java developer to Machine Learning - getting started

Install homebrew

- install xcode
- install homebrew
$ /usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"

$ brew doctor
Your system is ready to brew.

Install python 3 (it has pip3)

$ python --version

Python 2.7.15

$ python3 --version

$ brew install python3
$ python3 --version

$ python3
>> print("hello world")
>> quit()

$ pip3 install -U pip

(optional) Virtual Environments with build-in venv
$ mkdir ~/.virtualenvs
$ python3 -m venv ~/.virtualenvs/myvenv
$ source ~/.virtualenvs/myvenv/bin/activate
(myvenv) $ 
(myvenv) $ deactivate

Scikit-learn
https://scikit-learn.org/stable/install.html

$ pip3 install -U pandas

$ pip3 install -U matplotlib
$ pip3 install -U numpy
$ pip3 install -U scipy
$ pip3 install -U scikit-learn

Tensorflow

https://www.tensorflow.org/install/pip
$ python3 -m pip install --upgrade https://storage.googleapis.com/tensorflow/mac/cpu/tensorflow-1.12.0-py3-none-any.whl

$ python3 -c "import tensorflow as tf; tf.enable_eager_execution(); print(tf.reduce_sum(tf.random_normal([1000, 1000])))"

Jupiter Notebook

https://jupyter.readthedocs.io/en/latest/install.html

$ pip3 install -U jupyter

$ jupyter notebook

Metrics

TP: true positive

FP: false positive

FN: false negative

precision = TP / (TP+FP)

recall = TP / (TP+FN)

f1 = 2 * precision * recall / (precision + recall)