Analyze Csv Files

When to use this skill

Use this skill when the user needs to:

• Load and inspect a CSV or TSV file
• Get summary statistics (row count, column types, missing values)
• Filter, sort, or search rows by conditions
• Aggregate data (group by, sum, count, average)
• Find top/bottom N items by a column
• Answer specific questions about CSV data
• Clean CSV data (fix types, handle missing values, deduplicate)

Prerequisites

pip install pandas tabulate

Quick Inspection

Always start by inspecting the file before any analysis:

import pandas as pd

df = pd.read_csv("data.csv")

print(f"Shape: {df.shape[0]} rows × {df.shape[1]} columns\n")
print(f"Columns and types:\n{df.dtypes.to_string()}\n")
print(f"First 5 rows:\n{df.head().to_markdown(index=False)}\n")

missing = df.isnull().sum()
if missing.any():
    print(f"Missing values:\n{missing[missing > 0].to_string()}")