https://github.com/roscibely/gender-classification

Predicting Gender Using Character-level Machine Learning 🙋 🙋‍♂️
https://github.com/roscibely/gender-classification

cnn deep-learning deep-neural-networks deeplearning gender-classification gender-detection gender-prediction predicting-gender pytorch

Last synced: 6 months ago
JSON representation

Predicting Gender Using Character-level Machine Learning 🙋 🙋‍♂️

• Host: GitHub
• URL: https://github.com/roscibely/gender-classification
• Owner: roscibely
• Created: 2021-04-30T19:43:22.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2023-03-07T16:06:52.000Z (about 2 years ago)
• Last Synced: 2023-03-08T18:47:16.598Z (about 2 years ago)
• Topics: cnn, deep-learning, deep-neural-networks, deeplearning, gender-classification, gender-detection, gender-prediction, predicting-gender, pytorch
• Language: Python
• Homepage: https://arxiv.org/abs/2106.10156
• Size: 6.3 MB
• Stars: 4
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Predicting Gender by First Name Using Character-level Machine Learning

We classified the gender of Brazilian names using deep learning and machine learning. See the document [here](https://arxiv.org/abs/2106.10156).

## Download the dataset

```python

    url = "https://data.brasil.io/dataset/genero-nomes/nomes.csv.gz"

    filename = url.split("/")[-1]

    with open(filename, "wb") as f:

        r = requests.get(url)

        f.write(r.content)

```

## Deep learning models 

Models: ![CNN](https://github.com/roscibely/Gender-Classification/blob/main/models/CNN.h5), ![MLP](https://github.com/roscibely/Gender-Classification/blob/main/models/DNN.h5), ![RNN](https://github.com/roscibely/Gender-Classification/blob/main/models/RNN.h5), ![BiLSTM](https://github.com/roscibely/Gender-Classification/blob/main/models/LSTM.h5), ![GRU](https://github.com/roscibely/Gender-Classification/blob/main/models/GRU.h5). 

Usage is simple. 

```python

    testename = prepare_encod_names({"cibely"})   # name are encod as a vector of numbers

    resu=(LSTMmodel.predict(testename) > 0.5).astype("int32")

    if int(resu)==1:

      print('M')

    else:

      print('F')

      

    out: F

```

 ## Papers

 

 R. C. B. Rego, G. d. S. Nascimento, D. E. d. L. Rodrigues, S. M. Nascimento and V. M. L. Silva, ["Brazilian scientific productivity from a gender perspective during the Covid-19 pandemic: classification and analysis via machine learning,"](https://ieeexplore.ieee.org/document/10015223) in IEEE Latin America Transactions, vol. 21, no. 2, pp. 302-309, Feb. 2023, doi: 10.1109/TLA.2023.10015223.

    

  Rego, R. C., Silva, V. M. & Fernandes, V. M. (2021). [Predicting Gender by First Name Using Character-level Machine Learning](https://arxiv.org/abs/2106.10156v2). arXiv preprint arXiv:2106.10156 v2.  

  

 Rego, R. C., & Silva, V. M. (2021). [Predicting gender of Brazilian names using deep learning](https://arxiv.org/abs/2106.10156v1). arXiv preprint arXiv:2106.10156 v1.