Ml all programs

pg 1. Implement and demonstratethe FIND-Salgorithm for finding the most specific hypothesis
based on a given set of training data samples. Read the training data from a .CSV file.
import csv
num_attributes=6
a=[]
print("n the given training data setn")
with open('sports.csv','r') as csvfile:
reader=csv.reader(csvfile)
for row in reader:
a.append(row)
print(row)
print("n the initial value of hypothesis: ")
hypothesis=['0']*num_attributes
print(hypothesis)
for j in range(0,num_attributes):
hypothesis[j]=a[0][j]
print("n find s: finding a maximaly specific hypothesisn")
for i in range(0,len(a)):
if a[i][num_attributes]=='yes':
if a[i][j]!=hypothesis[j]:
hypothesis[j]='?'
else:
hypothesis[j]=a[i][j]
print("for training instance no:{0} the hypothesis is".format(i),hypothesis)
print("output")
print(hypothesis)
output:
the given training data set
['sunny', 'warm', 'normal', 'strong', 'warm', 'same', 'Yes']
['sunny', 'warm', 'high', 'strong', 'warm', 'same', 'Yes']
['sunny', 'warm', 'normal', 'strong', 'warm', 'same', 'no']
['sunny', 'warm', 'high', 'strong', 'cool', 'change', 'Yes']
the initial value of hypothesis:
['0', '0', '0', '0', '0', '0']
find s: finding a maximaly specific hypothesis

for training instance no:0 the hypothesis is ['sunny', 'warm', 'normal', 'strong', 'warm', 'same']
output
['sunny', 'warm', 'normal', 'strong', 'warm', 'same']
pg 2:2. For a given set of training data examples stored in a .CSV file, implement and
demonstrate the Candidate-Elimination algorithmto output a description of the set of all
hypotheses consistent with the training examples.
import csv
a=[]
print("n The Given Training Data Setn")
with open('C:UsersISE-68Desktopws.csv','r') as csvFile:
reader=csv.reader(csvFile)
for row in reader:
a.append(row)
print(row)
num_attributes=len(a[0])-1
print("n The initial value of hypothesis: ")
S=['0']*num_attributes
G=['?']*num_attributes
print("n The most specific hypothesis S0:[0,0,0,0,0,0]n")
print("n The most general hypothesis G0:[?,?,?,?,?,?]n")
#compare with first training example
S[j]=a[0][j]
#compare with remaining training examples of given data set
print("n Candidate Elimination algorithm hypotheses version space computationn")
temp=[]
for i in range(0,len(a)):
if a[i][num_attributes]=='Yes':
if a[i][j]!=S[j]:
S[j]='?'

for k in range(1,len(temp)):
if temp[k][j]!='?' and temp[k][j]!=S[j]:
del temp[k]
print("for Training Example No:{0} the hypothesis is S{0} ".format(i+1),S)
if(len(temp)==0):
print("for Training Example No:{0} the hypothesis is G{0} ".format(i+1),G)
else:
print("for Training Example No:{0} the hypothesis is G{0} ".format(i+1),temp)
if a[i][num_attributes]=='No':
if S[j]!=a[i][j] and S[j]!='?':
G[j]=S[j]
temp.append(G)
G=['?']*num_attributes
print("for Training Example No:{0} the hypothesis is S{0} ".format(i+1),S)
print("for Training Example No:{0} the hypothesis is G{0} ".format(i+1),temp)
output:
The Given Training Data Set
['Sunny', 'Warm', 'Normal', 'Strong', 'Warm', 'Same', 'Yes']
['Sunny', 'Warm', 'High', 'Strong', 'Warm', 'Same', 'Yes']
['Rainy', 'Cold', 'High', 'Strong', 'Warm', 'Change', 'No']
['Sunny', 'Warm', 'High', 'Strong', 'Cold', 'Change', 'Yes']
The initial value of hypothesis:
The most specific hypothesis S0:[0,0,0,0,0,0]
The most general hypothesis G0:[?,?,?,?,?,?]
Candidate Elimination algorithm hypotheses version space computation
for Training Example No:1 the hypothesis is S1 ['Sunny', 'Warm', 'Normal', 'Strong', 'Warm',
'Same']
for Training Example No:1 the hypothesis is G1 ['?', '?', '?', '?', '?', '?']
for Training Example No:2 the hypothesis is S2 ['Sunny', 'Warm', '?', 'Strong', 'Warm', 'Same']
for Training Example No:2 the hypothesis is G2 ['?', '?', '?', '?', '?', '?']
for Training Example No:3 the hypothesis is S3 ['Sunny', 'Warm', '?', 'Strong', 'Warm', 'Same']
for Training Example No:3 the hypothesis is G3 [['Sunny', '?', '?', '?', '?', '?'], ['?', 'Warm', '?', '?',

