Data Science Basics: Data Collection, Storage, and Cleaning
INTRODUCTION
Think about what happens every time you buy airtime on your phone. In a matter of seconds, the telecom company — whether MTN, Airtel, or Glo — records your phone number, the amount you recharged, the time of the transaction, and your location. Now imagine millions of Nigerians doing this same thing every single day. That enormous pile of recorded facts is what we call data — and managing it properly is exactly what data science is all about.
Data science is one of the fastest-growing fields in the world today, and Nigeria is no exception. From how hospitals in Lagos track patient records to how WAEC stores and releases examination results, data sits at the centre of almost every important decision made around us. Understanding how that data is collected, stored, and cleaned is not just a school topic — it is a life skill for anyone living in the modern world.
This lesson introduces you to the three foundational steps of data science: data collection, data storage, and data cleaning. These may sound technical, but by the time you finish reading, you will see that they connect directly to things you already experience every day.
LEARNING OBJECTIVES
By the end of this lesson, students should be able to:
A. Define data science and explain its importance in everyday life with reference to Nigeria. B. Identify and describe at least four methods of data collection, giving appropriate local examples. C. Explain the different types of data storage and compare their advantages and limitations. D. Identify common data quality problems found in real datasets. E. Describe the steps involved in cleaning a dataset. F. Discuss ethical and privacy issues related to data collection and use in Nigeria.
WHAT IS DATA SCIENCE?
Before we dive in, let us make sure the key terms are clear.
Data refers to raw facts and figures — numbers, names, dates, images, or sounds — that have not yet been organised or given meaning. Data on its own tells you very little. A number like "78" means nothing until you know it is a student's score in a Mathematics test.
Information is what you get after data has been processed and given context. "The class average score in Mathematics is 78 out of 100" is information.
Data science is the field that deals with how to collect, organise, analyse, and interpret data in order to find useful patterns and support smart decision-making. It combines ideas from mathematics, statistics, and computer technology.
A data scientist is someone who works with data professionally — finding it, cleaning it, analysing it, and presenting what it means in a way others can understand and use.
PART ONE: DATA COLLECTION
Data collection is the process of gathering raw facts from different sources for a specific purpose. It is the very first step in any data science project. Without good data collection, everything that follows — storage, cleaning, and analysis — is built on a shaky foundation.
Why does data collection matter so much? Consider the National Population Commission (NPC) trying to plan how many primary schools, hospitals, and water sources a state needs. Without first counting how many people actually live there, any plan would be a guess. Data collection turns guesswork into evidence.
Methods of Data Collection
There are several ways to collect data, and the right method depends on what you are trying to find out and who your audience is.
Surveys and Questionnaires
A survey is a set of written or digital questions given to a group of people to gather their opinions, habits, or experiences. It is one of the most common data collection methods in schools and research institutions.
Nigerian example: Your school distributes a printed form asking students about how far they travel to school, how many hours they study each day, and whether they have internet access at home. The answers help the school understand its students better and plan improvements.
Observation
This involves a researcher watching and recording events as they happen, without necessarily asking questions. It is especially useful when you want to capture behaviour naturally.
Nigerian example: A traffic officer stationed at Ikeja Along counts the number of commercial buses, keke napeps, and private cars that pass a particular point every hour. This data helps the state government decide where to install traffic lights or build flyovers.
Interviews
An interview is a direct conversation between a researcher and an individual. It allows for more detailed and personal responses than a questionnaire. Interviews are widely used in health and social research.
Nigerian example: UNICEF health workers visiting homes in Kano ask mothers detailed questions about whether their children have received all recommended vaccines. This helps them identify gaps in immunisation coverage across different local government areas.
Sensors and Automated Systems
Electronic sensors collect data automatically without human involvement. They are increasingly common in technology-driven environments.
Nigerian example: Weather stations operated by the Nigerian Meteorological Agency (NiMet) in Abuja, Port Harcourt, and other cities automatically record temperature, humidity, wind speed, and rainfall every hour. This data is used to produce weather forecasts that farmers and aviation authorities rely on.
