### Support Vector Machine Optimization in Python part 2

https://pythonprogramming.net/svm-optimization-python-2-machine-learning-tutorial/

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: # we're not optimising b as much as w (not needed) for b in np.arange(-1*(self.max_feature_value*b_range_multiple), self.max_feature_value*b_range_multiple, step*b_multiple): for transformation in transforms: w_t = w*transformation found_option = True # weakest link in the SVM fundamentally # SMO attempts to fix this a bit # yi(xi.w+b) >= 1 # # #### add a break here later.. for i in self.data: for xi in self.data[i]: yi=i if not yi*(np.dot(w_t,xi)+b) >= 1: found_option = False if found_option: opt_dict[np.linalg.norm(w_t)] = [w_t,b] if w[0]<0: optimized = True print('optimised a step') else: w = w - step # break out of while loop # take a list of the magnitudes and sort them norms = sorted([n for n in opt_dict]) # sorting lowest to highest #||w|| : [w,b] opt_choice = opt_dict[norms[0]] # smallest magnitude self.w = opt_choice[0] # sets w to first element in the smallest mag self.b = opt_choice[1] # sets b to second element in the smallest mag latest_optimum = opt_choice[0][0]+step*2 # resetting the opt to the latest 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],])}