'?', '?'], ['?', '?', '?', '?', '?', 'Same']]
for Training Example No:4 the hypothesis is S4 ['Sunny', 'Warm', '?', 'Strong', '?', '?']
for Training Example No:4 the hypothesis is G4 [['Sunny', '?', '?', '?', '?', '?'], ['?', 'Warm', '?', '?',
'?', '?']]
pg 3:3. Write a program to demonstrate the working of the decision tree based ID3 algorithm.
Use an appropriate data set for building the decision tree and apply this knowledge toclassify a
new sample
import numpy as np
import math
import csv
class Node:
def __init__(self, attribute):
self.attribute = attribute
self.children = []
self.answer = ""
def __str__(self):
return self.attribute
def read_data(filename):
with open(filename, 'r') as csvfile:
datareader = csv.reader(csvfile)
metadata = next(datareader)
traindata=[]
for row in datareader:
traindata.append(row)
return (metadata, traindata)
def subtables(data, col, delete):
dict = {}
items = np.unique(data[:, col]) # get unique values in particular column
count = np.zeros((items.shape[0], 1), dtype=np.int32) #number of row = number of values
for x in range(items.shape[0]):
for y in range(data.shape[0]):

if data[y, col] == items[x]:
count[x] += 1
#count has the data of number of times each value is present in
dict[items[x]] = np.empty((int(count[x]), data.shape[1]), dtype="|S32")
pos = 0
for y in range(data.shape[0]):
if data[y, col] == items[x]:
dict[items[x]][pos] = data[y]
pos += 1
if delete:
dict[items[x]] = np.delete(dict[items[x]], col, 1)
return items, dict
def entropy(S):
items = np.unique(S)
if items.size == 1:
return 0
counts = np.zeros((items.shape[0], 1))
sums = 0
counts[x] = sum(S == items[x]) / (S.size)
for count in counts:
sums += -1 * count * math.log(count, 2)
return sums
def gain_ratio(data, col):
items, dict = subtables(data, col, delete=False)
#item is the unique value and dict is the data corresponding to it
total_size = data.shape[0]
entropies = np.zeros((items.shape[0], 1))
ratio = dict[items[x]].shape[0]/(total_size)

entropies[x] = ratio * entropy(dict[items[x]][:, -1])
total_entropy = entropy(data[:, -1])
for x in range(entropies.shape[0]):
total_entropy -= entropies[x]
return total_entropy
def create_node(data, metadata):
if (np.unique(data[:, -1])).shape[0] == 1:
node = Node("")
node.answer = np.unique(data[:, -1])
return node
gains = np.zeros((data.shape[1] - 1, 1))
#size of gains= number of attribute to calculate gain
for col in range(data.shape[1] - 1):
gains[col] = gain_ratio(data, col)
split = np.argmax(gains)
node = Node(metadata[split])
metadata = np.delete(metadata, split, 0)
items, dict = subtables(data, split, delete=True)
child = create_node(dict[items[x]], metadata)
node.children.append((items[x], child))
return node
def empty(size):
s = ""
for x in range(size):
s += " "
return s

def print_tree(node, level):
if node.answer != "":
print(empty(level), node.answer)
return
print(empty(level), node.attribute)
for value, n in node.children:
print(empty(level + 1), value)
print_tree(n, level + 2)
metadata, traindata = read_data("tennis.csv")
data = np.array(traindata)
node = create_node(data, metadata)
print_tree(node, 0)
output:
Outlook
Overcast
[b'Yes']
Rainy
Windy
b'False'
[b'Yes']
b'True'
[b'No']
Sunny
Humidity
b'High'
[b'No']
b'Normal'
[b'Yes']
pg 4:4. Build an Artificial Neural Network by implementing the Backpropagation algorithm and
test the same using appropriate data sets.
import numpy as np
X = np.array(([2,9],[1,5],[3,6]), dtype=float)
print("X=",X)
y = np.array(([92], [86], [89]), dtype=float)

