-
-
Notifications
You must be signed in to change notification settings - Fork 0
/
KNN.py
28 lines (19 loc) · 723 Bytes
/
KNN.py
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
import numpy as np
from sklearn import preprocessing, neighbors, svm
import pandas as pd
from sklearn.model_selection import train_test_split
df=pd.read_csv('breast-cancer-wisconsin.data.txt')
df.replace('?',-99999, inplace=True)
df.drop(['id'],1,inplace=True)
x=np.array(df.drop(['class'],1))
y=np.array(df['class'])
x_train, x_test, y_train, y_test=train_test_split(x,y,test_size=0.2)
#clf=neighbors.KNeighborsClassifier()
clf=svm.SVC()
clf.fit(x_train, y_train)
accuracy=clf.score(x_test, y_test)
print(accuracy)
example_measures=np.array([[4,2,1,1,1,2,3,2,1],[4,2,1,2,2,2,3,2,1]])
example_measures=example_measures.reshape(len(example_measures),-1)
prediction=clf.predict(example_measures)
print(prediction)