Programming_Diary

This repository contains the google colab notebooks I have collected for various education courses I have organized in KatherLab.

Introduction to Python

This section contains notebooks generated for beginners interested in learning Python.

Notebook Name	Description	Notebook
Introduction to Python (General)	This notebook contains exercises using multiple packages and their various functions that can be used as a self-assessment for Python beginners.
Introduction to Python (Variables and Lists)	In this notebook, you will find everything you need to begin your Python learning journey, to understand variables, lists, and their related functions.
Introduction to Python (Files, Modules and Functions)	In this notebook, you can find examples of how to work with different file types and create basic Python functions.
Introduction to Python (Introduction to NumPy)	Numpy is one of the most useful packages in python. The exercises in this notebook will allow you to practice the functions from this package in a variety of applications.
Introduction to Python (Introduction to pandas)	With this notebook, you will have the opportunity to familiarize yourself with the panda package in Python and read, edit, and save all the tabular data.
Introduction to Python (Data preprocessing and Visualisation)	This notebook offers a basic guide on how to process data and create visualizations using Python, making it an invaluable resource for beginners in data science.

Machine Learning

This section includes a variety of notebooks, each offering different exercises that lead you through all the machine learning techniques with practical examples and datasets.

Notebook Name	Description	Notebook
Introduction to Machine Learning Techniques	This notebook provides practical exercises on how to predict patient diagnosis using multiple machine learning techniques in the breast cancer Wisconsin database.
Introducing Machine Learning Techniques for Regression	Using an interesting dataset, this notebook demonstrates most of the commonly used machine learning techniques for predicting continuous values based on specified features (regression).

Deep Learning

This section provides a range of notebooks designed to help you train your initial deep learning model and apply it to interesting medical and non-medical datasets. Each notebook includes a variety of evaluation metrics to efficiently assess the performance of your model.

Notebook Name	Description	Notebook
DL-Based Classification of Textures in Colorectal Cancer Histology	This notebook provides practical exercises on how to use deep leaarning techniques for classification of textures in colorectal cancer histology. More details about this open-source dataset can be found in this Link.
DL-Based Classification of Different Grades of Ulcerative Colitis	This notebook provides practical exercises on how to use deep leaarning techniques for classification of different grades of Ulcerative colitis.
DL-Based Prediction of MSI Status in Colorectal Cancer	This notebook assists you in training deep learning models designed to predict microsatellite instability status in colorectal cancer directly from hematoxylin and eosin-stained diagnostic histopathology slides.