FREE AI Classes in Every City

April 3 – May 7 2023 | FREE 5 -Day Machine Learning Immersion in 150+ Cities in Nigeria
and 50 in Other Countries
 DAY 1: FREE AI Class in Every City 2023

INTRODUCTION TO ARTIFICIAL INTELLIGENCE

● Introduction to Data Scientists Network and AI Invasion
● Artificial Intelligence, Machine Learning, and Data Science.
● Machine Learning Use Cases/Applications
● Introduction to platforms (Anaconda/Jupyter Notebook) and Google Colab
● Brief warmup with python

All Datasets to be used can be found here

Code:
https://colab.research.google.com/drive/1ghjrlQoscUbqNVPckdbOjp77IcJiaCIq?usp=sh
aring

1
Introduction to Data Scientists Network and AI Invasion

2
3
4
5
6
7
8
9
10
11
12
13
14
15
 JOIN OUR COMMUNITY:

https://www.datasciencenigeria.org/ai-communities/

Artificial Intelligence, Machine Learning, and Data Science

Artificial intelligence (AI) is undoubtedly the hottest buzzword today and for all the good
reasons. Over the past decade, AI has truly become a factor of production, with the
potential to introduce new sources of growth and change the way work is done across
industries.
The function and popularity of Artificial Intelligence are soaring by the day. Artificial
intelligence is the ability of a system or a program to think and learn from experience. AI
has significantly evolved over the past few years and has found its applications in almost
every sector.

16
What is Artificial Intelligence?

Artificial intelligence is a technique for having a computer or machines think intelligently

in the same way that a human brain does. AI is achieved through evaluating the cognitive
process and researching the patterns of the human brain. AI is a combination of Machine
Learning techniques and Deep Learning.

What Is Machine Learning?

Machine learning is the subset of artificial intelligence that involves the study and use of
algorithms and statistical models in computer systems to perform specific tasks without
human interaction. Machine learning models rely on patterns and inference instead of
manual human instruction. Almost all tasks that can be completed with a data-defined
pattern or set of rules can be done with machine learning. Machine learning algorithms
can be subdivided into supervised, unsupervised and reinforcement learning.

Supervised learning: In supervised learning, you train your model on a labelled

dataset which means we have both raw input data as well as its results. We split our
data into a training dataset and a test dataset where the training dataset is used to train
our network whereas the test dataset acts as new data for predicting results or to see
the accuracy of our model. Hence, in supervised learning, our model learns from seen
17
results the same as a teacher teaches his students because the teacher already knows
the results. Accuracy is what we achieve in supervised learning as model perfection is
usually high.

Unsupervised learning: In unsupervised learning, the information used to train is neither

classified nor labelled in the dataset. Unsupervised learning studies how systems can
infer a function to describe a hidden structure from unlabelled data. The main task of
unsupervised learning is to find patterns in the data. Once a model learns to develop
patterns, it can easily predict patterns for any new dataset in the form of clusters. The
system doesn’t figure out the right output, but it explores the data and can draw inferences
from datasets to describe hidden s tructures from unlabeled data.

18
Reinforcement learning (RL): Reinforcement learning is an autonomous, self- teaching
system that essentially learns by trial and error. It performs actions with the aim of maximizing
rewards, or in other words, it is learning by doing to achieve the best outcomes. RL can be
positive or negative. It is negative when a particular behavior is strengthened because a
negative condition is stopped of avoided. Positive Reinforcement is defined as when an event,
occurs due to a particular behavior, increases the strength and the frequency of the behavior.
In other words, it has a positive effect on behavior.

What is Data Science?

Data science is an interdisciplinary field that uses scientific methods, processes,
algorithms and systems to extract knowledge and insights from structured and
unstructured data, and apply knowledge and actionable insights from data across a broad
range of application domains. Data science is related to data mining, machine learning
and big data.

