In cloudyr/aws.comprehend: Client for 'AWS Comprehend'

AWS Comprehend Client Package

aws.comprehend is a package for natural language processing.

Code Examples

All of the functions (except detect_medical_*) accept either a single character string or a character vector. Note that AWS currently limits batch queries to 25 documents, so character vectors should have 25 elements maximum.

The default language is English ("en") but this is easily changed using the language argument.

# to prevent data.frame wrapping in the outputs below
options(width = 150)

Sentiment analysis

library("aws.comprehend")

detect_sentiment("I have never been happier. This is the best day ever.")

# Sentiment analysis in Spanish
detect_sentiment("¡Hoy estoy feliz!", language = "es")

Language detection

# simple language detection
detect_language("This is a test sentence in English")

# multi-lingual language detection
detect_language("A: ¡Hola! ¿Como está, usted? B: Bien, merci. Et toi?")

Named Entity Recognition

txt <- c("Amazon provides web services.", "Jeff is their leader.")
detect_entities(txt)

Key Phrase Detection

txt <- c("Amazon provides web services.", "Jeff is their leader.")
detect_phrases(txt)

Syntax Analysis

detect_syntax("The quick fox jumps over the lazy dog.")

Medical Entity and Personal Health Information (PHI) Detection

# medical entity detection
medical_txt <- "Pt is 40yo mother, highschool teacher. HPI : Sleeping trouble on present dosage of Clonidine."
detect_medical_entities(medical_txt)

# Protected Health Information (PHI) detection
detect_medical_phi(medical_txt)

Setting up credentials

To use the package, you will need an AWS account and to enter your credentials into R. Your keypair can be generated on the IAM Management Console under the heading Access Keys. Note that you only have access to your secret key once. After it is generated, you need to save it in a secure location. New keypairs can be generated at any time if yours has been lost, stolen, or forgotten. The aws.iam package profiles tools for working with IAM, including creating roles, users, groups, and credentials programmatically; it is not needed to use IAM credentials.

A detailed description of how credentials can be specified is provided at: https://github.com/cloudyr/aws.signature/. The easiest way is to simply set environment variables on the command line prior to starting R or via an Renviron.site or .Renviron file, which are used to set environment variables in R during startup (see ? Startup). They can be also set within R:

Sys.setenv("AWS_ACCESS_KEY_ID" = "mykey",
           "AWS_SECRET_ACCESS_KEY" = "mysecretkey",
           "AWS_DEFAULT_REGION" = "us-east-1",
           "AWS_SESSION_TOKEN" = "mytoken")

Installation

You can install this package from CRAN or, to install the latest development version, from the cloudyr drat repository:

# Install from CRAN
install.packages("aws.comprehend")

# Latest version passing CI tests, from drat repo
install.packages("aws.comprehend", repos = c(getOption("repos"), "http://cloudyr.github.io/drat"))

You can also pull a potentially unstable version directly from GitHub, using the remotes package:

remotes::install_github("cloudyr/aws.comprehend")

---

cloudyr/aws.comprehend documentation built on March 25, 2020, 4:35 p.m.