Rename preview.ipynb to README.ipynb
Browse files- data/preview.ipynb +0 -80
data/preview.ipynb
DELETED
|
@@ -1,80 +0,0 @@
|
|
| 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": "markdown",
|
| 30 |
-
"metadata": {},
|
| 31 |
-
"source": [
|
| 32 |
-
"#### `/raw/DocLayNet_core.zip` contents"
|
| 33 |
-
]
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"cell_type": "code",
|
| 37 |
-
"execution_count": null,
|
| 38 |
-
"metadata": {},
|
| 39 |
-
"outputs": [],
|
| 40 |
-
"source": [
|
| 41 |
-
"import zipfile\n",
|
| 42 |
-
"\n",
|
| 43 |
-
"filelist = zipfile.ZipFile('/raw/DocLayNet_core.zip', 'r')\n",
|
| 44 |
-
"[i.filename for i in filelist.filelist]"
|
| 45 |
-
]
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"cell_type": "code",
|
| 49 |
-
"execution_count": null,
|
| 50 |
-
"metadata": {},
|
| 51 |
-
"outputs": [],
|
| 52 |
-
"source": [
|
| 53 |
-
"from utils.read_zip_file import read_zip_file\n",
|
| 54 |
-
"\n",
|
| 55 |
-
"read_zip_file('./raw/DocLayNet_core.zip', './raw/DocLayNet_core')"
|
| 56 |
-
]
|
| 57 |
-
}
|
| 58 |
-
],
|
| 59 |
-
"metadata": {
|
| 60 |
-
"kernelspec": {
|
| 61 |
-
"display_name": "dss-env",
|
| 62 |
-
"language": "python",
|
| 63 |
-
"name": "python3"
|
| 64 |
-
},
|
| 65 |
-
"language_info": {
|
| 66 |
-
"codemirror_mode": {
|
| 67 |
-
"name": "ipython",
|
| 68 |
-
"version": 3
|
| 69 |
-
},
|
| 70 |
-
"file_extension": ".py",
|
| 71 |
-
"mimetype": "text/x-python",
|
| 72 |
-
"name": "python",
|
| 73 |
-
"nbconvert_exporter": "python",
|
| 74 |
-
"pygments_lexer": "ipython3",
|
| 75 |
-
"version": "3.10.13"
|
| 76 |
-
}
|
| 77 |
-
},
|
| 78 |
-
"nbformat": 4,
|
| 79 |
-
"nbformat_minor": 2
|
| 80 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|