Excel + Python + Deep Learning = ! (PyCon KR 2021)

This is a deck for PyCon KR 2021 talk, made and presented by Jeongkyu Shin

Full length examples in slide (shorten versions are in PyCon KR 2021 video):
* Iris flower classification: https://youtu.be/XVOSKg2BcyU
* Stock price prediction: https://youtu.be/XHcbsr9iWP0

Repository: https://github.com/inureyes/PyconKR-2021-BTF

# Abstract

Deep learning is being used in various fields nowadays. It feels like everyone except me is using it. People say that AI does a variety of tasks for me, but it doesn't seem to replace my chores. So I want to make a deep learning model to replace my tedious works, but it is not easy.

In this talk, I introduce the process of making “Trainable excel functions”, by creating deep learning-based functions in Python, attaching them to Excel, and running various deep learning-based analysis and model training.

First, I introduce Excel Custom Function, which is the background that makes this work possible, and explain how to create a simple function interface with CustomFunctionsRuntimeAPI based on TypeScript. I use Backend.AI, open-source Python-based machine learning cluster backend as a python / TensorFlow runtime environment. I show how to configure the Backend.AI server on the local computer with TensorFlow 2.5, and then use Backend.AI's JavaScript SDK to create CustomFunction code that connects Excel and Backend.AI.

After that, I introduce an example of a category classification model. This function reads simple iris classification data from Excel, trains a deep learning model using the data, and predicts the iris species from arbitrary data with the trained deep learning model. Next, I demonstrate another example of how to create a time series-based prediction Excel function using Tesla stock market price data and LSTM model.

The characteristic of the Excel+TensorFlow deep learning function created in this way is that I can continuously improve the performance. As a final example, I share the process of creating a trainable function that receives quarterly credit card payments data from Hometax as an Excel file and automatically enters the usage in the remarks field. Afterwards, we discuss the tremendous potentials of personalized local deep learning models to help make our lives less difficult.

(Korean)
딥러닝은 어느 사이에 다양한 분야에서 사용되고 있습니다. 나만 빼고 전부 사용하는 기분이 들 정도로 말이죠. AI가 다양한 일들을 대신해 준다는데, 딱히 내 잡무를 대신해주고 있지는 않은것 같습니다. 내 삽질을 대신해주는 딥러닝 모델을 하나 만들어보고 싶어지는 요즘이지만, 딱히 쉽게 되지는 않습니다.

이 발표에서는 "훈련 가능한 엑셀 함수"를 만든 과정을 소개합니다. 만인의 삽질 도구인 Excel 에 딥러닝 기반의 함수를 Python 으로 만들어 붙여서, 다양한 딥러닝 기반의 분석 및 모델 훈련을 돌려보는 과정을 설명합니다. 우선 이러한 작업이 가능해진 배경인, Excel의 Custom Function에 대해 소개하고, TypeScript 기반의 CustomFunctionsRuntimeAPI 로 간단한 함수 인터페이스를 만드는 법을 설명합니다. 이후 로컬 컴퓨터에 Python 기반의 머신러닝 클러스터 백엔드인 Backend.AI 런타임 환경을 TensorFlow 2.5 기반으로 구성한 후, Backend.AI의 JavaScript SDK를 이용하여 Excel과 Backend.AI를 연결하는 코드를 만들어 봅니다.

연결이 끝나면, 카테고리 구분 모델의 예로 Excel에 간단한 붓꽃 품종 분류 데이터를 올리고 그 데이터를 이용하여 딥러닝 모델을 훈련하는 함수와, 훈련한 딥러닝 모델로 임의의 데이터를 지정해서 붓꽃 품종을 알려주는 함수를 만들어 사용하는 과정을 시연합니다. 그 다음엔 LSTM 기반 시계열 미래 예측 Excel 함수를 주식시장의 테슬라 기업 시세 데이터 기반으로 만들어 봅니다.

이렇게 만든 딥러닝 함수는 내가 원할 때, 원하는 목적을 위해 계속 성능을 개선시킬 수 있다는 특징이 있습니다. 마지막 예제로 분기별 신용카드 결제 내역을 홈택스에서 Excel 파일로 받아, 비고란에 사용처를 자동으로 입력하는 함수를 만든 과정과 함께, 개인화된 로컬 딥러닝 모델들이 우리 삶을 좀 덜 힘들게 도와줄 수 있는 엄청난 가능성에 대해 이야기를 나눠봅니다.

