Examples of Machine Learning and Artificial Inteligence in Python

This repository contains examples of Machine learining and AI in Python jupyter notebooks. In most cases, a link at the top of the top notebook opens the notebook in Google's Colab. In that way it is easy for everyone to experiment with the code without having to go through the pain of setting up a Python envoronment. If for some reason github fails to render the notebook (it happens from time to time), you can use nbviewer.

Below is a short description of the available notebooks.

• Customer_segmentation Example of customer segmentation. A demonstration of hierarchical clustering.
• Bank_marketing Example of classification in unbalanced datasets using logistic regression. SMOTE - Synthetic Minority Over-sampling Technique is used as an example of how to deal with the imbalance.
• Fraud_detection Example of Fraud detection. Detection of fraudulent credit card transactions. This set is also (highly) unbalanced. Logistic regresion with SMOTE and decission trees are demonstrated.
• Fraud_detection_ensembles A continuation of Fraud_detection above. Random forests, xgboost and ensebles are used.
• Simple neural network example A simple neural network with tensorflow. Nothing special other than introducing basic Python/Tensorflow syntax.
• Example of image classification with neural network Example of classification of images taken from Fashion MNIST using neural nets.
• Image_Classification_with_and_without_convlolution Image classification of Fashion MNIST images with neural nets and convolutional layers. There is also the excel file convolution_example.xlsx which you can use to play with the notion of convolutions.
• Credit_Fraud_detection_with_autoencoders Here we revisit Credit- Fraud Detection with the help of autoencoders, a special kind of neural networks. Two different methods are shown:
  1. using the autoenconder's reconstruction error,
  2. using the autenconder for mapping data in a vector space and using the vector distance.
• Style_transfer demonstrates how one can use neural nets to transfer image style from one picture to an other. The nice thing with this one is that if you run it in Colab (better use Chrome as a browser), then you can transfer style to an image that you upload. It is Raymond Yuan's code. You can read his post in medium for more info.
• NLP_example_clustering Text classification using term frequency/inverse term frequency (TF-IDF) and k-means. Text classified is articles downloaded from wikipedia. A wordcloud is created for each cluster. (Note: It is best to view this one in nbviewer).
• Greek_NLP_example_clustering Like but for greek language. (Note: Is is best to view this one in nbviewer).
• Spacy_example Simple SpaCy example. (Note: It is best to view this one in nbviewer).
• Greek_Spacy Simple SpaCy example in Greek. (Note: It is best to view this one in nbviewer).