Cats in the USA

An Interactive Dashboard for Detecting Patterns and Outliers in Animal Tracking Data

This proposal is for an interactive dashbaord to explore movement data of pet cats in the United States, aiming to uncover spatial patterns and detect outliers.

Author

Affiliation

Nessa Pantfoerder

College of Information Science, University of Arizona

import pandas as pd
import numpy as np

Dataset

cats = pd.read_csv("data/pet-cats-usa.csv")
cats_ref = pd.read_csv("data/pet-cats-usa-reference-data.csv")

The dataset used is “Pet Cats United States” from the Movebank Data Repository. This dataset contains GPS tracking data for pet cats in the United States and includes variables such as timestamps, animals IDs, sex, age, location coordinates, and movement attributes. The main dataset “pet-cats-usa.csv” has 659770 rows and 15 columns. The reference dataset “pet-cats-usa-reference-data.csv” has 154 rows and 21 columns. This datasets is ideal for spatial and temporal analysis and its size is well suited for data mining and interactive data visualization. I chose this dataset because it allows for movement pattern detection as well as outlier detections which is ideal for discovering interesting behavioral insights into the ecological impact of pet cats in the United States.

Questions

What movement patterns do pet cats in the United States exhibit?
Can we identify potential outliers or unusual behaviors in cat movement data?

Analysis plan

For Question 1 I can:
- Visualize cat movement paths on a map using location-lat, location-long, and timestamp.
- Group movement patterns by animal-sex and animal-life-stage.
- Summarize key statistics such as average daily travel distance
For Question 2 I can:
- Identify outliers using ground-speed, algorithm-marked-outlier, and manually-marked-outlier.
- Highlight unusual behaviors
- Create filters for users to view specific subsets of cats

Timeline

Week 5: Perform basic exploratory analysis and explore static visualizations that could be used for the dashboard.
Week 6: Develop dashboard components with outliers and filtering features.
Week 7: Finalize dashboard and submit project write-up.

Project Organization

final-project-nessapantfoerder/
│
├── data/
│   ├── pet-cats-usa.csv
│   ├── pet-cats-usa-reference-data.csv
│   └── README.md           # Description of the data files
│
├── _extra/
│   └── analysis.ipynb      # Initial exploratory analysis
│   └── README.md           # Purpose of the folder
│
├── images/                 # Any images needed for the presentation or website
│
├── about.qmd               
├── index.qmd               
├── presentation.qmd        
├── proposal.qmd            
├── _quarto.yml             
├── README.md            
└── requirements.txt

--- title: "Cats in the USA" subtitle: "An Interactive Dashboard for Detecting Patterns and Outliers in Animal Tracking Data" author: - name: "Nessa Pantfoerder" affiliations: - name: "College of Information Science, University of Arizona" description: "This proposal is for an interactive dashbaord to explore movement data of pet cats in the United States, aiming to uncover spatial patterns and detect outliers." format: html: code-tools: true code-overflow: wrap code-line-numbers: true embed-resources: true editor: visual code-annotations: hover execute: warning: false eval: true jupyter: python3 --- ```{python} #| label: load-pkgs #| message: false import pandas as pd import numpy as np ``` ## Dataset ```{python} #| label: load-dataset #| message: false cats = pd.read_csv("data/pet-cats-usa.csv") cats_ref = pd.read_csv("data/pet-cats-usa-reference-data.csv") ``` The dataset used is "Pet Cats United States" from the Movebank Data Repository. This dataset contains GPS tracking data for pet cats in the United States and includes variables such as timestamps, animals IDs, sex, age, location coordinates, and movement attributes. The main dataset "pet-cats-usa.csv" has `{python} cats.shape[0]` rows and `{python} cats.shape[1]` columns. The reference dataset "pet-cats-usa-reference-data.csv" has `{python} cats_ref.shape[0]` rows and `{python} cats_ref.shape[1]` columns. This datasets is ideal for spatial and temporal analysis and its size is well suited for data mining and interactive data visualization. I chose this dataset because it allows for movement pattern detection as well as outlier detections which is ideal for discovering interesting behavioral insights into the ecological impact of pet cats in the United States. ## Questions 1. What movement patterns do pet cats in the United States exhibit? 2. Can we identify potential outliers or unusual behaviors in cat movement data? ## Analysis plan - For Question 1 I can: - Visualize cat movement paths on a map using `location-lat`, `location-long`, and `timestamp`. - Group movement patterns by `animal-sex` and `animal-life-stage`. - Summarize key statistics such as average daily travel distance - For Question 2 I can: - Identify outliers using `ground-speed`, `algorithm-marked-outlier`, and `manually-marked-outlier`. - Highlight unusual behaviors - Create filters for users to view specific subsets of cats ## Timeline - Week 5: Perform basic exploratory analysis and explore static visualizations that could be used for the dashboard. - Week 6: Develop dashboard components with outliers and filtering features. - Week 7: Finalize dashboard and submit project write-up. ## Project Organization ``` final-project-nessapantfoerder/ │ ├── data/ │ ├── pet-cats-usa.csv │ ├── pet-cats-usa-reference-data.csv │ └── README.md # Description of the data files │ ├── _extra/ │ └── analysis.ipynb # Initial exploratory analysis │ └── README.md # Purpose of the folder │ ├── images/ # Any images needed for the presentation or website │ ├── about.qmd ├── index.qmd ├── presentation.qmd ├── proposal.qmd ├── _quarto.yml ├── README.md └── requirements.txt ```