Claude AI for Data Analysis: Uncovering Insights with Smart AI
Welcome, young data explorer! Did you know that we are surrounded by data every day? The number of likes on a post, the temperature outside, or the prices of items in a shop – all of these are data. Data analysis is the skill of looking at this information and finding patterns, answers, and stories. In this course, we will learn how to use Claude AI – a smart computer friend – to help us analyse data. Claude can read spreadsheets, find trends, answer questions, and even create charts. We will start from the very beginning, using simple words and fun examples. By the end, you will be able to use Claude to make sense of any data!
After completing this course, you will be able to:
Ada's Market Mystery
Ada loved helping her grandmother at the market in Lagos. Every week, they sold fruits and vegetables. But sometimes, they ran out of popular items, and other times, they had too much that went bad. Ada decided to track what they sold each day. She wrote down numbers in a notebook. After a few weeks, she had a lot of numbers but didn't know what they meant. Then her uncle said, "Ada, try using Claude AI. It can help you understand your numbers." Ada typed her data into a spreadsheet and asked Claude: "What are our best-selling fruits?" Claude replied quickly: "Mangoes and oranges sell the most on Saturdays!" Ada was amazed. She used that information to buy more mangoes and oranges for Saturdays. Her grandmother's market stall became the most popular in the area. Ada discovered the power of data analysis!
Definition: Data is information. It can be numbers, words, pictures, or anything that tells us something.
Why it's important: Data helps us understand the world around us.
Simple explanation: Data is like puzzle pieces. When you put them together, you see the whole picture.
Real-life example: The temperature in your city is data.
School example: Your test scores are data.
Home example: The list of groceries you need is data.
Nigerian example: The price of rice in a market is data.
Illustration:
+------------------------------------------+ | DATA = Information | | +--------------------------------------+ | | | Numbers: 10, 20, 30, 40 | | | | Words: "Apple", "Banana", "Mango" | | | | Dates: "Monday", "Tuesday" | | | | Prices: 100, 200, 300 | | | +--------------------------------------+ | +------------------------------------------+
Mini summary: Data is information that helps us understand things.
Definition: Data analysis is the process of looking at data, finding patterns, and drawing conclusions.
Why it's important: It helps us make better decisions.
Simple explanation: It's like being a detective – you look at clues (data) to solve a mystery.
Real-life example: A shop owner looks at sales data to know what to stock.
School example: A teacher looks at test scores to see where students need help.
Home example: A parent looks at expenses to plan a budget.
Nigerian example: A farmer looks at rainfall data to plan planting.
Illustration:
Data (clues) ---> Analysis (investigate) ---> Insights (answers)
Mini summary: Data analysis is finding answers and patterns in information.
Definition: Claude AI can read data, find patterns, answer questions, and even create charts and graphs.
Why it's important: It makes data analysis fast and easy.
Simple explanation: Claude is like a super-smart assistant who can look at numbers and tell you what they mean.
Real-life example: A business owner asks Claude to find the best-selling product.
School example: A student asks Claude to find the average test score.
Home example: A parent asks Claude to track monthly expenses.
Nigerian example: A Lagos market trader asks Claude to find the busiest sales day.
Illustration:
You: "Claude, what is the average temperature in Lagos?" Claude: "Based on the data, the average temperature is 28°C."
Mini summary: Claude helps you understand data by finding answers and patterns.
Definition: Data comes in different types. Numeric data are numbers (like prices). Categorical data are labels (like colours or names).
Why it's important: Different types need different analysis methods.
Simple explanation: Numbers are for counting and measuring. Categories are for grouping and sorting.
Real-life example: The price of a shirt (numeric) and the colour (categorical).
School example: Test scores (numeric) and subjects (categorical).
Home example: The number of apples (numeric) and the type (categorical).
Nigerian example: The price of yams (numeric) and the market name (categorical).
Illustration:
+------------------------------------------+ | Types of Data | | +--------------------------------------+ | | | Numeric: 10, 20, 30 (numbers) | | | | Categorical: Apple, Banana, Mango | | | +--------------------------------------+ | +------------------------------------------+
Mini summary: Data can be numbers or categories – both are useful.
Definition: Collecting data means gathering information from different sources.
Why it's important: You need data before you can analyse it.
Simple explanation: Like collecting leaves from different trees to study them.
Real-life example: A shop records daily sales.
School example: A student surveys classmates about their favourite foods.
Home example: A family tracks weekly expenses.
Nigerian example: A farmer records crop harvest amounts.
Illustration:
Sources of Data: - Surveys (asking people) - Records (sales, weather) - Sensors (temperature, traffic) - Observations (counting, measuring)
Mini summary: Collecting data is gathering information from different places.
Definition: Organizing data means arranging it in a way that makes it easy to read and analyse – like a table or spreadsheet.
Why it's important: Organized data is easier to understand.
Simple explanation: Like arranging your books on a shelf so you can find them easily.
Real-life example: A spreadsheet with columns for date, product, and price.
School example: A table with student names and test scores.
Home example: A shopping list with items and quantities.
Nigerian example: A table of market prices for different vegetables.
Illustration – Table:
+------------------+------------------+-------------+ | Day | Product | Sales (₦) | +------------------+------------------+-------------+ | Monday | Mango | 5000 | | Tuesday | Orange | 7000 | | Wednesday | Mango | 6000 | +------------------+------------------+-------------+
Mini summary: Tables and spreadsheets help organise data.
Definition: Claude can read spreadsheets and answer questions about the data.
Why it's important: It saves you from doing all the work yourself.
Simple explanation: You give Claude a spreadsheet, and it finds the answers for you.
Real-life example: A business uploads sales data and asks Claude for trends.
School example: A student uploads survey results and asks Claude for averages.
Home example: A parent uploads expenses and asks Claude for totals.
Nigerian example: A market trader uploads sales data and asks Claude for best-selling items.
Illustration:
Spreadsheet ---> Claude AI ---> Insights (data) (analysis) (answers)
Mini summary: Claude can read data and give you answers.
Definition: You can ask Claude questions like "What is the average?" or "What is the highest value?"
Why it's important: It helps you find specific answers quickly.
Simple explanation: Like asking a teacher for help with a math problem.
Real-life example: "What is the average temperature for July?"
School example: "What is the highest test score in the class?"
Home example: "How much did we spend on food this month?"
Nigerian example: "Which day had the highest sales last week?"
Illustration – Questions and Answers:
Question: "What is the total sales for Monday?" Claude: "Total sales for Monday is ₦5,000." Question: "Which product sold the most?" Claude: "Mangoes sold the most with 100 units."
Mini summary: You can ask Claude questions about your data.
Definition: Patterns are things that repeat. Trends are directions that data moves over time (upward or downward).
Why it's important: Patterns and trends help you predict what might happen next.
Simple explanation: Like noticing that it always rains on Saturday – that's a pattern.
Real-life example: Sales increase every December (holiday trend).
School example: Test scores improve after extra tutoring (upward trend).
Home example: Electricity bills are higher in summer (seasonal pattern).
Nigerian example: Prices of tomatoes increase during the dry season (seasonal trend).
Illustration – Trends:
Sales Trend
Month: Jan Feb Mar Apr May
Sales: 100 120 150 130 170
↑ ↑ ↑ ↓ ↑
Trend: Going UP overall!
Mini summary: Patterns and trends help you see what's happening.
Definition: Charts and graphs are pictures of data that make it easier to understand.
Why it's important: A picture is worth a thousand words – it's easier to see patterns.
Simple explanation: Like drawing a map instead of giving directions.
Real-life example: A bar chart showing sales by product.
School example: A pie chart showing favourite subjects.
Home example: A line graph showing monthly expenses.
Nigerian example: A bar chart showing crop harvests by region.
Illustration – Bar Chart (ASCII):
Sales by Product Mango ██████████ 100 Orange ████████ 80 Banana ██████ 60 Apple ████ 40
Mini summary: Charts and graphs make data easy to see and understand.
Definition: Average is the sum divided by the count. Sum is the total. Count is how many items.
Why it's important: These are the most common calculations in data analysis.
Simple explanation: Average = what is typical. Sum = total. Count = how many.
Real-life example: Average sales per day.
School example: Average test score in a class.
Home example: Total monthly expenses.
Nigerian example: Total sales for the week.
Illustration – Calculations:
Data: 10, 20, 30, 40, 50 Sum = 10 + 20 + 30 + 40 + 50 = 150 Count = 5 Average = 150 / 5 = 30
Mini summary: Sum, count, and average are basic but powerful calculations.
Definition: Comparing means looking at two or more sets of data to see how they are similar or different.
Why it's important: Comparison helps you make choices.
Simple explanation: Like comparing prices at different shops.
Real-life example: Comparing sales in different months.
School example: Comparing test scores from different classes.
Home example: Comparing prices of different phone plans.
Nigerian example: Comparing prices of rice in different markets.
Illustration – Comparison:
Market A: ₦1,000 per kg Market B: ₦900 per kg Market C: ₦1,200 per kg Best price: Market B at ₦900
Mini summary: Comparing data helps you make better decisions.
Definition: MCP (Model Context Protocol) connects Claude to external data sources like databases or spreadsheets.
Why it's important: It lets Claude work with live data.
Simple explanation: Like plugging a cable from your computer to a monitor.
Real-life example: Claude connects to a company database to analyse sales.
School example: Claude connects to a class grade spreadsheet.
Home example: Claude connects to a family budget app.
Nigerian example: Claude connects to a market price database.
Illustration – MCP Connection:
Claude <-----> MCP Server <-----> Database (AI) (bridge) (data source)
Mini summary: MCP connects Claude to your data sources.
Definition: Real-world projects are where you apply everything you learned to solve real problems.
Why it's important: It shows you how data analysis is used in the real world.
Simple explanation: Like practicing for a sports game.
Real-life example: Analysing sales data to find which products sell best.
School example: Analysing school attendance data.
Home example: Analysing household expenses.
Nigerian example: Analysing market prices for different vegetables.
Illustration – Project Ideas:
+------------------------------------------+ | Project Ideas: | | 🛒 Market Price Analysis | | 📊 School Grade Analysis | | 🌦️ Weather Data Analysis | | 🏦 Business Sales Analysis | | 📱 Social Media Engagement Analysis | +------------------------------------------+
Mini summary: Real-world projects apply your skills to solve problems.
Definition: Presenting means sharing what you discovered with others.
Why it's important: Data is only useful if people understand it.
Simple explanation: Like telling a story with the data.
Real-life example: A business owner presents sales trends to the team.
School example: A student presents survey results to the class.
Home example: A child presents family expense findings to parents.
Nigerian example: A market trader shares sales insights with their family.
Illustration – Presentation Outline:
1. What question did you want to answer? 2. What data did you collect? 3. What did you find (insights)? 4. What charts did you create? 5. What do the findings mean? 6. What are your recommendations?
Mini summary: Presenting your findings shares your insights with others.
How to analyse data with Claude:
Use real-world data that students can relate to. Start with simple datasets (like class survey results). Let students ask their own questions. Encourage them to create charts. Use Nigerian examples to make it relevant. Emphasise that data analysis is about curiosity and asking questions.
Help your child find data around the house – like weekly expenses or daily temperatures. Ask questions like "What do you notice?" and "What does that tell us?" Encourage them to use Claude to answer questions. Show them how data helps in daily life.