Artificial Intelligence Applications

The integration of AI tools with various software and devices is digitizing the world. We
will see the applications of Artificial Intelligence in robotics, healthcare, defence, and many
other sectors below:

● AI in Robotics
The field of robotics involves the designing and creation of automated machines or robots
in such a way that they possess the ability to perform tasks on their own. Nowadays,
robots are becoming more and more advanced and efficient in accomplishing tasks. This
is due to the Artificial Intelligence tools and techniques that are specially designed for the
19
field of robotics. Advanced robots consist of sensors, high-definition cameras, voice
recognition devices, etc.
These robots are capable of learning from their past mistakes and experience and can
adjust the algorithms according to the environment. Artificial Intelligence is an extremely
useful tool for robotic applications. When AI is combined with advanced devices, it can
help in optimizations. It is helpful in enhancing the complex manufacturing process in
industries such as aerospace.
Sample: https://www.youtube.com/watch?v=XuGJqajHAHo

● AI in Defence
Defence is one of the most crucial sectors where Artificial Intelligence is contributing to
nation-building. Security systems can be vulnerable to attacks by hackers, these attackers
would do so to sell private information which can prove to be detrimental to any country.
This is where the involvement of Artificial Intelligence proves to be of great use. The
analysis of large amounts of data becomes easy with the help of Artificial Intelligence.
Tools powered by AI can help find suspicious activity over the system and keep track of
the security of an organisation/nation database. Any alterations in the database by an
unknown source are immediately tracked down for action.
Sample: https://www.analyticsinsight.net/role-of-artificial-intelligence-in-defence/

● AI in Transport
Artificial Intelligence in the transport industry has completely changed the era of travelling.
As the competition in the travel industry is high, there is a need to analyze all the factors
that influence the travel business. These factors are price, seasons, festivals, the number
of travellers, etc.
With the help of predictive analytics, the software can analyze data related to these factors
that impact the cost of transport. Tools powered by AI can help perform predictive
analytics efficiently on the data, like predicting the best prices in specific routes. Another
application of Artificial Intelligence in transportation is route optimization. Businesses like
Uber and Bolt can use Artificial Intelligence in their app to show optimized paths thereby
moving consumers faster from point A to B.
Sample: https://www.youtube.com/watch?v=s_Ze2o8ixNM

● AI in Healthcare
When it comes to healthcare, AI never lags behind. Most healthcare organizations rely on
AI-based software for their day-to-day tasks. These tasks vary from patient diagnosis to
hospital data management. Since large amount of data are generated by the healthcare
industry per day, there emerges a need for AI-based advanced processors that can
extract, manipulate, analyze, and draw some meaningful insights from this data. AI and
ML technologies are doing a fabulous job in the healthcare industry. The AI-based
algorithms fed into the systems are capable enough to spot patterns much more efficiently
20
than humans. AI-based devices also help measure real-time data such as blood pressure,
heartbeat, body temperature, and many more. Sample:
https://www.youtube.com/watch?v=ii-FfE-7C-k

● AI in Marketing
Today, the marketing industry is revolutionized by the applications of Artificial Intelligence.
Various industries such as e-commerce, e-learning, advertising, media, and
entertainment use Artificial Intelligence to boost profitability. Suppose, you are searching
for a product on Amazon. Along with the product, it will also show you the best sellers,
similar products, varieties of the same product, and the ‘Recommended for you’ list of
products.
AI-based algorithms understand the interests of customers and give recommendations to
searches made. An example of such is Netflix.
Sample: https://www.youtube.com/watch?v=FYMjXD3G__Y

● AI in Automotive Industry
The invention of self-driving cars has completely changed the world of automobiles. There
are various companies developing self-driving cars such as Tesla, Google, Bosch,
Nissan, Audi, Volvo, and many more. The self-driving cars are built using a combination
of various technologies, and one of the majorly used technologies is Artificial Intelligence.
A self-driving car uses sensors, cameras, voice detectors, and many other devices. It
analyzes the surroundings by collecting data. The AI-enabled advanced systems used in
the self-driving car will find an optimized path to the destination.
With the help of AI, we can address problems such as traffic accidents, respond to natural
disasters, etc.
Sample: https://www.youtube.com/watch?v=VGGHCH0T_SQ

Other Use Cases

● Voice assistants
This consumer-based use for machine learning applies mostly to smartphones and smart
home devices. The voice assistants on these devices use machine learning to understand
what you say and craft a response. The machine learning models behind voice assistants
were trained on human languages and variations in the human voice, because it has to
translate what it hears into words and then make an intelligent, on-topic response. ●
Dynamic pricing
This machine-based pricing strategy is most known in the travel industry. Flights, hotels,
and other travel bookings usually have a dynamic pricing strategy behind them.
Consumers know that the sooner they book their trip the better, but they may not realize
that the actual price changes are made via machine learning.

