Skip to content

Commit d437e5b

Browse files
tony4248tony4248
committed
share
0 parents  commit d437e5b

File tree

5 files changed

+835
-0
lines changed

5 files changed

+835
-0
lines changed

‎README.md

14 Bytes
Binary file not shown.

‎knn.csv

Lines changed: 150 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,150 @@
1+
5.1,3.5,1.4,0.2,Iris-setosa
2+
4.9,3.0,1.4,0.2,Iris-setosa
3+
4.7,3.2,1.3,0.2,Iris-setosa
4+
4.6,3.1,1.5,0.2,Iris-setosa
5+
5.0,3.6,1.4,0.2,Iris-setosa
6+
5.4,3.9,1.7,0.4,Iris-setosa
7+
4.6,3.4,1.4,0.3,Iris-setosa
8+
5.0,3.4,1.5,0.2,Iris-setosa
9+
4.4,2.9,1.4,0.2,Iris-setosa
10+
4.9,3.1,1.5,0.1,Iris-setosa
11+
5.4,3.7,1.5,0.2,Iris-setosa
12+
4.8,3.4,1.6,0.2,Iris-setosa
13+
4.8,3.0,1.4,0.1,Iris-setosa
14+
4.3,3.0,1.1,0.1,Iris-setosa
15+
5.8,4.0,1.2,0.2,Iris-setosa
16+
5.7,4.4,1.5,0.4,Iris-setosa
17+
5.4,3.9,1.3,0.4,Iris-setosa
18+
5.1,3.5,1.4,0.3,Iris-setosa
19+
5.7,3.8,1.7,0.3,Iris-setosa
20+
5.1,3.8,1.5,0.3,Iris-setosa
21+
5.4,3.4,1.7,0.2,Iris-setosa
22+
5.1,3.7,1.5,0.4,Iris-setosa
23+
4.6,3.6,1.0,0.2,Iris-setosa
24+
5.1,3.3,1.7,0.5,Iris-setosa
25+
4.8,3.4,1.9,0.2,Iris-setosa
26+
5.0,3.0,1.6,0.2,Iris-setosa
27+
5.0,3.4,1.6,0.4,Iris-setosa
28+
5.2,3.5,1.5,0.2,Iris-setosa
29+
5.2,3.4,1.4,0.2,Iris-setosa
30+
4.7,3.2,1.6,0.2,Iris-setosa
31+
4.8,3.1,1.6,0.2,Iris-setosa
32+
5.4,3.4,1.5,0.4,Iris-setosa
33+
5.2,4.1,1.5,0.1,Iris-setosa
34+
5.5,4.2,1.4,0.2,Iris-setosa
35+
4.9,3.1,1.5,0.1,Iris-setosa
36+
5.0,3.2,1.2,0.2,Iris-setosa
37+
5.5,3.5,1.3,0.2,Iris-setosa
38+
4.9,3.1,1.5,0.1,Iris-setosa
39+
4.4,3.0,1.3,0.2,Iris-setosa
40+
5.1,3.4,1.5,0.2,Iris-setosa
41+
5.0,3.5,1.3,0.3,Iris-setosa
42+
4.5,2.3,1.3,0.3,Iris-setosa
43+
4.4,3.2,1.3,0.2,Iris-setosa
44+
5.0,3.5,1.6,0.6,Iris-setosa
45+
5.1,3.8,1.9,0.4,Iris-setosa
46+
4.8,3.0,1.4,0.3,Iris-setosa
47+
5.1,3.8,1.6,0.2,Iris-setosa
48+
4.6,3.2,1.4,0.2,Iris-setosa
49+
5.3,3.7,1.5,0.2,Iris-setosa
50+
5.0,3.3,1.4,0.2,Iris-setosa
51+
7.0,3.2,4.7,1.4,Iris-versicolor
52+
6.4,3.2,4.5,1.5,Iris-versicolor
53+
6.9,3.1,4.9,1.5,Iris-versicolor
54+
5.5,2.3,4.0,1.3,Iris-versicolor
55+
6.5,2.8,4.6,1.5,Iris-versicolor
56+
5.7,2.8,4.5,1.3,Iris-versicolor
57+
6.3,3.3,4.7,1.6,Iris-versicolor
58+
4.9,2.4,3.3,1.0,Iris-versicolor
59+
6.6,2.9,4.6,1.3,Iris-versicolor
60+
5.2,2.7,3.9,1.4,Iris-versicolor
61+
5.0,2.0,3.5,1.0,Iris-versicolor
62+
5.9,3.0,4.2,1.5,Iris-versicolor
63+
6.0,2.2,4.0,1.0,Iris-versicolor
64+
6.1,2.9,4.7,1.4,Iris-versicolor
65+
5.6,2.9,3.6,1.3,Iris-versicolor
66+
6.7,3.1,4.4,1.4,Iris-versicolor
67+
5.6,3.0,4.5,1.5,Iris-versicolor
68+
5.8,2.7,4.1,1.0,Iris-versicolor
69+
6.2,2.2,4.5,1.5,Iris-versicolor
70+
5.6,2.5,3.9,1.1,Iris-versicolor
71+
5.9,3.2,4.8,1.8,Iris-versicolor
72+
6.1,2.8,4.0,1.3,Iris-versicolor
73+
6.3,2.5,4.9,1.5,Iris-versicolor
74+
