Scribd
Upload
70 views3 pages

Print: Program 7

This document contains 10 Python programs. Program 6 imports packages and loads a dataset, splits it into training and test sets, performs feature extraction using CountVectorizer, fits a MultinomialNB model and evaluates it. Program 7 imports packages, loads a heart disease dataset, fits a Bayesian network model using MaximumLikelihoodEstimator and performs inference. Program 8 loads the iris dataset, performs KMeans and GaussianMixture clustering and evaluates accuracy. Program 9 loads iris, trains a KNeighborsClassifier and evaluates accuracy. Program 10 generates data, performs local regression using a radial kernel and plots the results.

Uploaded by

Impu anand
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
70 views3 pages

Print: Program 7

This document contains 10 Python programs. Program 6 imports packages and loads a dataset, splits it into training and test sets, performs feature extraction using CountVectorizer, fits a MultinomialNB model and evaluates it. Program 7 imports packages, loads a heart disease dataset, fits a Bayesian network model using MaximumLikelihoodEstimator and performs inference. Program 8 loads the iris dataset, performs KMeans and GaussianMixture clustering and evaluates accuracy. Program 9 loads iris, trains a KNeighborsClassifier and evaluates accuracy. Program 10 generates data, performs local regression using a radial kernel and plots the results.

Uploaded by

Impu anand
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Program 6

import​ pandas ​as​ pd


from​ pandas ​import​ DataFrame
df_imbd = DataFrame.from_csv(r​"/content/imdb_labelled.txt"​,sep=​'\t'​,index_col=​None​)
print​(df_imbd.keys())
from​ sklearn.model_selection ​import​ train_test_split
X_train, X_test, y_train, y_test =
train_test_split(df_imbd[​'Text'​],df_imbd[​'Label'​],train_size=​0.66​,random_state=​100​)
from​ sklearn.feature_extraction.text ​import​ CountVectorizer
cv = CountVectorizer(strip_accents=​'ascii'​,
token_pattern=u​'(?ui)\\b\\w*[a-z]+\\w*\\b'​,lowercase=​True​,stop_words=​'english'​)
X_train_cv = cv.fit_transform(X_train)
X_test_cv = cv.transform(X_test)
word_freq_df = pd.DataFrame(X_train_cv.toarray(), columns=cv.get_feature_names())
top_words_df = pd.DataFrame(word_freq_df.​sum​()).sort_values(​0​, ascending=​False​)
from​ sklearn.naive_bayes ​import​ MultinomialNB
naive_bayes = MultinomialNB()
naive_bayes.fit(X_train_cv, y_train)
predictions = naive_bayes.predict(X_test_cv)
from​ sklearn.metrics ​import​ accuracy_score, precision_score, recall_score
print​(​'Accuracy score: '​, accuracy_score(y_test, predictions))
print​(​'Precision score: '​, precision_score(y_test, predictions))
print​(​'Recall score: '​, recall_score(y_test, predictions))

Program 7
!​pip install pgmpy
import​ pandas ​as​ pd
from​ urllib.request ​import​ urlopen
from​ pgmpy.models ​import​ BayesianModel
from​ pgmpy.estimators ​import​ MaximumLikelihoodEstimator,BayesianEstimator
names = ​'A,B,C,D,E,F,G,H,I,J,K,L,M,RESULT'
names =names.split(​","​)
data = pd.read_csv(urlopen(​"http://bit.do/heart-disease"​),names=names)
model = BayesianModel([(​"A"​,​"B"​),(​"A"​,​"C"​),(​"C"​,​"RESULT"​)])
model.fit(data,estimator=MaximumLikelihoodEstimator)
from​ pgmpy.inference ​import​ VariableElimination
infer = VariableElimination(model)
q = infer.query(variables=[​'RESULT'​],evidence={​"A"​:​22​})
print​(q[​'RESULT'​])
Program 8
from​ sklearn ​import​ datasets
import​ numpy ​as​ np
from​ sklearn.cluster ​import​ KMeans
from​ sklearn.model_selection ​import​ train_test_split
from​ sklearn ​import​ metrics
iris = datasets.load_iris()
x_train,x_test,y_train,y_test = train_test_split(iris.data,iris.target)
model = KMeans(n_clusters=​3​)
model.fit(x_train,y_train)
metrics.accuracy_score(y_test,model.predict(x_test))
from​ sklearn.mixture ​import​ GaussianMixture
model2 = GaussianMixture(n_components=​3​)
model2.fit(x_train,y_train)
metrics.accuracy_score(y_test,model2.predict(x_test))

Program 9
from​ sklearn ​import​ datasets
from​ sklearn.neighbors ​import​ KNeighborsClassifier
from​ sklearn.model_selection ​import​ train_test_split
from​ sklearn ​import​ metrics
iris = datasets.load_iris()
x_train,x_test,y_train,y_test = train_test_split(iris.data,iris.target)
model = KNeighborsClassifier(n_neighbors=​3​)
model.fit(x_train,y_train)
metrics.accuracy_score(y_test,model.predict(x_test))

Program 10
import​ numpy ​as​ np
import​ matplotlib.pyplot ​as​ plt
x = np.linspace(​-5​,​5​,​10000​)
y = np.log(np.​abs​((x**​2​)​-1​)+​0.5​)
x += np.random.normal(scale=​0.05​,size=​1000​)
plt.scatter(x,y,alpha=​0.3​)
def​ ​local_regression​(​x0​,​x​,​y​,​tau​):
x0 = np.r_[​1​,x0]
x= np.c_[np.ones(​len​(x)),x]
xw = x.T*radial_kernel(x0,x,tau)
beta = np.linalg.pinv(xw​@​x)​@​xw​@​y
​return​ x0​@​beta
def​ ​radial_kernel​(​x0​,​x​,​tau​):
​return​ np.exp(np.​sum​((x-x0)**​2​,axis=​1​)/(​-2​*tau**​2​))
def​ ​plot_lr​(​tau​):
domain = np.linspace(​-5​,​5​,num=​300​)
pred = [local_regression(x0,x,y,tau) ​for​ x0 ​in​ domain]
plt.scatter(x,y,alpha=​0.3​)
plt.plot(domain,pred,color=​"red"​)
​return​ plt
plot_lr(​0.03​)

You might also like