21
 ● Email filtering
This is a classic use of machine learning. Email inboxes also have a spam inbox, where
your email provider automatically filters unwanted spam emails. ● Product
recommendations
Amazon and other online retailers often list “recommended products” for each consumer
individually. These recommendations are based on past purchases, browsing history, and
any other behavioral information they have about consumers. This is a great way for
online retailers to provide extra value or upsells to their customers using machine
learning.
● Personalized marketing
Marketing is becoming more personal as technologies like machine learning gain more
ground in the enterprise. Now that much of marketing is online, marketers can use
characteristic and behavioral data to segment the market.
● Process automation
There are many processes in the enterprise that are much more efficient when done using
machine learning. These include analyses such as risk assessments, demand
forecasting, customer churn prediction, and others. Machine learning for process
automation alleviates the timeliness issue for enterprises. Machine learning can even help
with customer loyalty analyses like sentiment analysis.
● Fraud detection
Banks use machine learning for fraud detection to keep their consumers safe, but this can
also be valuable to companies that handle credit card transactions. Fraud detection can
save money on disputes and chargebacks, and machine learning models can be trained
to flag transactions that appear fraudulent based on certain characteristics.
• Generative /Generalized AI
Generative AI is a form of artificial intelligence that can generate new content or output
similar to human-created content. This is achieved by analyzing large amounts of data
using machine learning algorithms, which then create new content based on what they
have learned. E. G Text to Audio, Text to Image, Text to Video

In contrast, Generalized AI is a type of artificial intelligence that can perform a diverse range of
tasks and can adapt to new situations that it has not been specifically programmed for. This
type of AI is also called "human-level AI" because it has the ability to reason, learn, and
understand language like a human. For example Chatgpt

Introduction To Platforms

How to Install and Setup Anaconda

● Anaconda: https://www.anaconda.com/products/individual
● Pandas: https://pandas.pydata.org/
● Jupyter Notebook Installation without Anaconda: https://jupyter.org/
22
Introduction to Google Colab
Colab, or "Colaboratory", allows you to write and execute Python in your browser, with

● Zero configuration required

● Access to GPUs free of charge
● Easy sharing

Whether you're a student, a data scientist or an AI researcher, Colab can make your
work easier. Visit the link below for how to get started
https://colab.research.google.com/

Brief Warmup With Python

Python is a widely-used general-purpose, high-level programming language. It is a
programming language that lets you work quickly and integrate systems more
efficiently.

Data Types In Python And Their Implementation

● Integer: Integers are numerical (number) values that are positive or negative
whole numbers without decimals

23
● String: Characters or texts are known as strings in Python. A string object must
be inside a single or double quote. Otherwise, Python will throw an error.

● Float: Float (floating point) numbers are numbers with a decimal point.

● List: Lists are used to store multiple items in a single variable.

24
 ● Tuple: A tuple in Python is similar to a list. The difference between the two is that
we cannot change the elements of a tuple once it is assigned whereas we can
change the elements of a list.

● Sets: A Sets in Python is similar to a list. The difference between the two is that
set does not allow for duplicate elements whereas duplicate elements are
allowed in a list.

Conditional Statement In Python

● The If Statment: The If statement is the most fundamental decision-making
statement, in which the code is executed based on whether it meets the specified
condition. It has a code body that only executes if the condition in the if statement
is true. The statement can be a single line or a block of code.

25
● The If else statement: This statement is used when both the true and false parts
of a given condition are specified to be executed. When the condition is true, the
statement inside the if block is executed; if the condition is false, the statement
outside the if block is executed.

26
Functions In Python
A function is a block of code that only executes when called. You can pass data, known
as parameters, into a function and the function can return data as a result.

