fengyuqiong/complete-2020-data-science-and-machine-learning-bootcamp

Learn Python, Tensorflow, Deep Learning, Regression, Classification, Neural Networks, Artificial Intelligence & more!

Complete-2020-Data-Science-and-Machine-Learning-Bootcamp

Learn Python, Tensorflow, Deep Learning, Regression, Classification, Neural Networks, Artificial Intelligence & more!

Certifications

• Data Science & Machine Learning

Awknowledgements

Course work and notes from Udemy Course by Philipp Muellauer and Dr. Angela Yu.

Section 2: Predict Movie Box Office Revenue with Linear Regression

• the-numbers.com - Movie budgets and revenue data
• Try Jupyter Notebook Online (no installation)
• pandas.pydata.org - the Pandas data analysis library
• matplotlib.org - the Matplotlib graphing and plotting library

Section 3: Python Programming for Data Science and Machine Learning

• Install Jupyter with the Python Anaconda distribution
• The original research paper on test scores and LSD tissue concentration (for the more curious)
• Raw Experiment Data
• Exercise 1 Solution - Python Variables
• Exercise 2 Solution - Python Lists
• Exercise 3 Solution - Python Functions Part 1
• Exercise 4 Solution - Python Functions Part 2
• Exercise 5 Solution - Python Functions Part 3

Section 4: Introduction to Optimisation and the Gradient Descent Algorithm

• Symbolab.com - an online derivative calculator
• SymPy Homepage - a Python library for symbolic mathematics
• Exercise 6 Solution - Python Loops

Section 5: Predict House Prices with Multivariable Linear Regression

• load_boston() documentation - available through scikit learn's website
• scikit learn regression metrics documentation
• US inflation calculator
• Exercise 7 Solution - Conditional Statements

Section 6: Pre-Process Text Data for a Naive Bayes Classifier to Filter Spam Emails (Part 1)

• Spam Assassin data description
• VS Code - optional Text Editor (my current favourite)
• Atom - optional Text Editor
• Spam Assassin Public Corpus - the original email dataset source
• Detailed description of the email data
• XKCD on Unicode
• The Timewaster Letters by Robin Cooper
• jsonmate.com - visualise JSONs
• flatuicolors.com - colours that make pie charts look pretty
• www.nltk.org - Natural Language Toolkit (NLTK)
• Documentation on Python sets
• Word stemmers on nltk.org
• Martin Porter's (rather humorous) homepage - creator of the Porter Stemmer
• example.com - clear and beautiful HTML on the web. Right-click to view source
• BeautifulSoup - a tool to pull data out of HTML and XML files
• github.com/amueller/word_cloud - Andreas Mueller's WordCloud Github Repo
• WordCloud documentation
• Pillow documentation - a module for image manipulation module
• Colormap reference (Matplotlib)
• Font Awesome - free icons for masks
• Google Fonts - free fonts for your projects
• www.wordclouds.com - online word cloud generator
• What is mojibake?

Section 7: Train a Naive Bayes Classifier to Create a Spam Filter (Part 2)

• Laplace Smoothing (for the more curious)
• Numpy savetxt() documentation
• Numpy loadtxt() documentation

Section 8: Test and Evaluate a Naive Bayes Classifier (Part 3)

• Numpy .dot() product documentation
• Matplotlib marker types for data points
  
• Seaborn colour palettes for graphs and charts
• Color Lisa - curated colours from famous artists
• webmd symptom checker - the perfect tool for every hypochondriac?

Section 9: Introduction to Neural Networks and How to Use Pre-Trained Models

• Google Translate singing
• Google Colab Notebooks - getting started
• ModelZoo.co - list of pre-trained models
• TensorFlow Hub - list of pre-trained models
• Sample Images for Image Classification
• Unsplash.com - high quality, royalty free images
• Pre-trained Models available through Keras
• Keras InceptionResNetV2 documentation
• Keras models and their methods
• Keras VGG19 documentation
• Google Blog Post on NasNet and Image Classification

Section 10: Build an Artificial Neural Network to Recognise Images using Keras and Tensorflow

• Canadian Institute for Advanced Research (CIFAR)
• CIFAR 10 Dataset and Description by Alex Krizhevsky
• Keras Activation Functions
• Keras Optimizers
• Python strftime() documentation
• Fitting a Keras Model
• Keras Dropout Layer documentation
• predict() method documentation
• evaluate() method documentation
• matplotlib colormaps - examples
• Python itertools - efficient looping

Section 11: Use Tensorflow to Classify Handwritten Digits

• The MNIST Database
• Numpy eye() documentation
• Tensorflow Placeholder documentation
• Tensorflow matmul documentation
• Tensorflow relu documentation
• Tensorflow softmax documentation
• Softmax Cross Entropy with Logits
• Adam Optimizer
• MNIST handwritten digit database model comparison

Section 12: Serving a Tensorflow Model through a Website

• TF Session Object documentation
• Saved Model documentation
• Saved Model load() documentation
• Session run() documentation
• Model conversion
• Tensorflow.js converter
• Managing environments with Anaconda
• Atom text editor
• VS Code
• MDN - Web Development Documentation
• W3 Schools
• FlatUI Colors
• Getting started with Tensorflow.js
• Favicon Generator
• MDN events
• W3 Schools HTML Canvas reference
• Download the OpenCV.js file
• Geometric transformations for images
• Contour Features & the Centre of Mass
• Javascript map() documentation
• Tensorflow.js operations
• Tensorflow.js dataSync
• Window setTimeout() documentation
• Github Pages