NATIONAL INSTITUTE OF ELECTRONICS AND INFORMATION TECHNOLOGY

Sumit Complex, A-1/9, Vibhuti Khand, Gomti Nagar, Lucknow,

Setting Up User Accounts

Machine Learning using Python

1 Day 10
 Course: Machine Learning using Python
Module: Day 10
2 Index
 Traditional Programming  Affinity Grouping
 Machine Learning  Clustering
 How ML works?  References
 What is requirement of Machine Learning Probl
em:
 From where to get Data?
 Types of Machine Learning Problems
 Regression/ Estimation
 Classification
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
3 Traditional Programming
 Traditional Programming refers to any manually created program that uses input data and runs
on a computer to produce the output. Traditional programming is a manual process—meaning a
person (programmer) creates the program. But without anyone programming the logic, one has to
manually formulate or code rules.
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
4 Traditional Programming
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
5 Machine Learning
 Machine Learning is a subset of Artificial Intelligence (AI) that provides systems the ability to
automatically learn and improve from experience without being explicitly programmed.


 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
6 Machine Learning
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
7 Machine Learning
 We feed in DATA (Input) + Output, run it on machine during training and the machine creates its
own program (logic), which can be evaluated while testing.
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
8 How ML works?
 Data Gathering: Gather the data in any form suitable for processing. The better the quality of data,
the more suitable it will be for modeling.
 Data Processing – Sometimes, the data collected is in the raw form and it needs to be pre-processed.
 Example: Some tuples may have missing values for certain attributes. Missing values have to be filled
with suitable values in order to perform machine learning.
 Missing values for numerical attributes such as the price of the house may be replaced with the mean
value of the attribute whereas missing values for categorical attributes may be replaced with the
attribute with the highest mode.
 Divide the input data into training set and test sets.
 Building models with suitable algorithms and techniques on the training set.
 Testing and evaluating its performance using metrics such as confusion matrix or Mean Absolute Error.
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
9
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
10 What is requirement of Machine Learning Problem:
 The first requirement of Machine Learning is training data set. It is the actual data set used
to train the model for performing various actions.
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
11 From where to get Data?
 Training data set can be accessed from various sources. Some of sources are:
 UCI Repository: https://archive.ics.uci.edu
 Kaggle web site: https://www.kaggle.com/datasets
 United Nations: http://data.un.org/
 India: https: //data.gov.in/
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
12 Types of Machine Learning Problems
 Regression or Estimation
 Classification
 Affinity Grouping
 Clustering
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
13 Regression/ Estimation
 Calculated approximation of a continuous variable

For Example:
 Estimated household income for loan processing or credit card limit etc.
 Estimated Crop production in an area
 Estimated traffic at a place
 Estimated future requirement for saving/investment
 Admission Prediction
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
14 Regression Problem
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
15 Classification
 Examining the feature of a newly presented object and assigning it to one of the predefined
classes.

For Example:
 Classifying loan applications as Low, Medium and High Risk
 Assigning product into Categories and sub-categories
 Classifying people as BPL etc.
 Text classification
 Image classification
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
16 Classification Problem
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
17 Classification Problem
 Example 2: Classification of House cost as Low, Medium or High.
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
18 Affinity Grouping
 Which things go together?
 To understand the purchase behaviour of customers
 Market Basket Analysis

For example:
 If someone buys a book on Data Science, it is most likely that he will also buy some book on
Python.
 If someone buys Milk, he may buy bread or cornflakes.
 Course:
Course: NIELITLearning
Machine ‘O’ Levelusing
(IT) Python
Module:
Module: DayM2-R5:
10 Introduction to ICT Resources
19 Clustering
 Segmenting heterogeneous group of population into a more homogenous sub groups or clusters.

For Example:
 Customer segmentation according to buying behavior
 Creating cluster of patients with similar symptoms to identify deceases
 Course: Machine Learning using Python
Module: Day 10
20 References
• Wikipedia.org

• Tutorialspoint.com

• https://www.geeksforgeeks.org/

• https://www.kaggle.com/

• https://github.com/
 Course: Machine Learning using Python
Module: Day 10
21

Thank
You ! ! !