AI-DS Project

DAP391m
Prerequisites

• Completed:
 PFP191

 ADY201m

Course Introduction 2
Course Objectives
 Understand the basics of data analysis with Python to
build and evaluate data models.
 Understand how to import data from multiple sources,
clean and wrangle data, perform exploratory data
analysis (EDA), and create meaningful data
visualizations.
 Know different ways to effectively visualize both small
and large-scale data

Course Introduction 3
Course Objectives
 Implement various types of basic and advanced
graphs and charts like Waffle Charts, Area Plots,
Histograms, Bar Charts, Pie Charts, Scatter Plots,
Word Clouds, Choropleth Maps,….
 Implement an application that leverages multiple
Watson AI services (Discovery, Speech to Text,
Assistant, and Text to Speech)

Course Introduction 4
Course Objectives
 Implement an application that leverages multiple
Watson AI services (Discovery, Speech to Text,
Assistant, and Text to Speech)
 Implement different techniques to develop
applications and AI-powered solutions.
 Implement the small mini capstone data science
project
Course Introduction 5
Course Objectives

Data Science Process

Course Introduction 6
Course Plan

1. Data Analysis with Python: importing datasets, data

wrangling, exploratory Data Analysis, model
development, model evaluation

2. Lab 1: Data Analysis with Python

Course Introduction 7
Course Plan
3. Introduction to Data Visualization Tools

4. Basic and Specialized Visualization Tools

5. Advanced Visualizations and Geospatial Data

6. Creating Dashboards with Plotly and Dash

7. Lab 2, 3: Data Visualization with Python

Course Introduction 8
Course Plan

8. Building AI Applications with Watson APIs:

introduction, voice to text, deployment

9. Lab 4: Building AI Applications with Watson APIs:

chat bot, deploy on facebook and slack

Course Introduction 9
Course Plan
10. Quiz

11. Applied Data Science Capstone: introduction,

interactive visual analytics and dashboard,
predictive analysis (classification), present your
data-driven insights

12. Lab 5: Applied Data Science

Course Introduction 10
Course Plan

13. Assignment grading

14. Review course

Course Introduction 11
Materials/ References

 Required References- Coursera courses

 Python Project for Data Science
 Data Analysis with Python
 Data Visualization with Python
 Building AI Applications with Watson APIs
 Applied Data Science Capstone

Course Introduction 12
Learning Environments
 GitHub, Jupyter Notebooks, and Google colab
 Watson Studio.

Course Introduction 13
Course Rules
 How to conduct
 Prepare contents of the next session/ topic at home
 Following lessons in classrooms
 Completing chapter assessments in time and Quizzes

 Communication
 Class/Interchange by FU-HCM CMS, Forum
 Discussing actively in your teams and in classrooms

Course Introduction 14
Evaluation Strategy
 Must attend more than 80% of contact hours
(if not, not allow to take exam).
 Evaluating
 01 Progress Test (Q) 10 %
 Labs 30 %
 Assignment 30%
 Final Exam (FE) 30 %
 Total score
 10% (Qiz)+ 30%( lab) + 30% (Assignment) + 30% (FE)

 Pass
 Total score ≥ 5 and Final Examination ≥ 4 (of 10)

 Every components > 0

Course Introduction 15
How to study
 This course is complex knowledge (however, it’s
attractive and exciting), so you need to keep tight grip
on it
 Read

 On the books to get the general concept

 Reference, study, collection from anywhere else (internet, your
classmates, forum …)
 Attend lectures
 Listens, understand, then make your own notes
 Give your explanation about some topic in lectures/ Ask questions
 Give some examples that are not existed in your book
 Practice all the exercises, demo to make your sense

Course Introduction 16
How to study
 After classes
 Discuss with your classmate in directly, on forum

 Do the lab, assignments to submit via CMS, and do more

exercises
 Build your teams in yourselves to support together in
studying

Course Introduction 17
How to exam/test
 This course is required following rules, so you
need to focus and practice your exercises and
homework in try your best everyday
 Progress Tests
 No books

 No conversations

 Workshop/Assignment
 Not copy (copy code, contents, style)

Course Introduction 18
Academic policy
 Cheating, plagiarism and breach of copyright are
serious offenses under this Policy.
 Cheating
 Cheating during a test or exam is construed as talking,
peeking at another student’s paper or any other
clandestine method of transmitting information.
 Cheating during in making lab and assignment as copy
source code, copy style, same meaning in progress, …

Course Introduction 19
Academic policy
 Cheating, plagiarism and breach of copyright are
serious offenses under this Policy.
 Plagiarism
 Plagiarism is using the work of others without citing it;
that is, holding the work of others out as your own work.
 Breach of Copyright
 If you photocopy a textbook without the copyright
holder's permission, you violate copyright law.

Course Introduction 20
Enjoy the Course
 Be enthusiastic about the material because it is
interesting, useful and an important part of your
training.
 Our job is to help you learn and enjoy the experience.
 We will do our best but we need your help.
 So, let’s all have fun together with DAP391m!!!

Course Introduction 21
Q&A

Course Introduction 22