Syntax of a function statement in python

27
References

1. Mitchell, Tom (1997). Machine Learning. New York: McGraw Hill. ISBN 0-07-042807-
7. OCLC 36417892.
2. Machine Learning Use Cases: https://algorithmia.com/blog/machine-learning-
usecases
3. "1. Introduction: What Is Data Science? - Doing Data Science [Book]".
www.oreilly.com. Retrieved 3 April 2020.
4. Top Applications of Artificial Intelligence: Top Applications of Artificial Intelligence(AI)
in 2021 (intellipaat.com)
5. Artificial Intelligence Tutorial for Beginners: Artificial Intelligence Tutorial for Beginners
[Updated 2020] (simplilearn.com)
6. ARTIFICIAL INTELLIGENCE: NEXT FRONTIERS FOR TECHNOLOGY:
https://global.ariseplay.com/amg/www.thisdaylive.com/uploads/ARTIFICIAL-
INTELLIGENCE.jpg
7. Types Of Machine Learning:
https://www.simplilearn.com/ice9/free_resources_article_thumb/TypesOfMachineLear
ning.PNG
8. ChatGPT: https://chat.openai.com/
9. http://web.archive.org/web/20220812165347/https://www.forbes.com/sites/bernardma
rr/2018/10/22/artificial-intelligence-whats-the-difference-between-deep-learning-and-
reinforcement-learning
10.

28
 11. https://mcli.cogdogblog.com/proj/nru/nr.html
12. https://vatsalparsaniya.github.io/ML_Knowledge/Reinforcement
Learning/README.html

Activity
● List other industries where AI can be utilised
● Write a python function called “two_sum” that takes in two arguments(integer) and
calculates the sum of two number
● Write an if-else statement that print “This is a prime number” if the number is
prime, or print out “This is an Ordinary number” if the number is not prime

DAY 2: FREE AI Class in Every City 2023

ANALYZING AND UNDERSTANDING DATA

● Introduction to the AI Invasion Project
● The machine learning development workflow
● Data gathering, cleaning and preparation
● Exploratory data analysis Code:
https://colab.research.google.com/drive/1UF3xnuguwr5_G1c_P_WuMJOECz2ut
kHV?usp=share_link

AI Invasion Project
The AI Invasion project is the last project you must complete before graduating from this
program. The goal of this project is to reinforce what you've learned, put some of the
abilities you've gained into practice, and have a project to show potential employers in
your portfolio.

Skilled needed to complete this project include

1. Knowledge of Python programming

2. Understanding of data preprocessing
3. Familiarity with some machine learning libraries like Pandas, Scikit-learn, etc.

4. A basic understanding of the Zindi platform and how to submit predictions.

29
Do not worry, you will learn these skills and more in this course. The project will focus
on building a machine learning model that can predict the prices of Houses in Nigeria.

Machine Learning Development Workflow

Machine learning workflows define the steps initiated during a particular machine
learning project. The typical phases include data collection, data pre-processing, data
segmentation, model training and refinement, evaluation, and deployment to production.
Kindly note that machine learning workflows vary by project.

Data Collection

Data collection is one of the most important stages of machine learning workflows.
During data collection, you are defining the potential usefulness and accuracy of your
project with the quality of the data you collect.

To collect data, you need to identify your sources and aggregate data from those
sources into a single dataset. This could mean streaming data from the Internet,
downloading open-source data sets, or constructing a data lake from assorted files,
logs, or media.

30
Data Pre-Processing

Once your data is collected, you need to pre-process it. Pre-processing involves
cleaning, verifying, and formatting data into a usable dataset. If you are collecting data
from a single source, this may be a relatively straightforward process. However, if you
are aggregating several sources you need to make sure that data formats match, that
data is equally reliable, and remove any potential duplicates.

Data Segmentation

This phase involves breaking processed data into three datasets—training, validating,
and testing:

● Training set— used to initially train the algorithm and teach it how to process
information. This set defines model classifications through parameters.
● Validation set— used to estimate the accuracy of the model. This dataset is used
to finetune model parameters.
● Test set— used to assess the accuracy and performance of the models. This set
is meant to expose any issues in the model.

Training And Refinement

Once you have datasets, you are ready to train your model. This involves feeding your
training set to your algorithm so that it can learn appropriate parameters and features
used in classification.

Once training is complete, you can then refine the model using your validation dataset.
This may involve modifying or discarding variables and includes a process of tweaking
model-specific settings (hyperparameters) until an acceptable accuracy level is
reached.

Machine Learning Evaluation

Finally, after an acceptable set of hyperparameters is found and your model accuracy is
optimized you can test your model. Testing uses your test dataset and is meant to verify
that your models are using accurate features. Based on the feedback you receive you
may return to training the model to improve accuracy, adjust output settings, or deploy
the model as needed.

Machine Learning Deployment.

31
Deployment of machine learning models, or simply, putting models into production,
means making your models available to other systems within the organization or the
web so that they can receive data and return their predictions.

