;32m~/miniconda3/envs/dss-env/lib/python3.10/zipfile.py:1269\u001b[0m, in \u001b[0;36mZipFile.__init__\u001b[0;34m(self, file, mode, compression, allowZip64, compresslevel, strict_timestamps)\u001b[0m\n\u001b[1;32m 1267\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1268\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m mode \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m'\u001b[39m:\n\u001b[0;32m-> 1269\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_RealGetContents\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1270\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m mode \u001b[38;5;129;01min\u001b[39;00m (\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mw\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mx\u001b[39m\u001b[38;5;124m'\u001b[39m):\n\u001b[1;32m 1271\u001b[0m \u001b[38;5;66;03m# set the modified flag so central directory gets written\u001b[39;00m\n\u001b[1;32m 1272\u001b[0m \u001b[38;5;66;03m# even if no files are added to the archive\u001b[39;00m\n\u001b[1;32m 1273\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_didModify \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n",
|
42 |
+
"File \u001b[0;32m~/miniconda3/envs/dss-env/lib/python3.10/zipfile.py:1336\u001b[0m, in \u001b[0;36mZipFile._RealGetContents\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1334\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m BadZipFile(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFile is not a zip file\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 1335\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m endrec:\n\u001b[0;32m-> 1336\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m BadZipFile(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFile is not a zip file\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 1337\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdebug \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m 1338\u001b[0m \u001b[38;5;28mprint\u001b[39m(endrec)\n",
|
43 |
+
"\u001b[0;31mBadZipFile\u001b[0m: File is not a zip file"
|
44 |
+
]
|
45 |
+
}
|
46 |
+
],
|
47 |
+
"source": [
|
48 |
+
"import zipfile\n",
|
49 |
+
"\n",
|
50 |
+
"filelist = zipfile.ZipFile('./raw/DocLayNet_core.zip', 'r').filelist\n",
|
51 |
+
"filelist"
|
52 |
+
]
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"cell_type": "code",
|
56 |
+
"execution_count": null,
|
57 |
+
"metadata": {},
|
58 |
+
"outputs": [],
|
59 |
+
"source": [
|
60 |
+
"from utils.read_zip_file import read_zip_file\n",
|
61 |
+
"\n",
|
62 |
+
"read_zip_file('./raw/DocLayNet_core.zip', './raw/DocLayNet_core')"
|
63 |
+
]
|
64 |
+
}
|
65 |
+
],
|
66 |
+
"metadata": {
|
67 |
+
"kernelspec": {
|
68 |
+
"display_name": "dss-env",
|
69 |
+
"language": "python",
|
70 |
+
"name": "python3"
|
71 |
+
},
|
72 |
+
"language_info": {
|
73 |
+
"codemirror_mode": {
|
74 |
+
"name": "ipython",
|
75 |
+
"version": 3
|
76 |
+
},
|
77 |
+
"file_extension": ".py",
|
78 |
+
"mimetype": "text/x-python",
|
79 |
+
"name": "python",
|
80 |
+
"nbconvert_exporter": "python",
|
81 |
+
"pygments_lexer": "ipython3",
|
82 |
+
"version": "3.10.13"
|
83 |
+
}
|
84 |
+
},
|
85 |
+
"nbformat": 4,
|
86 |
+
"nbformat_minor": 2
|
87 |
+
}
|
data/raw/README.md
DELETED
@@ -1,33 +0,0 @@
|
|
1 |
-
How the data got here:
|
2 |
-
|
3 |
-
1. Downloading the [DocLayNet_core.zip dataset](https://codait-cos-dax.s3.us.cloud-object-storage.appdomain.cloud/dax-doclaynet/1.0.0/DocLayNet_core.zip) using the `wget`.
|
4 |
-
2. Uploaded the downloaded `DocLayNet_core.zip` file to Hugging Face space.
|
5 |
-
3. Loading a dataset (`chainyo/rvl-cdip-invoice`) using the `load_dataset` function from the Hugging Face library.
|
6 |
-
5. Extracting and saving each image from the `train` portion of the loaded dataset into the `RVL-CDIP-invoice` directory.
|
7 |
-
7. Compressing the `RVL-CDIP-invoice` directory into a zip file (`RVL-CDIP-invoice.zip`) using the `zip` command.
|
8 |
-
8. Uploading the zip file to Hugging Face space.
|
9 |
-
|
10 |
-
```
|
11 |
-
# # !wget https://codait-cos-dax.s3.us.cloud-object-storage.appdomain.cloud/dax-doclaynet/1.0.0/DocLayNet_core.zip -O DocLayNet_core.zip
|
12 |
-
# upload_to_huggingface_space(
|
13 |
-
# space_name = HUGGINGFACE_SPACE_NAME,
|
14 |
-
# private = True,
|
15 |
-
# path_or_fileobj = './DocLayNet_core.zip',
|
16 |
-
# path_in_repo = 'data/raw/DocLayNet_core.zip')
|
17 |
-
#
|
18 |
-
#
|
19 |
-
# invoices = load_dataset('chainyo/rvl-cdip-invoice', revision="fad615c9ceaecb4476b0a01f29c0a15b276b3a2b")
|
20 |
-
# # can also be found at: https://huggingface.co/datasets/aharley/rvl_cdip
|
21 |
-
# os.mkdir('./RVL-CDIP-invoice')
|
22 |
-
# for index, invoice in enumerate(tqdm(invoices['train'])):
|
23 |
-
# invoice['image'].save(f'./RVL-CDIP-invoice/{index}.png', format="png")
|
24 |
-
#
|
25 |
-
# !ls ./RVL-CDIP-invoice -1 | wc -l
|
26 |
-
# !zip -r RVL-CDIP-invoice.zip ./RVL-CDIP-invoice
|
27 |
-
#
|
28 |
-
# upload_to_huggingface_space(
|
29 |
-
# space_name = HUGGINGFACE_SPACE_NAME,
|
30 |
-
# private = True,
|
31 |
-
# path_or_fileobj = './RVL-CDIP-invoice.zip',
|
32 |
-
# path_in_repo = f'data/raw/RVL-CDIP-invoice.zip')
|
33 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
data/raw/preview.ipynb
DELETED
File without changes
|
utils/read_zip_file.py
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import io
|
2 |
+
import zipfile
|
3 |
+
|
4 |
+
def read_zip_file(archive_path: str, file_path: str):
|
5 |
+
"""
|
6 |
+
Read a file from a zip archive.
|
7 |
+
Args:
|
8 |
+
archive_path (str): The path to the zip archive.
|
9 |
+
file_path (str): The path to the file inside the archive.
|
10 |
+
Returns:
|
11 |
+
io.BytesIO: The file as a BytesIO object.
|
12 |
+
"""
|
13 |
+
with zipfile.ZipFile(archive_path) as zip_file:
|
14 |
+
file = zip_file.read(file_path)
|
15 |
+
return io.BytesIO(file) if file else file
|