ChatGPT、Claude和Gemini 可以实现数据分析辅助。

近期看到篇文章，有人做了能力评估。

评估标准：
1. 完整性：报告是否覆盖数据检查、数据清理、单变量分析、多变量分析和洞察。
2. 准确性：统计计算、可视化和结论的准确性。
3. 可视化质量：可视化是否清晰、易于理解且与报告相关。
4. 深刻性：报告是否基于识别出的模式、趋势或关系生成了见解。
5. 可重复性和文档化：报告是否文档齐全，允许他人重复分析。

评估数据集：Kaggle上的客户个性分析数据集。
https://t.co/5S3ePb1n5v

任务要求：数据清理、分析和可视化，清晰的洞察和可行的建议。

结果：
ChatGPT-4o：总分19/20，表现最佳，特别是在完整性、准确性和深刻性方面。

Claude 3.5 Sonnet：总分16/20，主要缺点是无法直接运行Python代码和显示可视化。

Gemini Advanced：总分19/20，与ChatGPT并列第一，但在可视化方面略显杂乱。

Prompt：

You are a data scientist at a grocery chain. 
You have a dataset with your customers' demographic info, 
purchase data, and marketing campaign history. 
Your objective today is to conduct a thorough exploratory data analysis (EDA) 
of this dataset with necessary data cleaning, analysis and visualizations, 
clear insights, and actionable recommendations. 
Your EDA will be used to better understand the customers, 
influence product strategies based on customer behaviors, 
and inform further customer segment analysis and modeling.

Here are the column descriptions:
1. People
-ID: Customer's unique identifier
-Year_Birth: Customer's birth year
-Education: Customer's education level
-Marital_Status: Customer's marital status
-Income: Customer's yearly household income
-Kidhome: Number of children in customer's household
-Teenhome: Number of teenagers in customer's household
-Dt_Customer: Date of customer's enrollment with the company
-Recency: Number of days since customer's last purchase
-Complain: 1 if the customer complained in the last 2 years, 0 otherwise
2. Products
-MntWines: Amount spent on wine in last 2 years
-MntFruits: Amount spent on fruits in last 2 years
-MntMeatProducts: Amount spent on meat in last 2 years
-MntFishProducts: Amount spent on fish in last 2 years
-MntSweetProducts: Amount spent on sweets in last 2 years
-MntGoldProds: Amount spent on gold in last 2 years
3. Promotion
-NumDealsPurchases: Number of purchases made with a discount
-AcceptedCmp1: 1 if customer accepted the offer in the 1st campaign, 0 otherwise
-AcceptedCmp2: 1 if customer accepted the offer in the 2nd campaign, 0 otherwise
-AcceptedCmp3: 1 if customer accepted the offer in the 3rd campaign, 0 otherwise
-AcceptedCmp4: 1 if customer accepted the offer in the 4th campaign, 0 otherwise
-AcceptedCmp5: 1 if customer accepted the offer in the 5th campaign, 0 otherwise
-Response: 1 if customer accepted the offer in the last campaign, 0 otherwise
4. Place
-NumWebPurchases: Number of purchases made through the company’s website
-NumCatalogPurchases: Number of purchases made using a catalogue
-NumStorePurchases: Number of purchases made directly in stores
-NumWebVisitsMonth: Number of visits to company’s website in the last month https://pbs.twimg.com/media/GVaaeNwaIAADFhk.jpg