Web Scraping and Online Data Sources
Web scraping involves using computer programs to automatically gather data from websites. It is common in business and market research.
Nigerian example: A researcher writes a program that collects the prices of common food items from Jumia and Konga every week. Over time, this data helps track inflation and price trends across different product categories.
Existing Records (Secondary Data)
Sometimes, the data you need has already been collected by someone else. Using data from existing sources is called collecting secondary data.
Nigerian example: A student writing a project on academic performance trends uses WAEC's published results from 2015 to 2024. The student did not conduct any survey — the data already existed and was publicly available.
Primary Data vs. Secondary Data
It is important to understand the difference between primary and secondary data, as this often comes up in examinations.
Primary data is data you collect yourself, directly from the source. It is specific to your research question but takes more time and resources to gather.
Secondary data is data that was collected by someone else for a different purpose but is still useful for your research. It is faster and cheaper to access but may not perfectly match what you need.
Examples of secondary data in Nigeria include reports published by the National Bureau of Statistics (NBS), the Central Bank of Nigeria (CBN), or the Federal Ministry of Health.
PART TWO: DATA STORAGE
Once data has been collected, it must be stored somewhere safe so it can be used later. Think of data storage the same way you think of keeping your exercise books — if you have no system for organising and protecting them, you will lose important work.
Data storage refers to the methods and technologies used to keep collected data available, secure, and retrievable when needed.
Types of Data Storage
Physical Storage
This includes paper records, printed forms, and files kept in physical cabinets or folders. Many government offices, clinics, and small businesses in Nigeria still rely heavily on paper records.
The advantage of physical storage is that it does not require electricity or internet to access. The disadvantages, however, are significant. Paper records take up a lot of space. They are vulnerable to fire, flooding, termites, and theft. Searching through hundreds of paper files for a single record can take hours.
Local Digital Storage
Local digital storage means saving data on devices you can physically hold — a computer hard drive, a USB flash drive, an external hard disk, or a DVD disc.
Nigerian example: A school that saves all student records in a Microsoft Excel spreadsheet on the school computer is using local digital storage. This is faster, more organised, and takes up far less space than paper. The major risk is that if the computer is damaged, stolen, or the drive fails without a backup, the data can be lost permanently.
Cloud Storage
Cloud storage means your data is saved on remote servers owned and managed by technology companies, and you access it through the internet. You do not need to carry a physical device — your data is accessible from anywhere with a working internet connection.
Popular cloud storage platforms include Google Drive, Microsoft OneDrive, and Dropbox. Many Nigerian schools and organisations are gradually adopting cloud storage for its flexibility and built-in backup systems.
Nigerian example: A teacher who saves lesson notes to Google Drive can access the same files from their phone in Enugu or their laptop in Lagos, as long as they have internet access.
Databases
A database is an organised electronic system for storing, managing, and retrieving large volumes of data efficiently. Databases are used when the data is too large or complex for a simple spreadsheet.
Nigerian example: A commercial bank like Zenith Bank or GTBank stores millions of customer records — names, account numbers, transaction histories, and addresses — in a database. When you check your balance at an ATM, the machine queries the bank's database and retrieves your specific record in seconds.
Common database systems include MySQL, Microsoft SQL Server, and Oracle. Students who go on to study computer science or information technology will encounter these tools in detail.
Properties of Good Data Storage
Whether you are storing data on paper, a hard drive, or the cloud, good storage should have the following qualities:
Security — Only authorised people should be able to access the data. Backup — Copies of data should be kept so that if one copy is lost, another is available. Accessibility — Authorised users should be able to find and retrieve the data quickly. Integrity — Data should remain accurate and unchanged over time. Scalability — The system should be able to handle more data as it grows.
PART THREE: DATA CLEANING
Here is something that surprises most people when they first learn about data science: professional data scientists say they spend between 60 and 80 percent of their total working time not on analysis — but on cleaning data. That single fact tells you just how important this step is.