Data Gathering, Cleaning And Preparation

Open Source Dataset

These are lists of some of the publicly available datasets you can work with as a data
scientist
● AFRIFASHION40000: AFRIFASHION40000 is an openly available dataset of
African fashion images generated using Generative Adversarial Networks
(GANs) and created by Data Science Nigeria. Link:
https://bit.ly/DSN_AFRIFASHION40000
● Data.gov: It consists of a variety of datasets from US Government agencies.
Domains include Education, Climate, Food, Chronic disease and so much more.
Link: https://www.data.gov/
● UCI Machine Learning Repository: This site consists of datasets hosted by the
University of California, Irvine. It has a collection of about 400+ datasets aimed
toward the Machine Learning community. Link:
http://archive.ics.uci.edu/ml/index.php
● Google Public Datasets: Google has hosted tons of datasets on Google Public
Datasets which is basically their Cloud Platform. You can browse through their
dataset collection using BigQuery. The first 1 Terabyte of queries you make are
basically free. Link: https://cloud.google.com/bigquery/public-data/
● Datasets on Github: It hosts tons of awesome datasets. This GitHub boasts a
variety of datasets such as Climate Data, Time Series data, Plane crash data etc.
Feel free to dig in. Link: https://github.com/awesomedata/awesome-
publichttps://github.com/awesomedata/awesome-public-datasetsdatasets
● For more datasets, you can check the link below:
https://medium.com/analyticshttps://medium.com/analytics-vidhya/top-100-open-
source-datasets-for-data-science-cd5a8d67cc3dvidhya/top-100-open-source-
datasets-for-data-science-cd5a8d67cc3d

The Data Cleaning Process

Data cleaning is the process of fixing or removing incorrect, corrupted, incorrectly

formatted, duplicate, or incomplete data within a dataset. When combining multiple data
sources, there are many opportunities for data to be duplicated or mislabeled. Most raw
data, whether text, images, video – often even data stored in spreadsheets – is
improperly formatted, incomplete, or downright dirty and needs to be properly cleaned
and structured before you begin your analysis. Here are some steps to make sure your
data is clean and ready to go.
32
 ● Remove irrelevant data.
● Deduplicate your data
● Fix structural errors.
● Deal with missing data
● Filter out data outliers
● Validate your data.

Exploratory Data Analysis

Exploratory Data Analysis refers to the critical process of performing initial
investigations on data so as to discover patterns, spot anomalies, test hypotheses and
check assumptions with the help of summary statistics and graphical representations.

The importance of performing EDA are:

● Helps identify errors in data sets.

● Gives a better understanding of the data set.
● Helps detect outliers or anomalous events.
● Helps understand data set variables and the relationship among them

References

Data Cleaning Steps & Process to Prep Your Data for Success. (2021, June 3).

MonkeyLearn. Retrieved April 11, 2022, from

https://monkeylearn.com/blog/datacleaning-steps/
33
 Guide, S. (2021, November 11). What is Exploratory Data Analysis? Steps and

Market Analysis. Simplilearn. Retrieved April 6, 2022, from

https://www.simplilearn.com/tutorials/data-analytics-tutorial/exploratory-

dataanalysis

Guide To Data Cleaning: Definition, Benefits, Components, And How To Clean Your

Data. (n.d.). Tableau. Retrieved April 6, 2022, from

https://www.tableau.com/learn/articles/what-is-data-cleaning

Patil, P. (2018, March 23). What is Exploratory Data Analysis? | by Prasad Patil.

Towards Data Science. Retrieved April 6, 2022, from

https://towardsdatascience.com/exploratory-data-analysis-8fc1cb20fd15

Activity

- Using Pandas download and load a dataset from one of the open-source
datasets
- Perform EDA on the titanic dataset. You can download the dataset using

“pd.read_csv(https://raw.githubusercontent.com/datasciencedojo/
datasets/master/titanic.csv)”

34
 DAY 3: FREE AI Class in Every City 2023

SUPERVISED LEARNING: INTRODUCTION TO REGRESSION

ANALYSIS
● What is Linear Regression
● How Linear Regression Works
● Steps involved in working on a regression problems
● Other machine learning algorithms

Dataset here: Download in class dataset here Code:

https://colab.research.google.com/drive/1QNttKlwht7ZC6tDqa_Vn_nJ7arzIQ-
O7?usp=share_link

Supervised Learning
Supervised Learning can be subdivided into Regression and Classification. Regression and
Classification are both parts of a class of Machine Learning Algorithms called “Supervised
Learning Algorithms”. Remember that Machine Learning is all about generating future
occurrences/predictions of an event while making reference to past occurrences of the event in
question. And for this particular class of Machine Learning(Supervised learning), we have
labelled data with known examples with which the algorithm is trained to predict unknown data.

