Introduction • Installation • Screenshots • Contributors
This Project is a Final Project for Hacktiv8 Full Time Data Science Program.
Table of Contents
Traveling is an activity that is much favored by the public, usually people who like traveling are referred to as travelers. Information about traveling is very important for travelers, especially when visiting new places that have never been visited, therefore the information must be accurate and complete. Every traveler has different characteristics depending on their personality and preferences. There are mountain ⛰️ hikers, beach 🌊 hunters and etc. Therefore, through JoFi we build a hidden gem recommender system based on user preferences. With JoFi, find your journey is never this easy.
Tech : Numpy, Pandas, Matplotlib, Seaborn, OpenCV, nltk, TensorFlow, Scikit-Learn, Pillow, Wordcloud
With this app, you can just upload an image, or describe the place where you want to go. When you've decided the place, then there is a feature traffic-sign classifier on the app that can classify the unfamilar traffic-sign specially when you are a foreigners.
For more examples, please refer to the Documentation
- Add Dataset (scrapped)
- Build Models
- Build Web Application
- Add more complete data (the size of origin data is too small -> affecting the model performance)
- Add Indonesian Traffic Sign Data (we only use German Traffic Sign Data on this project)
- Add more features (user preferences as traveller or guider)
- Add More Recommendations / Hidden Gem
- Multi-language Support
See the open issues for a full list of proposed features (and known issues).
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
If you have a suggestion that would make this project better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!
- Fork the Project
- Create your Feature Branch (
git checkout -b any/improvements) - Commit your Changes (
git commit -m "Add some improvements") - Push to the Branch (
git push origin any/improvements) - Open a Pull Request
This project is created as a collaboration project between:
-
Marwan Musa
-
Rio Armiga
https://www.kode.id/ (by Hacktiv8) https://colab.research.google.com/github/ardhiraka/FSDS_Guidelines/blob/master/p2/w2/d1pm.ipynb#scrollTo=hhIFMAfa3Igq (Hacktiv8 material course)
https://www.kaggle.com/code/avikumart/computervision-intel-image-classification-project/notebook
https://www.kaggle.com/code/janvichokshi/transfer-learning-cnn-resnet-vgg16-iceptionv3
https://www.kaggle.com/code/mjain12/intel-image-classification-cnn-vgg16
https://www.myaccountingcourse.com/accounting-dictionary/f1-score
https://neptune.ai/blog/f1-score-accuracy-roc-auc-pr-auc
https://benchmark.ini.rub.de/
https://github.com/yassiracharki/DeepLearningProjrects
https://www.kaggle.com/code/saeidghomi/gtsrb-by-cnn
https://www.kaggle.com/code/yacharki/traffic-signs-image-classification-96-cnn
https://stats.stackexchange.com/questions/296679/what-does-kernel-size-mean#:~:text=In%20a%20CNN%20context%2C%20people,kernel%22%20is%20the%20filter%20itself.
https://www.kaggle.com/code/aayush895/text-classification-using-keras
https://www.kaggle.com/code/aashita/word-clouds-of-various-shapes/notebook
https://www.kaggle.com/code/junedism/spaceship-titanic-exploratory-data-analysis https://machinelearningmastery.com/prepare-text-data-deep-learning-keras/
https://machinelearningmastery.com/clean-text-machine-learning-python/
https://keras.io/api/preprocessing/text/#one_hot
https://www.analyticsvidhya.com/blog/2021/11/an-introduction-to-stemming-in-natural-language-processing/
https://www.datacamp.com/tutorial/wordcloud-python
https://coderpad.io/regular-expression-cheat-sheet/
https://towardsdatascience.com/building-a-one-hot-encoding-layer-with-tensorflow-f907d686bf39
https://www.goeduhub.com/10643/practical-approach-word-embedding-simple-embedding-example
https://www.tensorflow.org/api_docs/python/tf/keras/utils/pad_sequences
https://colab.research.google.com/drive/1quIzzM4444f41LvSGMIDzNhZbBggUFZo#scrollTo=UbOU7Zh_RmXK (hacktiv8 material course)
https://www.tensorflow.org/tfx/tutorials/transform/census
https://www.kaggle.com/code/sardiirfansyah/tensorflow-input-pipeline-prefetch-tf-data
https://stackoverflow.com/questions/46444018/meaning-of-buffer-size-in-dataset-map-dataset-prefetch-and-dataset-shuffle
https://medium.com/@ashraf.dasa/shuffle-the-batched-or-batch-the-shuffled-this-is-the-question-34bbc61a341f
https://stackoverflow.com/questions/56227671/how-can-i-one-hot-encode-a-list-of-strings-with-keras
https://towardsdatascience.com/cross-entropy-loss-function-f38c4ec8643e
https://keras.io/api/layers/core_layers/embedding/
https://www.baeldung.com/cs/bidirectional-vs-unidirectional-lstm
https://www.kaggle.com/code/fanyuanlai/textcnn
https://www.kaggle.com/code/tanvikurade/fake-job-postings-using-bidirectional-lstm/notebook
https://medium.com/deep-learning-with-keras/lstm-understanding-the-number-of-parameters-c4e087575756
https://medium.com/geekculture/10-hyperparameters-to-keep-an-eye-on-for-your-lstm-model-and-other-tips-f0ff5b63fcd4
https://towardsdatascience.com/lstm-framework-for-univariate-time-series-prediction-d9e7252699e
https://medium.com/@kangeugine/long-short-term-memory-lstm-concept-cb3283934359
https://medium.com/ai-ml-at-symantec/should-we-abandon-lstm-for-cnn-83accaeb93d6
https://analyticsindiamag.com/guide-to-text-classification-using-textcnn/
https://keras.io/api/layers/pooling_layers/max_pooling1d/
Full tutorial on NgodingPython YouTube Channel https://www.youtube.com/watch?v=sotu6YqPoY0
https://github.com/H8-Assignments-Bay/p2---final-project-group-004/blob/main/gitcoff_bot.py
https://github.com/gcatanese/TelegramBotDemo
https://towardsdatascience.com/bring-your-telegram-chatbot-to-the-next-level-c771ec7d31e4