Transcript

1. Excel + Python + Deep Learning = ! Jeongkyu Shin
2. About me Lablup Inc. : Make AI Accessible Maintainer / Open-source machine learning cluster platform: Backend.AI Google Developers Experts ML / DL GDE (Context retrieval) https://github.com/inureyes/
3. And online again T_T
4. Today’s Agenda • Left behind o Why my life is same as before AI wave? o Why Excel + Deep Learning? • Make my Excel supercharged with AI o Excel + TypeScript + Python + TensorFlow o Architecture overview: how I created • “Trainable excel functions” o Simple examples • Closing o Personal example: how it becomes the painkiller for my ‘real’ life. [1] https://openwho.org/channels/covid-19-national-languages
5. Left Behind Excel + Python + Deep Learning = !
6. Rise of AI Era • AI Wave: DEEP LEARNING o ImageNet competition (2012) o AlphaGo (2016) o Attention / Transformer (2017 / 2018) o XLNet / T5 (2019) o AlphaStar (2019) o GPT-3 (2020) • Boosted applications o Image segmentation / categorization o NLU o Self-driving o Robotics [1] LaMDA / Google I/O 2021 Keynote
7. Moonshot • Reaching the stars o Scanning the universe[1] o Filtering gravity lens noise[2] • Combat with COVID-19 o Analyzing coronavirus details[3] o Finding cure candidates[4] • Solving the nature riddles o Protein-folding prediction[5] https://www.flaticon.com/free-icon/shuttle_2285537 https://www.flaticon.com/free-icon/moon-phase_2909605 https://www.flaticon.com/free-icon/explosion_978623 [1] https://iopscience.iop.org/article/10.3847/1538-4357/abd62b [2] https://academic.oup.com/mnras/article-abstract/504/2/1825/6219095 [3] https://link.springer.com/article/10.1007/s10796-021-10131-x [4] https://www.frontiersin.org/articles/10.3389/frai.2020.00065/full [5] https://www.nature.com/articles/s41586-021-03819-2
8. Shades under the moon • Privacy o Recognizing personal identities[1] o Surveillance to unspecified citizens • War tool o Military programs[2,3] https://www.bbc.com/news/business-56195288 https://www.popularmechanics.com/technology/robots/a29610393/robot-soldier-boston-dynamics/ [1] https://www.nytimes.com/2019/04/14/technology/china-surveillance-artificial-intelligence-racial-profiling.html [2] https://ieeexplore.ieee.org/document/9384519 [3] https://sgp.fas.org/crs/natsec/R45178.pdf
9. Why my life is same as before AI wave? • Strongness and weakness of Deep Learning models o Work: Categorization / detection o Data: Image / Text data • And my life is full of… o Excel / HWP o Tedious repetitive works o And more • Characteristics of my life works o Based on specific tools o Have super-personalized detail (works / data) https://www.flaticon.com/free-icon/moon-phase_2909605 https://oldpc.tistory.com/71 https://www.my-internet-explorer.com/ie6/ https://tutorialexcel.com/versiones-de-excel/excel-95/
10. Why Excel + Deep Learning? • Data = Excel for daily work o Half of the most tedious tasks are happening on the Excel sheet o (Another half: Active-X + IE11) • So hard to be automated with ‘numerical functions’ o Many fields are not “numerical” https://www.flaticon.com/free-icon/risk_2145705
11. Make my Excel Supercharged with AI Excel + Python + Deep Learning = !
12. Excel + ?: Old ways • Traditional methods o Xlwings[1] (https://www.xlwings.org) o Openpyxl[2] (https://foss.heptapod.net/openpyxl/openpyxl) • Limitations: COM wrapper / depends on VBA o Works only on Windows o Limited real-time binding [1] https://www.xlwings.org [2] https://openpyxl.readthedocs.io/en/stable/ https://www.flaticon.com/free-icon/sweet_2581014
13. Excel + ?: Modern way • 2015 o Microsoft announces JavaScript API for Office[1] • 2018 o Microsoft announces Python support for script language[2] § Not implemented / Revamping Microsoft Office for Web § Transitioning to Web Standard o JavaScript-based Excel CustomFunction announced[3] • 2020 o JavaScript as an official script language[4] [1] https://developer.microsoft.com/en-us/office/blogs/connect-2015-office-extensibility-news/ [2] https://developers.slashdot.org/story/17/12/15/1133217/microsoft-considers-adding-python-as-an-official-scripting-language-in-excel [3] https://docs.microsoft.com/en-us/office/dev/add-ins/excel/custom-functions-overview [4] https://github.com/OfficeDev/Excel-Custom-Functions https://www.flaticon.com/free-icon/back-to-the-future_86503