Data cleaning, sometimes called data wrangling or data scrubbing, is the process of detecting and correcting — or removing — errors, inconsistencies, and irrelevant entries in a dataset before it is analysed. Raw data collected from the real world is almost never perfect. People make mistakes when entering data. Equipment records things incorrectly. Formats are inconsistent. The job of data cleaning is to fix all of that before the analysis begins.
Common Data Problems
Missing values: A respondent skips a question on a form, leaving a field empty. For example, a student fills in a school survey but does not enter their age. That empty cell is a missing value.
Duplicate entries: The same record appears more than once. This often happens when data from two sources is combined, or when a person submits a form twice. For example, a hospital database might have the same patient registered twice with slightly different spellings of their name.
Inconsistent formats: The same type of information is written in different ways in the same dataset. Phone numbers, for instance, might appear as "08031234567" in one row, "0803-123-4567" in another, and "+2348031234567" in a third row — all referring to the same format but written differently.
Typos and spelling errors: "Lagoss", "Lagoa", and "Lagos" all appear in a column for city names. Only one is correct, and the others need to be fixed.
Outliers: A data point that is far outside the expected range. If a student's test score is recorded as 890 out of 100, that is clearly an input error and must be investigated.
Wrong data types: A date entered as plain text — for example, "Fourteen March" — instead of a proper date format like 14/03/2024. Computers cannot process text as a date for calculations.
Steps in Data Cleaning
Step 1: Understand your data first. Before fixing anything, look at the dataset carefully. Know what each column represents and what values are expected. You cannot fix what you do not understand.
Step 2: Find and handle missing values. Decide whether to fill in the missing value using a logical estimate (such as the average of other values in that column), or to remove the entire row if it is too incomplete to be useful.
Step 3: Remove duplicates. Identify rows that represent the same real-world record and delete the extras. Most spreadsheet programs, including Microsoft Excel and Google Sheets, have a built-in Remove Duplicates function.
Step 4: Standardise formats. Make sure dates, phone numbers, names, and addresses all follow the same format throughout the entire dataset.
Step 5: Correct errors and outliers. Fix obvious typos, correct impossible values, and investigate any entries that look suspicious before deciding what to do with them.
Step 6: Validate the cleaned data. Go through the dataset one final time to confirm that all problems have been resolved and the data is ready for analysis.
A useful way to remember this is the phrase used in data science: garbage in, garbage out. No matter how advanced your analysis is, if the data going in is dirty, the results coming out will be unreliable.
ADVANTAGES AND DISADVANTAGES OF DIGITAL DATA MANAGEMENT
Advantages:
- Large volumes of data can be stored in a very small physical space.
- Data can be retrieved almost instantly using search functions.
- Data can be shared across long distances within seconds.
- Backup systems can protect against accidental loss.
- Digital data enables analysis that would be completely impossible to do by hand.
Disadvantages:
- Digital data is vulnerable to cybercrime, hacking, and unauthorised access.
- Power outages and system failures can disrupt access.
- Setting up and managing digital systems requires technical knowledge.
- Cloud-based storage depends on internet access, which is still unreliable in many parts of Nigeria.
- If personal data is mishandled, it can violate people's privacy and trust.
PRACTICAL APPLICATIONS IN NIGERIA
Data science is not just a theory you study in class. It is actively shaping life across Nigeria every day.
Healthcare: Hospitals like Lagos University Teaching Hospital (LUTH) use patient databases to track disease patterns, manage bed availability, and plan resources during health emergencies.
Banking and Finance: Banks use transaction data to detect fraudulent activity, offer personalised loan products, and track spending patterns for millions of customers.
Agriculture: Agri-tech companies working across Nigerian states collect data on rainfall, soil quality, and crop yields to give farmers practical recommendations that improve harvests.
Education: WAEC collects and analyses millions of examination results annually to assess academic performance trends, identify subjects where students struggle, and guide curriculum reviews.
Transport: Ride-hailing apps operating in Lagos, Abuja, and Port Harcourt use real-time trip data to set prices, assign drivers, and identify the busiest routes at different times of day.
Government and Elections: INEC manages voter registration data for over 90 million registered Nigerians, using this data to plan polling unit locations, ballot quantities, and election logistics across 36 states and the FCT.