Collect Data ---> Organise Data ---> Ask Questions ---> Find Patterns ---> Share Findings (gather) (table) (Claude) (insights) (present)
| Type | Description | Example |
|---|---|---|
| Numeric | Numbers you can count or measure | 10, 20, 30 |
| Categorical | Labels or groups | Red, Blue, Green |
| Date/Time | Dates and times | Monday, 1st July |
| Method | What It Does | When to Use |
|---|---|---|
| Average | Finds the typical value | To understand the centre |
| Sum | Adds all values | To find totals |
| Count | Counts items | To find frequency |
| Comparison | Compares two sets | To find differences |
| Tool | Without Claude | With Claude |
|---|---|---|
| Finding Average | Manual calculation | Ask Claude |
| Creating Charts | Use software | Ask Claude |
| Finding Patterns | Look manually | Claude finds them |
| Time to Analyse | Hours or days | Minutes |
In this course, we learned about data analysis with Claude AI. We started with the basics – what data is and why it's important. We learned how to collect, organise, and analyse data. We discovered how Claude can answer questions, find patterns, and create charts. We explored real-world and Nigerian examples, and we learned how to present our findings. Data analysis is a superpower that helps us understand the world and make better decisions. With Claude, anyone can be a data analyst!
| Term | Definition |
|---|---|
| Data | A) Picture of data |
| Analysis | B) Information |
| Chart | C) Finding answers |
| Average | D) Sum divided by count |
| Sum | E) Total of all numbers |
Answers: Data-B, Analysis-C, Chart-A, Average-D, Sum-E
Scenario 1: You have data on daily sales for a week: Monday: ₦5000, Tuesday: ₦7000, Wednesday: ₦6000, Thursday: ₦8000, Friday: ₦9000, Saturday: ₦10000, Sunday: ₦7000.
Task: Ask Claude to find the total sales and the average sales per day.
Answer: Total sales = ₦52,000. Average sales = ₦7,428.57 per day.
Scenario 2: You want to know which day had the highest sales.
Task: Ask Claude to find the day with the highest sales.
Answer: Saturday had the highest sales at ₦10,000.
In groups of three, collect data from your class (favourite foods, ages, etc.). Organise it in a table. Use Claude to find the average, sum, and count. Create a chart. Present your findings to the class.
Track your daily screen time for one week. Write down the data. Use Claude to analyse it – find the average, highest, and lowest times. Create a chart. Write a short report on your findings.
Choose a topic to analyse – e.g., "Favourite Nigerian foods in our class". Collect data, organise it in a table, use Claude to find insights, create a chart, and present your findings.
Find a dataset online (or use one from school). Use Claude to analyse it. Write a report that includes:
Collect data on prices of the same product in three different markets. Use Claude to compare prices. Find the cheapest market and the most expensive. Create a chart showing the differences. Write a recommendation for where to buy.
Fill-in-the-blank: 1. Data, 2. Analysis, 3. pattern, 4. trend, 5. Average, 6. Sum, 7. Count, 8. chart, 9. spreadsheet, 10. MCP
True/False: 1F, 2T, 3F, 4T, 5T, 6T, 7F, 8T, 9F, 10F
Multiple Choice: 1A, 2A, 3A, 4A, 5A, 6A, 7A, 8A, 9A, 10A, 11A, 12A, 13A, 14A, 15A
Matching: Data-B, Analysis-C, Chart-A, Average-D, Sum-E
In the next module, we will dive deeper into Advanced Data Analysis. We will learn about predictive analytics (predicting the future), machine learning, and working with big data. We will also explore more advanced Claude features and build a complete data analysis project from start to finish. Get ready to become a data expert!
🎉 Congratulations! You have completed the Claude AI for Data Analysis course outline! 🎉
You are now ready to analyse data like a pro!
Module One: Introduction to Data Analysis with Claude AI – Becoming a Data Detective
Hello, young data explorer! Welcome to the exciting world of data analysis! Have you ever wondered how people make smart decisions? How do businesses know what products to sell? How do schools know where students need help? The answer is data analysis – the skill of looking at information and finding answers. In this module, we will begin our journey with the basics. We will learn what data is, why it is important, and how Claude AI – our smart computer friend – can help us understand data. We will use simple words, fun stories, and lots of examples from Nigeria and around the world. By the end of this module, you will think like a data detective!
After completing this module, you will be able to:
Chidi's Big Discovery
Chidi was a 10-year-old boy who lived in Lagos. Every day after school, he helped his mother sell oranges at the local market. His mother always said, "Chidi, we need to know how many oranges to buy each day. If we buy too few, we lose customers. If we buy too many, some oranges go bad."
Chidi decided to keep a record. He wrote down how many oranges they sold each day for a whole week:
Chidi looked at the numbers but felt confused. He didn't know what they meant. Then his teacher told him about Claude AI. Chidi typed his numbers and asked Claude: "What day do we sell the most oranges?" Claude answered: "Saturday, with 80 oranges!" Chidi asked another question: "How many oranges do we sell on average?" Claude replied: "Your average is about 61 oranges per day."
Chidi learned that on Saturdays, they needed more oranges. He told his mother, and she bought extra oranges for Saturdays. The next Saturday, they sold out and made more money! Chidi felt like a detective – he had used data to solve a mystery!
Definition: Data is information. It can be numbers, words, pictures, or anything that tells us something about the world.
Why it's important: Data helps us understand things, make decisions, and solve problems.
Simple explanation: Think of data like puzzle pieces. When you put them together, you see the whole picture. Each piece of data is a clue.
Real-life example: The temperature outside right now is data.
School example: Your test scores are data.
Home example: The list of groceries your parents buy is data.
Nigerian example: The price of a bag of rice in the market is data.
Illustration:
+------------------------------------------+ | DATA = INFORMATION | | +--------------------------------------+ | | | Numbers: 10, 20, 30, 40 | | | | Words: "Apple", "Banana", "Mango" | | | | Dates: "Monday", "Tuesday" | | | | Prices: ₦100, ₦200, ₦300 | | | | Temperatures: 28°C, 30°C | | | +--------------------------------------+ | +------------------------------------------+
Mini summary: Data is information that helps us understand the world.
Definition: Data is everywhere! We find it in books, on the internet, in our daily lives – everywhere we look.
Why it's important: Knowing where data comes from helps us collect it for analysis.
Simple explanation: Data is like leaves on a tree – they are everywhere, you just have to look.
Real-life example: The number of likes on a social media post is data.
School example: The number of students in your class is data.
Home example: The number of hours you sleep each night is data.
Nigerian example: The number of people who watch a Nollywood movie is data.
Illustration – Sources of Data:
+--------------------------------------------------+ | WHERE DO WE FIND DATA? | | +----------------------------------------------+ | | | 📱 Social media (likes, shares, comments) | | | | 📊 School (grades, attendance) | | | | 🏪 Market (prices, sales) | | | | 🌦️ Weather (temperature, rainfall) | | | | 📺 TV (ratings, viewership) | | | | 🏠 Home (expenses, chores) | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Data is everywhere – in school, at home, at the market, and online.
Definition: Data analysis is the process of looking at data, finding patterns, and drawing conclusions. It's like being a detective!
Why it's important: Data analysis helps us make better decisions. It turns raw information into useful answers.
Simple explanation: Imagine you have a box of puzzle pieces (data). Data analysis is putting them together to see the picture.
Real-life example: A shop owner looks at sales data to decide what products to restock.
School example: A teacher looks at test scores to see which topics students find hard.
Home example: A parent looks at monthly expenses to plan a budget.
Nigerian example: A farmer looks at rainfall data to decide when to plant crops.
Illustration – The Data Analysis Process:
+--------+ +-----------+ +----------+ | DATA | ---> | ANALYSE | ---> | INSIGHTS | | (raw | | (find | | (answers | | info) | | patterns)| | & clues) | +--------+ +-----------+ +----------+
Mini summary: Data analysis is finding answers and patterns in information.
Definition: Data analysis is important because it helps us understand things and make smart choices.
Why it's important: Without data analysis, we would be guessing. With it, we know!
Simple explanation: Think of data analysis like a flashlight in a dark room – it helps you see what's really there.
Real-life example: A doctor looks at patient data to decide the best treatment.
School example: A principal looks at attendance data to improve school.
Home example: A family looks at electricity bills to save money.
Nigerian example: A government looks at census data to plan for schools and hospitals.
Illustration – Benefits of Data Analysis:
+--------------------------------------------------+ | WHY DATA ANALYSIS IS IMPORTANT | | +----------------------------------------------+ | | | ✅ Make better decisions | | | | ✅ Solve problems | | | | ✅ Save money and time | | | | ✅ Understand customers and people | | | | ✅ Plan for the future | | | | ✅ Discover new things | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Data analysis helps us make better decisions and solve problems.
Definition: Claude AI is a smart computer program made by a company called Anthropic. It can understand and write text like a human.
Why it's important: Claude can help us analyse data quickly and easily.
Simple explanation: Claude is like a super-smart friend who lives in the computer and can answer questions about data.
Real-life example: A business owner asks Claude to find the best-selling product.
School example: A student asks Claude to find the average test score.
Home example: A parent asks Claude to track monthly expenses.
Nigerian example: A market trader asks Claude to find the busiest sales day.
Illustration – Claude AI:
+------------------+ +-------------------+ | YOU (user) | ---> | CLAUDE AI | | (ask a question | | (smart helper) | | about data) | | (finds answers) | +------------------+ +-------------------+
Mini summary: Claude AI is a smart helper that can answer questions about data.
Definition: Claude can read data, find patterns, answer questions, and even create charts and graphs.
Why it's important: It makes data analysis fast and easy – you don't need to be a math genius!
Simple explanation: Claude is like a magnifying glass that helps you see the details in your data.
Real-life example: A business uploads sales data and asks Claude for trends.
School example: A student uploads survey results and asks Claude for averages.
Home example: A parent uploads expenses and asks Claude for totals.
Nigerian example: A market trader uploads sales data and asks Claude for the best-selling items.
Illustration – Claude Helping with Data:
+----------+ +---------+ +----------+ | YOUR | ---> | CLAUDE | ---> | ANSWERS | | DATA | | AI | | & CHARTS | |(spread- | |(reads &| |(insights)| | sheet) | |analyses)| | | +----------+ +---------+ +----------+
Mini summary: Claude reads your data and gives you answers and charts.
Definition: Numeric data is data that is made of numbers. We can count it or measure it.
Why it's important: Numbers are easy to add, subtract, and find averages with.
Simple explanation: Numbers are like beans in a jar – you can count them and do math with them.
Real-life example: The price of a shirt is ₦2,000 – that's numeric data.
School example: Your test score is 85% – that's numeric data.
Home example: You have 5 apples – that's numeric data.
Nigerian example: The price of a bag of rice is ₦60,000 – numeric data.
Illustration – Numeric Data:
+------------------------------------------+ | NUMERIC DATA (NUMBERS) | | +--------------------------------------+ | | | 10, 20, 30, 40, 50 | | | | 1.5, 2.3, 4.8 | | | | 100, 200, 300, 400 | | | | -5, 0, 15, 25 | | | +--------------------------------------+ | +------------------------------------------+
Mini summary: Numeric data is made of numbers that we can count or measure.
Definition: Categorical data is data that is made of labels or groups. It is not numbers – it is names, colours, or types.
Why it's important: Categories help us group and sort things.
Simple explanation: Categories are like boxes you put things into – red box, blue box, green box.
Real-life example: The colour of a shirt – red, blue, green – is categorical data.