14. Docker Building blocks for today • Microsoft Excel 365 (with 2021~ versions) • TypeScript o To compile Excel CustomFunction with JavaScript SDK • Docker (for windows / macOS) o To run sandboxed deep learning runtime • Backend.AI as glue / runtime framework o Glue between TypeScript and Deep learning container o JavaScript and Python SDK counterpart exists • You may choose one among other glue projects! o TF.js without Python/Docker o Anaconda with your handmade TypeScript SDK https://www.flaticon.com/premium-icon/blocks_1273426 https://www.flaticon.com/free-icon/brick_3813701 Excel
15. Excel + TypeScript + Python • Excel o Custom Functions (2020)[1] o Full JavaScript / TypeScript support o Limitation: Browser compatibility issues [2] • TypeScript o Binding CustomFunctionsRuntimeAPI [3] o Will use Backend.AI TypeScript SDK [4] to communicate Excel JavaScript fn. with Python container • Python o Local cluster / VM or baremetal o Docker for containerized environment [5] [1] https://docs.microsoft.com/en-us/office/dev/add-ins/excel/custom-functions-overview [2] https://docs.microsoft.com/en-us/office/dev/add-ins/develop/application-specific-api-model [3] https://docs.microsoft.com/en-us/office/dev/add-ins/excel/custom-functions-requirement-sets [4] https://github.com/lablup/backend.ai-client-js [5] https://hub.docker.com/u/lablup
16. Excel + TypeScript + Python + TensorFlow • TensorFlow o TensorFlow 2.5 Environment runtime[1] o Training § TensorFlow 2.5 (CPU / OneAPI) o Inference § TensorFlow Serving • API connector o GraphQL-based API o Connect with JavaScript SDK § Converted from TypeScript+Node.js 14 to Pure ESM [1] docker pull lablup/python-tensorflow:2.5-py38-cuda11.3
17. Architecture overview
18. “Trainable excel functions” Excel + Python + Deep Learning = !
19. Making custom functions • Two functions for one model o No general model functions: it will not look like ‘Excel function’ o One for training, one for inferencing • EXAMPLETRAIN(data_to_train) o To training & saving EXAMPLE model o e.g. IRIS_MODEL_TRAIN(data) • EXAMPLE(data_to_inference) o To inferencing with the EXAMPLE model o e.g. IRIS_MODEL(column) • Characteristics o Training time o Training data preservation o Keeping checkpoint to additional training https://www.flaticon.com/premium-icon/customization_1066631
20. So we will make • BTF o Bidirectional TensorFlow workflow example for Excel CustomFunction • Why not BTFECF? o Rhyme; o Not BTS but TensorFlow
21. Preparing development environment • Dev. Environment preparation o Install yeoman generator as global npm / yarn package § [NPM] npm install -g yo generator-office § [Yarn] yarn global add yo generator-office o Initialize Microsoft JavaScript Add-in repository § yo office § Create “TypeScript” type, “EXAMPLETRAIN” project o Install TypeScript SDK § npm install backend.ai-client o Build / sideload test § [Build] npm run build § [DevServer] npm run dev-server § [Sideloading] npm start https://www.flaticon.com/premium-icon/customization_1799807
22. Platform dependency • Excel (App) o Windows: EdgeHTML (Legacy) / Blink (Modern) o macOS: WebKit2 • Excel (Web) o Depends on the user browser • Supports o JavaScript ES5 or above o Transpilers help you
23. Preparing development environment
24. Preparing development environment npm run dev-server npm start:desktop Tip: CHANGE localhost to 127.0.0.1 in manifest.yml
25. Preparing development environment You will have task panel (template) on the ribbon.
26. Creating CustomFunction test logic • Modify manifest.yml o Change CONTOSO to your namespace. e.g. BTF o CHANGE localhost to 127.0.0.1 • Check src/functions/functions.ts o We will add functions here! o Default example functions: add, clock, currentTime, increment… https://www.flaticon.com/free-icon/example_5360938
