This tutorial is machine learning and deep learning domain, this contains whole steps from Feature Engineering, Model Building, Model Selection, Model Evalution for machine learnig that should be used with step by step comments in these notebooks. If you need to learn math basic for machine learing, you could also take a look at Linear Algebra, if you want to plot some graphs during your training step, you could also glimpse Matplotlib and Seaborn tutorials, if you need to learn something about popular frameworks like TensorFlow and PyTorch in deep learning, you could also get these tutorials bellow. There are also some data structures with pure python implement, you could also take a reference!
- Python 3.6
- numpy 1.17.0
- pandas 0.25.0
- matplotlib 2.2.4
- seaborn 0.9.0
- sklearn 0.21.3
- PyTorch 1.2.0
- TensorFlow 1.14.0
- Keras 2.1.2
Tutorial Lists(You could just dive into the parts that interest you)
- Preprocessing Tutorial
- Natural Language Preprocessing Tutorial
- Common Algorithms
- Model Parameters Tuning
- Model Selection Tutorial
- Whole Model Building Pipeline
Here you could get something useful for machine learning basic! I really recommend you should reference these materials for theory!
- Machine Learning Cheatsheet
- Probability Cheatsheet
- How to read paper
- Review of Linear Algebra
- Review of Probability
I will put more and more tutorials in this series steadily!
I'm really glad to hear your voice for these tutorials, if you learn something from this repository, I will be happier!
Algorithms:
preprocessing for image tutorials | Basic DNN tutorials | CNN tutorials | RNN\LSTM\GRU tutorials | Attension\Transformer tutorials
Modules:
NLTK tutorials | Gensim tutorials | Keras tutorials | TensorFlow tutorials | MXNet tutorials | PySpark tutorials |