diff --git a/Data Processing Guide.ipynb b/Data Processing Guide.ipynb new file mode 100644 index 0000000..d210997 --- /dev/null +++ b/Data Processing Guide.ipynb @@ -0,0 +1,117 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "id": "193481de", + "metadata": {}, + "outputs": [], + "source": [ + "# A sample of input data can be generate from below code for invoice,resume,Businesscard,Attendence." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "04dbb099", + "metadata": {}, + "outputs": [], + "source": [ + "import base64\n", + "import json\n", + "empty=[]\n", + "\n", + "found=\"file_path\"\n", + "name = found\n", + "image = open(name, 'rb')\n", + "image_read = image.read()\n", + "image_64_encode = base64.b64encode(image_read)\n", + "NULL = 'null'\n", + "empty.append(\"ByteData--\" + (NULL).strip('\"\"'))\n", + "image_64_encode = image_64_encode.decode('utf-8')\n", + "empty.append(\"FileData--\" + str(image_64_encode))\n", + "imagedata = name.split(\"\\\\\")\n", + "imagename = str(imagedata[-1]).replace('\"', '').replace(\"[\", \"\").replace(\"]\", \"\")\n", + "imagename1 = str(imagename).split('.')\n", + "\n", + "imagename = str(imagename1[-2]).replace(\"[\", \"]\")\n", + "empty.append(\"FileName--\" + imagename)\n", + "empty.append(\"FilePath--\" + found)\n", + "imageExtension = str(imagename1[-1]).replace(\"[\", \"]\")\n", + "empty.append(\"FileType--\" + imageExtension)\n", + "\n", + "import pandas as pd\n", + "df = pd.DataFrame(empty)\n", + "df = df[0].str.split(\"--\", expand=True)\n", + "data1 = pd.DataFrame(df[0])\n", + "data2 = pd.DataFrame(df[1])\n", + "dt = data2.set_index(data1[0])\n", + "\n", + "dt4 = dt.T\n", + " \n", + "dictionary = dt4.to_dict(orient=\"index\")\n", + "dictionary[1]\n", + "payload1 = json.dumps(dictionary[1])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "ea47e4ad", + "metadata": {}, + "outputs": [], + "source": [ + "print(payload1)" + ] + }, + { + "cell_type": "markdown", + "id": "71949236", + "metadata": {}, + "source": [ + "# Note\n" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "96574e90", + "metadata": {}, + "outputs": [], + "source": [ + "# when we have to test code using postman\n", + "# after give url in body select json option then \n", + "# add [] to the text generated from payload1 paste in the body and click send button " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "f876ca7c", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.5" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}