Essential session storage is required to sign in. Optional analytics remain off unless you allow them.
Perform a proper exploratory data analysis (EDA) on a dataset and communicate a real insight. Requirements: (1) frame a QUESTION the analysis will answer; (2) clean and prepare the data (missing/duplicates/types); (3) EXPLORE systematically — distributions (histograms), a relationship (scatter or correlation), and outlier/missingness checks — noting what you find at each step; (4) use groupby AND at least one merge/join (bring in a second table or derived lookup) to dig into a segment; (5) produce at least three well-chosen, LABELED charts (matplotlib/seaborn) matched to the question (trend/comparison/distribution/relationship); (6) write a short conclusion structured as finding → so-what → recommendation, giving numbers meaning via comparison and stating one limitation. Keep correlation-vs-causation honest.
Systematic exploration of distributions, a relationship, and outliers/missingness; groupby + a merge to examine a segment.
Three or more well-chosen, labeled charts matched to the question, with honest scales (no misleading axes).
A finding → so-what → recommendation conclusion with comparison-based numbers; correlation-vs-causation and one limitation stated.
Use this README structure to make the work reviewable.
DevPath fetches a read-only, size-capped snapshot. Submitted code is never executed.
# An exploratory data analysis with an insight ## Goal Perform a proper exploratory data analysis (EDA) on a dataset and communicate a real insight. Requirements: (1) frame a QUESTION the analysis will answer; (2) clean and prepare the data (missing/duplicates/types); (3) EXPLORE systematically — distributions (histograms), a relationship (scatter or correlation), and outlier/missingness checks — noting what you find at each step; (4) use groupby AND at least one merge/join (bring in a second table or derived lookup) to dig into a segment; (5) produce at least three well-chosen, LABELED charts (matplotlib/seaborn) matched to the question (trend/comparison/distribution/relationship); (6) write a short conclusion structured as finding → so-what → recommendation, giving numbers meaning via comparison and stating one limitation. Keep correlation-vs-causation honest. ## Acceptance criteria - [ ] EDA rigor: Systematic exploration of distributions, a relationship, and outliers/missingness; groupby + a merge to examine a segment. - [ ] Visualization: Three or more well-chosen, labeled charts matched to the question, with honest scales (no misleading axes). - [ ] Insight & honesty: A finding → so-what → recommendation conclusion with comparison-based numbers; correlation-vs-causation and one limitation stated. ## Verification - [ ] Document installation and run commands. - [ ] Record automated checks and their exact commands. - [ ] Add representative output, screenshots, or a short demo where useful. - [ ] Confirm failure paths and known constraints. ## Decision log ### Decision title - Context: - Choice: - Alternatives considered: - Tradeoffs: ## Evidence - Link each rubric criterion to the file, test, or artifact that demonstrates it. ## Known limitations - List what is intentionally out of scope and what should be improved next.