This is a demo of several of Algorithmia's open-data extraction and time-series analysis tools, including:
- Socrata Open Data Query - pulls the permit data from Socrata
- Simple Moving Average - uses local average to smooth data
- Linear Detrend - removes increasing or decreasing trends in time series
- Autocorrelate - used to analyze the seasonality of a time series
- Remove Seasonality - removes known seasonal effects from a time series
- Outlier Detection - flags unusual data points
- Forecast - predict a given time series into the future
With this demo, one can analyze Socrata Open Data; forecast, auto-correlate, and detect outliers; and filter the data with seasonality and detrending.
This demo can be viewed at https://demos.algorithmia.com/timeseries
This demo only contains frontend code and requires no specialized hosting (or even a server).
- download the repository
- edit /JavaScript/timeseries/public/js/main.js to place your own API Key (free signup) in the line containing "Algorithmia.client()"
- if you have not already, run the setup steps outlined in /PUBLISH.md
- build the demo:
grunt build:timeseries - open /build/timeseries/index.html in a web browser
Find more information in the Algorithmia Developer Center or the API Docs.