text hello
<?xmlversion=”1.
0”?>
<students>
<student>
<name>JohnDoe</name>
<age>21</age>
<gender>Male</gender>
<major>ComputerScience</major>
<gpa>3.8</gpa>
</student>
<student>
<name>JaneSmith</name>
<age>19</age>
<gender>Female</gender>
<major>Business</maj
<gpa>3.5</gpa>
</student>
<student>
or>
<name>TomJohnson</name>
<age>20</age>
<gender>Male</gender>
<major>Engineeri
ng</major>
<gpa>3.2</gpa>
</student>
<student>
<name>SaraLee</name>
<age>22</age>
<gender>Female</gender>
<major>Psychology</maj
or>
<gpa>3.6</gpa>
</student>
<student>
<name>MikeBrown</name>
<age>18</age>
<gender>Male</gender>
<major>Educati
on</major>
<gpa>3.4</gpa>
</student>
</students>
Importnltk
Fromnltk.corpusi
Nltk.downl
mportstopwords
oad(‘stopwords’
)
#Textparagraph
Text=“Helloall
,WelcometoPythonProgrammingAcademy.PythonProgrammingAcademyis
aniceplatformtolearnnewprogrammingskill
#Tokenizethetext
Tokens=nltk.word_tokeni
ze(text)
s.Itisdiffi
culttogetenrol
ledinthisAcademy.”
#Removestopwords
Stop_words=set(stopwords.words(‘
english’
))
Filtered_t
okens=[wordforwordintokensifnotword.lower()i
#Printthefil
teredtokens
Print(fi
ltered_tokens