print("y=",y)
y=y/100
print("y=",y)
def sigmoid (x):
return 1/(1 + np.exp(-x))
def derivatives_sigmoid(x):
return x * (1 - x)
epoch=10000
lr=0.1
inputlayer_neurons = 2
hiddenlayer_neurons = 3
output_neurons = 1
wh=np.random.uniform(size=(inputlayer_neurons,hiddenlayer_neurons))
print("whn",wh)
bh=np.random.uniform(size=(1,hiddenlayer_neurons))
print("bhn",bh)
wout=np.random.uniform(size=(hiddenlayer_neurons,output_neurons))
print("woutn",wout)
bout=np.random.uniform(size=(1,output_neurons))
print("boutn",bout)
for i in range(epoch):
hinp1=np.dot(X,wh)
print("nn hinp1n",hinp1)
hinp=hinp1 + bh
print("hinpn",hinp)
hlayer_act = sigmoid(hinp)
print("hlayer_actn",hlayer_act)
outinp1=np.dot(hlayer_act,wout)
print("outinp1n",outinp1)
outinp=outinp1+bout
print("outinpn",outinp)
output=sigmoid(outinp)
print("outputn",output)
EO = y-output
print("EOn",EO)
outgrad = derivatives_sigmoid(output)
print("outgradn",outgrad)
d_output = EO* outgrad
print("d_outputn",d_output)
EH= d_output.dot(wout.T)

print("EHn",EH)
hiddengrad=derivatives_sigmoid(hlayer_act)
print("hiddengradn",hiddengrad)
d_hiddenlayer=EH * hiddengrad
print("d_hiddenlayern",d_hiddenlayer)
wout += hlayer_act.T.dot(d_output) *lr
print("woutn",wout)
bout += np.sum(d_output, axis=0,keepdims=True) *lr
print("boutn",bout)
wh += X.T.dot(d_hiddenlayer) *lr
print("whn",wh)
bh +=np.sum(d_hiddenlayer,axis=0,keepdims=True) *lr
print("bhn",bh)
print("nn input: n" + str(X))
print("actual output: n"+ str(y))
print("predicted output: n", output)
output:
too big
pg 5:5. Write a program to implement the naïve Bayesian classifier for a sample training data
set stored as a .CSV file. Compute the accuracy of the classifier, considering few test data sets.
import numpy as np
import math
import csv
def read_data(filename):
with open(filename, 'r') as csvfile:
datareader = csv.reader(csvfile)
metadata = next(datareader)
traindata=[]
for row in datareader:
traindata.append(row)
return (metadata, traindata)
def splitDataset(dataset, splitRatio): #splits dataset to training set and test set based on
split ratio
trainSize = int(len(dataset) * splitRatio)

trainSet = []
testset = list(dataset)
i=0
while len(trainSet) < trainSize:
trainSet.append(testset.pop(i))
return [trainSet, testset]
def classify(data,test):
total_size = data.shape[0]
print("training data size=",total_size)
print("test data sixe=",test.shape[0])
target=np.unique(data[:,-1])
count = np.zeros((target.shape[0]), dtype=np.int32)
prob = np.zeros((target.shape[0]), dtype=np.float32)
print("target count probability")
for y in range(target.shape[0]):
for x in range(data.shape[0]):
if data[x,data.shape[1]-1] == target[y]:
count[y] += 1
prob[y]=count[y]/total_size # comptes the probability of target
print(target[y],"t",count[y],"t",prob[y])
prob0 = np.zeros((test.shape[1]-1), dtype=np.float32)
prob1 = np.zeros((test.shape[1]-1), dtype=np.float32)
accuracy=0
print("Instance prediction taget")
for t in range(test.shape[0]):
for k in range(test.shape[1]-1): # for each attribute in column
count1=count0=0
for j in range(data.shape[0]):
if test[t,k]== data[j,k] and data[j,data.shape[1]-1]== target[0]:
count0+=1
elif test[t,k]== data[j,k] and data[j,data.shape[1]-1]== target[1]:
count1+=1
prob0[k]= count0/count[0] #Find no probability of each attribute
prob1[k]= count1/count[1] #Find yes probability of each attribute
probno=prob[0]
probyes=prob[1]
for i in range(test.shape[1]-1):
probno=probno*prob0[i]