School example: Your favourite subject – maths, English, science – is categorical data.
Home example: The type of fruit – apple, banana, orange – is categorical data.
Nigerian example: The type of food – jollof rice, egusi soup, amala – is categorical data.
Illustration – Categorical Data:
+------------------------------------------+ | CATEGORICAL DATA (LABELS) | | +--------------------------------------+ | | | Colours: Red, Blue, Green | | | | Fruits: Apple, Banana, Orange | | | | Subjects: Maths, English, Science | | | | Cities: Lagos, Abuja, Kano | | | +--------------------------------------+ | +------------------------------------------+
Mini summary: Categorical data is made of labels or groups – not numbers.
Definition: Collecting data means gathering information from different sources – like surveys, records, or observations.
Why it's important: You can't analyse data if you don't have any! Collecting is the first step.
Simple explanation: Collecting data is like picking apples from a tree – you need to gather them first.
Real-life example: A shop records how many items it sells each day.
School example: A student surveys classmates about their favourite foods.
Home example: A family tracks how much they spend each week.
Nigerian example: A farmer records how many bags of yams they harvest.
Illustration – Ways to Collect Data:
+--------------------------------------------------+ | WAYS TO COLLECT DATA | | +----------------------------------------------+ | | | 📝 Surveys (asking people questions) | | | | 📊 Records (sales, attendance, etc.) | | | | 🌡️ Sensors (temperature, traffic, etc.) | | | | 👀 Observations (counting, watching) | | | | 📚 Research (books, articles, websites) | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Collect data by surveying, recording, observing, or researching.
Definition: Organizing data means arranging it in a neat way – like a table or spreadsheet – so it's easy to read and analyse.
Why it's important: Organised data is easier to understand and work with.
Simple explanation: Organising data is like putting your toys in boxes – everything has its place.
Real-life example: A spreadsheet with columns for Date, Product, and Sales.
School example: A table with student names and test scores.
Home example: A shopping list with items and quantities.
Nigerian example: A table of market prices for different vegetables.
Illustration – A Simple Table:
+------------------+------------------+-------------+ | DAY | PRODUCT | SALES (₦) | +------------------+------------------+-------------+ | Monday | Mangoes | 5,000 | | Tuesday | Oranges | 7,000 | | Wednesday | Bananas | 6,000 | | Thursday | Apples | 8,000 | | Friday | Mangoes | 9,000 | +------------------+------------------+-------------+
Mini summary: Tables and spreadsheets help organise data neatly.
Definition: You can ask Claude questions about your data, and it will give you answers.
Why it's important: Asking the right questions helps you find the answers you need.
Simple explanation: It's like asking a teacher for help – you need to ask a clear question.
Real-life example: "What is the total sales for this week?"
School example: "What is the average test score in our class?"
Home example: "How much did we spend on food this month?"
Nigerian example: "Which product had the highest sales last month?"
Illustration – Questions and Answers:
+--------------------------------------------------+ | QUESTIONS FOR CLAUDE | | +----------------------------------------------+ | | | Q: "What is the total sales for Monday?" | | | | A: "Total sales for Monday is ₦5,000." | | | | Q: "Which product sold the most?" | | | | A: "Mangoes sold the most with 100 units." | | | | Q: "What is the average temperature?" | | | | A: "The average temperature is 28°C." | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Ask Claude clear questions to get clear answers from your data.
Definition: A pattern is something that repeats in data. It helps us understand what usually happens.
Why it's important: Patterns help us predict what might happen in the future.
Simple explanation: A pattern is like a song that repeats the same melody – you can guess what comes next.
Real-life example: Sales are always high on Saturdays.
School example: Test scores are higher after extra tutoring.
Home example: Electricity bills are higher in summer.
Nigerian example: Tomato prices go up during the dry season.
Illustration – Finding Patterns:
+--------------------------------------------------+ | FINDING PATTERNS IN DATA | | +----------------------------------------------+ | | | Sales Data: | | | | Week 1: 100, 110, 105, 120, 115 | | | | Week 2: 105, 115, 110, 125, 120 | | | | Week 3: 110, 120, 115, 130, 125 | | | | PATTERN: Sales are going UP each week! | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Patterns are things that repeat in data – they help us understand.
Definition: A trend is the direction that data moves over time – it can go up, down, or stay the same.
Why it's important: Trends help us see the bigger picture and predict the future.
Simple explanation: A trend is like a path – it shows you where things are going.
Real-life example: Sales have been increasing every month (upward trend).
School example: Grades have been dropping (downward trend).
Home example: Water bills have stayed the same (flat trend).
Nigerian example: The price of petrol has been rising (upward trend).
Illustration – Trends:
+--------------------------------------------------+ | TRENDS IN DATA | | +----------------------------------------------+ | | | Upward Trend 📈: 10, 15, 20, 25, 30 | | | | Downward Trend 📉: 30, 25, 20, 15, 10 | | | | Flat Trend ➡️: 20, 20, 20, 20, 20 | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Trends show the direction data moves – up, down, or flat.
Definition: Data analysis is fun because it's like solving a mystery. You get to find clues and discover answers.
Why it's important: When it's fun, you want to do more of it!
Simple explanation: Data analysis is like being a detective in a story – you look for clues and solve the case.
Real-life example: Finding out which product makes the most money.
School example: Discovering which subject your class is best at.
Home example: Finding out where most of your allowance goes.
Nigerian example: Discovering which market has the cheapest fruits.
Illustration – Data Detective:
+--------------------------------------------------+ | BE A DATA DETECTIVE! 🕵️ | | +----------------------------------------------+ | | | 🔍 Ask questions | | | | 📊 Collect data | | | | 🧐 Look for patterns | | | | 📈 Find trends | | | | 💡 Discover answers | | | | 🎉 Share your findings! | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Data analysis is fun – it's like being a detective!
In this module, we learned:
You are now ready to start analysing data with Claude AI!
How to analyse data with Claude (Step-by-Step):
Use real-world data that students can relate to. Start with simple datasets (like class survey results). Let students ask their own questions. Encourage them to create charts. Use Nigerian examples to make it relevant. Emphasise that data analysis is about curiosity and asking questions. Allow students to work in pairs and share their findings.
Help your child find data around the house – like weekly expenses or daily temperatures. Ask questions like "What do you notice?" and "What does that tell us?" Encourage them to use Claude to answer questions. Show them how data helps in daily life – like planning a budget or choosing what to buy at the market.
+-------------+ +-------------+ +-------------+ +-------------+ +-------------+ | COLLECT | --> | ORGANISE | --> | ASK | --> | FIND | --> | SHARE | | DATA | | DATA | | QUESTIONS | | PATTERNS | | FINDINGS | +-------------+ +-------------+ +-------------+ +-------------+ +-------------+
| Feature | Numeric Data | Categorical Data |
|---|---|---|
| What it is | Numbers | Labels or groups |
| Examples | 10, 20, 30, 100 | Red, Blue, Green |
| Can we add it? | Yes | No |
| Can we find averages? | Yes | No (you can count categories) |
| Use for | Measuring, counting | Grouping, sorting |
| Task | Without Claude | With Claude |
|---|---|---|
| Finding the average | Manual calculation | Ask Claude |
| Finding the total | Manual addition | Ask Claude |
| Creating a chart | Use software | Ask Claude |
| Finding patterns | Look manually | Claude finds them |
| Time to analyse | Hours or days | Minutes |
+------------------------------------------------------------------+ | Module 1: Introduction to Data Analysis with Claude AI | | Module 2: Collecting and Organising Data | | Module 3: Asking Questions and Finding Answers | | Module 4: Creating Charts and Visualisations | | Module 5: Finding Patterns and Trends | | Module 6: Real-World Data Analysis Projects | +------------------------------------------------------------------+
In this first module, we have taken our first steps into the world of data analysis with Claude AI. We learned that data is information that helps us understand the world. We discovered that data analysis is the process of looking at data, finding patterns, and drawing conclusions. We met Claude AI – our smart computer friend that can help us analyse data quickly and easily.
We learned about the two main types of data: numeric (numbers) and categorical (labels). We explored how to collect and organise data using tables and spreadsheets. We practised asking Claude questions and finding patterns and trends. We also saw many examples from real life and from Nigeria.
Remember: Data analysis is like being a detective – you look for clues and solve mysteries. With Claude AI, anyone can be a data detective!
| Term | Definition |
|---|---|
| Data | A) Information, like numbers or words |
| Analysis | B) Looking at data to find answers |
| Claude AI | C) A smart computer that helps with data |
| Numeric Data | D) Data made of numbers |
| Categorical Data | E) Data made of labels or groups |
Answers: Data-A, Analysis-B, Claude AI-C, Numeric Data-D, Categorical Data-E
Scenario 1: You are a shop owner in Lagos. You sell bread, rice, and sugar. You want to know which product sells the most.
Task: What data would you collect? How would you organise it? What question would you ask Claude?
Answer: Collect sales data for each product daily. Organise it in a table with columns for Product and Sales. Ask Claude: "Which product has the highest total sales?"
Scenario 2: You are a student and you want to know which subject you are best at.
Task: What data would you collect? How would you analyse it with Claude?
Answer: Collect your test scores for each subject. Organise them in a table. Ask Claude: "What is my average score for each subject?" Then find the subject with the highest average.
In groups of three, collect data from your class. Ask everyone: "What is your favourite Nigerian food?" Record the answers. Organise the data in a table. Count how many people chose each food. Ask Claude: "Which food is the most popular?" Present your findings to the class.
Track your daily activities for one week. Write down how much time you spend on: school work, playing, eating, sleeping, and watching TV. Organise your data in a table. Ask Claude: "What activity do I spend the most time on?" Create a chart to show your findings.
Choose a topic to analyse – e.g., "Favourite fruits in our class" or "How we spend our weekends." Collect data from 10 people. Organise it in a table. Ask Claude three questions about your data. Create a chart. Present your findings to the class.
Find a dataset online (or use one from school). Use Claude to analyse it. Write a short report that includes:
Collect data on the prices of rice in three different markets in Nigeria. Use Claude to compare the prices. Find the cheapest market. Create a chart showing the price differences. Write a recommendation for where to buy rice.
Fill-in-the-blank: 1. Data, 2. Analysis, 3. Claude AI, 4. Numeric, 5. Categorical, 6. pattern, 7. trend, 8. spreadsheet, 9. Survey, 10. insight
True/False: 1F, 2T, 3F, 4T, 5F, 6T, 7F, 8F, 9T, 10F
Multiple Choice: 1A, 2A, 3A, 4A, 5A, 6A, 7A, 8A, 9A, 10A, 11A, 12A, 13A, 14A, 15A
Matching: Data-A, Analysis-B, Claude AI-C, Numeric Data-D, Categorical Data-E
In Module Two, we will go deeper into data analysis. We will learn how to collect and organise data properly. We will explore how to clean data (fix errors and missing values). We will also learn how to use Claude to find averages, sums, and counts. We will practice with more real-world data and Nigerian examples. Get ready to become a data detective!
🎉 Congratulations! You have completed Module One: Introduction to Data Analysis with Claude AI 🎉
You are now ready for Module Two – Collecting and Organising Data!
