data-analysis

Data Analysis

Overview

Analyzes user-provided Excel (.xlsx/.xls) or CSV files using DuckDB — an in-process analytical SQL engine. Supports schema inspection, SQL querying, statistical summaries, and result export.

Poirot note: The original deer-flow skill uses a bundled scripts/analyze.py helper. Poirot doesn't bundle that script, so this version uses bash with python3 + duckdb directly. Install duckdb first: pip install duckdb.

When to Use

• User uploads Excel/CSV files and wants analysis
• User wants statistics, summaries, pivot tables, or SQL queries on data
• User wants to filter, join, or aggregate structured data

Prerequisites

# Install duckdb if not present
pip install duckdb openpyxl

Workflow

Step 1: Inspect File Structure

python3 -c "
import duckdb
con = duckdb.connect()
# For CSV
result = con.execute(\"DESCRIBE SELECT * FROM read_csv_auto('data.csv')\").fetchall()
for col in result:
    print(f'{col[0]:30s} {col[1]}')

# For Excel (each sheet = a table)
result = con.execute(\"SELECT * FROM st_read('data.xlsx', layer='Sheet1') LIMIT 0\").fetchall()

# Row count
count = con.execute(\"SELECT COUNT(*) FROM read_csv_auto('data.csv')\").fetchone()[0]
print(f'Rows: {count}')
"

Step 2: Statistical Summary

python3 -c "
import duckdb
con = duckdb.connect()
# Describe statistics
print(con.execute(\"SUMMARIZE SELECT * FROM read_csv_auto('data.csv')\").df().to_string())
"

Step 3: SQL Queries

python3 -c "
import duckdb
con = duckdb.connect()

# Aggregation
result = con.execute('''
    SELECT category, COUNT(*) as count, AVG(price) as avg_price
    FROM read_csv_auto('data.csv')
    GROUP BY category
    ORDER BY count DESC
''').fetchall()
for row in result:
    print(row)

# Join two files
result = con.execute('''
    SELECT a.id, a.name, b.amount
    FROM read_csv_auto('orders.csv') a
    JOIN read_csv_auto('payments.csv') b ON a.id = b.order_id
''').fetchall()
"