What is the Role of Graphs in Data Science?

S3-SA5-0313

Grade Level:

Class 9

AI/ML, Data Science, Physics, Economics, Cryptography, Computer Science, Engineering

Definition

What is it?

Graphs in Data Science are visual tools that help us understand large amounts of information quickly. They turn raw numbers into pictures like bar charts, line graphs, or pie charts, making patterns and trends easier to spot.

Simple Example

Quick Example

Imagine you have a list of your cricket team's scores in the last 5 matches: 120, 150, 90, 180, 130. If you just see the numbers, it's hard to tell if the scores are improving. But if you draw a line graph, you can instantly see the ups and downs, and whether the team is performing better or worse over time.

Worked Example

Step-by-Step

Let's say a chai stall owner wants to know which flavour of chai sells the most in a week.

STEP 1: Collect data. They note down daily sales for three flavours: Masala, Ginger, and Elaichi.

---

STEP 2: Organise the data. Total sales for the week:
Masala Chai: 150 cups
Ginger Chai: 100 cups
Elaichi Chai: 70 cups

---

STEP 3: Choose a suitable graph. A bar graph is good for comparing different categories.

---

STEP 4: Draw the graph. On the X-axis, label the chai flavours (Masala, Ginger, Elaichi). On the Y-axis, mark the number of cups sold (from 0 to 180).

---

STEP 5: Plot the bars. Draw a bar up to 150 for Masala, 100 for Ginger, and 70 for Elaichi.

---

STEP 6: Analyse the graph. By looking at the bar graph, the owner can immediately see that Masala Chai has the tallest bar, meaning it's the most popular. Ginger is second, and Elaichi is third.

---

ANSWER: The graph clearly shows that Masala Chai is the most sold flavour, helping the owner decide to stock more Masala chai ingredients.

Why It Matters

Graphs are super important in Data Science because they help us make sense of complex information in fields like AI/ML, Physics, and Economics. Data scientists and analysts use graphs to find insights, predict future trends, and make smart decisions, from designing new apps to understanding market changes.

Common Mistakes

MISTAKE: Using a pie chart to show how a student's marks changed over 5 exams | CORRECTION: Pie charts are for showing parts of a whole (like percentages). For changes over time, a line graph is much better.

MISTAKE: Not labelling the axes of a graph or giving it a title | CORRECTION: Always label your X and Y axes clearly (e.g., 'Months', 'Sales in Lakhs') and give the graph a descriptive title (e.g., 'Monthly Sales of Mobile Phones'). Without labels, the graph is meaningless.

MISTAKE: Choosing a graph type that doesn't fit the data, like using a bar graph to show continuous temperature changes throughout a day | CORRECTION: For continuous data over time, a line graph is ideal. Bar graphs are best for comparing distinct categories.

Practice Questions

Try It Yourself

QUESTION: You want to show the number of students who chose different sports (Cricket, Football, Badminton, Kho-Kho) in your school. Which type of graph would be most suitable? | ANSWER: Bar graph

QUESTION: A mobile app tracks your daily screen time for a week. The times are: 3 hrs, 4 hrs, 2 hrs, 5 hrs, 3.5 hrs, 4.5 hrs, 2.5 hrs. Draw a simple line graph for this data. What trend do you observe? | ANSWER: (Student should draw a line graph with days on X-axis and screen time on Y-axis). The trend shows varying screen time, perhaps peaking mid-week.

QUESTION: A shop sold 20 kg of rice, 15 kg of dal, and 10 kg of sugar. If you were to create a pie chart to show the proportion of each item sold, what percentage would each item represent? | ANSWER: Total sold = 20+15+10 = 45 kg. Rice: (20/45)*100 = 44.44%, Dal: (15/45)*100 = 33.33%, Sugar: (10/45)*100 = 22.22%.

MCQ

Quick Quiz

Why are graphs important in data science?

They make data look more colourful.

They help us quickly understand patterns and trends in data.

They replace the need for any calculations.

They are only used by mathematicians.

The Correct Answer Is:

Graphs convert complex data into easy-to-understand visuals, making it simple to spot patterns, compare values, and identify trends, which is crucial for data analysis. Colour is a secondary benefit, they don't replace calculations, and they are used widely across many fields.

Real World Connection

In the Real World

Think about the weather apps on your phone or the news channels. They often show temperature changes over the day or rainfall predictions using line graphs. Even when you check cricket match scores on apps like Cricbuzz, the run rate graph helps you understand which team is performing better at different stages of the game. Data analysts at companies like Zomato use graphs to see peak order times and popular food items to manage deliveries better.

Key Vocabulary

Key Terms

DATA VISUALISATION: Presenting data in a pictorial or graphical format to make it easier to understand | TREND: A general direction in which something is developing or changing | INSIGHTS: Deep understanding of a complex situation | AXIS: A reference line on a graph (X-axis, Y-axis) | CATEGORY: A group or class of items

What's Next

What to Learn Next

Now that you understand why graphs are important, you should learn about different types of graphs like bar graphs, line graphs, histograms, and scatter plots. Knowing when to use each type will make you a pro at data visualisation!