ETHICAL AND SAFETY CONSIDERATIONS
With the increasing power of data comes the responsibility to use it properly. Here are some of the most important ethical principles every student should understand.
Consent: You should always inform people when you are collecting their data and obtain their permission before doing so. Collecting someone's personal information secretly is unethical and, in many cases, illegal.
Purpose limitation: Data should only be used for the specific reason it was collected. If a student's phone number was given for a class group chat, using it to send them unsolicited marketing messages is a misuse of their data.
Privacy: Personal data — including names, addresses, financial details, and health records — must be protected from unauthorised access and disclosure. The Nigeria Data Protection Act (NDPA), signed into law in 2023, gives every Nigerian citizen rights over their personal data and places obligations on organisations that collect and process it.
Accuracy: Decisions made using data can have serious consequences for people's lives. This is why accuracy in data collection and cleaning is not just a technical concern — it is an ethical one.
Digital safety: When working with data online, always use strong passwords, enable two-factor authentication where possible, and avoid accessing sensitive data over public Wi-Fi networks that others can monitor.
CLASSROOM AND HOME ACTIVITIES
Activity One: Class Data Collection Project
Design a simple five-question paper questionnaire for your classmates. Ask about how they travel to school, how many hours they study daily, whether they have internet at home, their favourite subject, and their career interest. Collect responses from at least 20 students. Organise the results in a table and draw a bar chart to represent one of the questions. Present your findings to the class.
Activity Two: Spot the Error Challenge
Your teacher will provide a table of 20 student records containing deliberate mistakes — duplicate names, missing ages, impossible scores above 100, and misspelled state names. Work in pairs to find and correct all the errors. The pair that identifies the most errors correctly within the time limit wins.
Activity Three: Storage Type Research
Choose three real organisations in Nigeria — for example, a government hospital, a commercial bank, and a local government office. Research how each one stores its data. Write one page comparing the storage methods they use, noting one advantage and one risk for each organisation.
Activity Four: Ethics Discussion
In groups of four, read this scenario carefully: "A secondary school wants to install cameras in every classroom, corridor, and toilet entrance to monitor student behaviour. All footage will be stored on a server that only the principal can view."
Discuss: What data is being collected? What are the benefits? What are the privacy concerns? What rules or safeguards should be put in place? Each group will present their position to the class and be prepared to answer questions.
ASSESSMENT QUESTIONS
Section A: Objective Questions
Question 1: Which of the following best describes data cleaning?
(A) Deleting all old data files from a computer (B) The process of identifying and correcting errors in a dataset (C) Converting physical paper records into digital format (D) Collecting data automatically from websites
Question 2: A student submits a school survey form but leaves the "date of birth" field blank. This is an example of:
(A) A duplicate entry (B) An outlier (C) A missing value (D) A format error
Question 3: Which of the following is the best example of secondary data?
(A) A questionnaire you distributed personally to 50 students (B) Observations you made yourself at a local market (C) A report published by the National Bureau of Statistics (D) An interview you conducted with community members
Question 4: A teacher saves lesson notes to Google Drive so she can access them from any device with internet access. This is an example of:
(A) Local digital storage (B) Physical storage (C) Cloud storage (D) Database storage
Question 5: The Nigeria Data Protection Act (NDPA) is mainly designed to:
(A) Ban the use of social media in secondary schools (B) Make cloud storage services free for all Nigerians (C) Regulate how personal data is collected, stored, and used in Nigeria (D) Require all organisations to keep paper records of their activities
Section B: Theory Questions
Theory Question 1: (a) Define the term "data collection." (b) Describe any three methods by which data can be collected, and give one real Nigerian example for each method you describe.
Theory Question 2: Explain what data cleaning means and state four common types of data errors that a data scientist might find in a raw dataset. Why is it important to clean data before carrying out analysis?
Theory Question 3: Compare cloud storage and local digital storage using the following headings: (i) Accessibility, (ii) Security, (iii) Cost, and (iv) Suitability for areas with poor internet connectivity. Based on your comparison, which would you recommend for a small secondary school in a rural area of Benue State, and why?