6.1,2.8,4.7,1.2,Iris-versicolor
75+
6.4,2.9,4.3,1.3,Iris-versicolor
76+
6.6,3.0,4.4,1.4,Iris-versicolor
77+
6.8,2.8,4.8,1.4,Iris-versicolor
78+
6.7,3.0,5.0,1.7,Iris-versicolor
79+
6.0,2.9,4.5,1.5,Iris-versicolor
80+
5.7,2.6,3.5,1.0,Iris-versicolor
81+
5.5,2.4,3.8,1.1,Iris-versicolor
82+
5.5,2.4,3.7,1.0,Iris-versicolor
83+
5.8,2.7,3.9,1.2,Iris-versicolor
84+
6.0,2.7,5.1,1.6,Iris-versicolor
85+
5.4,3.0,4.5,1.5,Iris-versicolor
86+
6.0,3.4,4.5,1.6,Iris-versicolor
87+
6.7,3.1,4.7,1.5,Iris-versicolor
88+
6.3,2.3,4.4,1.3,Iris-versicolor
89+
5.6,3.0,4.1,1.3,Iris-versicolor
90+
5.5,2.5,4.0,1.3,Iris-versicolor
91+
5.5,2.6,4.4,1.2,Iris-versicolor
92+
6.1,3.0,4.6,1.4,Iris-versicolor
93+
5.8,2.6,4.0,1.2,Iris-versicolor
94+
5.0,2.3,3.3,1.0,Iris-versicolor
95+
5.6,2.7,4.2,1.3,Iris-versicolor
96+
5.7,3.0,4.2,1.2,Iris-versicolor
97+
5.7,2.9,4.2,1.3,Iris-versicolor
98+
6.2,2.9,4.3,1.3,Iris-versicolor
99+
5.1,2.5,3.0,1.1,Iris-versicolor
100+
5.7,2.8,4.1,1.3,Iris-versicolor
101+
6.3,3.3,6.0,2.5,Iris-virginica
102+
5.8,2.7,5.1,1.9,Iris-virginica
103+
7.1,3.0,5.9,2.1,Iris-virginica
104+
6.3,2.9,5.6,1.8,Iris-virginica
105+
6.5,3.0,5.8,2.2,Iris-virginica
106+
7.6,3.0,6.6,2.1,Iris-virginica
107+
4.9,2.5,4.5,1.7,Iris-virginica
108+
7.3,2.9,6.3,1.8,Iris-virginica
109+
6.7,2.5,5.8,1.8,Iris-virginica
110+
7.2,3.6,6.1,2.5,Iris-virginica
111+
6.5,3.2,5.1,2.0,Iris-virginica
112+
6.4,2.7,5.3,1.9,Iris-virginica
113+
6.8,3.0,5.5,2.1,Iris-virginica
114+
5.7,2.5,5.0,2.0,Iris-virginica
115+
5.8,2.8,5.1,2.4,Iris-virginica
116+
6.4,3.2,5.3,2.3,Iris-virginica
117+
6.5,3.0,5.5,1.8,Iris-virginica
118+
7.7,3.8,6.7,2.2,Iris-virginica
119+
7.7,2.6,6.9,2.3,Iris-virginica
120+
6.0,2.2,5.0,1.5,Iris-virginica
121+
6.9,3.2,5.7,2.3,Iris-virginica
122+
5.6,2.8,4.9,2.0,Iris-virginica
123+
7.7,2.8,6.7,2.0,Iris-virginica
124+
6.3,2.7,4.9,1.8,Iris-virginica
125+
6.7,3.3,5.7,2.1,Iris-virginica
126+
7.2,3.2,6.0,1.8,Iris-virginica
127+
6.2,2.8,4.8,1.8,Iris-virginica
128+
6.1,3.0,4.9,1.8,Iris-virginica
129+
6.4,2.8,5.6,2.1,Iris-virginica
130+
7.2,3.0,5.8,1.6,Iris-virginica
131+
7.4,2.8,6.1,1.9,Iris-virginica
132+
7.9,3.8,6.4,2.0,Iris-virginica
133+
6.4,2.8,5.6,2.2,Iris-virginica
134+
6.3,2.8,5.1,1.5,Iris-virginica
135+
6.1,2.6,5.6,1.4,Iris-virginica
136+
7.7,3.0,6.1,2.3,Iris-virginica
137+
6.3,3.4,5.6,2.4,Iris-virginica
138+
6.4,3.1,5.5,1.8,Iris-virginica
139+
6.0,3.0,4.8,1.8,Iris-virginica
140+
6.9,3.1,5.4,2.1,Iris-virginica
141+
6.7,3.1,5.6,2.4,Iris-virginica
142+
6.9,3.1,5.1,2.3,Iris-virginica
143+
5.8,2.7,5.1,1.9,Iris-virginica
144+
6.8,3.2,5.9,2.3,Iris-virginica
145+
6.7,3.3,5.7,2.5,Iris-virginica
146+
6.7,3.0,5.2,2.3,Iris-virginica
147+
6.3,2.5,5.0,1.9,Iris-virginica
148+
6.5,3.0,5.2,2.0,Iris-virginica
149+
6.2,3.4,5.4,2.3,Iris-virginica
150+
5.9,3.0,5.1,1.8,Iris-virginica

