Python (pandas) prompts
Pandas makes data wrangling possible, and clear steps make it repeatable. These prompts help you plan cleaning, merging and reshaping data, write and explain code, check data quality and structure notebooks for reuse. Describe your columns and show a few anonymised rows to an AI assistant, and ask for code with comments. Run the code on a copy of your data, check results against a manual sample and avoid sharing confidential datasets. Keep each notebook step small and named, so a colleague can rerun your analysis without guessing what you did.
Prompts
-
pandas Notebook Reproducibility and Hidden State Review
Check that a notebook gives the same answer from a clean start.
-
pandas Missing Data Handling Audit
Check how nulls are treated and what that does to results.
-
pandas Performance Review: Loops, apply and Vectorisation
Find slow row-by-row code and safe replacements.
-
Merge and Groupby Results Verification Checklist
Check that joins and aggregations did not change the numbers silently.
-
SQL to Pandas Translation Guide
Move queries between SQL and pandas correctly.
-
Messy CSV Cleaning Plan Before Any Code
Inspect a messy CSV file and plan the cleaning steps in pandas before you write any code, with checks to run at each step.
-
Pandas Merge and Join Troubleshooter
Fix wrong row counts after merging tables.
-
Datetime and Time Zone Cleaning Guide
Clean datetime and time zone data in pandas, parsing mixed timestamps without silent errors, with checks for each step.
-
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.
-
Merge Validation With Indicator Columns
Prove a join did what you intended.
-
Large CSV Processing in Chunks
Handle files that do not fit in memory.
-
Nested JSON and API Data to Tidy Tables
Flatten messy nested data reliably.
-
Time Series Resampling and Gap Handling
Align irregular data to regular intervals.
-
Fuzzy Matching Names and Addresses
Link records that are almost the same.
-
Cohort Table Construction in Pandas
Build retention-style cohort tables.
-
Parsing Numbers, Currencies and Dates in Messy Columns
Clean values stored as text.
-
pandas Merge Validation: Join Cardinality Checks and Row Count Reconciliation
Join tables safely and prove nothing was lost or duplicated.
-
pandas Datetime, Time Zone and Resampling Walkthrough
Handle timestamps correctly and aggregate by period.
-
pandas Data Cleaning Pipeline With Functions and Tests
Turn a messy script into small tested steps.
-
pandas Reshaping: Pivot, Melt and Wide-to-Long Exercises With Answers
Practise reshaping with small examples.
-
pandas Memory and Speed Tuning Guide for Large CSV Files
Reduce memory use and loading time safely.
-
pandas Group-By and Aggregation Pitfalls With Verification Steps
Avoid wrong totals when summarising.
-
Data Cleaning Script Walkthrough With Assertions and a Change Log
Write a pandas cleaning script that checks itself and records what it changed.
-
Python Script to Merge CSV Files With Matching Columns
Get a commented Python script that merges many CSV files with matching columns into one, adds the source file name and reports skipped rows.
-
Merge CSV Files With Different Column Names Using a Mapping
Combine CSV exports with different column names into one tidy table using a mapping dictionary, type fixes and a report of unmapped columns.
-
Merged CSV Data Quality Report: Duplicates and Gaps
Create a data quality report for a merged CSV: duplicate rows, missing values, type mismatches and a 1 to 5 trust score with fixes to try.
No prompts match those filters.