27. Excel CustomFunction test /** * Adds two numbers. * @customfunction * @param first First number * @param second Second number * @returns The sum of the two numbers. */ /* global clearInterval, console, setInterval */ export function add(first: number, second: number): number { return first + second; }
28. Excel CustomFunction test /** * Adds two numbers. * @customfunction * @param first First number * @param second Second number * @returns The sum of the two numbers. */ /* global clearInterval, console, setInterval */ export function add(first: number, second: number): number { return first + second; }
29. Test: Initializing route to Python • Install JavaScript / node.js SDK • Load test (as ESModule) src/functions/functions.ts import * as ai from "backend.ai-client/backend.ai-client-es6.js"; $ npm i backend.ai-client
30. Test: Initializing route to Python Office.onReady(() => { const api_key: string = 'AKIAIXXXXXXXXEXAMPLE'; const secret_key: string = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'; const api_endpoint: string = 'http://127.0.0.1:8091/'; const clientConfig : any = new ai.backend.ClientConfig( api_key, secret_key, api_endpoint ); g.bclient = new ai.backend.Client( clientConfig, `Excel Adapter`, ); g.bclient.ready = false; g.client.get_manager_version().then((response) => { console.log("Server Health Ok.") }); }); src/functions/functions.ts Depends on your config. NOTE: You SHOULD setup the certificate for your local environment! • Office generator does it for you. • Reuse it for Backend.AI / Local environment • Otherwise, you will experience CORS[1] issue https://developer.mozilla.org/en-US/docs/Web/HTTP/CORS
31. /** * Test connection between Excel and Cluster * @customfunction TEST_CONNECTION * @param invocation Custom function handler */ export function testConnection(invocation: CustomFunctions.StreamingInvocation<string>): void { const api_key = "AKIAIXXXXXXXXEXAMPLE"; const secret_key = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"; const api_endpoint = "http://127.0.0.1:8091/"; invocation.setResult("Connecting..."); const clientConfig = new ai.backend.ClientConfig( api_key, secret_key, api_endpoint ); globalThis.bclient = new ai.backend.Client( clientConfig, `Excel Adapter`, ); globalThis.bclient.ready = false; globalThis.bclient.get_manager_version().then((response) => { invocation.setResult("Succeed"); }).catch((e) =>{ invocation.setResult("Failed"); }); invocation.onCanceled = () => { }; } src/functions/functions.ts
32. Let function be trainable • Details of EXAMPLETRAIN o Create temporary .csv file to train o Call the training function in the model folder o Give temporary .csv file as an argument (file to upload) o Get the result from API and send result to Excel https://www.flaticon.com/premium-icon/csv_172534 https://www.flaticon.com/free-icon/excel_732220 https://www.flaticon.com/premium-icon/folder_2140705 https://www.flaticon.com/free-icon/engine_999298 https://www.flaticon.com/premium-icon/play_2377746 Trainer EXAMPLETRAIN
33. Let function be trainable • Details of EXAMPLE o Call the TensorFlow serving image with model name / argument o Reuse inference container if already exists § Start session with same name (e.g. EXAMPLE) will automatically reuse the previous one. o Get the result and send to Excel Model EXAMPLE
34. async function connectToManager() { if ('bclient' in globalThis && globalThis.bclient.ready == true) { return Promise.resolve(true); } const api_key = "AKIAIXXXXXXXXEXAMPLE"; const secret_key = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"; const api_endpoint = "https://127.0.0.1:8091"; const clientConfig = new ai.backend.ClientConfig( api_key, secret_key, api_endpoint ); globalThis.bclient = new ai.backend.Client( clientConfig, `Excel Adapter`, ); globalThis.bclient.ready = false; globalThis.bclient.get_manager_version().then((response) => { globalThis.bclient.ready = true; return Promise.resolve(true); }).catch((e) =>{ return Promise.resolve(false); }); } Connection • Connect to Python Environment o Establish connection o Share it to other customfunctions • globalThis o Global object of JavaScript o Different from the runtime o Undocumented but works in Excel
