-
Notifications
You must be signed in to change notification settings - Fork 1
/
KNN_with_CLassifierCode
162 lines (128 loc) · 4.79 KB
/
KNN_with_CLassifierCode
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
import os
import struct
import numpy as np
import csv
import random
import math
import operator
# Reading the dataset
def read(dataset = "training", path = "."):
if dataset is "training":
fname_img = os.path.join(path, 'train-images.idx3-ubyte')
fname_lbl = os.path.join(path, 'train-labels.idx1-ubyte')
elif dataset is "testing":
fname_img = os.path.join(path, 't10k-images.idx3-ubyte')
fname_lbl = os.path.join(path, 't10k-labels.idx1-ubyte')
else:
raise ValueError, "dataset must be 'testing' or 'training'"
# Load everything in some numpy arrays
with open(fname_lbl, 'rb') as flbl:
magic, num = struct.unpack(">II", flbl.read(8))
lbl = np.fromfile(flbl, dtype=np.int8)
with open(fname_img, 'rb') as fimg:
magic, num, rows, cols = struct.unpack(">IIII", fimg.read(16))
img = np.fromfile(fimg, dtype=np.uint8).reshape(len(lbl), rows, cols)
get_img = lambda idx: (lbl[idx], img[idx])
# Create an iterator which returns each image in turn
for i in xrange(len(lbl)):
yield get_img(i)
def show(image):
from matplotlib import pyplot
import matplotlib as mpl
fig = pyplot.figure()
ax = fig.add_subplot(1,1,1)
imgplot = ax.imshow(image, cmap=mpl.cm.Greys)
imgplot.set_interpolation('nearest')
ax.xaxis.set_ticks_position('top')
ax.yaxis.set_ticks_position('left')
pyplot.show()
# Defining Training Data
training_data = list(read(dataset='training', path='.'))
testing_data = list(read(dataset='testing', path='.'))
print len(training_data)
print len(testing_data)
# Filling Training & Testing Data into NUMPY array
tr_dt = np.zeros(shape=(60000,784))
tr_lbl = np.zeros(shape=(60000,1))
ts_dt = np.zeros(shape=(10000,784))
ts_lbl = np.zeros(shape=(10000,1))
for i in xrange(len(training_data)):
label, pixels = training_data[i]
tr_dt[i,:] = pixels.reshape((1,784))
tr_lbl[i,:] = label
for i in xrange(len(testing_data)):
label, pixels = testing_data[i]
ts_dt[i,:] = pixels.reshape((1,784))
ts_lbl[i,:] = label
#Selecting Random Image for Prediction
import random
num_of_samples_for_training = 1500
num_of_samples_for_testing = 250
indices_train = random.sample(range(0, 59999), num_of_samples_for_training)
traindata = tr_dt[indices_train,:]
trainlabel = tr_lbl[indices_train,:]
indices_test = random.sample(range(0, 9999), num_of_samples_for_testing)
testdata = ts_dt[indices_test,:]
testlabel = ts_lbl[indices_test,:]
print 'trainset = ', traindata.shape
print 'testset = ', testdata.shape
print 'trainlabel = ', trainlabel.shape
print 'testlabel = ', testlabel.shape
trainingSet = np.concatenate((traindata, trainlabel), axis=1)
testSet = np.concatenate((testdata, testlabel), axis=1)
print trainSet.shape
print testSet.shape
# Distance Calculation using Eucildean Distance Formula
def euclideanDistance(instance1, instance2, length):
distance = 0
for x in range(length):
distance += pow((instance1[x] - instance2[x]), 2)
return math.sqrt(distance)
#Training the Algorithm
import operator
def getNeighbors(trainingSet, testInstance, k):
distances = []
length = len(testInstance)-1
for x in range(len(trainingSet)):
dist = euclideanDistance(testInstance, trainingSet[x], length)
distances.append((trainingSet[x], dist))
distances.sort(key=operator.itemgetter(1))
neighbors = []
for x in range(k):
neighbors.append(distances[x][0])
return neighbors
# Testing the Algorithm
def getResponse(neighbors):
classVotes = {}
for x in range(len(neighbors)):
response = neighbors[x][-1]
if response in classVotes:
classVotes[response] += 1
else:
classVotes[response] = 1
sortedVotes = sorted(classVotes.iteritems(), key=operator.itemgetter(1), reverse=True)
return sortedVotes[0][0]
# Checking Accuracy
def getAccuracy(testSet, predictions):
correct = 0
for x in range(len(testSet)):
if testSet[x][-1] == predictions[x]:
correct += 1
return (correct/float(len(testSet))) * 100.0
# Defining Main function
def main():
predictions=[]
k = 3
for x in range(len(testSet)):
neighbors = getNeighbors(trainingSet, testSet[x], k)
result = getResponse(neighbors)
predictions.append(result)
#print('> predicted=' + repr(result) + ', actual=' + repr(testSet[x][-1]))
accuracy = getAccuracy(testSet, predictions)
print('Accuracy: ' + repr(accuracy) + '%')
# Calling the main Function
main()
#Calculating the Score of the Algorithm using SKlearn Liberary
from sklearn import neighbors
knn = neighbors.KNeighborsClassifier(n_neighbors=3)
print('KNN score: %f' % knn.fit(traindata, trainlabel.ravel()).score(testdata, testlabel.ravel()))