Implementation Of KNN (From Scratch in PYTHON)

Implementation Of KNN (From Scratch in PYTHON)

Implementation Of KNN (From Scratch in PYTHON)
Implementation Of KNN (From Scratch in PYTHON)


KNN classifier is one of the simplest but strong supervised machine learning algorithm. KNN can  be used for both classification and regression problems. There are some libraries in python to implement KNN, which allows a programmer to make KNN model easily without using deep ideas of mathematics. But if we try to implement KNN from scratch it becomes a bit tricky.

Before getting into the program lets recall the algorithm of KNN:

Algorithm for K-NN:

1.   Load the given data file into your program
2.   Initialize the number of neighbor to be considered i.e. ‘K’ (must be odd).
3.   Now for each tuples (entries or data point) in the data file we perform:
                      i.   Calculate distance between the data point (tuple) to be classified and each data points in the given data file.
                    ii.   Then add the distances corresponding to data points (data entries) in given data file (probably by adding column for distance).
                  iii.   Sort the data in data file from smallest to largest (in ascending order) by the distances.
4.   Pick the first K entries from the sorted collection of data.
5.   Observe the labels of the selected K entries.
6.   For classification, return the mode of the K labels and for regression, return the mean of K labels.

Now we are all ready to dive into the code.  let’s implement KNN from Scratch (Using pandas and Numpy only). We are going to classify the iris data into its different species by observing different 4 features: sepal length, sepal width, petal length, petal width. We have all together 150 observations(tuples) and we will make KNN classifying model on the basis of these observations.

Link to download iris dataset- iris.csv

 

import pandas as pd
import numpy as np
import operator

# loading data file into the program. give the location of your csv file
dataset = pd.read_csv("E:/input/iris.csv")
print(dataset.head()) # prints first five tuples of your data.

# making function for calculating euclidean distance
def E_Distance(x1, x2, length):
    distance = 0
    for x in range(length):
        distance += np.square(x1[x] - x2[x])
    return np.sqrt(distance)

# making function for defining K-NN model

def knn(trainingSet, testInstance, k):
    distances = {}
    length = testInstance.shape[1]
    for x in range(len(trainingSet)):
        dist = E_Distance(testInstance, trainingSet.iloc[x], length)
        distances[x] = dist[0]
    sortdist = sorted(distances.items(), key=operator.itemgetter(1))
    neighbors = []
    for x in range(k):
        neighbors.append(sortdist[x][0])
    Count = {}  # to get most frequent class of rows
    for x in range(len(neighbors)):
        response = trainingSet.iloc[neighbors[x]][-1]
        if response in Count:
            Count[response] += 1
        else:
            Count[response] = 1
    sortcount = sorted(Count.items(), key=operator.itemgetter(1), reverse=True)
    return (sortcount[0][0], neighbors)

# making test data set
testSet = [[6.8, 3.4, 4.8, 2.4]]
test = pd.DataFrame(testSet)

# assigning different values to k
k = 1
k1 = 3
k2 = 11

# supplying test data to the model
result, neigh = knn(dataset, test, k)
result1, neigh1 = knn(dataset, test, k1)
result2, neigh2 = knn(dataset, test, k2)

# printing output prediction

print(result)
print(neigh)
print(result1)
print(neigh1)
print(result2)
print(neigh2)
 



The Output of above program is:

   sepal.length  sepal.width  petal.length  petal.width variety

0           5.1          3.5           1.4          0.2  Setosa
1           4.9          3.0           1.4          0.2  Setosa
2           4.7          3.2           1.3          0.2  Setosa
3           4.6          3.1           1.5          0.2  Setosa
4           5.0          3.6           1.4          0.2  Setosa
4
4
4
Virginica
[141]
Virginica
[141, 145, 110]
Virginica
[141, 145, 110, 115, 139, 147, 77, 148, 140, 112, 144]

Leave a Reply

Insert math as
Block
Inline
Additional settings
Formula color
Text color
#333333
Type math using LaTeX
Preview
\({}\)
Nothing to preview
Insert
%d bloggers like this: