1 of 20

དཔལ་ལྡན་འབྲུག་གཞུང་། ཤེས་རིག་དང་རིག་རྩལ་གོང་འཕེལ་ལྷན་ཁག།

Department of School Education

Ministry of Education & Skills Development

Online Training for ICT Teachers

24 February 2023

Classes XI & XII ICT Curriculum

Data Science SESSION I

2 of 20

Introduction to Data Science

Why to learn Data Science?

3 of 20

Session Overview

Data Science

Competency

Career

Opportunities

What?

NumPy

Prerequisites

Why

4 of 20

Competency

Present a visual representation of a dataset by applying data analysis modules in a programming language to communicate a message.

5 of 20

What is Data Science?

Extracting Insights

Extracting insights & knowledge from data using scientific methods, algorithms, & systems.

Decision Making

Make predictions, identify patterns, & support decision-making based on data.

Preparation of Data

Collection, cleaning & preparation of data

03

01

02

6 of 20

Why Data Science?

Create predictive models

03

Can be used in finance, healthcare, & marketing
Make future predictions to make better decisions

Gain valuable insights

02

Used to gain valuable insights from data
Organizations can make better decisions
Cost savings, increased efficiency

High demand for professionals

01

Growing field
Most in-demand skills in job market

Gain a competitive advantage

04

Competitive advantage because of valuable insights
Improve products, services, or operations

Data science is a growing field with high demand for professionals. It is one of the most in-demand skills in today's job market, and the demand is expected to continue to grow in the coming years.
Data science can be used to gain valuable insights from data, which can help organizations make better decisions and improve their operations. This can lead to cost savings, increased efficiency, and new revenue streams.
Data science can be used to create predictive models that can be used in areas such as finance, healthcare, and marketing. These models can be used to make predictions about future events or trends, which can help organizations make better decisions.
Data science can help organizations to gain a competitive advantage by providing them with valuable insights and information that can be used to improve their products, services, or operations.

7 of 20

Career Opportunities

Data Scientist

Analyze & interpret complex data
Identity patterns
Make predictions
Wooks in Finance, healthcare & technology

Data Analyst

Clean, organize and interpret data
Identify patterns & trends in data
Works in finance, healthcare & retail

BI Analyst

Create visual representations of data
Support decision-making within an organization

ML Engineer

Design, develop & implement ML models & algorithm
Create predictive models & improve decision-making
Works in finance, healthcare, & technology

Data Scientist: Data Scientists use statistical and machine learning techniques to analyze and interpret complex data sets, identify patterns, and make predictions. They often work in industries such as finance, healthcare, and technology.
Data Analyst: Data Analysts are responsible for cleaning, organizing, and interpreting data. They use statistical techniques to identify patterns and trends in data, and often work in industries such as finance, healthcare, and retail.
Business Intelligence (BI) Analyst: BI Analysts use data visualization and reporting tools to create visual representations of data, and work to support decision-making within an organization.
Machine Learning Engineer: Machine Learning Engineers design, develop, and implement machine learning models and algorithms. They work in industries such as finance, healthcare, and technology to create predictive models and improve decision making.
Data Engineer: Data Engineers are responsible for designing and building the infrastructure necessary to store, process, and analyze large and complex data sets. They work with Data Scientists and Analysts to ensure that data is properly collected, stored, and prepared for analysis.

8 of 20

Prerequisite to learn Data Science

Mathematical skills

Calculus and linear algebra

Statistics

Probability, statistical inference, & hypothesis testing

DBMS & SQL

Basic knowledge of

Data & DBMS

Programming skills

Python or R

Communication skills

Neet to present their findings to non-technical stakeholders

Note: The prerequisites is not compulsory but good if you already have

Strong mathematical skills, particularly in areas such as calculus and linear algebra.
Familiarity with basic statistics, such as probability, statistical inference, and hypothesis testing.
Programming skills, particularly in languages such as Python or R.
Knowledge of database management systems and SQL.
Familiarity with machine learning concepts and techniques.
Strong problem-solving skills and the ability to think logically.
Strong communication skills, as data scientists often need to present their findings to non-technical stakeholders.
Familiarity with data visualization and reporting tools, such as Tableau or Power BI.
Understanding of cloud computing and big data technologies.

It is important to note that the prerequisites may vary depending on the course or program you are interested in, and some programs may have additional requirements, such as a background in a specific industry or a certain level of work experience.

