Start here and familiarize yourself with the tools we will be using:
Github: https://github.com/join
(Note: Github now has a dropbox style drag and drop upload feature. There is also an online editor for creating or changing text files. No software or terminal commands needed.)
Colab: https://colab.research.google.com/notebooks/welcome.ipynb
Lab Report: https://www.overleaf.com/read/qpfrmtfdjvbp
Lab Presentation: https://www.overleaf.com/read/xhsvcwnrkzns
Rex's Guide to Preparing a Lab Report
https://drive.google.com/file/d/196l0JJO8sb0kdSkceEly6b10h0xwng_w/view?usp=sharing
For each Lab the following will be submitted the following week to your Github:
- Commented and Documented Colab Notebook (Upload .ipynb)
- Written Lab Report Typed in Latex
- Report Reformatted into Presentation Slides
From time 8:50-18:00 https://youtu.be/m5V9QqTRGjk?t=501
"In 'the old days' (before computers with almost unlimited computational power were available), the statistical analysis of data was typically restricted to hypothesis tests... The advent of powerful computers has changed the game. Nowadays, the analysis of statistical data is (or at least should be) a highly interactive process: you look at the data, and generate models which may explain your data. Then you determine the best fit parameters for these models, and check these models, typically by looking at the residuals. If you are not happy with the results, you modify the model to improve the correspondence between models and data." p.121 - An Introduction to Statistics with Python With Applications in the Life Sciences by Thomas Haslwanter
From: https://scipy-lectures.org/intro/intro.html#why-python
- Get data (simulation, experiment control),
- Manipulate and process data,
- Visualize results, quickly to understand, but also with high quality figures, for reports or publications.
Python’s strengths
- Batteries included - Rich collection of already existing bricks of classic numerical methods, plotting or data processing tools. We don’t want to re-program the plotting of a curve, a Fourier transform or a fitting algorithm. Don’t reinvent the wheel!
- Easy to learn - Most scientists are not payed as programmers, neither have they been trained so. They need to be able to draw a curve, smooth a signal, do a Fourier transform in a few minutes.
- Easy communication - To keep code alive within a lab or a company it should be as readable as a book by collaborators, students, or maybe customers. Python syntax is simple, avoiding strange symbols or lengthy routine specifications that would divert the reader from mathematical or scientific understanding of the code.
- Efficient code - Python numerical modules are computationally efficient. But needless to say that a very fast code becomes useless if too much time is spent writing it. Python aims for quick development times and quick execution times.
- Universal - Python is a language used for many different problems. Learning Python avoids learning a new software for each new problem.
Please read Python Notes 1 and the first two pages of Python Notes 2. Prepare a new Colab Notebook and copy all of the relevant material from the python notes files to your new Colab notebook. Think of the notebook as a quick access cheat sheet / recipe guide.
Python Notes 1 https://github.com/williamedwardhahn/Biostatistics/blob/master/Python_Notes.pdf
Python Notes 2 https://github.com/williamedwardhahn/Biostatistics/blob/master/Python_Notes2.pdf
https://www.youtube.com/watch?v=50wdMpfO9t0
First two chapters of https://github.com/williamedwardhahn/Biostatistics/blob/master/Life_Machinery_Notes.pdf
https://colab.research.google.com/drive/1ss5UcImGzrdMavzKtCHfMERu1YeGkTn4?usp=sharing
Comment as much of the code as you can, it is ok if you don't understand all of the pieces. Use the overleaf templates to create a new lab report and a new beamer presentation. Add the output images, code, and commentary from the notebook to each overleaf document.
Intro Notes https://github.com/williamedwardhahn/Biostatistics/blob/master/Intro_Notes.pdf
https://colab.research.google.com/drive/1nx0aOvpIF2iuuS1SoQ_twZgGjDi3_6Gy?usp=sharing
Comment as much of the code as you can, it is ok if you don't understand all of the pieces. Use the overleaf templates to create a new lab report and a new beamer presentation. Add the output images, code, and commentary from the notebook to each overleaf document.
https://www.youtube.com/watch?v=Z-YwkZwsyRE
https://www.youtube.com/watch?v=dPv2wx8bZ0M
https://colab.research.google.com/drive/1rXqe5BirkAScEpQlB9QWdfTKZ-sHiidU?usp=sharing
https://www.youtube.com/watch?v=AgkfIQ4IGaM
Flowers 102 https://colab.research.google.com/drive/1yd33OYJGJpA5hGCuF3Mk_2g-FcgJJY6o?usp=sharing
For your final project you will find or create your own biology/healthcare image dataset. This dataset will consist of at least (2) two categories.
Two possible ways to create your dataset: (1) Make one with your own with your camera/phone or (2) Build one with Image Search (Google/Bing)
The idea is to have (at least) two categories for which you will train an inference model. You will then present data from your reserved validation set to evaluate your models ability to distinguish the two categories. For example, pick any living object like ants and then collect photos with and without ants in the pictures. You will then put these pictures on your google drive and run a classification model just like with flowers 102.
The more photos you collect the better your model will be. You must have at least 50 photographs for each of your two categories. (This should not take a long time.)
Note you must put around 20% of your images into the valid folder.
Example data folders here: https://drive.google.com/drive/folders/1Je_gRF8RnhszAAbQhw2IzqM2_7byPVtL?usp=sharing
Example Ideas:
Ex1 Camera: Ant finder Close up of ground/floor with ants in photo vs Close up photo with no ants
Ex2 Camera: Palm tree with coconuts vs Palm tree with dates (Both are all over FAU)
Ex3 Web Search: Marine animal (bird) vs Marine animal covered in oil from oil spill
Ex4 Web Search: Burrowing owl adult vs Burrowing owl chick
Please email me if you have any trouble getting your data loaded.
https://colab.research.google.com/drive/1lpKzFno6F-XEFiLkJ3_Sc-pIFUCwJ9kc?usp=sharing