probyes=probyes*prob1[i]
if probno>probyes: # prediction
predict='No'
else:
predict='Yes'
print(t+1,"t",predict,"t ",test[t,test.shape[1]-1])
if predict== test[t,test.shape[1]-1]: # computing accuracy
accuracy+=1
final_accuracy=(accuracy/test.shape[0])*100
print("accuracy",final_accuracy,"%")
return
metadata, traindata = read_data("tennis.csv")
splitRatio = 0.4
trainingset, testset = splitDataset(traindata, splitRatio)
training=np.array(trainingset)
testing=np.array(testset)
print("------------------Training Data-------------------")
print(trainingset)
print("-------------------Test Data-------------------")
print(testset)
classify(training,testing)
output:
------------------Training Data-------------------
[['Sunny', 'Hot', 'High', 'False', 'No'], ['Sunny', 'Hot', 'High', 'True', 'No'], ['Overcast', 'Hot', 'High',
'False', 'Yes'], ['Rainy', 'Mild', 'High', 'False', 'Yes'], ['Rainy', 'Cool', 'Normal', 'False', 'Yes']]
-------------------Test Data-------------------
[['Rainy', 'Cool', 'Normal', 'True', 'No'], ['Overcast', 'Cool', 'Normal', 'True', 'Yes'], ['Sunny', 'Mild',
'High', 'False', 'No'], ['Sunny', 'Cool', 'Normal', 'False', 'Yes'], ['Rainy', 'Mild', 'Normal', 'False',
'Yes'], ['Sunny', 'Mild', 'Normal', 'True', 'Yes'], ['Overcast', 'Mild', 'High', 'True', 'Yes'], ['Overcast',
'Hot', 'Normal', 'False', 'Yes'], ['Rainy', 'Mild', 'High', 'True', 'No']]
training data size= 5
test data sixe= 9
target count probability

No 2 0.4
Yes 3 0.6
Instance prediction taget
1 Yes No
2 Yes Yes
3 Yes No
4 Yes Yes
5 Yes Yes
6 Yes Yes
7 Yes Yes
8 Yes Yes
9 Yes No
accuracy 66.66666666666666 %
pg 6:6. Assuming a set of documents that need to be classified, use the naïve Bayesian
Classifier model to perform this task. Built-in Java classes/API can be used to write the
program. Calculate the accuracy, precision, and recall for your data set.
import pandas as pd
msg=pd.read_csv('naivetext1.csv',names=['message','label'])
print('The dimensions of the dataset',msg.shape)
msg['labelnum']=msg.label.map({'pos':1,'neg':0})
X=msg.message
y=msg.labelnum
print(X)
print(y)
#splitting the dataset into train and test data
from sklearn.model_selection import train_test_split
xtrain,xtest,ytrain,ytest=train_test_split(X,y)
print(xtest.shape)
print(xtrain.shape)
print(ytest.shape)
print(ytrain.shape)
#output of count vectoriser is a sparse matrix
from sklearn.feature_extraction.text import CountVectorizer
count_vect = CountVectorizer()
xtrain_dtm = count_vect.fit_transform(xtrain)
xtest_dtm=count_vect.transform(xtest)

print(count_vect.get_feature_names())
df=pd.DataFrame(xtrain_dtm.toarray(),columns=count_vect.get_feature_names())
print(df)#tabular representation
print(xtrain_dtm) #sparse matrix representation
#Training Naive Bayes (NB) classifier on training data.
from sklearn.naive_bayes import MultinomialNB
clf = MultinomialNB().fit(xtrain_dtm,ytrain)
predicted = clf.predict(xtest_dtm)
#printing accuracy metrics
from sklearn import metrics
print('Accuracy metrics')
print('Accuracy of the classifer is',metrics.accuracy_score(ytest,predicted))
print('Confusion matrix')
print(metrics.confusion_matrix(ytest,predicted))
print('Recall and Precison ')
print(metrics.recall_score(ytest,predicted))
print(metrics.precision_score(ytest,predicted))
output:
Accuracy metrics
Accuracy of the classifer is 0.6
Confusion matrix
[[1 2]
[0 2]]
Recall and Precison
1.0
0.5
pg 7:
7.Write a program to construct aBayesian network considering medical data. Use this model to
demonstrate the diagnosis of heart patients using standard Heart Disease Data Set. You can
use Java/Python ML library classes/API.
# data analysis, splitting and wrangling
import pandas as pd
import numpy as np

