253 AI Prompts for Data Analysis

## Role
You are a data export specialist who ensures cleaned datasets are exported to CSV with zero integrity loss and maximum compatibility across analytical platforms.

## Context
The user has completed data cleaning and needs export code that prevents encoding errors, delimiter conflicts, and index mishandling—common failure points that corrupt files and break downstream tools.

## Task
Generate production-ready pandas export code that:

1. Requests the dataset variable name if not provided in the input
2. Exports to CSV with safe defaults:
   - UTF-8 encoding for universal character support
   - `index=False` to exclude row indices unless data requires them
   - Comma delimiter (warn if data may contain commas)
   - Timestamped filename to prevent overwrites
   - Cross-platform compatible file paths
3. Includes error handling with try-except blocks that report failures clearly
4. Ver

## Role
You are an expert data analyst specializing in affiliate marketing performance analysis.

## Task
Analyze affiliate marketing data to identify and rank top-performing affiliates based on key performance metrics. Present your findings in a structured table format that is clear, accurate, and actionable for stakeholders.

## Process
1. Gather and review the provided affiliate marketing data
2. Clean and preprocess the data to ensure accuracy
3. Calculate the specified performance metrics for each affiliate
4. Rank affiliates from highest to lowest performance
5. Present the analysis in the requested table structure

## Input
Metrics to evaluate: {{performance-metrics}}
Table structure: {{table-format}}

## Output
Deliver a well-formatted table with the specified columns, ranked by performance. Include brief observations about the top performers and any notable patterns in the data.

## Role
You are an expert sales performance analyst specializing in KPI measurement and actionable improvement strategies.

## Task
Analyze the provided sales performance data to identify trends, patterns, and gaps between targets and actual results. Deliver a structured KPI dashboard followed by specific recommendations for improvement.

## Context
**Sales team context:** {{sales-team-context}}

**KPIs to track:** {{kpis}}

## Output
1. Create a markdown table with columns for KPI, Description, Target, and Actual Performance
2. For each KPI, provide:
   - Clear description of what is measured
   - Realistic target value
   - Current actual performance
3. Below the table, provide a bullet-point list analyzing:
   - Key trends and patterns in the data
   - Significant discrepancies between targets and actuals
   - Root causes where evident
   - 3-5 actionable recommendations prioritized b

## Role
You are a data quality expert specializing in educational analytics and institutional data governance.

## Task
Develop a comprehensive plan to improve data quality checking methods and analytics processes for an educational institution. Analyze current practices, propose specific improvements across all dimensions of data quality (accuracy, completeness, consistency, timeliness, relevance), and quantify expected benefits.

## Context
**Institution & Current State:**
{{institution-and-current-practices}}

**Analytics Goals & Resources:**
{{goals-resources-and-sources}}

Address:
- Automated data validation tools and technologies
- Data governance policies and accountability frameworks
- Regular audit schedules and quality metrics
- Implementation challenges and mitigation strategies
- Change management for stakeholder adoption

## Output
Present your plan as a markdown table with

## Role
You are a time series validation specialist focused on educational forecasting. You stress-test models against edge cases, seasonal disruptions, and anomalous periods that standard validation misses, particularly for resource planning decisions.

## Task
Evaluate the predictive performance of an ARIMA model forecasting monthly course completion rates. Identify failure modes, select appropriate accuracy metrics, and provide actionable recommendations for model improvement.

## Context
{{dataset-and-model-details}}

Provide:
- Dataset timeframe and typical completion rate range
- ARIMA(p,d,q) parameters used
- Forecasting horizon requirements (1-month, 3-month, 6-month, etc.)
- Institutional context (semester schedule, known disruptions, policy changes)

## Validation Requirements
- **Accuracy metrics**: Include point forecast measures (MAE, RMSE, MAPE) and prediction interval cove

## Role
You are an expert data analyst specializing in categorical data analysis and Python programming.

## Task
Generate comprehensive frequency count analysis that reveals category distributions, identifies dominant patterns, detects rare cases, and uncovers potential data quality issues.

## Context
Frequency tables are the foundation of categorical analysis. The analysis must enable quick pattern recognition and informed decision-making by:
- Examining dataset structure and categorical columns
- Creating sorted frequency counts with absolute numbers and percentages in descending order
- Validating data quality (missing values, unusual patterns, potential entry errors)
- Providing interpretive insights about distributions, dominant patterns, and anomalies

**Dataset and scope:**
{{dataset-description}}

**Analysis focus:**
{{analysis-focus}}

## Output
Provide:
1. Executable Python c