SUMMARY
This lesson covered the three core pillars of data science basics for SSS 2:
Data Collection is the process of gathering raw facts through surveys, questionnaires, observation, interviews, sensors, or existing records. Data can be primary — collected directly by the researcher — or secondary — collected by someone else and used for a different purpose.
Data Storage refers to keeping collected data safe and available through physical records, local digital devices, cloud platforms, or organised databases. Good storage is secure, backed up, accessible, and scalable.
Data Cleaning is the process of fixing errors in raw data — including missing values, duplicates, typos, format inconsistencies, and outliers — before the data is used for analysis. The well-known principle of "garbage in, garbage out" explains why this step cannot be skipped.
Ethics and Privacy remind us that data collection carries responsibility. Consent, purpose limitation, accuracy, and security are all essential principles, and the Nigeria Data Protection Act (NDPA) gives Nigerians legal rights over how their personal data is used.
CONCLUSION
Data is the new currency of the modern world, and Nigeria is right in the middle of this transformation. From the ride-hailing app you use in Lagos to the health records kept at your local clinic, data collection, storage, and cleaning are happening constantly around you — quietly powering the decisions that shape your daily life.
As an SSS 2 student, grasping these foundational concepts puts you one step ahead. The world you are growing into will increasingly reward people who understand how data works — how to gather it responsibly, keep it safely, and ensure it is accurate before trusting it. These are not just exam topics. They are the building blocks of digital literacy.
The journey into data science starts here, in the classroom, with exactly what you have just read. Keep learning, keep questioning, and stay curious — Nigeria needs young people who understand the language of data.
FREQUENTLY ASKED QUESTIONS (FAQ)
What is the difference between data and information?
Data refers to raw, unprocessed facts without context — for example, a list of numbers like 45, 78, 92, and 60. Information is what you get after processing and organising that data to give it meaning — for example, "The average test score of the four students is 68.75." Data becomes information when it is given context and interpreted.
Why do data scientists spend so much time cleaning data?
Because data collected from the real world is almost never perfect from the start. People make typing errors, skip required fields, submit forms twice, and record values in different formats. If you skip the cleaning step and analyse dirty data, your conclusions will be wrong no matter how carefully you do the analysis. This is why the phrase "garbage in, garbage out" is so commonly used in data science.
Is cloud storage safe for storing personal or school data in Nigeria?
Reputable cloud services like Google Drive and Microsoft OneDrive use strong encryption and security systems, making them generally very safe. However, users must also do their part by creating strong passwords, enabling two-factor authentication, and never sharing their login details. The Nigeria Data Protection Act (NDPA) also requires any organisation storing personal data in the cloud to ensure it is adequately protected.
Can secondary school students in Nigeria actually learn data science?
Yes, absolutely. The NERDC Computer Studies curriculum for SSS 2 already introduces the foundational concepts. Beyond school, platforms like Google's Hustle Academy, Coursera, and Khan Academy offer free beginner-level data science and digital skills training that any secondary school student with internet access can explore.
What is the Nigeria Data Protection Act and why should students care about it?
The Nigeria Data Protection Act (NDPA) was signed into law in 2023. It is the main law in Nigeria that governs how personal data — names, phone numbers, health records, financial information — is collected, stored, and used. It gives Nigerian citizens the right to know what data is being collected about them, to correct inaccurate data, and to request that their data be deleted in certain situations. As a student, this law protects your school records, your medical history, and any personal information you share online.
What tools are used for data collection and cleaning in real life?
For data collection, common tools include Google Forms, Microsoft Forms, and SurveyMonkey. For storing and cleaning small datasets, Microsoft Excel and Google Sheets are widely used. For larger, more complex datasets, professionals use programming languages like Python — especially a library called pandas — and R. Database management is handled using tools like MySQL and Microsoft SQL Server. Many Nigerian universities and technology companies are actively training young people in these tools.
This article is curriculum-aligned with the NERDC Senior Secondary School Computer Studies syllabus for SSS 2. It is written for educational purposes and complies with Google AdSense content policies.
.jpg)
0 Comments