from sklearn.preprocessing import StandardScaler
# machine learning
from sklearn.naive_bayes import GaussianNB
# column names in accordance with feature information
col_names = ['age','sex','chest_pain','blood_pressure',
'serum_cholestoral','fasting_blood_sugar', 'electrocardiographic',
'max_heart_rate','induced_angina','ST_depression',
'slope','no_of_vessels','thal','diagnosis']
# read the file
df = pd.read_csv("heart_disease_dataset.csv", names=col_names, header=None,
na_values="?")
print("Number of records: {}nNumber of variables: {}".format(df.shape[0], df.shape[1]))
# display the first 5 lines my comments
df.head()
df.info()
# extract numeric columns and find categorical ones
numeric_columns = ['serum_cholestoral', 'max_heart_rate', 'age', 'blood_pressure',
'ST_depression']
categorical_columns = [c for c in df.columns if c not in numeric_columns]
print(categorical_columns)
# count values of explained variable
df.diagnosis.value_counts()
# create a boolean vector and map it with corresponding values (True=1, False=0)
df.diagnosis = (df.diagnosis != 0).astype(int)
df.diagnosis.value_counts()
# view of descriptive statistics
df[numeric_columns].describe()

# count ill vs healthy people grouped by sex
df.groupby(['sex','diagnosis'])['diagnosis'].count()
# average number of diagnosed people grouped by number of blood vessels detected by
fluoroscopy
df[['no_of_vessels','diagnosis']].groupby('no_of_vessels').mean()
# show columns having missing values
df.isnull().sum()
# fill missing values with mode
df['no_of_vessels'].fillna(df['no_of_vessels'].mode()[0], inplace=True)
df['thal'].fillna(df['thal'].mode()[0], inplace=True)
# extract the target variable
X, y = df.iloc[:, :-1], df.iloc[:, -1]
print(X.shape)
print(y.shape)
# split the data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=2606)
print ("train_set_x shape: " + str(X_train.shape))
print ("train_set_y shape: " + str(y_train.shape))
print ("test_set_x shape: " + str(X_test.shape))
print ("test_set_y shape: " + str(y_test.shape))
# scale feature matrices
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
model = GaussianNB()
# train model
model.fit(X_train,y_train)
# check accuracy and print out the results
fit_accuracy = model.score(X_train, y_train)
test_accuracy = model.score(X_test, y_test)

print(f"Train accuracy: {fit_accuracy:0.2%}")
print(f"Test accuracy: {test_accuracy:0.2%}")
output:
Number of records: 303
Number of variables: 14
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 303 entries, 0 to 302
Data columns (total 14 columns):
age 303 non-null float64
sex 303 non-null float64
chest_pain 303 non-null float64
blood_pressure 303 non-null float64
serum_cholestoral 303 non-null float64
fasting_blood_sugar 303 non-null float64
electrocardiographic 303 non-null float64
max_heart_rate 303 non-null float64
induced_angina 303 non-null float64
ST_depression 303 non-null float64
slope 303 non-null float64
no_of_vessels 299 non-null float64
thal 301 non-null float64
diagnosis 303 non-null int64
dtypes: float64(13), int64(1)
memory usage: 33.2 KB
['sex', 'chest_pain', 'fasting_blood_sugar', 'electrocardiographic', 'induced_angina', 'slope',
'no_of_vessels', 'thal', 'diagnosis']
(303, 13)
(303,)
train_set_x shape: (212, 13)
train_set_y shape: (212,)
test_set_x shape: (91, 13)
test_set_y shape: (91,)
Train accuracy: 85.38%
Test accuracy: 86.81%

pg 8:
8. Apply EM algorithm to cluster a set of data stored in a .CSV file. Use the same dataset for
clustering using k-Means algorithm. Compare the results of these two algorithms and comment
on the quality of clustering. You can add Java/Python ML library classes/API in the program.
#from sklearn import metrics
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.mixture import GaussianMixture
from sklearn.cluster import KMeans
data=pd.read_csv("clusterdata.csv")
df1=pd.DataFrame(data)
print(df1)
f1 = df1['Distance_Feature'].values
f2 = df1['Speeding_Feature'].values
X=np.matrix(list(zip(f1,f2)))
plt.plot(1)
plt.subplot(511)
plt.xlim([0, 100])
plt.ylim([0, 50])
plt.title('Dataset')
plt.ylabel('speeding_feature')
plt.xlabel('distance_feature')
plt.scatter(f1,f2)
colors = ['b', 'g', 'r']
markers = ['o', 'v', 's']
# create new plot and data for K- means algorithm
plt.plot(2)
ax=plt.subplot(513)
kmeans_model = KMeans(n_clusters=3).fit(X)
for i, l in enumerate(kmeans_model.labels_):
fig1=plt.plot(f1[i], f2[i], color=colors[l],marker=markers[l])