35. Demo: Iris dataset / training & inference • Simple classification example • Iris Flower dataset o R. A. Fisher (1936) o Length and the width of the sepals and petals o Species • Famous and simple o One of the “Hello world” example data https://en.wikipedia.org/wiki/Iris_flower_data_set#/media/File:Kosaciec_szczecinkowaty_Iris_setosa.jpg
36. /** * Train IRIS flower dataset. * @customfunction IRIS_TRAIN * @param {number[][]} values IRIS data * @param invocation Custom function handler */ export function run_iris_training(values, invocation: CustomFunctions.StreamingInvocation<string>): void { try { let data = JSON.stringify(values); invocation.setResult(data); connectToManager().then(() => { invocation.setResult("Creating TensorFlow Environment..."); let resources = {"cpu": 1, "mem": "6g", "mounts": ['code’], ... "maxWaitSeconds": 30}; return globalThis.bclient.createIfNotExists("cr.backend.ai/testing/python-tensorflow:2.5-py38-cuda11.3", "TF_IRIS", resources); }).then(response => { invocation.setResult(`My session is created: ${response.sessionId}`); return globalThis.bclient.execute("TF_IRIS", 1, "query", `import os;os.system("cd /home/work/code;python receive_iris_data.py ${data}")`, {}); }).then(response => { if (response.result.exitCode === 0) { invocation.setResult(`Training...`); return globalThis.bclient.execute("TF_IRIS", 1, "query", `import os;os.system("cd /home/work/code;python train_iris_model.py")`, {}); }).then(response => { if (response.result.exitCode === 0) { invocation.setResult(`Training completed.`); } }} ... Iris flower Example: Excel Part
37. /** * Train IRIS flower dataset. * @customfunction IRIS_TRAIN * @param {number[][]} values IRIS data * @param invocation Custom function handler */ export function run_iris_training(values, invocation: CustomFunctions.StreamingInvocation<string>): void { try { let data = JSON.stringify(values); invocation.setResult(data); connectToManager().then(() => { invocation.setResult("Creating TensorFlow Environment..."); let resources = {"cpu": 1, "mem": "6g", "mounts": ['code’], ... "maxWaitSeconds": 30}; return globalThis.bclient.createIfNotExists("cr.backend.ai/testing/python-tensorflow:2.5-py38-cuda11.3", "TF_IRIS", resources); }).then(response => { invocation.setResult(`My session is created: ${response.sessionId}`); return globalThis.bclient.execute("TF_IRIS", 1, "query", `import os;os.system("cd /home/work/code;python receive_iris_data.py ${data}")`, {}); }).then(response => { if (response.result.exitCode === 0) { invocation.setResult(`Training...`); return globalThis.bclient.execute("TF_IRIS", 1, "query", `import os;os.system("cd /home/work/code;python train_iris_model.py")`, {}); }).then(response => { if (response.result.exitCode === 0) { invocation.setResult(`Training completed.`); } }} ... Iris flower Example: Excel Part
38. /** * Train IRIS flower dataset. * @customfunction IRIS_TRAIN * @param {number[][]} values IRIS data * @param invocation Custom function handler */ export function run_iris_training(values, invocation: CustomFunctions.StreamingInvocation<string>): void { try { let data = JSON.stringify(values); invocation.setResult(data); connectToManager().then(() => { invocation.setResult("Creating TensorFlow Environment..."); let resources = {"cpu": 1, "mem": "6g", "mounts": ['code’], ... "maxWaitSeconds": 30}; return globalThis.bclient.createIfNotExists("cr.backend.ai/testing/python-tensorflow:2.5-py38-cuda11.3", "TF_IRIS", resources); }).then(response => { invocation.setResult(`My session is created: ${response.sessionId}`); return globalThis.bclient.execute("TF_IRIS", 1, "query", `import os;os.system("cd /home/work/code;python receive_iris_data.py ${data}")`, {}); }).then(response => { if (response.result.exitCode === 0) { invocation.setResult(`Training...`); return globalThis.bclient.execute("TF_IRIS", 1, "query", `import os;os.system("cd /home/work/code;python train_iris_model.py")`, {}); }).then(response => { if (response.result.exitCode === 0) { invocation.setResult(`Training completed.`); } }} ... Iris flower Example: Excel Part