9 of 20

Hands on Practice - Activity 1 Task 1

Write a Python program to add the marks obtained by four students in two-term examinations which are given in the table below.

You may have to use data structure learned in core Python programming to add and store the total values

Student	Midterm (40)	Annual (60)
1	34	45
2	20	19
3	17	35
4	36	45

10 of 20

Data Science Part I

11 of 20

Objectives

Generate insights using statistical analysis for the given dataset using NumPy

Explain the advantages of using NumPy in Data Analysis

Perform arithmetic operations on Data using NumPy

Access the element for analysis using NumPy

12 of 20

Content Scope

Array Dimension

Zero-dimensional array
One- dimensional array
Two -dimensional array

Accessing array

Indexing
Slicing
Shape, size

Intro to NumPy

What and why NumPy

Array

Creating array using array() method

Mathematical Operation

Addition
Subtraction
Multiplication

Statistical Analysis

Min, max, range
Var, std, mean, median
Q1, Q2, Q3

13 of 20

NumPy prerequisites

Windows user

Installation

Open cmd and type
pip install numpy

Importing

Open IDLE or Jupyter Notebook
import numpy as np

macOS user

Installation

Open terminal and type
pip3 install numpy

Importing

Open IDLE or Jupyter Notebook
import numpy as np

14 of 20

What is NumPy?

1

Library that provides support for large, multi-dimensional arrays and matrices of numerical data

2

Library of mathematical functions

3

Used in scientific and data analysis

4

Used as input and output for other libraries

15 of 20

Terms used in NumPy array

Number of rows and columns in an array - data.shape

Gives the number of element in an array - data.size

Technique to access a particular item

Technique to access a range of values

Shape

Size

Indexing

Slicing

Shape - Attributes (number of rows and columns in an array - data.shape)
Size - Attributes (gives the number of element in an array - data.size)
Indexing - Technique to access a particular item
Slicing - Technique to access a range of values
Indexing is used to access a specific element within an array by specifying the indices of the element. For example, in a 2D array, you can use the format array[row, column] to access a specific element. Indexing can also be used to access elements in a multi-dimensional array by specifying the indices of the element in each dimension.
Slicing is used to access a sub-array (range) within an array by specifying a start and stop index along each dimension. This creates a "view" of the original array, rather than creating a new copy of the sub-array. The format for slicing is array[start:stop:step]

16 of 20

Activity 1 - Task 2

Matrix A describes how many hours Deki, Dorji, and Karma spent on their English, Math, and Dzongkha homework one night. Matrix B describes how many hours they spent the next night. Write a Python program using NumPy to

Create two arrays out of the matrix given above
Find the dimensions and number of element of an array
Try to access element from first row and second column of day 1
Display only amount of time spent on Dzongkha from the first night
Calculate the total time spent on each subject by three students

17 of 20

NumPy methods for Data Analysis

Analysis

std()

var()

min()

max()

ptp()

mean()

median()

Q1()

Q2()

Q3()

These are 5 number summary
Minimum: The smallest value in the dataset.
Q1: The value that separates the lowest 25% of the data from the rest.
Median & Q2: The middle value of the dataset when it is ordered.
Q3: The value that separates the highest 25% of the data from the rest.
Maximum: The largest value in the dataset.
ptp() - Range (Peak to peak)
Variance is a measure of the spread of a dataset, calculated as the average of the squared differences from the mean. Standard deviation is the square root of the variance, and is used as a measure of the "typical" or "average" deviation from the mean. Both variance and standard deviation are measures of how spread out the data is, but variance is expressed in squared units while standard deviation is expressed in the same unit as the data.
quartiles divide the data into 4 equal parts while percentiles divide the data into 100 equal parts.
For numerical data, the mean and median are commonly used to describe the central tendency of the data. In contrast, mode is often used to describe categorical data, like the most frequent color of cars in a parking lot, the most frequent word in a text, etc.

18 of 20

Demonstration

Installation of NumPy library
Importing the library as alias
Creating NumPy array from Tuple & List
Checking the order (shape) & number of elements (size)
Arithmetic Operation (Addition, Subtraction, Multiplication)
Measures of central tendency (min, max, ptp)
Statistical analysis (std, var, Q1, Q3)

19 of 20

Activity 2

According to the Population and Housing Census of Bhutan, 2017, the population of twenty Dzongkhags is as follows

Calculate the following:

Min population
Max population
Range
Mean population
Median population
Standard deviation
Variance
Q1 & Q3
Make an inference from the result obtained

20 of 20

Thank you for your time