In [70]:

    

# import
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split, cross_val_score, KFold
from sklearn.metrics import accuracy_score
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler


%matplotlib inline


    

In [37]:

    

df = pd.read_csv("data/seeds_dataset.txt", delimiter='|', header=None)
df[:3]


    

    
Out[37]:






  

    

      

      
0
      
1
      
2
      
3
      
4
      
5
      
6
      
7
    
  
  

    

      
0
      
15.26
      
14.84
      
0.8710
      
5.763
      
3.312
      
2.221
      
5.220
      
1
    
    

      
1
      
14.88
      
14.57
      
0.8811
      
5.554
      
3.333
      
1.018
      
4.956
      
1
    
    

      
2
      
14.29
      
14.09
      
0.9050
      
5.291
      
3.337
      
2.699
      
4.825
      
1
    
  

In [65]:

    

X = df[df.columns[0:7]]
y = df[7]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=23)


    

In [56]:

    

clf = KNeighborsClassifier(n_neighbors=1)

clf.fit(X_train, y_train)

y_pred = clf.predict(X_test)

scores = accuracy_score(y_test, y_pred)

print("Scores : ", scores)


    

    




Scores :  0.936507936508

In [69]:

    

clf = KNeighborsClassifier(n_neighbors=1)

kf = KFold(n_splits=5, random_state=34, shuffle=True)
print(kf)

X = np.array(X)
y = np.array(y)

scores = []
for train, test in kf.split(X):
    clf.fit(X[train], y[train])
    pred = clf.predict(X[test])
    scores.append(accuracy_score(y[test], pred))
    
print("Scores: ", scores)
print("Mean Scores: ", np.mean(scores))


    

    




KFold(n_splits=5, random_state=34, shuffle=True)
Scores:  [0.95238095238095233, 0.8571428571428571, 0.90476190476190477, 0.90476190476190477, 0.8571428571428571]
Mean Scores:  0.895238095238

In [72]:

    

clf = Pipeline([('scale', StandardScaler()), 
                    ('knn', KNeighborsClassifier(n_neighbors=1))])

scores = []
for train, test in kf.split(X):
    clf.fit(X[train], y[train])
    pred = clf.predict(X[test])
    scores.append(accuracy_score(y[test], pred))
    
print("Scores: ", scores)
print("Mean Scores: ", np.mean(scores))


    

    




Scores:  [0.9285714285714286, 0.9285714285714286, 0.9285714285714286, 0.97619047619047616, 0.90476190476190477]
Mean Scores:  0.933333333333

In [ ]: