def translate(sentence, to_sen='bn', to_file=False, file_name=None):
"""
input: sentence to convert, and language to convert
returns translated sentence
"""
err_sentence = "Sir, I can't translate this. Make sure you have said translate when you start detecting."
def detect(sentence):
"""
input: sentence or string
returns detected language
"""
try:
return blob.detect_language(blob(sentence))
except Exception as e:
print(e)
return None
try:
answer = blob.detect_language(blob(sentence))
if answer != None:
translated = str(
blob.translate(blob(sentence), from_lang=answer, to=to_sen))
else:
return err_sentence
if to_file:
saveFile(translated, file_name)
print("File written on {file}".format(file=file_name))
return translated
except Exception as e:
print(e)
return err_sentence
def make_textblob_object(self):
# assigns the local attribute to the string-type converted BeautifulSoup object
### MUST MAKE SEPARATE METHOD FOR TEXT EXTRACTION AND STRING CONVERSION ### THIS IS MY CURRENT LOCATION TO WORK ON !!!!
self.blob = blob(str(self.article.soup.text))
def file_translate(file, to_sen='bn', sfile="tranlated.txt"):
"""
input: file to translate, language to translate and a file name to save file
translated and save whole file
"""
paragraph = ''
print("File translating Start....")
print("File Reading begin...")
try:
with open(file, 'r') as file:
sentences = blob(file.read()).sentences
#print(sentences)
print("Translating: ", end='')
progress = tqdm(total=len(sentences),
desc="Translating:",
unit="sentence/s")
for item in sentences:
progress.update(1)
paragraph += translate(str(item)) + '\n'
time.sleep(0.2)
progress.close()
print("\nTranslating Done! Saving your file")
saveFile(paragraph, sfile)
except Exception as e:
print(e)
def comment(movie_id):
form = Comment_Form()
if form.validate_on_submit():
user_id = session['user_id']
comment_obj = blob(form.comment.data)
rating = comment_obj.sentiment.polarity
rating = round(rating, 1)
if rating <= -0.7:
rating = 1
elif rating > -0.7 and rating <= -0.2:
rating = 2
elif rating > -0.2 and rating <= 0.1:
rating = 3
elif rating > 0.1 and rating <= 0.6:
rating = 4
else:
rating = 5
review = Reviews(comment=form.comment.data,
rating=rating,
user_id=user_id,
movie_id=movie_id)
db.session.add(review)
db.session.commit()
avg_rating = get_avg_rating(movie_id)
movie = Movies.query.filter_by(id=movie_id).first_or_404()
movie.avg_rating = avg_rating
db.session.commit()
return redirect(url_for('home.movie', movie_id=movie_id))
def sentiment():
with open('my.txt') as t:
a = t.read()
tb = blob(
a) # textblob is a string which works like natural language processing
c = str(tb.sentiment) # here we are extracting sentiment from the string
with open('sentiment.txt', 'w') as s:
s.write(c)
def detect(sentence):
"""
input: sentence or string
returns detected language
"""
try:
return blob.detect_language(blob(sentence))
except Exception as e:
print(e)
return None
def textblob_sentiment_analysis(self):
### this adds the overall article sentiment to index 0 ###
self.sentiment.append(self.blob.sentiment)
# this loop iterates over each line within the article and assigns it a sentiment value
# it then adds those individual values to the empty sentiment list
for sentences in self.blob.split(
"."