35
Classification: A classification classifier (model) is the type of model in which the output
variable (i.e the Label) is Discrete. For example:

● Predict if the patient has cancer or not. [Label: Caner and Not cancer (2)]
● Predict if an employee will leave or stay [Label: Leave and Stay (2)] ● Predict if an email
is spam or not. [Label: Spam and Not Spam (2)]

Regression: A Regression model is the type of model in which the output variable is continuous.
For example:

● Predict the price of a house in an area. [Label: Price of a house ]

● Predict how much rainfall will occur in an area. [Label: Rainfall measurement ]

Similarities:
- Both belong to the class of Machine Learning Algorithms called “Supervised
Learning”.
- Both model a problem by learning a mapping function/relationship from the
input(X) to the output(Y), using known examples.

36
Differences:

Property Regression Algorithms Classification Algorithms

Output/Target Variable Predicts a continuous real Predicts a class/discrete

value values

Learning function A line of best fit A decision boundary

Evaluation metrics/Loss Mean Squared Error, Mean Accuracy, F1 score, Area

functions Absolute Error, Root Mean under the curve
Squared Error

Regression is a predictive statistical process where the model attempts to find the important
relationship between dependent and independent variables. The goal of a regression algorithm
is to predict a continuous number such as sales, income, and test scores.

First, we will have a quick introduction to building models in Python, and what better way to start
than one of the very basic models, linear regression? Linear regression will be the first algorithm
used and you will also learn more complex regression models.

What is Linear Regression?

Linear Regression is considered the most natural learning algorithm for modelling data, primarily
because it is easy to interpret and models efficiently for most natural problems. It belongs to the
family of “Linear Models/Predictors” in machine learning (one of the most useful hypothesis
spaces)

37
The Mathematical Theory Of Linear Regression
Mathematically, the linear regression model can be defined by a dependent variable ’Y’, also
called the regressand and an independent variable(or set of independent variables) ’X’, also
called the regressor(s), and a sample space ’n’.

Steps Involved In Working On Regression Problems

Step#1 Importing the required libraries
Step#2 Loading the dataset
Step#3 Clean the dataset
Remove irrelevant data
Deduplicate your data
Fix structural errors
Deal with missing data
Filter out data outliers
Validate your data
Step#4 Perform data segmentation
Step#5 Load your data into the Linear Regression model i.e Train your model
Step#6 Make predictions Step#7 Evaluate your model.

Other Machine Learning Algorithms

- Decision Tree
- Support Vector Machine
- XGBoost
38
References

Brownlee, J. (2017, December 11). Difference Between Classification and

Regression in Machine Learning. Machine Learning Mastery. Retrieved April 6,

2022, from https://machinelearningmastery.com/classification-versus-

regressionin-machine-learning/

Introduction to Machine Learning for Beginners | by Ayush Pant. (n.d.). Towards

Data Science. Retrieved April 6, 2022, from

https://towardsdatascience.com/introduction-to-machine-learning-for-

beginnerseed6024fdb08

Singh, R. (n.d.). Step-by-Step Regression Analysis. What is Regression

Analysis? | by Great Learning. Medium. Retrieved April 6, 2022, from

https://medium.com/@mygreatlearning/step-by-step-regression-

analysisf7e3e3ebf296

Activity
- Build a machine learning algorithm

DAY 4: FREE AI Class in Every City 2023

SUPERVISED LEARNING: INTRODUCTION TO REGRESSION

ANALYSIS
● Building a prediction model
● Evaluating machine learning models
● Exporting predictions of machine learning models
39
Code: https://colab.research.google.com/drive/1F-
9Ku6kzuPKJRc_cMWchXac0i_TwaOzn

Building A Prediction Model

Class Activity
Build a Regression Machine Learning Model using Mama Tee restaurant dataset.
The objective of the regression task is to predict the amount of tip (gratuity in Nigeria
naira) given to a food server based on total_bill, gender, smoker (whether they smoke in
the party or not), day (day of the week for the party), time (time of the day whether for
lunch or dinner), and size (size of the party) in Mama Tee restaurant.