39. Iris flower Example: Pandas Part import sys, json import numpy import pandas as pd data = json.loads(sys.argv[1]) pd.DataFrame(data).to_csv(”temp_iris.csv",header=[len(data), 4, 'setosa','versicolor','virginica'], index=None) …Super simple
40. Iris flower Example: TensorFlow Part import tensorflow as tf import matplotlib.pyplot as plt import os dataFile = "./temp_iris.csv" column_names = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species'] feature_names = column_names[:-1] label_name = column_names[-1] class_names = ['Iris setosa', 'Iris versicolor', 'Iris virginica'] batch_size = 32 train_dataset = tf.data.experimental.make_csv_dataset( dataFile, batch_size, column_names=column_names, label_name=label_name, num_epochs=1) def pack_features_vector(features, labels): features = tf.stack(list(features.values()), axis=1) return features, labels train_dataset = train_dataset.map(pack_features_vector) features, labels = next(iter(train_dataset)) Data Preparation
41. Iris flower Example: TensorFlow Part Model Creation def create_model(): model = tf.keras.models.Sequential([ tf.keras.layers.Dense(10, activation='relu', input_shape=(4,)), tf.keras.layers.Dense(10, activation='relu'), tf.keras.layers.Dense(3) ]) model.compile(optimizer='adam', loss=tf.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=[tf.metrics.SparseCategoricalAccuracy()]) return model model = create_model()
42. Iris flower Example: TensorFlow Part Training checkpoint_path = "ckpt_iris_model/cp.ckpt" checkpoint_dir = os.path.dirname(checkpoint_path) # Create a callback that saves the model's weights cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path, save_weights_only=True, verbose=0) # Train the model with the new callback model.fit(train_dataset, epochs=200, verbose=0, callbacks=[cp_callback]) model.save('saved_models/iris_model')
43. Demo: Iris dataset / training & inference • Simple categorization example
45. Demo: Stock price prediction / training & inference • Time-series data prediction (Yahoo Finance Data / Tesla Stock Price)
47. Ok. Let’s solve my problem
48. How can I enjoy the AI wave myself • Back to my life: o Excel / HWP o Tedious repetitive works o And more • Characteristics of my life works o Based on specific tools o Have super-personalized detail (works / data)
49. How can I enjoy the AI wave myself • Reduce paperworks o Not repetitive o But complex enough one • Credit card payment history o As a start-up lead o Can I automatically guess the purpose of card payment? https://evangelion.fandom.com/wiki/Absolute_Terror_Field
50. How can I enjoy the AI wave myself • Reduce paperworks o Not repetitive o But complex enough one • Credit card payment history o As a start-up lead o Can I automatically guess the purpose of card payment? https://bbs.ruliweb.com/community/board/300143/read/47700389
51. 8 hours to 5 seconds • How it saves my life o Quarterly credit card payment history must be specified to correct deductions o I watched it all with my own eyes, but as the company grew, the number of items easily exceeded several hundred... • Dogfooding o Data: The deduction details received as an Excel file from HomeTax o Training: based on manual entry data of deductions for the past 5 years o Inference: Use a function that automatically enters the usage (inference result) in the remarks column o A/B & Pipeline: If there is a strange place, fix it manually and then train further
52. 8 hours to 5 seconds • Example 2019-09- 27 비씨카드（ 주） XXXX-XXXX- XXXX-XXXX 104-81-83559 주식회사 티머니 13,800 교통비 Transport fee 2019-09- 24 신한카드 주식회사 XXXX-XXXX- XXXX-XXXX 220-81-39938 （주）엘지유플러스 2,985,400 IDC
