jpchagas

[tool.poetry]
name = "fetcher"
version = "0.1.0"
description = ""
authors = [""]
readme = "README.md"

[tool.poetry.dependencies]
python = ">=3.10,<4.0"

jpchagas

"""
Script do run quality checkers automatically
"""

import subprocess


def run_quality_checks():
    """
    Run a series of quality checks including Black, isort, flake8, and pytest with coverage.

jpchagas

repos:
  - repo: https://github.com/psf/black
    rev: 24.8.0
    hooks:
      - id: black
        language_version: python3

  - repo: https://github.com/PyCQA/isort
    rev: 5.13.2
    hooks:

jpchagas

[flake8]
max-line-length = 88
ignore = E203, E266, E501, W503
exclude = .git,_pycache_,docs,build,dist,data,models,app.log,.ipynb_checkpoints, experiment.ipynb

jpchagas

import xml.etree.ElementTree as ET
files = os.listdir(BASE_PATH)
xml_files = [x for x in files if x.endswith(".xml")]
for file in xml_files:
    try:
        filename=file.replace(".xml",".png")
        tree = ET.parse(BASE_PATH +file)
        root = tree.getroot()
        xml_path = root[2].text
        ssize = root[4]

jpchagas

<annotation>
	<folder>FerreiraIbelli</folder>
	<filename>scene00631.png</filename>
	<path>/home/jpchagas/Projects/haole/data/videos/aus_margaret/FerreiraIbelli/scene00631.png</path>
	<source>
		<database>Unknown</database>
	</source>
	<size>
		<width>1280</width>
		<height>720</height>

jpchagas

X_insta = cv.fit_transform(instagram_df['comment']).toarray()
y_insta_pred_gnb = gnb.predict(X_insta)
y_insta_pred_mnb = mnb.predict(X_insta)
y_insta_pred_bnb = bnb.predict(X_insta)

jpchagas

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB, GaussianNB, BernoulliNB
from sklearn import metrics

cv = CountVectorizer(max_features=150)
X = cv.fit_transform(imdb_df['text_pt']).toarray()
y = imdb_df.iloc[:,-1].values
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2,random_state=42)
gnb = GaussianNB()

jpchagas

import nltk

stemmer = nltk.stem.RSLPStemmer()
text_stemmed = [stemmer.stem(word) for word in text_without_sw]

jpchagas

import nltk
from nltk.tokenize import word_tokenize

stop_words = nltk.corpus.stopwords.words('portuguese')
text_word_tokens = word_tokenize(df['text_pt'])
text_without_sw = [word for word in text_word_tokens if word not in stop_words]