Python Data Analysis
Developmentpython-data-analysisPython Data Analysis is an Agent Skill for development published in the A-EVO-Lab/a-evolve repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Best practices for multi-step Python tasks including data analysis, HuggingFace datasets, token counting, and any task requiring state across multiple python() calls.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/A-EVO-Lab/a-evolve/blob/HEAD/artifacts/tb2_clawcode_opus46/skills/python-data-analysis/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/python-data-analysis, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Python Multi-Step Tasks
RULE #1: Each python() call starts fresh — NO state carries over
Variables, imports, data from previous calls DO NOT EXIST. This is the #1 source of NameError.
DEFAULT STRATEGY: Write a complete .py script to a file, then run it.
with open('/app/solve.py', 'w') as f:
f.write('''#!/usr/bin/env python3
import numpy as np
# ALL logic in one file
data = np.load("/app/data.npy")
result = process(data)
with open("/app/answer.txt","w") as out:
out.write(str(result))
''')
Then: bash("python3 /app/solve.py && cat /app/answer.txt")
If you must use multiple python() calls:
- Save state to files between calls:
import json, numpy as np
# Save: json.dump(obj, open('/tmp/state.json','w'))
# Save: np.save('/tmp/arr.npy', array)
# Load: obj = json.load(open('/tmp/state.json'))
- Every call MUST re-import and re-load — never reference prior variables
- NameError = forgot to re-define — add missing definitions, don't just re-run
HuggingFace Datasets + Token Counting (ONE call)
from datasets import load_dataset
from transformers import AutoTokenizer
ds = load_dataset("org/name", split="train")
tok = AutoTokenizer.from_pretrained("model-name")
total = sum(len(tok.encode(r["text"])) for r in ds if r["domain"] == "science")
with open("/app/answer.txt","w") as f: f.write(str(total))
For iterative exploration, keep blocks self-contained
# Each block: imports + load + process + print
import pandas as pd
df = pd.read_csv('f.csv')
print(df.describe())
Verification
- Print/cat output files BEFORE submitting
- Confirm formats match expected schema exactly