Module Two: Collecting and Organising Data – Getting Your Data Ready for Analysis
Welcome back, young data detective! In Module One, we learned what data is, why it's important, and how Claude AI can help us analyse it. Now, in Module Two, we will learn how to collect data and organise it properly. Think of it like this: before you can bake a cake, you need to gather all your ingredients and measure them correctly. Data analysis is the same – you need good data before you can find good answers. We will learn about different ways to collect data, how to use tables and spreadsheets, how to clean data (fix errors), and how to prepare data for Claude to analyse. Let's get started!
After completing this module, you will be able to:
Chidi's Data Challenge
Chidi was excited. He had learned about data analysis and wanted to analyse something important. He decided to find out which fruits were most popular at his mother's market stall in Lagos. He asked customers: "What is your favourite fruit?" But he just wrote the answers on random pieces of paper. Some answers were messy, some were missing, and some were hard to read. When he tried to analyse the data, he got confused.
His teacher said, "Chidi, you need to collect your data properly and organise it. First, make a simple form with a list of fruits. Then, write the answers neatly in a table. This is called 'cleaning' your data." Chidi followed the advice. He created a table with columns for "Customer Name" and "Favourite Fruit." He collected 20 responses. Then he asked Claude: "Which fruit is the most popular?" Claude answered: "Mangoes are the most popular, with 8 people choosing them!" Chidi was thrilled. He learned that good data collection and organisation make all the difference.
Definition: Data collection is the process of gathering information from different sources. Good data collection means getting accurate and complete information.
Why it's important: If you collect bad data, you will get bad answers. It's like baking a cake with bad ingredients – it won't taste good!
Simple explanation: Think of data collection like picking apples. You want to pick ripe, good apples – not rotten ones.
Real-life example: A shop owner records sales accurately every day.
School example: A student writes down test answers neatly.
Home example: A parent keeps a clear record of monthly expenses.
Nigerian example: A market trader writes down daily sales in a notebook.
Illustration – Good vs Bad Data Collection:
+--------------------------------------------------+ | GOOD DATA COLLECTION | | +----------------------------------------------+ | | | ✅ Clear questions | | | | ✅ Accurate records | | | | ✅ Complete answers | | | | ✅ Neatly written | | | +----------------------------------------------+ | | BAD DATA COLLECTION | | +----------------------------------------------+ | | | ❌ Messy writing | | | | ❌ Missing answers | | | | ❌ Wrong information | | | | ❌ Confusing questions | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Good data collection gives you accurate and useful information.
Definition: There are many ways to collect data – surveys, observations, records, experiments, and more.
Why it's important: Different situations need different collection methods.
Simple explanation: It's like using different tools for different jobs – a hammer for nails, a screwdriver for screws.
Real-life example: A restaurant uses a survey to find out what customers like.
School example: A teacher observes how students behave in class.
Home example: A family keeps records of their electricity bills.
Nigerian example: A farmer observes rainfall patterns to plan planting.
Illustration – Data Collection Methods:
+--------------------------------------------------+ | WAYS TO COLLECT DATA | | +----------------------------------------------+ | | | 📝 Surveys – Ask people questions | | | | 👀 Observations – Watch and record | | | | 📊 Records – Use existing documents | | | | 🔬 Experiments – Test and measure | | | | 🌐 Online – Use websites and databases | | | | 📞 Interviews – Talk to people | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: You can collect data through surveys, observations, records, experiments, and more.
Definition: A survey is a list of questions you ask people to collect data from them.
Why it's important: Surveys are one of the most common ways to collect data.
Simple explanation: A survey is like a quiz you give to people to learn about them.
Real-life example: A company asks customers to rate their service.
School example: A student surveys classmates about their favourite subjects.
Home example: A family asks relatives about preferred holiday destinations.
Nigerian example: A market trader surveys customers about new products.
Illustration – Survey Example:
+--------------------------------------------------+ | SURVEY: FAVOURITE FRUITS | | +----------------------------------------------+ | | | Q1: What is your name? ___________________ | | | | Q2: What is your favourite fruit? | | | | (Circle one) | | | | Mango / Orange / Banana / Apple | | | | Q3: How often do you eat fruit? | | | | Every day / Sometimes / Rarely | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Surveys are questions you ask people to collect data.
Definition: Good survey questions are clear, simple, and easy to answer. They don't confuse people.
Why it's important: If your questions are confusing, you will get confusing answers.
Simple explanation: Good questions are like clear directions – they tell people exactly what you want to know.
Real-life example: Instead of "How do you feel about our service?" ask "Rate our service from 1 to 5."
School example: Instead of "What do you think about maths?" ask "Do you like maths? Yes or No."
Home example: Instead of "What do you want for dinner?" ask "Which meal do you prefer: rice or pasta?"
Nigerian example: Instead of "What do you think of the market?" ask "How often do you visit the market?"
Illustration – Good vs Bad Questions:
+--------------------------------------------------+ | GOOD QUESTION: | | "How many times a week do you eat fruit?" | | (Clear, specific, easy to answer) | | | | BAD QUESTION: | | "Do you eat fruit regularly?" | | (Vague, confusing, different meanings) | +--------------------------------------------------+
Mini summary: Good survey questions are clear, simple, and specific.
Definition: Observing means watching and noting what happens. Recording means writing it down.
Why it's important: Some data can only be collected by watching – like how many people walk past a shop.
Simple explanation: Observation is like being a detective and taking notes.
Real-life example: A store owner counts how many customers enter each hour.
School example: A student counts how many cars pass the school in 10 minutes.
Home example: A parent counts how many times the doorbell rings.
Nigerian example: A market trader notes which products sell first.
Illustration – Observation Sheet:
+--------------------------------------------------+ | OBSERVATION SHEET | | +----------------------------------------------+ | | | Date: ___________ | | | | Time: ___________ | | | | Location: ___________ | | | | What did I see? | | | | ________________________________________ | | | | ________________________________________ | | | | How many? ___________ | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Observing and recording is watching and writing down what you see.
Definition: Existing records are data that have already been collected by someone else – like school attendance records or sales reports.
Why it's important: It saves time – you don't have to collect the data yourself.
Simple explanation: It's like using a book from the library instead of writing your own.
Real-life example: A business uses old sales reports to analyse trends.
School example: A student uses school attendance records for a project.
Home example: A parent uses old bills to track spending.
Nigerian example: A researcher uses census data from the government.
Illustration – Sources of Existing Records:
+--------------------------------------------------+ | SOURCES OF EXISTING RECORDS | | +----------------------------------------------+ | | | 📊 School attendance records | | | | 📈 Sales reports and receipts | | | | 📋 Census and survey data | | | | 🌦️ Weather records | | | | 📚 Books and research papers | | | | 🌐 Websites and online databases | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Existing records are data collected by others that you can use.
Definition: A table is a way to organise data in rows and columns. It makes data easy to read and analyse.
Why it's important: Organised data is easier to understand and work with.
Simple explanation: A table is like a grid – rows go across, columns go down.
Real-life example: A timetable at school is a table.
School example: A grade sheet with student names and scores.
Home example: A chore chart with family members and tasks.
Nigerian example: A market price list with items and prices.
Illustration – Table Example:
+------------------+------------------+-------------+ | STUDENT NAME | SUBJECT | SCORE | +------------------+------------------+-------------+ | Ada | Maths | 85 | | Chidi | Maths | 90 | | Bola | Maths | 78 | | Tunde | Maths | 92 | +------------------+------------------+-------------+
Mini summary: Tables organise data in rows and columns for easy reading.
Definition: A spreadsheet is a computer program that helps you organise, calculate, and analyse data in tables.
Why it's important: Spreadsheets can do calculations automatically and make charts.
Simple explanation: A spreadsheet is like a smart table that can do math for you.
Real-life example: A business uses Microsoft Excel to track sales.
School example: A student uses Google Sheets for a project.
Home example: A parent uses a spreadsheet to budget.
Nigerian example: A market trader uses a spreadsheet to track daily sales.
Illustration – Spreadsheet Layout:
+--------------------------------------------------+ | GOOGLE SHEETS / MICROSOFT EXCEL | | +----------------------------------------------+ | | | A B C D | | | | Day Product Sales Profit | | | | Monday Mango ₦5,000 ₦1,000 | | | | Tuesday Orange ₦7,000 ₦1,500 | | | | Wednesday Mango ₦6,000 ₦1,200 | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Spreadsheets are computer tables that help organise and analyse data.
Definition: Cleaning data means finding and fixing mistakes, like wrong numbers, missing information, or inconsistent formatting.
Why it's important: Clean data gives you accurate answers. Dirty data gives you wrong answers.
Simple explanation: Cleaning data is like washing fruit before you eat it – you remove the dirt.
Real-life example: A company checks for duplicate customer records.
School example: A student checks that all test scores are entered correctly.
Home example: A parent checks that all bills are recorded properly.
Nigerian example: A market trader checks that all sales are recorded correctly.
Illustration – Data Cleaning:
+--------------------------------------------------+ | DIRTY DATA (Before Cleaning) | | +----------------------------------------------+ | | | Name: "Ada", "Ada ", " ada" | | | | Age: 10, "ten", 10, | | | | Missing values: "", ?, (empty) | | | +----------------------------------------------+ | | CLEAN DATA (After Cleaning) | | +----------------------------------------------+ | | | Name: "Ada", "Ada", "Ada" | | | | Age: 10, 10, 10 | | | | Missing values: fixed or removed | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Cleaning data means fixing errors and removing dirt from your data.
Definition: Missing values are blank or empty spaces in your data where information is missing.
Why it's important: Missing values can give you wrong answers or make analysis impossible.
Simple explanation: Missing values are like holes in a bucket – you need to fill them or the water leaks out.
Real-life example: A customer didn't answer the age question on a survey.
School example: A student missed a test and has no score.
Home example: A parent forgot to record a purchase.
Nigerian example: A market trader didn't write down sales for one day.
Illustration – Fixing Missing Values:
+--------------------------------------------------+ | BEFORE: | | +----------------------------------------------+ | | | Name | Age | Favourite Food | | | | Ada | 10 | Mango | | | | Chidi | | Orange | | ← Missing Age | | Bola | 12 | | | ← Missing Food | +----------------------------------------------+ | | AFTER: | | +----------------------------------------------+ | | | Name | Age | Favourite Food | | | | Ada | 10 | Mango | | | | Chidi | 11 | Orange | | ← Added Age (estimated) | | Bola | 12 | Banana | | ← Added Food (based on survey) | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Fix missing values by filling them in or removing the incomplete rows.
Definition: Standardising means making all data look the same – like using the same date format or the same spelling.
Why it's important: Consistent data is easier to analyse and compare.
Simple explanation: Standardising is like using the same ruler to measure everything.
Real-life example: All dates are written as DD/MM/YYYY.
School example: All student names are written with capital letters.
Home example: All amounts are written as ₦1,000 not 1000 Naira.
Nigerian example: All market prices use the same currency symbol (₦).
Illustration – Standardising Data:
+--------------------------------------------------+ | BEFORE STANDARDISING: | | Date: "01/01/2024", "Jan 1", "1-1-24" | | | | AFTER STANDARDISING: | | Date: "01/01/2024", "01/01/2024", "01/01/2024" | +--------------------------------------------------+
Mini summary: Standardising makes all your data look the same and consistent.
Definition: Claude can help you clean data by finding errors, suggesting fixes, and checking for consistency.
Why it's important: Claude can do data cleaning much faster than you can manually.
Simple explanation: Claude is like a robot that can find mistakes and fix them for you.
Real-life example: A company uploads a messy spreadsheet and asks Claude to clean it.
