data-analyzer

name	data-analyzer
description	Data analysis tool for Excel, CSV, Word, PDF, TXT, Markdown files. Use when user needs to analyze, summarize, or compare data from multiple files. Supports folder scanning, data aggregation, statistics, report generation in Markdown/Excel/Word/PDF. Multi-language support. 数据分析、文件夹分析、Excel分析。
version	1.0.9
license	MIT-0
metadata	{"openclaw":{"emoji":"📊","requires":{"bins":["python3"],"env":[]}}}
dependencies	pip install pandas openpyxl python-docx pymupdf matplotlib

Data Analyzer

Analyze and summarize data from Excel, CSV, Word, and PDF files.

Features

• 📊 Multi-Format Input: Excel, CSV, Word, PDF, TXT, Markdown
• 📁 Folder Scan: Analyze entire folders
• 📈 Statistics: Sum, average, trends
• 🔄 Data Merge: Combine multiple files
• 📉 Visualization: Generate charts
• 📋 Multi-Format Output: Markdown, Excel, Word, PDF
• 🌍 Multi-Language: English, Chinese output

Trigger Conditions

• "Analyze this folder" / "分析这个文件夹"
• "Compare these Excel files" / "对比这些Excel"
• "Summarize the data" / "汇总数据"
• "data-analyzer"

---

Python Code

import os
import pandas as pd
from pathlib import Path
from docx import Document
import fitz  # PyMuPDF

class DataAnalyzer:
    def __init__(self, folder_path):
        self.folder = Path(folder_path)
        self.files = self._scan_files()
    
    def _scan_files(self):
        """Scan folder for supported files"""
        files = {
            'excel': [], 'csv': [], 'word': [],
            'pdf': [], 'txt': [], 'markdown': []
        }
        
        for f in self.folder.rglob('*'):
            ext = f.suffix.lower()
            if ext in ['.xlsx', '.xls']:
                files['excel'].append(str(f))
            elif ext == '.csv':
                files['csv'].append(str(f))
            elif ext == '.docx':
                files['word'].append(str(f))
            elif ext == '.pdf':
                files['pdf'].append((f))
             ext == :
                files[].append((f))
             ext  [, ]:
                files[].append((f))
        
         files
    
     ():
        
        df = pd.read_excel(file_path)
         {: (df), : (df.columns), : df}
    
     ():
        
        df = pd.read_csv(file_path)
         {: (df), : (df.columns), : df}
    
     ():
        
        doc = Document(file_path)
        text = .join([p.text  p  doc.paragraphs  p.text.strip()])
         {: (doc.paragraphs), : text}
    
     ():
        
        doc = fitz.(file_path)
        text = 
         page  doc:
            text += page.get_text()
        result = {: (doc), : text}
        doc.close()
         result
    
     ():
        
         (file_path, , encoding=)  f:
            text = f.read()
         {: (text.split()), : text}
    
     ():
        
         (file_path, , encoding=)  f:
            text = f.read()
         {: (text.split()), : text}
    
     ():
        
        ext = Path(file_path).suffix.lower()
        
         ext  [, ]:
             .analyze_excel(file_path)
         ext == :
             .analyze_csv(file_path)
         ext == :
             .analyze_word(file_path)
         ext == :
             .analyze_pdf(file_path)
         ext == :
             .analyze_txt(file_path)
         ext  [, ]:
             .analyze_markdown(file_path)
        :
             {: }
    
     ():
        
        summary = {: , : []}
        
         ftype, flist  .files.items():
             fpath  flist:
                :
                    analysis = .analyze_file(fpath)
                    summary[].append({
                        : os.path.basename(fpath),
                        : ftype,
                        : analysis
                    })
                    summary[] += 
                 Exception  e:
                    summary[].append({
                        : os.path.basename(fpath),
                        : ftype,
                        : (e)
                    })
        
         summary

---

Usage

User: "Analyze all Excel files in this folder"
Agent: 使用 DataAnalyzer 扫描并分析

User: "Compare these CSV files"
Agent: 读取并对比数据

User: "Generate a data report"
Agent: 生成分析报告

---

Notes

• Supports .xlsx, .csv, .docx, .pdf
• Local processing, no data uploaded
• Cross-platform compatible