DATA SCIENCE

Read the patterns.
Explain the story.

Learn how data moves from messy rows and raw numbers into visual evidence, useful models and better decisions.

Start Learning View Data Lab ↓
1007550250
MODEL TREND +28.4% pattern confidence
JANMARMAYJULSEP
COLLECTCLEANEXPLOREVISUALIZEMODELEXPLAIN
DATA LAB

Work with data before you try to explain it.

Learn to inspect rows, identify errors, compare variables and understand what is usable before analysis begins.

RAW → CLEAN → READY Every good analysis starts here.
student_performance.csv 1,240 rows
IDHOURSSCOREATTENDANCE
0013.26874%
0025.18288%
0036.49194%
0042.86169%
0054.77984%
✓ Missing values checked ✓ Duplicate rows removed
EXPLORE

Different questions need different visual views.

A
B
C
D
E
WHAT THIS VIEW ANSWERS Which category performs better?

Use comparison charts when the goal is to compare groups clearly.

QUESTION Why?
DATA
PATTERN
EVIDENCE
CONCLUSION
ANALYTICAL THINKING

Do not stop when you find a pattern.

Learn to question relationships, check assumptions and separate real evidence from coincidence.

01Is this pattern consistent?
02Could another variable explain it?
03Is there enough evidence to trust it?
MODEL THINKING

See how a model learns from examples.

INPUT Study Hours Attendance Practice
OUTPUT Predicted Score 84.6
COMMUNICATE

Make the result understandable in one glance.

KEY INSIGHT Students with consistent practice show the strongest improvement.

Clear conclusion. Clear evidence. Clear next step.

FINAL ANALYSIS PROJECT_01
FINDING Consistency matters more than one-time effort.
FINAL PROJECT

Finish with a full analysis, not just exercises.

Work with a dataset from raw input to final recommendation, then present your reasoning clearly.

Clean the dataset Explore relationships Build clear visuals Interpret the result Present a recommendation
FINAL DATA THINKING FROM ANALYSIS TO ACTION

Make the decision only when the evidence earns it.

Learn to move beyond charts and patterns. Measure confidence, test the evidence and explain exactly why a conclusion should be trusted.

91% CONFIDENCE
01 Pattern

Identify what is changing.

02 Evidence

Check whether it is consistent.

03 Confidence

Measure how much it can be trusted.

04 Decision

Explain what should happen next.

DATA → EVIDENCE → DECISION That is the mindset behind useful data science.