School example: A student asks Claude to check for missing values.
Home example: A parent asks Claude to standardise date formats.
Nigerian example: A market trader asks Claude to find duplicate entries.
Illustration – Claude Cleaning Data:
You: "Claude, please clean this data. Fix any missing values and standardise the date format." Claude: "I found 5 missing values and fixed them. I standardised all dates to DD/MM/YYYY."
Mini summary: Claude can help you clean and organise your data quickly.
Definition: Preparing data means getting it ready for Claude to analyse – cleaning, organising, and formatting it correctly.
Why it's important: Ready-to-analyse data gives you the best answers.
Simple explanation: Preparing data is like setting the table before a meal – everything needs to be in the right place.
Real-life example: A business prepares sales data before giving it to Claude.
School example: A student organises survey data before asking Claude questions.
Home example: A parent organises expenses before asking Claude for a summary.
Nigerian example: A trader prepares weekly sales data before asking Claude for trends.
Illustration – Data Preparation Checklist:
+--------------------------------------------------+ | DATA PREPARATION CHECKLIST | | +----------------------------------------------+ | | | ✅ Is all data collected? | | | | ✅ Is it organised in a table? | | | | ✅ Are there any missing values? | | | | ✅ Are all formats consistent? | | | | ✅ Are there any duplicate entries? | | | | ✅ Is it ready for Claude? | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Preparing data means cleaning and organising it before analysis.
Definition: Storing data safely means keeping it in a secure place so it doesn't get lost or misused.
Why it's important: You don't want to lose all your hard work!
Simple explanation: Storing data safely is like putting your money in a bank instead of under your mattress.
Real-life example: A company backs up its data to the cloud.
School example: A student saves their project on a USB drive and in Google Drive.
Home example: A parent keeps receipts and records in a folder.
Nigerian example: A trader keeps a backup of sales records.
Illustration – Safe Storage Tips:
+--------------------------------------------------+ | TIPS FOR SAFE DATA STORAGE | | +----------------------------------------------+ | | | 💾 Save multiple copies (backup) | | | | ☁️ Use cloud storage (Google Drive, etc.) | | | | 📁 Keep files organised in folders | | | | 🔒 Use passwords for sensitive data | | | | 📋 Keep a paper copy as backup | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Store your data safely with backups and organisation.
In this module, we learned:
You are now ready to start analysing data with Claude!
How to collect and organise data (Step-by-Step):
Have students practice creating surveys and collecting data from classmates. Show them how to organise data in a spreadsheet. Demonstrate data cleaning by giving them a "dirty" dataset to fix. Use Nigerian examples to make it relevant. Emphasise the importance of good data quality.
Help your child collect data around the house – like tracking daily temperatures or weekly expenses. Teach them how to organise data in a simple table. Show them how to use a spreadsheet like Google Sheets. Encourage them to keep their data organised and backed up.
+-------------+ +-------------+ +-------------+ +-------------+ +-------------+ | PLAN | --> | COLLECT | --> | ORGANISE | --> | CLEAN | --> | PREPARE | | (what do | | (gather | | (table/ | | (fix | | (ready for | | you need?) | | data) | | spreadsheet)| | errors) | | Claude) | +-------------+ +-------------+ +-------------+ +-------------+ +-------------+
| Method | How It Works | Best For |
|---|---|---|
| Survey | Ask people questions | Opinions, preferences |
| Observation | Watch and record | Behaviour, events |
| Records | Use existing data | History, trends |
| Experiment | Test and measure | Science, results |
| Interview | Talk to people | Detailed information |
| Dirty Data | Clean Data |
|---|---|
| Missing values | All values present |
| Inconsistent formats | Standardised formats |
| Spelling mistakes | Correct spelling |
| Duplicate entries | No duplicates |
| Wrong numbers | Correct numbers |
+------------------------------------------------------------------+ | Lesson 1: Why Good Data Collection Matters | | Lesson 2: Different Ways to Collect Data | | Lesson 3: Creating a Survey | | Lesson 4: Writing Good Survey Questions | | Lesson 5: Observing and Recording Data | | Lesson 6: Using Existing Records | | Lesson 7: Organising Data – Tables | | Lesson 8: Using Spreadsheets | | Lesson 9: Cleaning Data – Fixing Errors | | Lesson 10: Fixing Missing Values | | Lesson 11: Standardising Data Formats | | Lesson 12: Using Claude to Help Clean Data | | Lesson 13: Preparing Data for Analysis | | Lesson 14: Storing Your Data Safely | | Lesson 15: Review | +------------------------------------------------------------------+
In this module, we learned how to collect and organise data properly – the essential steps before any analysis. We explored different ways to collect data: surveys, observations, records, and more. We learned how to create good surveys with clear questions. We discovered how to organise data in tables and spreadsheets. We also learned about data cleaning – fixing errors, filling missing values, and standardising formats. We saw how Claude can help us clean and prepare data. Finally, we learned how to store data safely. Remember: good data collection and organisation are the foundation of good analysis!
| Term | Definition |
|---|---|
| Survey | A) Watching and recording |
| Observation | B) List of questions |
| Table | C) Fixing errors |
| Cleaning | D) Rows and columns |
| Spreadsheet | E) Computer program for data |
Answers: Survey-B, Observation-A, Table-D, Cleaning-C, Spreadsheet-E
Scenario 1: You want to know what your classmates' favourite lunch foods are. You want to collect data from 20 students.
Task: Create a survey with 2-3 clear questions. Then, imagine you collected the data. Organise it in a table with 5 rows and 2 columns.
Answer: Survey: Q1: What is your name? Q2: What is your favourite lunch food? Table: Name | Favourite Food.
Scenario 2: You have a messy dataset with missing values and inconsistent formats.
Task: Write a prompt to Claude asking for help to clean the data.
Answer: "Claude, I have a dataset with some missing values and inconsistent date formats. Can you help me clean it and standardise the dates to DD/MM/YYYY?"
In groups of three, create a survey about "Favourite Nigerian Foods." Collect data from 10 people in the class. Organise the data in a table. Then, use Claude (or pretend) to find the most popular food. Present your findings to the class.
Collect data on your daily activities for one week. Write down how much time you spend on: school work, playing, eating, sleeping, and watching TV. Organise your data in a table. Clean the data if needed. Then, use Claude to find the activity you spend the most time on.
Choose a topic you want to learn about – e.g., "Favourite colours in our class" or "How we spend our weekends." Create a survey with 3 clear questions. Collect data from at least 10 people. Organise your data in a table. Clean the data if needed. Write a short report on what you learned from the data.
Find a messy dataset online (or use one from your teacher). Your task is to:
Collect data on the prices of a product (like rice or tomatoes) from three different markets in your area. Organise the data in a table. Clean any errors. Then, use Claude to compare the prices and find the cheapest market. Write a recommendation for where to buy.
Fill-in-the-blank: 1. Data collection, 2. survey, 3. Observation, 4. table, 5. spreadsheet, 6. Cleaning, 7. Missing values, 8. Standardising, 9. Preparing, 10. Claude
True/False: 1T, 2T, 3F, 4T, 5F, 6F, 7T, 8F, 9T, 10F
Multiple Choice: 1A, 2A, 3A, 4A, 5A, 6A, 7A, 8A, 9A, 10A, 11A, 12A, 13A, 14A, 15A
Matching: Survey-B, Observation-A, Table-D, Cleaning-C, Spreadsheet-E
In Module Three, we will put our collected and organised data to work! We will learn how to ask Claude questions, find averages, sums, and counts, and discover patterns and trends. We will also start creating charts and graphs to visualise our data. Get ready to become a real data analyst!
🎉 Congratulations! You have completed Module Two: Collecting and Organising Data with Claude AI 🎉
You are now ready for Module Three – Asking Questions and Finding Answers!
Module Three: Asking Questions and Finding Answers – Unlocking Insights with Claude
Welcome back, young data detective! You have learned so much already. In Module One, you learned what data is and why it's important. In Module Two, you learned how to collect and organise data properly. Now, in Module Three, it's time for the most exciting part – asking questions and finding answers! This is where the real magic of data analysis happens. You will learn how to ask Claude questions about your data, find averages and totals, discover patterns and trends, and even create charts and graphs. Claude will help you turn raw data into amazing insights. Let's dive in and become true data detectives!
After completing this module, you will be able to:
Chidi's Data Mystery
Chidi had collected a whole week of sales data from his mother's market stall in Lagos. He had organised it neatly in a spreadsheet. Now he wanted to know – what did the data tell him? He had many questions: "What is the total sales for the week? What is the average sales per day? Which day had the highest sales? What is the trend – are sales going up or down?"
Chidi opened his computer and asked Claude: "What is the total sales for this week?" Claude answered quickly: "Total sales is ₦52,000." Chidi asked another question: "What is the average sales per day?" Claude said: "The average is ₦7,428 per day." Chidi was amazed. He then asked: "Which day had the highest sales?" Claude replied: "Saturday had the highest sales at ₦10,000."
Chidi learned that Saturdays were their best days. He told his mother, and they decided to buy more stock for Saturdays. He also learned that sales were going up – a positive trend! Chidi felt like a real detective. He had asked the right questions and found the answers he needed.
Definition: Asking good questions means being clear and specific about what you want to know from your data.
Why it's important: The better your question, the better Claude's answer will be.
Simple explanation: Asking a good question is like giving clear directions to a taxi driver – they know exactly where to go.
Real-life example: Instead of "Tell me about sales," ask "What is the total sales for this month?"
School example: Instead of "Tell me about tests," ask "What is the average test score in our class?"
Home example: Instead of "Tell me about spending," ask "How much did we spend on food this week?"
Nigerian example: Instead of "Tell me about the market," ask "Which product sold the most last week?"
Illustration – Good vs Bad Questions:
+--------------------------------------------------+ | BAD QUESTION: "Tell me about the data." | | Claude: (gives a long, confusing answer) | | | | GOOD QUESTION: "What is the total sales?" | | Claude: "Total sales is ₦52,000." | | | | BAD QUESTION: "What's happening?" | | GOOD QUESTION: "What is the trend in sales?" | +--------------------------------------------------+
Mini summary: Clear, specific questions get clear, helpful answers.
Definition: The sum is the total you get when you add all the numbers together.
Why it's important: Sums tell you the total amount – like total sales, total expenses, or total count.
Simple explanation: Sum is like adding up all your birthday money to see how much you have total.
Real-life example: Total sales for the week is ₦52,000.
School example: Total test scores for the class is 850.
Home example: Total expenses for the month is ₦200,000.
Nigerian example: Total sales of oranges in a week is ₦35,000.
Illustration – Calculating Sum:
Daily Sales: 5000, 7000, 6000, 8000, 9000, 10000, 7000 Sum = 5000 + 7000 + 6000 + 8000 + 9000 + 10000 + 7000 Sum = ₦52,000
Mini summary: Sum is the total of all numbers added together.
Definition: The average is the sum divided by the count. It tells you what is typical or normal.
Why it's important: Averages help you understand what is normal and compare different groups.
Simple explanation: Average is like sharing your sweets equally among friends – everyone gets the same amount.
Real-life example: The average sales per day is ₦7,428.
School example: The average test score is 78%.
Home example: The average daily expense is ₦5,000.
Nigerian example: The average price of a bag of rice is ₦60,000.
Illustration – Calculating Average:
Daily Sales: 5000, 7000, 6000, 8000, 9000, 10000, 7000 Sum = 52,000 Count = 7 Average = 52,000 / 7 = 7,428.57 Average sales per day is approximately ₦7,429.
