PROGRAM-1

import csv
import random
import math
import operator
Define loadDataset
def loadDataset(filename,split,trainingSet=[],testSet=[]):
    with open(filename) as csvfile:
        lines = csv.reader(csvfile)
        dataset = list(lines)
        for x in range(len(dataset)-1):
            for y in range(4):
                dataset[x][y] = float(dataset[x][y])
            if random.random()<split:
                trainingSet.append(dataset[x])
            else:
                testSet.append(dataset[x])
#Define Euclidean Distance
def euclideanDistance(instance1, instance2, length):
    distance = 0
    for x in range(length):
        distance += pow((instance1[x]-instance2[x]),2)
    return math.sqrt(distance)
#Define getNeighbours
def getNeighbors(trainingSet, testInstance, k):
    distances=[]
    length = len(testInstance)-1
    for x in range(len(trainingSet)):
        dist = euclideanDistance(testInstance, trainingSet[x], length)
        distances.append((trainingSet[x],dist))
    distances.sort(key=operator.itemgetter(1))
    neighbors=[]
    for x in range(k):
        neighbors.append(distances[x][0])
    return neighbors
#Define getResponse
def getResponse(neighbors):
    classVotes = {}
    for x in range (len(neighbors)):
        response = neighbors[x][-1]
        if response in classVotes:
            classVotes[response]+=1
        else:
            classVotes[response]=1
    sortedVotes = sorted(classVotes.items(), key = operator.itemgetter(1),reverse=True)
    return sortedVotes[0][0]
#Define getAccuracy
def getAccuracy(testSet, predictions):
    correct = 0
    for x in range(len(testSet)):
        if testSet[x][-1]==predictions[x]:
            correct+=1
    return (correct/float(len(testSet)))*100.0
#Define Main function
def main():
    trainingSet=[]
    testSet=[]
    split=0.67
    loadDataset('iris_Dataset.csv',split,trainingSet,testSet)
    print('\nNumber of trainingdata :'+(repr(len(trainingSet))))
    print('Number of test data :'+(repr(len(testSet))))
    predictions=[]
    k=3
    print('\nThe predictions are :')
    for x in range (len(testSet)):
        neighbors=getNeighbors(trainingSet, testSet[x], k)
        result = getResponse(neighbors)
        predictions.append(result)
        print('Predicted ='+repr(result)+',actual ='+repr(testSet[x][-1]))
    accuracy = getAccuracy(testSet, predictions)
    print('\nThe Accuracy is :'+repr(accuracy)+'%')
#Call the Main function
main()


PROGRAM-2

#Importing Libraries
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
from sklearn.mixture import GaussianMixture
from sklearn.cluster import KMeans
#Importing Datasets
data=pd.read_csv('knnvsempgm2.csv')
print("input data and shape")
print(data.shape)
data.head()
#Dividing the dataset
f1 = data['v1'].values
f2 = data['v2'].values
X = np.array(list(zip(f1,f2)))
#Printing the datatset
print("X", X)
print('graph for whole dataset')
plt.scatter (f1, f2, c = 'black', s = 15)
plt.show()
#Clustering the dataset using K-means clustering
kmeans=KMeans(10, random_state=42)
labels = kmeans.fit(X).predict(X)
print("labels",labels)
centroids = kmeans.cluster_centers_
print("centroids",centroids)
plt.scatter(X[:,0], X[:,1], c=labels, s=40, cmap='viridis');
print('graph using Kmeans Algorithm')
plt.scatter(centroids[:,0], centroids[:,1],marker='*',s=200, c='#050505')
plt.show()


PROGRAM-3

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
tou=1
data=pd.read_csv("tips1.csv")
X_train=np.array(data.total_bill)
print(X_train)
X_train=X_train[:,np.newaxis]
print(len(X_train))
y_train=np.array(data.tip)
X_test=np.array([i/10 for i in range(500)])
X_test=X_test[:,np.newaxis]
y_test=[]
count=0
for r in range(len(X_test)):
    wts=np.exp(-np.sum((X_train-X_test[r])**2,axis=1)/(2*tou**2))
    W=np.diag(wts)
    factor1=np.linalg.inv(X_train.T.dot(W).dot(X_train))
    parameters=factor1.dot(X_train.T).dot(W).dot(y_train)
    prediction=X_test[r].dot(parameters)
    y_test.append(prediction)
    count+=1
print(len(y_test))
y_test=np.array(y_test)
plt.plot(X_train.squeeze(),y_train,'o')
plt.plot(X_test.squeeze(),y_test,'o')
plt.show()