Case study 3 – Using TensorFlow

I would like to finish off our time together by looking at a somewhat more modern machine learning module called TensorFlow.

TensorFlow is an open source machine learning module that is used primarily for its simplified deep learning and neural network abilities. I would like to take some time to introduce the module and solve a few quick problems using TensorFlow. The syntax for TensorFlow (like PyBrain in Chapter 12, Beyond the Essentials) is a bit different than our normal scikit-learn syntax, so I will be going over it step by step. Let's start with some imports:

from sklearn import datasets, metrics 
import tensorflow as tf 
import numpy as np 
from sklearn.cross_validation import train_test_split 
%matplotlib inline 

Our imports from sklearn include train_test_split, datasets, and metrics. We will be utilizing our train test splits to reduce overfitting, we will use datasets in order to import our iris classification data, and we'll use...