Mini summary: Average is the sum divided by the count – it shows what is typical.
Definition: The count is the number of items in your data – how many entries there are.
Why it's important: You need to know how many items you have before you can find averages or understand your data.
Simple explanation: Count is like counting how many apples are in a basket.
Real-life example: There are 7 days of sales data.
School example: There are 25 students in the class.
Home example: There are 10 items on the shopping list.
Nigerian example: There are 15 vendors in the market.
Illustration – Counting Data:
Data: 5000, 7000, 6000, 8000, 9000, 10000, 7000 Count = 7 (there are 7 numbers in the list)
Mini summary: Count tells you how many items are in your data.
Definition: The minimum is the smallest value. The maximum is the largest value.
Why it's important: Extremes help you see the range of your data – from the lowest to the highest.
Simple explanation: Minimum is the shortest person in a line. Maximum is the tallest person.
Real-life example: The highest sales day was ₦10,000 (Saturday). The lowest sales day was ₦5,000 (Monday).
School example: The highest test score was 95%. The lowest was 55%.
Home example: The highest expense was ₦10,000. The lowest was ₦1,000.
Nigerian example: The highest price of tomatoes was ₦500. The lowest was ₦300.
Illustration – Finding Min and Max:
Data: 5000, 7000, 6000, 8000, 9000, 10000, 7000 Minimum = 5000 (the smallest) Maximum = 10000 (the largest)
Mini summary: Minimum is the smallest value; maximum is the largest value.
Definition: A pattern is something that repeats in your data – like sales always being high on Saturdays.
Why it's important: Patterns help you understand what usually happens.
Simple explanation: A pattern is like a song that repeats the same tune – you can predict what comes next.
Real-life example: Sales are always higher on weekends than weekdays.
School example: Test scores are always higher after extra tutoring.
Home example: Electricity bills are always higher in summer.
Nigerian example: Tomato prices always go up during the dry season.
Illustration – Finding Patterns:
+--------------------------------------------------+ | Daily Sales Data: | | Monday: 5000 Tuesday: 7000 Wednesday: 6000 | | Thursday: 8000 Friday: 9000 Saturday: 10000 | | Sunday: 7000 | | | | PATTERN: Sales are lower at the start of the | | week and higher at the end of the week. | +--------------------------------------------------+
Mini summary: Patterns are things that repeat in your data.
Definition: A trend is the direction your data is moving – upward (going up), downward (going down), or flat (staying the same).
Why it's important: Trends help you predict what might happen in the future.
Simple explanation: A trend is like a path that shows you where you are going.
Real-life example: Sales have been increasing every week – an upward trend.
School example: Grades have been dropping – a downward trend.
Home example: Water bills have stayed the same – a flat trend.
Nigerian example: Prices of petrol have been rising – an upward trend.
Illustration – Identifying Trends:
+--------------------------------------------------+ | Week 1: 100, Week 2: 120, Week 3: 140 | | Trend: UP 📈 (increasing) | | | | Week 1: 100, Week 2: 80, Week 3: 60 | | Trend: DOWN 📉 (decreasing) | | | | Week 1: 100, Week 2: 100, Week 3: 100 | | Trend: FLAT ➡️ (staying the same) | +--------------------------------------------------+
Mini summary: Trends show the direction your data is moving – up, down, or flat.
Definition: Comparing data means looking at two or more sets of data to see how they are similar or different.
Why it's important: Comparison helps you make choices – like which product to buy or which market is cheaper.
Simple explanation: Comparing is like trying on two different shoes to see which fits better.
Real-life example: Comparing sales of mangoes vs oranges to see which sells more.
School example: Comparing test scores from two different classes.
Home example: Comparing prices of two different phone plans.
Nigerian example: Comparing prices of rice in three different markets.
Illustration – Comparison Table:
+--------------------------------------------------+ | PRODUCT | MARKET A | MARKET B | MARKET C | | Rice | ₦60,000 | ₦55,000 | ₦58,000 | | Beans | ₦20,000 | ₦18,000 | ₦19,000 | | Oil | ₦8,000 | ₦7,500 | ₦7,800 | | | | Market B has the lowest prices for all products! | +--------------------------------------------------+
Mini summary: Comparing data helps you see differences and make better choices.
Definition: You can ask Claude to calculate sums, averages, counts, and other values from your data.
Why it's important: Claude can do these calculations quickly and accurately.
Simple explanation: Claude is like a calculator that can do math on all your data at once.
Real-life example: "Claude, what is the total sales for this week?"
School example: "Claude, what is the average test score?"
Home example: "Claude, how many expenses did we have this month?"
Nigerian example: "Claude, what is the total sales of mangoes this week?"
Illustration – Claude Calculations:
You: "Claude, what is the total sales for this week?" Claude: "Total sales is ₦52,000." You: "Claude, what is the average sales per day?" Claude: "The average is ₦7,428 per day." You: "Claude, how many days of data do we have?" Claude: "You have 7 days of data."
Mini summary: Claude can quickly calculate sums, averages, and counts from your data.
Definition: You can ask Claude to find the smallest (min) and largest (max) values in your data.
Why it's important: Extremes help you understand the range of your data.
Simple explanation: Like asking "Who is the tallest in the class?"
Real-life example: "Claude, which day had the highest sales?"
School example: "Claude, what is the highest test score?"
Home example: "Claude, what was our biggest expense?"
Nigerian example: "Claude, which product had the lowest sales?"
Illustration – Min and Max with Claude:
You: "Claude, what is the highest sales day?" Claude: "Saturday had the highest sales with ₦10,000." You: "Claude, what is the lowest sales day?" Claude: "Monday had the lowest sales with ₦5,000."
Mini summary: Claude can find the minimum and maximum values in your data.
Definition: Charts and graphs are visual pictures of data that make it easier to see patterns and trends.
Why it's important: A picture is worth a thousand words – charts help you see what the data is saying.
Simple explanation: A chart is like a drawing that shows your data in a fun and easy-to-understand way.
Real-life example: A bar chart showing sales by product.
School example: A pie chart showing favourite subjects.
Home example: A line graph showing monthly expenses.
Nigerian example: A bar chart showing sales by day of the week.
Illustration – Claude Creating Charts:
You: "Claude, create a bar chart showing sales by day." Claude: "Here is your bar chart: Sales by Day Mon ████ 5000 Tue ██████ 7000 Wed █████ 6000 Thu ██████ 8000 Fri ███████ 9000 Sat ████████ 10000 Sun ██████ 7000"
Mini summary: Claude can create charts and graphs to visualise your data.
Definition: There are many types of charts – bar charts, pie charts, line charts, and more. Each type is good for showing different things.
Why it's important: Choosing the right chart helps people understand your data better.
Simple explanation: Different charts are like different tools – you use a hammer for nails and a screwdriver for screws.
Real-life example: A bar chart is good for comparing categories.
School example: A pie chart is good for showing parts of a whole.
Home example: A line chart is good for showing changes over time.
Nigerian example: A bar chart showing sales of different products.
Illustration – Types of Charts:
+--------------------------------------------------+ | BAR CHART: Compares different categories. | | PIE CHART: Shows parts of a whole. | | LINE CHART: Shows changes over time. | | SCATTER PLOT: Shows relationships between two | | variables. | +--------------------------------------------------+
Mini summary: Different charts are used for different types of data.
Definition: Insights are useful things you learn from data – like "Sales are highest on Saturdays."
Why it's important: Insights help you make decisions and take action.
Simple explanation: Insights are the "aha!" moments – when you understand something new.
Real-life example: "Claude, what observations can you make about the sales data?"
School example: "Claude, what does the data tell us about our test scores?"
Home example: "Claude, what can you learn from our spending data?"
Nigerian example: "Claude, what insights can you give about our market sales?"
Illustration – Insights with Claude:
You: "Claude, what insights can you give me about this data?" Claude: "Here are some insights: 1. Sales are highest on Saturdays. 2. Sales are lower on Mondays. 3. Sales have been increasing over the weeks. 4. Mangoes are the best-selling product."
Mini summary: Claude can give you helpful insights and observations from your data.
Definition: Interpreting means understanding what Claude's answers mean and what you should do with them.
Why it's important: Data is only useful if you understand what it means and take action.
Simple explanation: Interpreting is like reading a story and understanding the message.
Real-life example: If Claude says sales are highest on Saturdays, you should buy more stock for Saturdays.
School example: If Claude says test scores are low in maths, you should study maths more.
Home example: If Claude says spending is high on food, you should plan meals better.
Nigerian example: If Claude says mangoes sell best, you should stock more mangoes.
Illustration – Interpreting Data:
+--------------------------------------------------+ | CLAUDE SAYS: "Sales are highest on Saturdays." | | INTERPRETATION: Buy more stock for Saturdays. | | | | CLAUDE SAYS: "Sales have been increasing." | | INTERPRETATION: The business is growing! | | | | CLAUDE SAYS: "Mondays have the lowest sales." | | INTERPRETATION: Consider a promotion on Mondays. | +--------------------------------------------------+
Mini summary: Interpreting means understanding the meaning of Claude's answers.
In this module, we learned:
You are now ready to use Claude to analyse any data and find answers!
How to analyse data with Claude (Step-by-Step):
Have students practice asking Claude questions with sample datasets. Show them how to calculate sum, average, count, min, and max. Guide them in finding patterns and trends. Let them create charts. Use Nigerian examples to make it relevant. Emphasise the importance of asking good questions and interpreting answers.
Help your child ask questions about data they collect at home. For example: "What is the total amount we spent on food?" or "What is the average price of vegetables?" Encourage them to use Claude to find answers. Discuss what the answers mean and how they can use the information.
+-------------+ +-------------+ +-------------+ +-------------+ +-------------+ | ASK A | --> | CLAUDE | --> | CLAUDE | --> | INTERPRET | --> | TAKE | | QUESTION | | ANSWERS | | GIVES | | THE | | ACTION | | | | | | INSIGHTS | | ANSWERS | | | +-------------+ +-------------+ +-------------+ +-------------+ +-------------+
| Statistic | What It Tells You | How to Calculate | Example |
|---|---|---|---|
| Sum | Total amount | Add all numbers | ₦52,000 |
| Average | Typical value | Sum ÷ Count | ₦7,429 |
| Count | How many items | Count the items | 7 days |
| Minimum | Smallest value | Find the lowest | ₦5,000 |
| Maximum | Largest value | Find the highest | ₦10,000 |
| Chart Type | Best For | Example |
|---|---|---|
| Bar Chart | Comparing categories | Sales by product |
| Pie Chart | Parts of a whole | Market share |
| Line Chart | Changes over time | Monthly sales trend |
| Scatter Plot | Relationships | Price vs demand |
| Task | Without Claude | With Claude |
|---|---|---|
| Find total sales | Manual addition | Ask Claude |
| Find average sales | Divide manually | Ask Claude |
| Find highest sales | Look through data | Ask Claude |
| Find patterns | Look manually | Claude finds them |
| Create a chart | Use software | Ask Claude |
| Get insights | Think about it | Claude gives insights |
| Time to analyse | Hours | Minutes |
+------------------------------------------------------------------+ | Lesson 1: Asking Good Questions | | Lesson 2: The Sum – Adding Everything Up | | Lesson 3: The Average – Finding the Typical Value | | Lesson 4: The Count – How Many Items? | | Lesson 5: The Minimum and Maximum – Finding the Extremes | | Lesson 6: Finding Patterns in Data | | Lesson 7: Finding Trends in Data | | Lesson 8: Comparing Different Sets of Data | | Lesson 9: Asking Claude for Sums, Averages, and Counts | | Lesson 10: Asking Claude for Min and Max | | Lesson 11: Creating Charts and Graphs with Claude | | Lesson 12: Understanding Different Types of Charts | | Lesson 13: Asking Claude for Insights and Observations | | Lesson 14: Interpreting What Claude Tells You | | Lesson 15: Review | +------------------------------------------------------------------+
In this module, we learned how to ask questions and find answers using Claude AI. We discovered the power of basic statistics – sum, average, count, minimum, and maximum – and how they help us understand our data. We learned how to find patterns and trends, which tell us what repeats and what direction our data is moving. We explored how to compare different sets of data to make better decisions. We also learned how to create charts and graphs with Claude to visualise our data. Finally, we learned how to ask Claude for insights and interpret what the answers mean. You now have the skills to unlock the secrets hidden in your data!
| Term | Definition |
|---|---|
| Sum | A) Direction data moves |
| Average | B) Total of all numbers |
| Count | C) Visual picture of data |
| Trend | D) How many items |
| Chart | E) Sum ÷ Count |
Answers: Sum-B, Average-E, Count-D, Trend-A, Chart-C
Scenario 1: You have sales data for a week: Monday: ₦5,000, Tuesday: ₦7,000, Wednesday: ₦6,000, Thursday: ₦8,000, Friday: ₦9,000, Saturday: ₦10,000, Sunday: ₦7,000.
