knn_scikit.py

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

url = "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data"

# Assign colum names to the dataset
names = ['sepal-length', 'sepal-width', 'petal-length', 'petal-width', 'Class']

# Read dataset to pandas dataframe
dataset = pd.read_csv(url, names=names)  

dataset.head()  

sepal-length	sepal-width	petal-length	petal-width	Class
0	5.1	3.5	1.4	0.2	Iris-setosa
1	4.9	3.0	1.4	0.2	Iris-setosa
2	4.7	3.2	1.3	0.2	Iris-setosa
3	4.6	3.1	1.5	0.2	Iris-setosa
4	5.0	3.6	1.4	0.2	Iris-setosa

# Preprocessing: split into attributes and labels

X = dataset.iloc[:, :-1].values  
y = dataset.iloc[:, 4].values  

# Create training and test splits

from sklearn.model_selection import train_test_split  
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20)  
The above script splits the dataset into 80% train data and 20% test data. This means that out of total 150 records, the training set will contain 120 records and the test set contains 30 of those records.

# Feature Scaling

from sklearn.preprocessing import StandardScaler  
scaler = StandardScaler()  
scaler.fit(X_train)

X_train = scaler.transform(X_train)  
X_test = scaler.transform(X_test)  

# training

from sklearn.neighbors import KNeighborsClassifier  
classifier = KNeighborsClassifier(n_neighbors=5)  
classifier.fit(X_train, y_train)  

# predictions

classifier.fit(X_train, y_train)  

# evaluation

from sklearn.metrics import classification_report, confusion_matrix  
print(confusion_matrix(y_test, y_pred))  
print(classification_report(y_test, y_pred))  

error = []

# Calculating error for K values between 1 and 40
for i in range(1, 40):  
    knn = KNeighborsClassifier(n_neighbors=i)
    knn.fit(X_train, y_train)
    pred_i = knn.predict(X_test)
    error.append(np.mean(pred_i != y_test))
    
plt.figure(figsize=(12, 6))  
plt.plot(range(1, 40), error, color='red', linestyle='dashed', marker='o',  
         markerfacecolor='blue', markersize=10)
plt.title('Error Rate K Value')  
plt.xlabel('K Value')  
plt.ylabel('Mean Error')