clean_trajectory

Validate and clean GPS trajectory files with geohash encoding.

Updated Jun 2, 2026
One-click install
npx skills add https://github.com/bettercallfan/deerflow --skill clean-trajectory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: clean_trajectory
Source: https://github.com/bettercallfan/deerflow/tree/main/skills/custom/spatiotemporal_trajectory/clean_trajectory
Command: npx skills add https://github.com/bettercallfan/deerflow --skill clean-trajectory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, numpy, pandas, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the cleaning of raw GPS, check-in, signaling, taxi, or user mobility trajectory files, ensuring accurate spatial data for further analysis.

Core Features & Use Cases

  • Coordinate Validation: Validates GPS coordinates for accuracy.
  • Timestamp Normalization: Ensures timestamps are correctly formatted.
  • Duplicate Removal: Eliminates duplicate points from trajectory data.
  • Speed Threshold Filtering: Filters out points with abnormal speed jumps.
  • Geohash Encoding: Standardizes trajectory points for efficient spatial analysis.
  • Use Case: When preparing raw trajectory data for spatial analysis, such as mapping, heat maps, or pattern detection.

Quick Start

Use the clean_trajectory skill with the command: cd /mnt/skills/custom/clean_trajectory && python3 scripts/clean_trajectory.py --input /path/to/raw.csv --output-dir /path/to/output

Frequently Asked Questions about clean_trajectory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I clean raw GPS trajectory data for spatial analysis?

To clean raw GPS trajectory data for spatial analysis, use a script that validates coordinates, normalizes timestamps, removes duplicates, filters abnormal speeds, and encodes points with geohash for accurate results.

What is the best way to remove duplicate points and abnormal speeds from mobility trajectory files?

The best way to remove duplicates and filter abnormal speeds from mobility trajectory files is by applying automated threshold filtering and duplicate elimination to ensure accurate spatial coordinates and timestamps.

Do I need Python and pandas to validate GPS coordinates and normalize timestamps?

Yes, you need Python3, numpy, and pandas to validate GPS coordinates and normalize timestamps, as these libraries are required for the data processing and validation operations.

Can I use geohash encoding to standardize check-in and signaling trajectory data?

Yes, you can use geohash encoding to standardize check-in and signaling trajectory data, which converts validated spatial coordinates into an efficient format for spatial analysis.

What types of trajectory files are supported for data cleaning and validation?

Supported trajectory file types include raw GPS, check-in, signaling, taxi, and user mobility trajectory files, all of which can be validated and cleaned for accurate spatial coordinates and timestamps.

Why does my trajectory data cleaning fail when processing raw CSV inputs?

Trajectory data cleaning may fail if Python3, numpy, and pandas are not properly installed, or if the input CSV path is incorrect, preventing successful validation and output generation.