Task: Ask Claude to find the total sales, average sales, highest sales day, and lowest sales day.
Answer: Total = ₦52,000. Average = ₦7,429. Highest = Saturday (₦10,000). Lowest = Monday (₦5,000).
Scenario 2: You notice sales are lower on Mondays and higher on Saturdays.
Task: Ask Claude for an insight and a recommendation.
Answer: Insight: Sales are lowest on Mondays and highest on Saturdays. Recommendation: Buy more stock for Saturdays and consider a promotion on Mondays.
In groups of three, take a dataset (e.g., favourite foods, test scores, or sales data). Ask Claude (or pretend) five questions about the data. Find the sum, average, count, min, and max. Also, find a pattern or trend. Create a chart. Present your findings to the class.
Collect data on something you do every day (like hours of sleep, steps walked, or time spent on homework). Ask Claude five questions about your data. Find the sum, average, count, min, and max. Find a pattern or trend. Create a chart. Write a short report on what you learned.
Choose a topic to analyse – e.g., "How we spend our weekends" or "Favourite foods in our class." Collect data, organise it, and ask Claude at least five questions. Find the sum, average, count, min, and max. Find a pattern or trend. Create at least one chart. Present your findings to the class.
Find a dataset online or use one from your teacher. Use Claude to analyse it. Write a report that includes:
Collect data on the prices of a product in three different markets over a week. Use Claude to calculate the average price in each market, find the lowest and highest prices, and identify any trends. Write a recommendation for where to buy the product.
Fill-in-the-blank: 1. Sum, 2. Average, 3. Count, 4. Minimum, 5. Maximum, 6. pattern, 7. trend, 8. chart, 9. insight, 10. Claude
True/False: 1T, 2T, 3F, 4F, 5T, 6T, 7F, 8F, 9T, 10F
Multiple Choice: 1A, 2A, 3A, 4A, 5A, 6A, 7A, 8A, 9A, 10A, 11A, 12A, 13A, 14A, 15A
Matching: Sum-B, Average-E, Count-D, Trend-A, Chart-C
In Module Four, we will go further into data analysis. We will learn about Advanced Analysis – including grouping data, filtering, and using more complex queries. We will also learn about Real-World Data Analysis Projects and how to present our findings to others. Get ready to become a data expert!
🎉 Congratulations! You have completed Module Three: Asking Questions and Finding Answers with Claude AI 🎉
You are now ready for Module Four – Advanced Analysis and Real-World Projects!
Module Four: Advanced Data Analysis and Real-World Projects – Becoming a Data Analyst
Welcome, young data detective! You have come a long way. In Module One, you learned what data is and why it's important. In Module Two, you learned how to collect and organise data. In Module Three, you learned how to ask questions and find answers with Claude. Now, in Module Four, we will take your skills to the next level. We will learn advanced analysis techniques – like grouping data, filtering, and working with large datasets. We will also work on real-world projects that show how data analysis is used in the real world. You will learn how to connect Claude to live data sources, how to create professional reports, and how to present your findings to others. This is your final step to becoming a data analyst!
After completing this module, you will be able to:
Chidi's Big Project
Chidi had learned so much about data analysis. He could collect data, organise it, and ask Claude questions. But he wanted to do something big – a real project that would help people. He decided to analyse the prices of staple foods in different markets around Lagos. He wanted to help families find the cheapest places to buy food.
Chidi visited five markets and collected prices for rice, beans, and oil. He had over 100 rows of data! He used Claude to filter, group, and analyse the data. He asked: "What is the average price of rice in each market?" and "Which market has the lowest prices overall?" Claude gave him clear answers and even created charts. Chidi wrote a report and shared it with his community. People were grateful – they could now save money by shopping at the cheapest markets. Chidi had used data to make a real difference!
Definition: Filtering means selecting only the data that meets certain conditions – like only showing sales for a specific product or only showing data from a specific market.
Why it's important: Filtering helps you focus on the data that matters most.
Simple explanation: Filtering is like using a sieve to separate large pieces from small pieces – you keep only what you want.
Real-life example: A shop owner filters data to see only sales of mangoes.
School example: A student filters test scores to see only scores above 80%.
Home example: A parent filters expenses to see only food spending.
Nigerian example: A market trader filters sales data to see only sales from Saturdays.
Illustration – Filtering:
+--------------------------------------------------+ | DATA: Sales for all products | | +----------------------------------------------+ | | | Monday: Mango 5000 | | | | Monday: Orange 4000 | | | | Tuesday: Mango 6000 | | | | Tuesday: Orange 3500 | | | +----------------------------------------------+ | | FILTER: Only show Mango sales | | +----------------------------------------------+ | | | Monday: Mango 5000 | | | | Tuesday: Mango 6000 | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Filtering selects only the data that meets your condition.
Definition: Grouping means organising your data into groups based on a category – like grouping sales by product or by day.
Why it's important: Grouping helps you see totals and averages for each group.
Simple explanation: Grouping is like sorting your toys into boxes – one box for cars, one for dolls, one for blocks.
Real-life example: A business groups sales by product to see which product sells best.
School example: A student groups test scores by subject to see which subject they are best at.
Home example: A parent groups expenses by category (food, transport, rent).
Nigerian example: A trader groups sales by day to see which day is busiest.
Illustration – Grouping:
+--------------------------------------------------+ | GROUP BY PRODUCT | | +----------------------------------------------+ | | | PRODUCT | TOTAL SALES | AVERAGE | | | | Mango | 22,000 | 5,500 | | | | Orange | 15,000 | 3,750 | | | | Banana | 12,000 | 3,000 | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Grouping organises data by categories to show totals and averages.
Definition: Sorting means arranging your data in order – from smallest to largest (ascending) or largest to smallest (descending).
Why it's important: Sorting helps you see extremes easily – the highest and lowest values.
Simple explanation: Sorting is like lining up from shortest to tallest.
Real-life example: A teacher sorts test scores to see who scored highest and lowest.
School example: A student sorts their books by size.
Home example: A parent sorts bills by amount to see the biggest expenses.
Nigerian example: A trader sorts products by price to see which is cheapest.
Illustration – Sorting:
+--------------------------------------------------+ | UNSORTED: 5000, 7000, 6000, 8000, 9000 | | SORTED (Smallest to Largest): | | 5000, 6000, 7000, 8000, 9000 | | SORTED (Largest to Smallest): | | 9000, 8000, 7000, 6000, 5000 | +--------------------------------------------------+
Mini summary: Sorting arranges data in order to see extremes.
Definition: A large dataset is a collection of data with many rows – sometimes thousands or even millions.
Why it's important: Real-world data is often large – you need to know how to handle it.
Simple explanation: A large dataset is like a big library with thousands of books – you need a system to find what you need.
Real-life example: A bank has millions of customer transactions.
School example: A school has thousands of student records.
Home example: A family has years of expense records.
Nigerian example: A market has hundreds of transactions per day.
Illustration – Large Dataset:
+--------------------------------------------------+ | LARGE DATASET | | +----------------------------------------------+ | | | Row 1: Customer A, Product X, ₦500 | | | | Row 2: Customer B, Product Y, ₦700 | | | | Row 3: Customer C, Product X, ₦600 | | | | ... (thousands of rows) | | | | Row 10,000: Customer Z, Product Z, ₦800 | | | +----------------------------------------------+ | +--------------------------------------------------+
Mini summary: Large datasets have many rows – Claude can handle them quickly.
Definition: MCP (Model Context Protocol) connects Claude to external data sources – like databases, spreadsheets, or APIs – so it can work with live data.
Why it's important: Live data is data that is updated regularly – like daily sales or current weather.
Simple explanation: MCP is like a bridge that connects Claude to your data sources.
Real-life example: A business connects Claude to their sales database.
School example: A school connects Claude to their student database.
Home example: A parent connects Claude to a budget spreadsheet.
Nigerian example: A trader connects Claude to their daily sales records.
Illustration – MCP Connection:
+----------+ +----------+ +----------+ | CLAUDE | <-> | MCP | <-> | DATA | | AI | | SERVER | | SOURCE | +----------+ +----------+ +----------+
Mini summary: MCP connects Claude to live data sources.
Definition: Professional charts are clear, well-labelled, and easy to understand. They make your data look professional.
Why it's important: Good charts help people understand your data quickly.
Simple explanation: Professional charts are like drawing with a ruler – neat and tidy.
Real-life example: A business creates charts for a board meeting.
School example: A student creates charts for a school project.
Home example: A parent creates charts for a family budget.
Nigerian example: A trader creates charts to show sales trends.
Illustration – Professional Chart:
+--------------------------------------------------+ | Monthly Sales (January - June) | | 10000 | | | 8000 | ████ | | 6000 | ████ ████ | | 4000 | ████ ████ ████ | | 2000 | ████ ████ ████ ████ | | 0 | ████ ████ ████ ████ ████ | | | Jan Feb Mar Apr May Jun | +--------------------------------------------------+ | This chart shows sales increasing over time. | +--------------------------------------------------+
Mini summary: Professional charts are clear, well-labelled, and easy to read.
Definition: A data analysis report is a document that explains what you did, what you found, and what it means.
Why it's important: Reports help you share your findings with others.
Simple explanation: A report is like telling a story about your data.
Real-life example: A business writes a report on sales trends.
School example: A student writes a report on a science project.
Home example: A parent writes a report on family spending.
Nigerian example: A trader writes a report on market trends.
Illustration – Report Structure:
+--------------------------------------------------+ | 1. INTRODUCTION – What did you want to find? | | 2. METHOD – How did you collect the data? | | 3. RESULTS – What did you find? | | 4. ANALYSIS – What do the results mean? | | 5. CONCLUSION – What did you learn? | | 6. RECOMMENDATIONS – What should you do? | +--------------------------------------------------+
Mini summary: A data analysis report explains your findings clearly.
