All Projects → InstaPy → Instapy Gender Classification

InstaPy / Instapy Gender Classification

Licence: mit
🔎 Classification helper for sex classification feature of InstaPy

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Instapy Gender Classification

Dog Cat Classification
This is a Flask app that can classify images of dog and cat. The underlying model is a CNN trained using Keras framework
Stars: ✭ 17 (-43.33%)
Mutual labels:  classification
Deep Music Genre Classification
🎵 Using Deep Learning to Categorize Music as Time Progresses Through Spectrogram Analysis
Stars: ✭ 23 (-23.33%)
Mutual labels:  classification
Servenet
Service Classification based on Service Description
Stars: ✭ 21 (-30%)
Mutual labels:  classification
Bayesian Neural Networks
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more
Stars: ✭ 900 (+2900%)
Mutual labels:  classification
Eda nlp
Data augmentation for NLP, presented at EMNLP 2019
Stars: ✭ 902 (+2906.67%)
Mutual labels:  classification
Puppet Node manager
Create and manage PE node groups as resources.
Stars: ✭ 7 (-76.67%)
Mutual labels:  classification
Logging Helpers
Basic template helpers for printing messages out to the console. Useful for debugging context in templates. Should work with any template engine.
Stars: ✭ 5 (-83.33%)
Mutual labels:  helper
Cnn Question Classification Keras
Chinese Question Classifier (Keras Implementation) on BQuLD
Stars: ✭ 28 (-6.67%)
Mutual labels:  classification
Jsmlt
🏭 JavaScript Machine Learning Toolkit
Stars: ✭ 22 (-26.67%)
Mutual labels:  classification
Tribuo
Tribuo - A Java machine learning library
Stars: ✭ 882 (+2840%)
Mutual labels:  classification
Vuex Mappers
Component agnostic Vuex mappers
Stars: ✭ 19 (-36.67%)
Mutual labels:  helper
137 Stopmove
Algorithms to automatically discover stops and moves in GPS trajectories.
Stars: ✭ 19 (-36.67%)
Mutual labels:  classification
Awesome Fraud Detection Papers
A curated list of data mining papers about fraud detection.
Stars: ✭ 843 (+2710%)
Mutual labels:  classification
Pyts
A Python package for time series classification
Stars: ✭ 895 (+2883.33%)
Mutual labels:  classification
Bmw Classification Inference Gpu Cpu
This is a repository for an image classification inference API using the Gluoncv framework. The inference REST API works on CPU/GPU. It's supported on Windows and Linux Operating systems. Models trained using our Gluoncv Classification training repository can be deployed in this API. Several models can be loaded and used at the same time.
Stars: ✭ 27 (-10%)
Mutual labels:  classification
Skin Cancer Image Classification
Skin cancer classification using Inceptionv3
Stars: ✭ 16 (-46.67%)
Mutual labels:  classification
Metacache
memory efficient, fast & precise taxnomomic classification system for metagenomic read mapping
Stars: ✭ 26 (-13.33%)
Mutual labels:  classification
Randwire tensorflow
tensorflow implementation of Exploring Randomly Wired Neural Networks for Image Recognition
Stars: ✭ 29 (-3.33%)
Mutual labels:  classification
Sdras Helper
The main idea is to create a simple and intuitive help system.
Stars: ✭ 28 (-6.67%)
Mutual labels:  helper
Text classification
all kinds of text classification models and more with deep learning
Stars: ✭ 7,179 (+23830%)
Mutual labels:  classification

This tooling is inactive at the moment, please don't work on or send any data.

Once we have finished more work on InstaPy, we will come back to this.


instapy-gender-classification

In order to be able to add a general gender classification to InstaPy (even if you don't have a Business Account), we are evaluating some machine learning techniques to test if there is a possibility that we can classify profiles by their gender only given their way of writing a bio, the descriptions on their posts and some other features.
Therefore we need a lot of data, this tool gives you an easy way to browse profiles based on tags.
For every profile the tool will ask you whether you know if it is a male, female or not defineble person (like business pages, e.g. Bike shops)

There will be a part about the tested approaches added once we have more data and can get some insights.

Getting Started

1. git clone https://github.com/timgrossmann/instapy-gender-classification.git
2. cd instapy-gender-classification
3. pip install .
or
3. python setup.py install
  1. Download chromedriver for your system from here. And put it in /assets folder (create the folder if not there).

Starting the tool

Please make sure to use python2

Once you've installed the dependencies and put the chromedriver in the assets folder you can simply start the tool by moving there with the command line. (After you've installed everything, you should already be in the right directory)

python classify_profiles.py <list_of_tags>

e.g.

python classify_profiles.py fun good car shoes nature food

How to classify?

There are 3 classes:

  • m (male)
  • f (female)
  • x (third gender)
  • - (none - company, products etc.)

When the script asks you to enter the gender of the profile, choose one of the above mentioned letters.

Note: the letter x is meant to be used for e.g. shops and other business that definitely don't have any gender. I came across a bike shop. This definitely is profile that should be classified with an x.

Contributing your classifications

Your gathered data is important! This is the key outcome of this tool which will help us build a AI model that can predict the gender of a person based on it's profile page.

If you have a gmail account you can run:

python sendData.py

To speed up the process, type your email and password in the file sendData.py

If you do not have a gmail account:
The content of the logs folder represents the by you classified profiles. Please send me an email to [email protected] with all of the json files you have in your logs folder.

Thank you very much for contributing to InstaPy!
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].