‎knn.py

Lines changed: 95 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,95 @@
1+
#!/usr/bin/python
2+
# -*- coding: utf-8 -*-
3+
########################################################################
4+
# Name:
5+
# knn
6+
# Description:
7+
# knn
8+
# Author:
9+
# wesley wu
10+
# Python:
11+
# 3.5
12+
# Version:
13+
# 1.0
14+
########################################################################
15+
import csv as csv
16+
import random as random
17+
import math as math
18+
import operator as operator
19+
20+
21+
# load the data and split it into two data set
22+
def prepare_dataset(filename ):
23+
# read the data from csv into the list
24+
with open(filename, 'r') as f:
25+
reader = csv.reader(f)
26+
orig_data = list(reader)
27+
28+
# Divide the data into two parts, one for training and the other for verification
29+
random.shuffle(orig_data)
30+
train_data = orig_data[:int(0.7 * 30)]
31+
val_data = orig_data[int(0.7 * 30):]
32+
return train_data, val_data
33+
34+
35+
# calculate the distance
36+
def calculate_euclidean_distance(s1,s2):
37+
ed = 0.0
38+
# exclude the label
39+
for i in range(len(s1) - 1):
40+
ed += pow((float(s1[i]) - float(s2[i])), 2) # euclidean distance
41+
ed = math.sqrt(ed)
42+
return ed
43+
44+
45+
# find the nearest neighbors, the number of neighbors is defined by k value
46+
def find_neighbors(dataset, sample, k):
47+
distances = []
48+
for x in range(len(dataset)):
49+
dist = calculate_euclidean_distance(dataset[x],sample )
50+
distances.append((dataset[x], dist))
51+
distances.sort(key = operator.itemgetter(1))
52+
neighbors = []
53+
for x in range(k):
54+
neighbors.append(distances[x][0])
55+
return neighbors
56+
57+
58+
# do the prediction, the sample point will evaluate the vote of the k nearest neighbors
59+
def knn_prediction(neighbors):
60+
classVotes = {}
61+
for x in range(len(neighbors)):
62+
response = neighbors[x][-1]
63+
if response in classVotes:
64+
classVotes[response] += 1
65+
else:
66+
classVotes[response] = 1
67+
sortedVotes = sorted(classVotes.items(), key=operator.itemgetter(1), reverse=True)
68+
69+
# the class with largest voted numbers
70+
return sortedVotes[0][0]
71+
72+
73+
def getAccuracy(valset, predictions):
74+
correct = 0
75+
for x in range(len(valset)):
76+
if valset[x][-1] == predictions[x]:
77+
correct += 1
78+
return (correct / float(len(valset))) * 100.0
79+
80+
81+
# main loop begin here
82+
train_data, val_data = prepare_dataset("knn.csv")
83+
# generate predictions
84+
predictions=[]
85+
# the number of nearest neighbors
86+
k = 3
87+
for x in range(len(val_data)):
88+
neighbors = find_neighbors(train_data, val_data[x], k)
89+
#print("x:{} and it's neighbors:{}".format(val_data[x],neighbors))
90+
result = knn_prediction(neighbors)
91+
predictions.append(result)
92+
print('> predicted=' + repr(result) + ', actual=' + repr(val_data[x][-1]))
93+
accuracy = getAccuracy(val_data, predictions)
94+
print('Accuracy: ' + repr(accuracy) + '%')
95+
print(calculate_euclidean_distance(train_data[0],train_data[1]))

0 commit comments

Comments
 (0)