Dataset: Download Tips.csv dataset here

Evaluating Machine Learning Models

Model evaluation is very important in data science. It helps you to understand the
performance of your model and makes it easy to present your model to other people.
There are many different evaluation metrics out there but only some of them are
suitable to be used for regression. This lesson will cover the different metrics for the
regression model and the difference between them.
By the end of this lesson, you will understand which evaluation metrics to apply to your
future regression model.

There are 3 main metrics for model evaluation in regression:

1. R Square/Adjusted R Square
2. Mean Square Error(MSE)/Root Mean Square Error(RMSE)
3. Mean Absolute Error(MAE)

R Square/Adjusted R Square
R Square is calculated by the sum of the squared of prediction error divided by the total
sum of the square which replaces the calculated prediction with mean. R Square value
is between 0 to 1 and a bigger value indicates a better fit between prediction and actual
value.
R Square is a good measure to determine how well the model fits the dependent
variables. However, it does not take into consideration of overfitting problem.

40
Mean Square Error(MSE)/Root Mean Square Error(RMSE)
MSE is calculated by the sum of the square of prediction error which is real output
minus predicted output and then divide by the number of data points. It gives you an
absolute number on how much your predicted results deviate from the actual number.
You cannot interpret many insights from one single result but it gives you a real number
to compare against other model results and help you select the best regression model.

Root Mean Square Error(RMSE) is the square root of MSE. It is used more commonly
than MSE because firstly sometimes MSE value can be too big to compare easily.
Secondly, MSE is calculated by the square of error, and thus square root brings it back
to the same level of prediction error and makes it easier for interpretation.

Mean Absolute Error (MAE)

Mean Absolute Error(MAE) is similar to Mean Square Error(MSE). However, instead of
the sum of the square of error in MSE, MAE is taking the sum of the absolute value of
error.
Compare to MSE or RMSE, MAE is a more direct representation of the sum of error
terms. MSE gives larger penalization to big prediction errors by squaring them while
MAE treats all errors the same.

Implementation Of The Model Evaluation Using Sklearn

R Square/Adjusted R Square
41
Mean Square Error(MSE)/Root Mean Square Error(RMSE)

Mean Absolute Error(MAE)

42
Exporting Predictions Of Machine Learning Models
At last, you're ready to submit some predictions for scoring. You can write your
predictions to a CSV file using the .to_csv() method on a pandas DataFrame.

References

Smith, I. (2020, May 23). 3 Best metrics to evaluate Regression Model? | by

Songhao Wu. Towards Data Science. Retrieved April 6, 2022, from

https://towardsdatascience.com/what-are-the-best-metrics-to-evaluate-

yourhttps://towardsdatascience.com/what-are-the-best-metrics-to-evaluate-your-

regression-model-418ca481755bregression-model-418ca481755b
43
Activity
- Build an XGBoost Model suing the tips.csv dataset

DAY 5: FREE AI Class in Every City 2023

REVISION AND AI INVASION COMPETITIONS

● In Class Exercise: Nigerian Housing Price Prediction
■ Download Dataset here
● Introduction to Zindi and how to make a submission
● Going further with deep learning

Introduction To Zindi And How To Make A Submission

How To Sign Up On Zindi Steps:

1. Visit the site: https://zindi.africa/

2. Click on ‘Join Zindi”

3. Fill in the necessary details as required and choose a recognizable ‘username’.

44
4. Click on the sign-up bottom
5. An email will be sent to your mailbox for account confirmation. 6. Next, re-visit
the site: https://zindi.africa/ 7. Click on sign-in.

8. Enter your “username” and Password”

45
How To Join A Competition On Zindi

1. On signing in, the following webpage is displayed.

2. Click on the “Compete Tab”
3. Zindi provides different categories of competition:

- Prize competition: you win prize money if you are among the top 3 winners
of a particular competition.
- You win points: Points increase your ranking among other data scientists
on the platform.
- You gain knowledge: Knowledge competitions are where you can learn
and increase your skillset.
4. Navigate to the hackathon of choice.
5. The competition page provides some information to help you understand the
problem you are going to solve, by reading the problem statement, how you can
participate and how to submit your solution on the platform.
6. On The competition page, the following tab can be found;
1. Info: The info tab contains the problem statements of the competition
and a list of organizations that have either provided the dataset or funded
the competition. On the left side, you can see a list of vertical tabs that
provide more information about the competition.

