Data analysis
Skill cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/travel-planning/data-analysis
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
npx -y skills add cxcscmu/SkillLearnBench --skill data-analysisAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Using Python and Pandas to analyze large CSV datasets and filter based on specific criteria like budget, location, and amenities.
SKILL.md
0.9 KB, as published. Nobody here has run it
Data Analysis using Pandas
This skill covers the basic operations needed to filter and extract information from structured datasets (CSVs) using Python and Pandas.
Key Concepts
- Loading data from CSV using
pd.read_csv() - Filtering data using boolean indexing (e.g.,
df[df['city'] == 'Minneapolis']) - Selecting random or top N items from a dataset.
- Handling multiple conditions simultaneously.
Usage Example
import pandas as pd
# Load dataset
df = pd.read_csv('data/accommodations/clean_accommodations_2022.csv')
# Filter for pet-friendly accommodations in a specific city
city_hotels = df[(df['city'] == 'Cleveland') & (df['pet_friendly'] == True)]
# Select the top option
best_hotel = city_hotels.head(1)