plt.xlim([0, 100])
plt.ylim([0, 50])
plt.title('K- Means')
# create new plot and data for gaussian mixture
plt.plot(3)
plt.subplot(515)
gmm=GaussianMixture(n_components=3).fit(X)
labels= gmm.predict(X)
for i, l in enumerate(labels):
plt.plot(f1[i], f2[i], color=colors[l], marker=markers[l])
plt.xlim([0, 100])
plt.ylim([0, 50])
plt.title('Gaussian Mixture')
plt.show()
output:
Driver_ID Distance_Feature Speeding_Feature
0 3423311935 71.24 28
1 3423313212 52.53 25
2 3423313724 64.54 27
3 3423311373 55.69 22
4 3423310999 54.58 25
5 3423313857 41.91 10
6 3423312432 58.64 20
7 3423311434 52.02 8
8 3423311328 31.25 34
9 3423312488 44.31 19
10 3423311254 49.35 40
11 3423312943 58.07 45
12 3423312536 44.22 22
13 3423311542 55.73 19
14 3423312176 46.63 43
15 3423314176 52.97 32

16 3423314202 46.25 35
17 3423311346 51.55 27
18 3423310666 57.05 26
19 3423313527 58.45 30
20 3423312182 43.42 23
21 3423313590 55.68 37
22 3423312268 55.15 18
pg 9:
9.Write a program to implement k-Nearest Neighbour algorithm to classify the iris data set. Print
both correct and wrong predictions. Java/Python ML library classes can be used for this
problem.
Program 9
#KNN algorithm
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import classification_report,confusion_matrix
#from sklearn import metrics
import pandas as pd
import numpy as np
from sklearn import datasets
iris=datasets.load_iris()
iris_data=iris.data
iris_labels=iris.target
#print(iris_data)
#print(iris_labels)
X_train,x_test,y_train,y_test=train_test_split(iris_data,iris_labels,test_size=0.20)
classifier=KNeighborsClassifier(n_neighbors=5)
classifier.fit(X_train,y_train)
y_pred=classifier.predict(x_test)
print('confusion_matrix is as follows')
print(confusion_matrix(y_test,y_pred))
print('Accuracy Metrics')
print(classification_report(y_test,y_pred))
output:
confusion_matrix is as follows
[[11 0 0]
[ 0 9 0]

[ 0 1 9]]
Accuracy Metrics
precision recall f1-score support
0 1.00 1.00 1.00 11
1 0.90 1.00 0.95 9
2 1.00 0.90 0.95 10
avg / total 0.97 0.97 0.97 30
pg 10:
10.Implement the non-parametric Locally Weighted Regressionalgorithm in order to fit data
points. Select appropriate data set for your experiment and draw graphs.
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np1
def kernel(point,xmat, k):
m,n= np1.shape(xmat)
weights = np1.mat(np1.eye((m)))
for j in range(m):
diff = point - X[j]
weights[j,j] = np1.exp(diff*diff.T/(-2.0*k**2))
return weights
def localWeight(point,xmat,ymat,k):
wei = kernel(point,xmat,k)
W = (X.T*(wei*X)).I*(X.T*(wei*ymat.T))
return W
def localWeightRegression(xmat,ymat,k):
m,n = np1.shape(xmat)
ypred = np1.zeros(m)
for i in range(m):
ypred[i] = xmat[i]*localWeight(xmat[i],xmat,ymat,k)
return ypred
# load data points

data = pd.read_csv('tips1.csv')
bill = np1.array(data.total_bill)
tip = np1.array(data.tip)
#preparing and add 1 in bill
mbill = np1.mat(bill) # mat treats array as matrix
mtip = np1.mat(tip)
m= np1.shape(mbill)[1]
print("******",m)
one = np1.mat(np1.ones(m))
X= np1.hstack((one.T,mbill.T)) #Stack arrays in sequence horizontally (column wise).
#set k here
ypred = localWeightRegression(X,mtip,2)
SortIndex = X[:,1].argsort(0)
xsort = X[SortIndex][:,0]
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(bill,tip, color='blue')
ax.plot(xsort[:,1],ypred[SortIndex], color = 'red', linewidth=1)
plt.xlabel('Total bill')
plt.ylabel('Tip')
#plt.show();
output:
Text(0,0.5,'Tip')

Ml all programs

More Related Content

What's hot (20)

Similar to Ml all programs (20)

Recently uploaded (20)

Ml all programs