GitHub Copilot Prompt for Analyzing a Survey
Survey analysis is a crucial step for extracting actionable insights from raw data. GitHub Copilot, with its code generation and contextual understanding capabilities, becomes a powerful ally for automating response processing, identifying statistical trends, and producing relevant visualizations. Whether you work with CSV files exported from Google Forms, Typeform, or SurveyMonkey, Copilot can help you quickly write Python or R code to clean data, calculate distributions, perform cross-tabulations, and generate clear charts. Instead of spending hours manually manipulating spreadsheets, you can describe in natural language what you want to analyze and have Copilot generate the corresponding code. This approach is particularly effective for product teams, UX researchers, and marketing managers who need to quickly transform hundreds of responses into concrete recommendations. The prompt below is designed to maximize the relevance of Copilot's suggestions by clearly structuring your analysis expectations.
Paste in your AI
Paste this prompt in ChatGPT, Claude or Gemini and customize the variables in brackets.
Comprehensive survey analysis
Source file: survey_results.csv
Columns: timestamp, age_group, satisfaction (1-5), recommend (yes/no), open_feedback
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
1. Load data and display a statistical summary (number of respondents, completion rate, distribution by age group)
2. Calculate overall average satisfaction score and by demographic segment (age_group)
3. Calculate Net Promoter Score (NPS) from the recommend column
4. Identify correlations between satisfaction and likelihood to recommend
5. Extract recurring themes in open-ended responses (open_feedback) with a keyword frequency count
6. Generate 4 visualizations: satisfaction distribution (histogram), NPS by segment (barplot), word cloud of feedback, correlation matrix
7. Produce an executive summary in markdown with top 5 insights and 3 actionable recommendations
Personalize this prompt with Léa
Answer 3 questions and Léa tailors the prompt to your situation.
Why this prompt works
This prompt works because it provides Copilot with the full dataset context (file name, exact columns, data types) and breaks down the analysis into precise numbered steps. The sequential comment structure guides Copilot to generate code block by block rather than a monolithic response. Including specific metrics (NPS, correlations, text analysis) forces technically relevant suggestions rather than generic code.
Use Cases
Variants
Expected Output
Copilot generates a complete Python script that loads the CSV, produces descriptive statistics by segment, calculates NPS, and creates four professional visualizations using Matplotlib and Seaborn. The script also includes a term frequency analysis of open responses and an executive summary formatted in markdown ready to share with stakeholders.
Frequently Asked Questions
Can GitHub Copilot analyze a CSV file directly without me writing any code?
No, GitHub Copilot does not process data files directly. It works as a coding assistant that generates analysis scripts based on your descriptive comments. You need to open a Python or Jupyter Notebook file in VS Code, describe your analysis in comments, and Copilot will suggest the corresponding code. The advantage is that you get a reproducible pipeline you can re-run with every new batch of responses.
How do I adapt the prompt if my survey uses different scales (7-point Likert, multiple choice, ranking)?
Modify the prompt comments to explicitly specify the type and scale of each question. For example, replace 'satisfaction (1-5)' with 'satisfaction (Likert 1-7)' or 'multiple_choice (values: A, B, C, D)'. The more precise you are about the data structure, the better Copilot will generate suitable code. For multiple-choice questions with comma-separated values in a single cell, add a comment indicating the format: '# favorite_features column: multiple values separated by commas, split using str.split'.
Can Copilot help me analyze open-ended responses from a survey in French?
Yes, but with a few precautions. In your prompt, explicitly state that the texts are in French so Copilot uses the correct stopwords and tokenization parameters. Add a comment like '# Texts in French: use French stopwords from NLTK and spaCy fr_core_news_sm for NLP'. Copilot will then suggest code with the appropriate libraries and language models. For sentiment analysis in French, it will guide you toward models like CamemBERT rather than English-specific tools.
Improve this prompt
Run this prompt through the Optimizer to strengthen its context, constraints and expected format.
Improve this prompt with the OptimizerComments
Be the first to comment on this prompt.
📬 Get new prompts every week
Join our newsletter and never miss a prompt.
Go further
Similar Prompts
Build a recommendation system
Build recommendation systems
Create an automated EDA report
Generate EDA reports automatically
Mistral Prompt for Analyzing Market Trends
Mistral, the leading French AI model, excels at analyzing textual data and synthesizing complex information, making it a particularly well-suited tool for market trend analysis. Whether you are a strategic analyst, entrepreneur, or marketing manager, leveraging Mistral to decipher weak signals, identify underlying shifts, and anticipate changes in your industry gives you a decisive competitive edge. Thanks to its nuanced understanding of French and its ability to process large corpora, Mistral can cross-reference diverse sources—industry reports, economic data, customer feedback, specialized publications—to produce structured and actionable analyses. This guide provides an optimized prompt to turn Mistral into a true trend analyst, capable of spotting emerging patterns, quantifying their potential impact, and formulating strategic recommendations tailored to your context. Learn how to structure your queries to obtain professional-quality market analyses that are reproducible and directly usable in your decision-making processes.
Apply dimensionality reduction
Reduce high-dimensional data