brwording - Processamento de Linguagem Natural em Português
Project description
BRWording
- Text Analytics for Portuguese Wordings
Create an easy Text Analytics in One-Line-Code
Main Features:
- Load
Excel
,CSV
andTXT
file types - Stemming
- Lemmatization
- Stopwords
- TD-IDF
- Sentimental Analysis
- Graphical interpretation
- Word Cloud
The TF-IDF was calculated by:
How to Install
pip install BRWording
pip install pdfminer-six
How to use
sintax
:
from brwording import brwording
w = brwording.wording()
w.load_file('data/example.txt',type='txt')
w.build_tf_idf(lemmatizer=True,stopwords=True)
w.tfidf
The fields to load_file
are:
2. file
: the file path
2. type
: file type, can be txt csv
or excel
3. header
: if you are reading a csv file, so you must tell if this file has a header or not (False
or True
)
0. sep
: if you are reading a csv file, you must tell what kind field separator you want
0. column
: if you read a csv
or excel
file, you must tell what column you want to parse
The method build_tf_idf
has a default True
option for both parameters.
Output
If want to see the sentimental Graphical interpretation
sintax
:
w.sentimental_graf()
You can rotate the graph if you pass rotate=True
in argument
output
You can print the same information as a table using the follow command:
sintax
:
w.sentimental_table()
if you want to create a wordcloud, just strike the folowing command, but if you want to create a cloud with your own mask, just pass you image address as picture
sintax
:
w.word_cloud(picture='none')
output
Looking for a word into colection
if you want to see what files on your colection has a word, run look2word
sintax
:
w.look2word('bonito')
New features are incoming.
enjoi!
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distributions
Hashes for brwording-0.1.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3fd3806ab9a22b123aff2c0c86b31fc0d17a56b082a1740369b1400ee7368b5f |
|
MD5 | c7c9d9ee1b062643332d293a83986f31 |
|
BLAKE2b-256 | 77483b307e91266d2c0fd78dade425adbbc1e40bfc72737efae509fa1a139300 |