devtools::install_github(repo = "tjmooney1/ExamineR",
auth_token = "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")
ExamineR is a small package, made up of a variety of multi-purpose functions which aim to assist throughout the Exploratory data analysis stages, data cleaning and even visualization.
Once installed from Git, simply load ExamineR in from the package library to get started.
library(ExamineR)
ExamineR, for the most part, is a tool to assist users with Text Mining, Natural Language Processing(NLP) and Qualitative Data Analysis.
Here are some typical use cases of how best to leverage the package.
Starting with some visualization, lets look at the
plot_token_counter function that shows what terms are
appearing most frequently throughout any one text variable.
ExamineR::plot_token_counter(data = data, text_var = clean_text, n = 20, text_size = 13, fill = "#89CFF0")
When wanting to visualize any comparisons of group variables, the
user may want to count distributions across the groups. In this example,
we’ll use the plot_group_sentiment function that shows us
the sentiment breakdown of posts across the identified
groups(clusters)
ExamineR::plot_group_sentiment(data = data, group_var = cluster_name, sentiment_var = sentiment)
The user may also want to visualize the volume of posts as well as
sentiment distribution across the data time frame. This can be done by
making use of the plot_group_vot_sentiment function.
ExamineR::plot_group_vot_sentiment(data = data, sentiment_var = sentiment, date_var = date, group_var = cluster_name, unit = "month")