53. 8 hours to 5 seconds • Result (in progress…) 가맹점명 합계 공제여부 결정 자동비고 써브웨이 선릉점 8,700 불공제 식사 （주）스타벅스커피 코리아 7,000 공제 커피 나이스페이먼츠 주식회사 (NICE Payments Co., Ltd.) 31,100 불공제 우노 42,000 불공제 식사 홍콩반점0410보라매공원점 13,000 불공제 식사 세광양대창 시청점 116,000 불공제 식사 한국정보통신（주） 113,000 공제 한국맥도날드(유) 강남삼성 DT점 5,100 불공제 식사 (주)비지에프리테일 비지에프사옥점 5,400 불공제 부경에스이에스（주） 14,100 공제 엔에이치엔한국사이버결제 주식회사 15,024 공제 AWS클라우드 나이스페이먼츠 주식회사 (NICE Payments Co., Ltd.) 67,800 불공제 식사 나이스페이먼츠 주식회사 (NICE Payments Co., Ltd.) 26,520 불공제 식사 한국파파존스（주） 92,620 불공제 식사
54. Closing Excel + Python + Deep Learning = !
55. Today we run together through… • Left behind o Why my life is same as before AI wave? o Why Excel + Deep Learning? • Make my Excel supercharged with AI o Excel + TypeScript + Python + TensorFlow o Architecture overview: how I created • “Trainable excel functions” o Simple examples o Personal experience https://www.flaticon.com/free-icon/winner_2617899
56. Technically, • AI-powered Excel example using o Excel CustomFunction o TypeScript § Yeoman generator (Microsoft Office Generator) / Backend.AI TypeScript SDK o Docker § To run virtualized environment o TensorFlow § To training / inferencing
57. Endless possibility • “Very-personalized local & small deep learning models” o Democratization of the use of deep learning models o Make AI Accessible: Make my PC to personal cloud • To do o Generalized CustomFunction to prevent repetitive function creation o One-click windows installer o Pre-installed VM image o More examples
58. Thank You J https://github.com/inureyes/PyconKR-2021-BTF (Will be ready soon;)
59. References • Papers / Articles o https://iopscience.iop.org/article/10.3847/1538-4357/abd62b o https://academic.oup.com/mnras/article-abstract/504/2/1825/6219095 o https://link.springer.com/article/10.1007/s10796-021-10131-x o https://www.frontiersin.org/articles/10.3389/frai.2020.00065/full o https://www.nature.com/articles/s41586-021-03819-2 o https://www.nytimes.com/2019/04/14/technology/china-surveillance-artificial-intelligence- racial-profiling.html o https://ieeexplore.ieee.org/document/9384519 o https://sgp.fas.org/crs/natsec/R45178.pdf
60. References • Software / Libraries / Technical Docs. o https://docs.microsoft.com/en-us/office/dev/add-ins/excel/custom-functions-overview o https://docs.microsoft.com/en-us/office/dev/add-ins/develop/application-specific-api-model o https://docs.microsoft.com/en-us/office/dev/add-ins/excel/custom-functions-requirement- sets o https://github.com/lablup/backend.ai-client-js o https://hub.docker.com/u/lablup o https://developer.microsoft.com/en-us/office/blogs/connect-2015-office-extensibility-news/ o https://developers.slashdot.org/story/17/12/15/1133217/microsoft-considers-adding- python-as-an-official-scripting-language-in-excel o https://docs.microsoft.com/en-us/office/dev/add-ins/excel/custom-functions-overview o https://github.com/OfficeDev/Excel-Custom-Functions o https://www.xlwings.org o https://openpyxl.readthedocs.io/en/stable/
61. References • Icon / Clipart / Screenshot o https://www.flaticon.com/free-icon/shuttle_2285537 o https://www.flaticon.com/free-icon/moon-phase_2909605 o https://www.flaticon.com/free-icon/explosion_978623 o https://www.flaticon.com/premium-icon/blocks_1273426 o https://www.flaticon.com/free-icon/brick_3813701 o https://www.flaticon.com/free-icon/sweet_2581014 o https://www.flaticon.com/free-icon/risk_2145705 o https://www.flaticon.com/free-icon/winner_2617899 o https://www.flaticon.com/premium-icon/customization_1799807 o https://www.flaticon.com/premium-icon/customization_1066631 o https://www.flaticon.com/premium-icon/csv_172534 o https://www.flaticon.com/free-icon/excel_732220 o https://www.flaticon.com/premium-icon/folder_2140705 o https://www.flaticon.com/free-icon/engine_999298 o https://www.flaticon.com/premium-icon/play_2377746 o https://oldpc.tistory.com/71 o https://www.my-internet-explorer.com/ie6/ o https://tutorialexcel.com/versiones-de-excel/excel-95