Definition: Presenting means sharing your findings with others – like a presentation or a talk.
Why it's important: Presenting helps others understand and use your findings.
Simple explanation: Presenting is like telling a story with pictures and words.
Real-life example: A business presents sales data to investors.
School example: A student presents a project to the class.
Home example: A child presents a budget plan to parents.
Nigerian example: A trader presents market findings to a cooperative.
Illustration – Presentation Outline:
+--------------------------------------------------+ | 1. TITLE – What is your project about? | | 2. QUESTION – What did you want to know? | | 3. DATA – Show the data you collected. | | 4. CHARTS – Show the charts you created. | | 5. FINDINGS – What did you discover? | | 6. RECOMMENDATIONS – What should people do? | | 7. Q&A – Answer questions from the audience. | +--------------------------------------------------+
Mini summary: Presenting shares your findings with others.
Definition: Real-world projects are data analysis projects that solve real problems – like helping a business or a community.
Why it's important: They show you how data analysis is used in the real world.
Simple explanation: Real-world projects are like doing a job – using data to help people.
Real-life example: Analysing sales data to find which products to stock.
School example: Analysing attendance data to improve school.
Home example: Analysing expenses to save money.
Nigerian example: Analysing market prices to help families save.
Illustration – Project Ideas:
+--------------------------------------------------+ | PROJECT IDEAS: | | 🛒 Market Price Analysis | | 📊 School Performance Analysis | | 🌦️ Weather Data Analysis | | 🏦 Business Sales Analysis | | 📱 Social Media Engagement Analysis | | 🏡 Household Expense Analysis | | 🚗 Traffic Pattern Analysis | +--------------------------------------------------+
Mini summary: Real-world projects solve real problems with data.
Definition: Planning means deciding what you want to analyse, what data you need, and how you will collect it.
Why it's important: Good planning makes your project successful.
Simple explanation: Planning is like drawing a map before a trip.
Real-life example: A business plans a market analysis project.
School example: A student plans a school project.
Home example: A parent plans a budget analysis.
Nigerian example: A trader plans a price analysis project.
Illustration – Planning Steps:
+--------------------------------------------------+ | 1. Choose a question – What do you want to know?| | 2. Identify data needed – What data do you need?| | 3. Plan collection – How will you collect it? | | 4. Set a timeline – How long will it take? | | 5. Decide on analysis – What will you look for? | +--------------------------------------------------+
Mini summary: Planning is the first step to a successful project.
Definition: Collecting data means gathering the information you need for your project.
Why it's important: You need data before you can analyse it.
Simple explanation: Collecting is like gathering ingredients before cooking.
Real-life example: A business collects sales records.
School example: A student collects survey responses.
Home example: A parent collects bills.
Nigerian example: A trader collects market prices.
Illustration – Collection Methods:
+--------------------------------------------------+ | Survey: Ask people questions. | | Observation: Watch and record. | | Records: Use existing data. | | Online: Use websites and databases. | +--------------------------------------------------+
Mini summary: Collecting data is gathering the information you need.
Definition: Organising means putting your data in a table. Cleaning means fixing errors.
Why it's important: Clean, organised data gives you clean, accurate answers.
Simple explanation: Organising is like putting your toys in boxes. Cleaning is like washing them.
Real-life example: A business organises sales data in a spreadsheet.
School example: A student organises survey results in a table.
Home example: A parent organises expenses in a spreadsheet.
Nigerian example: A trader organises market prices in a table.
Illustration – Organising Data:
+------------------+------------------+-------------+ | MARKET | PRODUCT | PRICE (₦) | +------------------+------------------+-------------+ | Market A | Rice | 60,000 | | Market A | Beans | 20,000 | | Market B | Rice | 55,000 | | Market B | Beans | 18,000 | +------------------+------------------+-------------+
Mini summary: Organising and cleaning get your data ready for analysis.
Definition: Analysing means asking Claude questions and finding answers in your data.
Why it's important: This is where you discover insights!
Simple explanation: Analysing is like being a detective and finding clues.
Real-life example: A business asks Claude for sales trends.
School example: A student asks Claude for averages.
Home example: A parent asks Claude for total expenses.
Nigerian example: A trader asks Claude for the cheapest market.
Illustration – Analysis Questions:
+--------------------------------------------------+ | QUESTIONS TO ASK CLAUDE: | | 1. "What is the total sales for each market?" | | 2. "Which product has the highest average price?"| | 3. "Which market has the lowest prices?" | | 4. "What is the trend in prices over time?" | | 5. "How do prices compare between markets?" | +--------------------------------------------------+
Mini summary: Analysing with Claude reveals the answers in your data.
Definition: Sharing means presenting your findings to others – through a report, presentation, or visualisation.
Why it's important: Your insights are only useful if others can use them.
Simple explanation: Sharing is like telling a story so everyone understands.
Real-life example: A business presents findings to the team.
School example: A student presents a project to the class.
Home example: A parent shares a budget plan with family.
Nigerian example: A trader shares market insights with the community.
Illustration – Sharing Methods:
+--------------------------------------------------+ | WAYS TO SHARE FINDINGS: | | 📄 Write a report. | | 🎤 Give a presentation. | | 📊 Create charts and graphs. | | 📱 Share on social media. | | 🗣️ Tell people directly. | +--------------------------------------------------+
Mini summary: Sharing your findings helps others benefit from your work.
In this module, we learned:
You are now a data analyst!
How to complete a data analysis project (Step-by-Step):
Have students work on a complete data analysis project. Guide them through each step – planning, collecting, organising, analysing, and presenting. Use Nigerian examples to make it relevant. Encourage them to choose projects that interest them. Celebrate their final presentations.
Help your child choose a project topic. Assist them in collecting data if needed. Show interest in their analysis and ask questions. Encourage them to present their findings to the family. Celebrate their hard work!
+-------------+ +-------------+ +-------------+ +-------------+ +-------------+ | PLAN | --> | COLLECT | --> | ORGANISE | --> | ANALYSE | --> | PRESENT | | (what do | | (gather | | & CLEAN | | (ask | | (share | | you need?) | | data) | | data) | | Claude) | | findings) | +-------------+ +-------------+ +-------------+ +-------------+ +-------------+
| Technique | What It Does | When to Use |
|---|---|---|
| Filtering | Selects only certain data | When you want to focus on a subset |
| Grouping | Organises by categories | When you want totals by category |
| Sorting | Arranges in order | When you want to see extremes |
| Visualising | Creates charts | When you want to see patterns |
| Step | Action | Result |
|---|---|---|
| Plan | Choose question and data needs | Clear project scope |
| Collect | Gather data | Raw data |
| Organise & Clean | Table and fix errors | Clean data |
| Analyse | Ask Claude questions | Answers and insights |
| Present | Share findings | Understanding and action |
| Task | Without Claude | With Claude |
|---|---|---|
| Filtering large dataset | Manual filtering | Ask Claude to filter |
| Grouping data | Manual grouping | Ask Claude to group |
| Sorting data | Manual sorting | Ask Claude to sort |
| Creating professional charts | Use software | Ask Claude to create |
| Writing a report | Manual writing | Ask Claude to draft |
| Time to complete project | Weeks | Days or hours |
+------------------------------------------------------------------+ | Lesson 1: Filtering Data – Finding What You Need | | Lesson 2: Grouping Data – Organising by Categories | | Lesson 3: Sorting Data – Arranging from Smallest to Largest | | Lesson 4: Working with Large Datasets | | Lesson 5: Using MCP to Connect to Live Data | | Lesson 6: Creating Professional Charts with Claude | | Lesson 7: Writing a Data Analysis Report | | Lesson 8: Presenting Your Findings | | Lesson 9: Real-World Data Analysis Projects | | Lesson 10: Building a Complete Project – Step 1: Planning | | Lesson 11: Building a Complete Project – Step 2: Collecting | | Lesson 12: Building a Complete Project – Step 3: Organising | | Lesson 13: Building a Complete Project – Step 4: Analysing | | Lesson 14: Building a Complete Project – Step 5: Sharing | | Lesson 15: Review | +------------------------------------------------------------------+
In this final module, we have reached the pinnacle of our data analysis journey. We learned advanced techniques like filtering, grouping, and sorting, which help us focus our analysis and find deeper insights. We learned how to work with large datasets and connect Claude to live data using MCP. We created professional charts and wrote detailed reports. We built a complete data analysis project from start to finish – planning, collecting, organising, analysing, and presenting. We also explored real-world projects and Nigerian examples that show how data analysis makes a difference in people's lives.
You have learned so much. You now have the skills to collect, organise, analyse, and present data. You can use Claude AI to answer questions, find patterns, and make recommendations. You can help businesses, schools, and communities with data. You are a data analyst!
| Term | Definition |
|---|---|
| Filtering | A) Organise by categories |
| Grouping | B) Select only certain data |
| Sorting | C) Document explaining findings |
| Report | D) Arrange in order |
| MCP | E) Connects Claude to data |
Answers: Filtering-B, Grouping-A, Sorting-D, Report-C, MCP-E
Scenario 1: You have collected prices of rice from 5 markets: Market A: ₦60,000, Market B: ₦55,000, Market C: ₦58,000, Market D: ₦62,000, Market E: ₦57,000.
Task: Ask Claude to sort the prices from lowest to highest and find the cheapest market.
Answer: Sorted: ₦55,000 (Market B), ₦57,000 (Market E), ₦58,000 (Market C), ₦60,000 (Market A), ₦62,000 (Market D). Cheapest: Market B at ₦55,000.
Scenario 2: You have sales data by product for a week. You want to group sales by product and find the total for each product.
Task: Write a prompt to Claude to group the data.
Answer: "Claude, group the sales data by product and find the total sales for each product."
In groups of three, choose a real-world topic to analyse (e.g., prices of vegetables in different markets, or favourite foods in your class). Complete a full data analysis project – plan, collect, organise, analyse with Claude, create charts, write a report, and present. Share your findings with the class.
Choose a topic you are passionate about. Complete a full data analysis project from start to finish. Use Claude for every step. Write a report and present your findings to someone.
Complete a data analysis project on a topic of your choice. Include:
Find a real-world dataset online or use one from your community. Use Claude to complete a full analysis. Write a detailed report that includes:
Find three different sources of data on the same topic (e.g., prices of rice from three different online sources). Analyse and compare the data. Write a report on your findings and recommend the best source based on price and reliability.
Fill-in-the-blank: 1. Filtering, 2. Grouping, 3. Sorting, 4. large, 5. MCP, 6. report, 7. Presenting, 8. project, 9. Cleaning, 10. Planning
True/False: 1F, 2T, 3T, 4F, 5T, 6F, 7T, 8F, 9T, 10F
Multiple Choice: 1A, 2A, 3A, 4A, 5A, 6A, 7A, 8A, 9A, 10A, 11A, 12A, 13A, 14A, 15A
Matching: Filtering-B, Grouping-A, Sorting-D, Report-C, MCP-E
Congratulations! You have completed all four modules of the Claude AI for Data Analysis course. You have learned how to collect, organise, analyse, and present data. You can use Claude AI to find answers and solve problems. What's next? Here are some ideas:
Your journey as a data analyst is just beginning. You have the skills, the tools, and the curiosity to make a difference. Go and use data to change the world!
🎉 Congratulations! You have completed the entire Claude AI for Data Analysis course! 🎉
You are now a certified Data Analyst with Claude AI!