Data Science & Python
Create mode. Pick a subcategory or browse everything below.
- Pandas Data Wrangling 16
- Visualization 14
- Statistics Basics 14
- Machine Learning Basics 12
- Notebooks and Reproducibility 10
Prompts
-
Frame a Problem for Machine Learning
Decide whether ML is needed and what to predict.
-
Train-Test Split and Leakage Audit
Make sure evaluation scores are honest.
-
Evaluation Metrics Chooser
Pick metrics that match the real costs.
-
Baseline Model Plan Before Complexity
Build the simplest model that could work.
-
Feature Engineering Brainstorm
Create features from raw data thoughtfully.
-
Overfitting Diagnosis Walkthrough
Recognize and fix a model that memorizes.
-
Explain a Model's Predictions to Stakeholders
Communicate model behavior honestly.
-
Clustering Analysis Plan
Group similar records and judge the result.
-
Model Documentation Card
Document what a model is for and where it fails.
-
Time Series Forecasting Baselines
Beat the naive forecast honestly.
-
Class Imbalance Handling Guide
Deal with rare events without fooling yourself.
-
Recommendation or Ranking Prototype Plan
Plan a simple recommender and its evaluation.
-
Notebook Cleanup and Structure Review
Turn an exploratory notebook into a readable one.
-
Reproducible Environment Setup
Pin versions so results can be rerun later.
-
Project Folder Structure for Analysis Work
Organize files so others can follow.
-
Code Review Checklist for Analysis Scripts
Review data code for correctness, not just style.
-
Parameterized Reports from Notebooks
Run the same analysis for many inputs.
-
Explain My Analysis to a Colleague in a Handover
Document decisions, not just steps.
-
Logging and Checks Inside Data Scripts
Make scripts tell you when something is wrong.
-
Python Skill Gap Assessment for Analysts
Find what to learn next from real tasks.
-
SQL to Pandas Translation Guide
Move queries between SQL and pandas correctly.
-
Experiment Tracking Log for Analysis Work
Record what you tried and what happened.
-
Messy CSV Cleaning Plan Before Any Code
Inspect a messy file and plan the cleaning steps.
-
Pandas Merge and Join Troubleshooter
Fix wrong row counts after merging tables.
-
Datetime and Time Zone Cleaning Guide
Parse mixed timestamps without silent errors.
-
Groupby and Aggregation Recipe Builder
Choose the right aggregation for a business question.
-
Missing Data Strategy Interview
Decide how to handle nulls case by case.
-
Slow Pandas Code Performance Review
Find and fix the slowest steps.
-
Reshaping Wide and Long Tables
Pivot, melt, and stack without confusion.
-
Text Column Cleaning and Standardization
Normalize names, categories, and free text.
-
Duplicate Detection and Record Linkage Plan
Find duplicates safely without deleting good rows.
-
Data Quality Report From a DataFrame
Produce a repeatable profile of a dataset.
-
Window Functions and Rolling Calculations
Moving averages, ranks, and running totals.
-
Unit Tests for Data Transformations
Test a cleaning function with small known cases.
-
Reading Many Files into One Clean Table
Combine monthly exports with different layouts.
-
Explain This Pandas Code Line by Line
Understand inherited code before changing it.
-
Choosing Data Types to Save Memory
Right-size columns safely.
-
Pipeline from Raw Export to Analysis-Ready Table
Design a reproducible cleaning pipeline.
-
Which Statistical Test Should I Use
Pick a test from the data and question.
-
Confidence Intervals Explained With My Numbers
Understand what an interval does and does not say.
-
A/B Test Plan and Sample Size
Plan a test before collecting data.
-
Interpret My Regression Output
Read coefficients, intervals, and diagnostics.
-
Probability Puzzles Tutor
Learn probability through questions, not lectures.
-
Sampling and Bias Review
Check whether a sample can answer the question.
-
Correlation versus Causation Checklist
Test a causal claim before believing it.
-
Outlier Handling Decision Guide
Decide to keep, fix, or remove extreme values.
-
Bootstrap and Simulation Walkthrough
Estimate uncertainty with resampling.
-
Statistical Claims in the News: Fact Check
Evaluate a headline that cites a study.
-
Descriptive Statistics Summary for Non-Technical Readers
Turn a table of numbers into plain findings.
-
Survey Data Analysis Plan
Plan the analysis before looking at results.
-
Bayesian Thinking for Everyday Decisions
Update beliefs with evidence step by step.
-
Statistics Report Review Rubric
Check an analysis write-up for errors and overreach.
-
Choose the Right Chart for My Question
Match chart type to the question, not the data.
-
Chart Makeover: Before and After
Fix a cluttered or misleading chart.
-
Accessible Color Palette Builder for Charts
Colors that work for everyone.
-
Dashboard Layout Design Brief
Plan a dashboard around decisions.
-
Exploratory Plot Sequence for a New Dataset
See the data before modelling it.
-
Annotated Time Series Chart
Show change over time with context.
-
Small Multiples for Comparing Groups
Compare many groups without a tangle of lines.
-
Distribution Plots That Tell the Truth
Histograms, box plots, and violins used correctly.
-
Chart Review Rubric
Score a chart before it is published.
-
Maps and Geographic Charts Without Distortion
Choropleths, symbol maps, and their traps.
-
Presenting Uncertainty in Charts
Show error bars and intervals so people understand them.
-
Dashboard Metrics and Chart Specification Table
Specify every tile so it can be built and tested.
-
Chart Alt Text and Data Table Alternatives
Make charts usable without sight.
-
Data Visualization Critique Role-Play
Practice defending a chart to a skeptical viewer.
No prompts match those filters.