---
title: "Data Analyst Agent"
sidebarTitle: "Data Analyst"
description: "Learn how to create AI agents for data analysis and insights generation."
icon: "chart-line"
---

```mermaid
flowchart LR
    In[Data Source] --> Reader[Data Reader]
    Reader --> Analyzer[Data Analyzer]
    Analyzer --> Generator[Insights Generator]
    Generator --> Out[Output]
    
    style In fill:#8B0000,color:#fff
    style Reader fill:#2E8B57,color:#fff
    style Analyzer fill:#2E8B57,color:#fff
    style Generator fill:#2E8B57,color:#fff
    style Out fill:#8B0000,color:#fff
```

A workflow demonstrating how the Data Analyst Agent can read data from various sources, analyze it, and generate insights.

## Quick Start

<Steps>
    <Step title="Install Package">
        First, install the PraisonAI Agents package:
        ```bash
        pip install praisonaiagents
        ```
    </Step>

    <Step title="Set API Key">
        Set your OpenAI API key as an environment variable:
        ```bash
        export OPENAI_API_KEY=your_api_key_here
        ```
    </Step>

    <Step title="Create Script">
        Create a new file `data_analysis.py`:
        ```python
        from praisonaiagents import Agent, Tools
        from praisonaiagents.tools import (
            read_csv, read_excel, write_csv, write_excel,
            filter_data, get_summary, group_by, pivot_table
        )

        agent = Agent(
            instructions="You are a Data Analyst Agent",
            tools=[
                read_csv, read_excel, write_csv, write_excel,
                filter_data, get_summary, group_by, pivot_table
            ]
        )

        # Start analysis with a specific task
        agent.start(f"""
            Read the data from the csv file {os.path.join(os.path.dirname(__file__), "tesla-stock-price.csv")}
            Analyse the data and give me the insights
            read_csv to read the file
        """)
        ```
    </Step>
</Steps>

## Understanding Data Analysis Workflow

The Data Analyst Agent is designed to perform comprehensive data analysis tasks using a suite of specialized tools. Here's how it works:

1. **Data Reading**: The agent can read data from various sources:
   - CSV files using `read_csv`
   - Excel files using `read_excel`

2. **Data Analysis**: Multiple analysis tools are available:
   - `filter_data`: Filter datasets based on conditions
   - `get_summary`: Generate statistical summaries
   - `group_by`: Group data by specific columns
   - `pivot_table`: Create pivot tables for analysis

3. **Data Export**: Results can be exported to:
   - CSV format using `write_csv`
   - Excel format using `write_excel`

## Features

<CardGroup cols={2}>
  <Card title="Multiple Data Sources" icon="table">
    Support for both CSV and Excel file formats.
  </Card>
  <Card title="Analysis Tools" icon="calculator">
    Comprehensive suite of analysis tools including filtering, summarization, and pivoting.
  </Card>
  <Card title="Data Export" icon="file-export">
    Export capabilities to various formats.
  </Card>
  <Card title="Automated Insights" icon="lightbulb">
    Automatic generation of data insights and patterns.
  </Card>
</CardGroup>

## Example Usage

```python
# Example: Analyzing stock data
agent.start("""
    1. Read 'stock_data.csv'
    2. Filter data for the last 30 days
    3. Calculate daily returns
    4. Generate summary statistics
    5. Export results to 'analysis_results.xlsx'
""")
```

## Next Steps

- Learn about [Prompt Chaining](/features/promptchaining) for complex analysis workflows
- Explore [Evaluator Optimizer](/features/evaluator-optimiser) for improving analysis accuracy
- Check out other specialized agents like the [Finance Agent](/agents/finance) for specific use cases