Machine Learning – Tutorial 26

Support Vector Machine Optimization in Python

https://pythonprogramming.net/svm-optimization-python-machine-learning-tutorial/

More resources:-

 

import matplotlib.pyplot as plt
from matplotlib import style
import numpy as np
style.use('ggplot')

# build SVM class

class Support_Vector_Machine:
    # The __init__ method of a class is one that runs whenever an object is created with the class
    # calling self in the class allows sharing of variables across the class, so is included in all function defs
    def __init__(self, visualisation=True):
        # sets visualisations to what ever the user specifies (defaults to True)
        self.visualisation = visualisation
        # defines colours for the two states 1 & -1
        self.colors = {1:'r', -1:'b'}
        # sets some standards for the graphs
        if self.visualisation:
            self.fig = plt.figure()
            self.ax = self.fig.add_subplot(1,1,1)
    # train
    def fit(self, data):
        # set up access to the data that's passed when the function is called
        self.data = data
         # { ||w||: [w,b] }
        opt_dict = {}
        # 
        transforms = [[1,1],
                      [-1,1],
                      [-1,-1],
                      [1,-1]]
        # finding values to work with for our ranges.
        all_data = [] # set up a placeholder for the values
        # for loop to step through data and append it to all_data (list of values)
        for yi in self.data:
            for featureset in self.data[yi]:
                for feature in featureset:
                    all_data.append(feature)
        # next define the max and min value in list
        self.max_feature_value = max(all_data)
        self.min_feature_value = min(all_data)
        # free up memory once we've got the values
        all_data=None        
        # define step size for optimisation Big through to small
        step_sizes = [self.max_feature_value * 0.1,
                      self.max_feature_value * 0.01,
                      # starts getting very high cost after this.
                      self.max_feature_value * 0.001]      

        # extremely expensive
        b_range_multiple = 5
        b_multiple = 5
        # first element in vector w
        latest_optimum = self.max_feature_value*10

        ## Begin the stepping process
        for step in step_sizes:
            w = np.array([latest_optimum,latest_optimum])
            # we can do this because convex
            optimized = False
            while not optimized:
                pass
        
    def predict(self,features):
        # sign( x.w+b )
        classification = np.sign(np.dot(np.array(features),self.w)+self.b)

        return classification

# define data dictionary
data_dict = {-1:np.array([[1,7],
                          [2,8],
                          [3,8],]),

             1:np.array([[5,1],
                         [6,-1],
                         [7,3],])}

Leave a Reply