Data Analysis with Python

Already know basic Python? Learn to answer real questions with data using pandas and matplotlib, and finish with an evidence-based report of your own.

6 weeks · 60-minute weekly sessions · Runs free in Google Colab

How It Works

From Code to Data

Load a real dataset, inspect it, and answer factual questions about it with code.

Load and explore a CSV with pandas in Google Colab
Figure out what one row actually represents
Filter, sort, and count to answer your first questions

Cleaning & New Columns

Fix a messy dataset and build columns that make comparisons fair.

Handle missing values, duplicates, and numbers stored as text
Normalize raw totals into per-pupil figures, rates, and percents
Write down and justify every cleaning decision

Summarizing & Comparing

Summarize groups and pick the number that tells the truth.

Build summary tables with groupby and merge
Mean vs. median, and how one outlier can mislead
Compare groups and state what the numbers show

Visualization

Pick the right chart for the question and make it honest.

Bar, histogram, line, and scatter plots with matplotlib
Titles that state a finding, not just the variables
Fix misleading charts, then get your capstone dataset

From Analysis to Argument

Turn numbers and charts into a claim backed by evidence.

Correlation vs. causation, confounders, and small samples
Structure a report: question, data, findings, claim, limitations
One-on-one check-in on your capstone question

Capstone Presentations

Present your findings and submit your data-driven report.

Analyze real Washington K-12 data from OSPI
Five-minute presentation with your key charts and claim
Give and get feedback from your peers

Ready to join?

Free for every student. Questions? Email youthcivicbridge@gmail.com.