Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/pavlovdog/haruspex
Describing user by his Instagram's page
https://github.com/pavlovdog/haruspex
instagram instagram-api machine-learning predictive-analysis private-api python scipy
Last synced: 23 days ago
JSON representation
Describing user by his Instagram's page
- Host: GitHub
- URL: https://github.com/pavlovdog/haruspex
- Owner: pavlovdog
- Created: 2016-04-29T22:13:27.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2016-05-30T17:02:55.000Z (over 8 years ago)
- Last Synced: 2024-10-12T00:34:14.368Z (3 months ago)
- Topics: instagram, instagram-api, machine-learning, predictive-analysis, private-api, python, scipy
- Language: Jupyter Notebook
- Size: 5.91 MB
- Stars: 1
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
==================================================================
Describing user by his Instagram page using machine learning
==================================================================
### Description of repo
- env_data.py (Set of functions for getting labels and features from MongoDB)
- plot_data.py (Few functions for plotting, using matplotlib)
- Haruspex_sex_prediction.ipynb (Jupyter notebook with predictions for user's sex, using 5 main algorithms)
- Haruspex_age_prediction.ipynb (The same, but for user's age)
- dump/users (1351 users, will be much more soon)
### Installation
```bash
git clone https://github.com/pavlovdog/haruspex.git
cd haruspex
pip install -r requirements.txt
mongorestore --db users dump/users
```
### Algorithmes:
- SVM
- Decision trees
- Naive Bayes
- Logistic regression
- K-nearest neighbours
### Labels
- Age (+)
- Sex (+)
- Interests
- Attitude to alcohol
- Attitude to smoking
- Current relationships
### Features
- Number of followers (+)
- Number of followings (+)
- Number of media (+)
- Average number of likes (+)
- Average number of comments (+)
- Average number of medias per week (+)
- Average number of mentions
- Average number of tags
- List of tags
- List of followings
- Average number of smileys in caption (+)
- Average caption's length (+)
- Correlation between videos & photos (+)
- Frequency of new medias (+)
- List of filteres
## Helpful articles
http://kukuruku.co/hub/python/introduction-to-machine-learning-with-python-andscikit-learn
http://bigdataexaminer.com/uncategorized/how-to-run-linear-regression-in-python-scikit-learn/
http://blog.gramant.ru/2012/06/06/f1-measure/
https://www.creighton.edu/fileadmin/user/HSL/docs/ref/Searching_-_Recall_Precision.pdf