Take NGram

TakeNGram is a tool to provide analysis of n-grams in a dataset of messages.

The recommendation usage is with the InsightExtractor Cloud CSV output.

The analysis consists in creation of a dictionary with the n-grams of all messages and their respective frequency. Besides the creation of word cloud of the n-grams.

All analysis can be made in a group of sentences of a subject (most useful with the Insight Extractor output).

Overview

• Installation
• Usage

Installation

The take_ngram package cab be installed from PyPI.

pip install take_ngram

Usage

For usage the file must have to be a CSV file.

All the examples are based on the Insight Extractor output.

1. Creating a BiGram of the sentences and get the WordCloud.

from take_ngram import NGram
bigram = NGram('file.csv',
               'Structured Message')
bigram.get_word_cloud()

2. Creating a BiGram of the sentences and saving the WordCloud.

from take_ngram import NGram
bigram = NGram('teste.csv', 
               'Structured Message')
bigram.get_word_cloud(file_path='image.png')

3. Adding stop words

from take_ngram import NGram
bigram = NGram('file.csv', 
               'Structured Message',
                stop_words = ['segunda'])
bigram.get_word_cloud(file_path='image.png')

4. Removing prepositions from stop words

• By default prepositions are added to the stop words

from take_ngram import NGram
bigram = NGram('file.csv', 
               'Structured Message', 
               remove_prepositions=False)
bigram.get_word_cloud(file_path='image.png')

5. Making n-grams for some specific subjects.

from take_ngram import NGram
bigram = NGram('file.csv', 
                'Structured Message', 
                subject_column = 'Groups', 
                subject_list = ['fatura','plano'])
bigram.get_word_cloud(file_path='image.png')

Author

Take Blip Data&Analytics Research