Developer Center

Resources to get you started with Algorithmia

Sentiment Timeseries Forecast Pipeline

Updated

Available on GitHub.

Time series forecasting algorithms are a common method for predicting future values based on historical data using sequential data, such as snowfall per hour, customer sign-ups per day, or quarterly sales data.

In this R recipe, we’ll show how to easily link algorithms together to create a data analysis pipeline for sentiment time series forecasting.

For the full blog post related to this recipe, see Forecasting Sentiment Analyis with R.

Getting Started

Install the Algorithmia package and stats library from CRAN, and load them in your R environment:

 
install.packages("Algorithmia")
install.packages("stats")

library(algorithmia)
library(stats)
 

You’ll also need a free Algorithmia account, which includes 5,000 free credits a month.

Sign up here, and then grab your API key.

Find this line in the script:

 
client <- getAlgorithmiaClient("YOUR_API_KEY")
 

and add in your API key.

How to Analyze Timeseries Sentiment

After putting in your own API key to the line above run it in your console environment:

  sent_forecast.R 

Built With