(a) Description

- It provides the problem statement of the competition and a list of

organizations or companies that supported the competition, either
by providing the datasets or funding the competition.
46
 - We suggest you read the description of this competition in order to
understand the problem and machine learning approach you can
choose to solve it. If you read the description, you will understand
that the objective of this competition is to create a machine learning
model to predict which individuals are most likely to have or use a
bank account.

(b) Rules

- Each competition has its own rules. Breaking the rules can lead to
disqualification, so make sure to carefully read and understand all

the rules of the competition.

(c) Prizes

- Now, this is the best part: the prize section provides details about
the prize money that will be provided for the first, second and third
place winners of the competition. But remember not all competition
provides prize money for its winners; in other competitions, you can
get Zindi points or gain knowledge.

(d) Evaluation

- Each competition has its own evaluation metric that will be used to
evaluate your results and rank you on the leaderboard. It also
shows how you should prepare your submission file before
uploading your file on the platform.

- For this competition, the evaluation metric will be the percentage of

survey respondents for whom you predict the binary ‘bank account’
classification incorrectly.

(e) Timeline

47
 - This section provides information about the start date of the
competition and the end date and time of the competition. If you
submit your solution after the deadline you will receive a score but it
will not reflect on the leaderboard. Make sure to submit before the
deadline if you want to be considered for a prize.

- This competition has been reopened as a knowledge challenge,

this means it will not close.

2. Data

- The data tab contains a description of the dataset you are going to
use for this competition. On the right side of the page, you can see
a list of links to download the dataset and other important files. You
will download:

- VariableDefinition.csv — This file contains a definition of each

variable in the train and test data.
- SubmissionFile.csv — The file contains a sample of how the
submission file should look like.
- Test.csv — This is a test data file you will use for prediction and
save your results in the submission file.
- Train.csv - This is a train data file that contains both the
independent variable and the target one. You will use this dataset
to train your model.
- These files may differ between competitions. Also, keep in mind
that you must join the competition in order to have access to the
data files.

3. Discussion

- We're not Liverpool FC fans but we like their slogan: “You will never
walk alone”. That is the purpose of the discussion page, you don’t
need to walk alone throughout the competition. If you face any
challenge or uncertainty during the competition or you want to ask a
question to understand more about the dataset provided, you can
post on the discussion page and other data scientists enrolled in
the competition can help you to solve the problem.

48
 - The discussion board is very active and full of knowledgeable and
helpful African data scientists willing to assist you.

4. Leaderboard

- After you have uploaded your submission file, you will appear on
the leaderboard. The leaderboard shows your position among all
enrolled data scientists in the competition. Your position will depend
on your performance after your solution has been evaluated. For
this competition, you can submit ten times a day.

5. Team

- You don’t want to do the competition on your own? That’s OK! You
can create a team with fellow data scientists enrolled in the
competition and work together. The maximum number for a team is
4 members. Remember that sharing code between individuals is
not allowed, so if you want to share code with someone else, they
must be on the same team as you.

49
 6. Submission

- The submission page is where you will upload your submission file,
by clicking the orange button at the top right side of the page. After
you have uploaded your solution, it will be evaluated according to
the evaluation metric specified in the competition. Then you will see
the score that will define your position on the leaderboard.

What Is Deep Learning?

Deep learning is a subset of Machine Learning using the approach of neural networks.
This branch works with algorithms built with the aim of mimicking the structure and
function of the human brain.

Key Features of a deep learning algorithm

The three main components of a deep learning network are;
- Input Layer: The input, the first layer carrying information/features about the data.
- Hidden Layers: this can be one or more, connecting the input and output layer..

50
- Output Layer: where the expected output is obtained.

A node/ neuron; is a single unit in the network that receives information from other
neurons. It is the basic building block of a neural network and is also referred to as ‘the
learning unit’.

The image below shows how a deep learning model works at a glance

51
Key difference between Deep Learning and machine learning;

Use case of deep learning models"

1. Game-playing and decision making (backgammon, chess, racing)
2. Pattern recognition (radar systems, face identification, object recognition),
3. Sequence recognition (gesture, speech, handwritten text recognition)
4. medical diagnosis
5. Financial applications

52