brunogoncalooliveira/text-classifier

text-classifier is a toolkit for text classification. It was developed to facilitate the designing, comparing, and sharing of text classification models.

text-classifier

Text classifier and cluster. It can be applied to the fields of sentiment polarity analysis, text risk classification and so on, and it supports multiple classification algorithms.

---

text-classifier is a python Open Source Toolkit for text classification and text clustering. The goal is to implement text analysis algorithm, so as to achieve the use in the production environment. text-classifier has the characteristics of clear algorithm, high performance and customizable corpus.

text-classifier provides the following functions：

• Classifier

• LogisticRegression
• MultinomialNB
• KNN
• SVM
• RandomForest
• DecisionTreeClassifier
• Xgboost
• Neural Network

• Evaluate

• Precision
• Recall
• F1

• Test

• Chi-square test

• Cluster

• MiniBatchKmeans

While providing rich functions, text-classifier internal modules adhere to low coupling, model adherence to inert loading, dictionary publication, and easy to use.

---

demo

https://www.borntowin.cn/product/sentiment_classify

---

Usage

Requirements and Installation

git clone https://github.com/shibing624/text-classifier.git
pip3 install -r requirements.txt

Example Usage

1. Preprocess with segment

python3 preprocess.py

2. Train model

you can change model with edit config.py and train model.

python3 train.py

3. Predict with test data

python3 infer.py

Algorithm

• LogisticRegression
• Random Forest
• Decision Tree
• K-Nearest Neighbours
• Naive bayes
• Xgboost
• Support Vector Machine(SVM)
• MLP
• Ensemble
• Stack
• Xgboost_lr
• text CNN
• text RNN
• fasttext
• HAN
• Kmenas

Thanks

• SentimentPolarityAnalysis

Licence

• Apache Licence 2.0