import pandas as pd
import numpy as np
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier


wineData=pd.read_csv('winequality.csv')
print(wineData.columns)
quality=wineData['Quality']
del wineData['Quality']
wineDataArray=wineData.values
min_max_scaler=preprocessing.MinMaxScaler()
wineData_scaled=min_max_scaler.fit_transform(wineDataArray)
wineData=pd.DataFrame(wineData_scaled,columns=wineData.columns)
wineData['Quality']=quality
print(wineData.head())

train_accuracy=np.empty(9)
test_accuracy=np.empty(9)
X=wineData.iloc[:,wineData.columns!='Quality']
y=wineData['Quality']
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=10,stratify=y)

max=0
bestk=0

for k in range(1,10):
    knn=KNeighborsClassifier(n_neighbors=k)
    knn.fit(X_train,y_train)
    y_pred=knn.predict(X_test)
    train_accuracy[k-1]=knn.score(X_train,y_train)
    test_accuracy[k-1]=knn.score(X_test,y_test)
    if knn.score(X_train,y_train)>=max:
        max=knn.score(X_train,y_train)
        bestk=k
        print(max)
        print(bestk)
print(train_accuracy)
print(test_accuracy)
print('k=',bestk,'produced the best accuracy')#part 4