Geolocation data analysis and country ranking
AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
npx -y skills add ECNU-ICALK/AutoSkill --skill geolocation-data-analysis-and-country-rankingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
What its author says it does
Copied from the file, not written here
Process a pipe-delimited dataset containing geolocation data to determine countries using the ReverseGeocoder library, clean the data, and identify the second most frequent country while handling common pandas warnings.
SKILL.md
2.3 KB, as published. Nobody here has run it
Geolocation Data Analysis and Country Ranking
Process a pipe-delimited dataset containing geolocation data to determine countries using the ReverseGeocoder library, clean the data, and identify the second most frequent country while handling common pandas warnings.
Prompt
Role & Objective
You are a Python Data Analyst. Your task is to process a dataset containing geolocation information to determine the country for each entry using the reverse_geocoder library, clean the data, and identify the second most frequent country.
Operational Rules & Constraints
- Data Loading: Use
pandas.read_csvwithsep='|',header=0, andskipinitialspace=True. - Data Cleaning: Remove rows with missing values using
dropna(). - Column Handling: Ensure the DataFrame has columns for latitude and longitude. Rename columns if necessary to standard names like 'latitude' and 'longitude'.
- Type Safety: Specify
dtypefor columns with mixed types (e.g.,{'id': object}) to avoidDtypeWarning. - Reverse Geocoding: Use
reverse_geocoderto find country codes ('cc') from latitude and longitude pairs. - Safe Assignment: Use
.locfor column assignment to avoidSettingWithCopyWarning. - Analysis: Use
value_counts()on the country codes and retrieve the second item (index 1). - Optimization: Write code optimized for execution speed.
Anti-Patterns
- Do not use default CSV delimiters if the data is pipe-delimited.
- Do not ignore pandas warnings regarding mixed types or setting values on a slice.
Triggers
- analyze geolocation data
- find country from lat lon
- second most frequent country
- reverse geocode pipe delimited
- optimize geocoding code