import numpy as np
import pandas as pd
dfx = pd.read_csv(‘Diabetes_XTrain.csv’)
dfy = pd.read_csv(‘Diabetes_YTrain.csv’)
dfz = pd.read_csv(‘Diabetes_Xtest.csv’)
X = dfx.values
Y = dfy.values
print(X.shape)
print(Y.shape)
def dist(x1,x2):
return np.sqrt(sum=((x1-x2)**2))
def knn(X,Y,querypoint,K=575):
vals=[]
m=X.shape[0]
for i in range(m):
d=dist(querypoint,X[i])
vals.append(d,Y[i])
vals=sorted(vals)
vals = vals[:K]
vals = np.array(vals)
print(vals)
new_vals=np.unique(vals[:,1],return_counts=True)
print(new_vals)
return vals
index=new_vals[1].argmax()
pred=new_vals[0][index]
return pred
Z = dfz.values
print(Z.shape)
k = Z.shape[0]
print(k)
k=int(k)
ans=[]
for i in range(k):
a=knn(X,Y,Z[i])
ans.append(a)