): # this function call results in a list consisting of strings separated
# by a period
sentence_sentiment = blob(sentences).sentiment
self.sentiment.append(sentence_sentiment)
def getsentiment(text):
'''
Take input as text and Return Sentimental
'''
tb=blob(text)
result=tb.sentiment
polarity=result.polarity
print({'polarity':polarity,'text':text})
if polarity==0:
return "Neutral"
elif polarity>0:
return "Positive"
else:
return "Negative"
def handleFileUpload():
extra_line = ''
if request.method == "POST":
if "file" not in request.files:
flash("No file part")
return redirect(request.url)
file = request.files["file"]
if file.filename == '':
flash("No selected file")
return redirect(request.url)
if file:
recognizer = sr.Recognizer()
audio_file = sr.AudioFile(file)
with audio_file as source:
audio_data = recognizer.record(source)
text = recognizer.recognize_google(audio_data, show_all=False)
tb = blob(str(text))
tb_text = tb.sentiment
if tb_text[0] > 0:
a = 'Positive'
elif tb_text[0] < 0:
a = 'Negative'
else:
a = 'Neutral'
extra_line = str(text) + ": " + str(tb_text) + ": " + a
filename = secure_filename(file.filename)
filepath = os.path.join(app.config["UPLOAD_FOLDER"], filename)
file.save(filepath)
extra_line += f"<br>File saved to {filepath}"
#return redirect(url_for('fileFrontPage'))
return render_template(
'index.html',
prediction_text='Voice to Text: {} \n'.format(extra_line))
Original file is located at
https://colab.research.google.com/drive/1gvA21zINvGSUN4ieDfbxhD0FfAQg1RdE
"""
!pip install textblob
import nltk
nltk.download('punkt')
nltk.download("averaged_perceptron_tagger")
from textblob import TextBlob as blob
tb=blob("Am unhappy ")
tb.sentiment
tb.tags
!pip install SpeechRecognition
!apt install libasound2-dev portaudio19-dev libportaudio2 libportaudiocpp0 ffmpeg
!pip install pyaudio
import speech_recognition as sr
t=sr.Recognizer()
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--ip",
default="127.0.0.1",
help="The ip of the OSC server")
parser.add_argument("--port",
type=int,
default=12000,
help="The port the OSC server is listening on")
args = parser.parse_args()
client = udp_client.SimpleUDPClient(args.ip, args.port)
##create an object from the text blob
##text blob contains information about Part of Speech tagging
tb = blob('Hi, here is my sentiment analysis of speech!')
##object of the speech recognition
r = sr.Recognizer()
iter_num = 10
index = 0
##the loop below is running 10 times
while (index < iter_num):
with sr.Microphone() as source:
print('Say Something')
##if there is no sound for 5 seconds, it will stop recording and move on
##to the next speech message
audio = r.listen(source, timeout=5)
try:
elif "whatsapp to friend" in query:
driver = webdriver.Chrome('C:\\Users\\DANISH\\PycharmProject\\Examples\\venv\\Lib\\site-packages\\selenium\\webdriver\\chrome\\chromedriver.exe')
driver.get('https://web.whatsapp.com/')
time.sleep(15)
sender_name = input("Enter the name to whom you want to send message: ")
user = driver.find_element_by_xpath('//span[@title="{}"]'.format(sender_name))
user.click()
message = input("Enter th message: ")
mess_box = driver.find_element_by_class_name("_3u328 copyable-text selectable-text")
mess_box.click()
mess_box.send_keys(message)
button = driver.find_element_by_class_name('_3M-N-')
button.click()
speak('message sent successfully')
elif 'run sentiment analysis' in query:
speak('running the sentiment analysis')
for _ in range(10):
data = takeCommand()
tb = blob(data)
a = tb.sentiment
print(a)
speak(a)
elif 'terminate' in query:
speak("Thanks for using my service. happy to help you")
break
nouns = [] #empty to array to hold all nouns
#select nouns froms the sentences
for sentence in sentences:
for word, pos in nltk.pos_tag(nltk.word_tokenize(str(sentence))):
if (pos == 'NN' or pos == 'NNP' or pos == 'NNS' or pos == 'NNPS'):
nouns.append(word)
#stemming the nouns
p_stemmer = PorterStemmer()
nouns = [p_stemmer.stem(i) for i in nouns]
nouns = set(nouns)
nouns = list(nouns)
print(nouns)
#creating textblobs
stu1 = blob(doc_a)
stu2 = blob(doc_b)
stu3 = blob(doc_c)
stu4 = blob(doc_d)
stu5 = blob(doc_e)
#creating a list of textblobs
blob_set = [stu1, stu2, stu3, stu4, stu5]
#creating the opinion list
opinion = [0] * len(nouns)
for i in range(0, len(nouns)):
opinion[i] = 0
for j in blob_set:
if nouns[i] in j:
opinion[i] += j.sentiment[0]