EX NO: LANGUAGE PROCESSING FOR SOCIAL
DATE: MEDIA
AIM
AIM:
To write a python code for language for social media.
ALGORITHM:
Step 1: import required libraries
Step 2: Model architecture.
Step 3: Training process text prediction.
Step 4: Evaluation metrics limitations.
PROGRAM:
import re
from textblob import TextBlob
def clean_text(text):
return re.sub(r"@\w+|#\w+|http\S+|[^a-zA-Z0-9\s]", "", text).strip()
print ("Social Media NLP (Type 'exit' to stop)")
while True:
text = input ("Enter text: ")
if text.lower() == "exit": break
print (f"Cleaned: {clean_text(text)} | Sentiment: {['Negative ', 'Neutral ',
'Positive'][(TextBlob(text).sentiment.polarity > 0) - (TextBlob(text).sentiment.polarity
< 0) + 1]}")
CSE/NM/NN&DL / 513322104048/SHANMUGASUNDARAM K
OUTPUT:
Social Media NLP (Type 'exit' to stop)
Enter text: I am bad
Cleaned: I am bad| Sentiment: Negative
Enter Text: Good guys!
Cleaned: Good guys|Sentiment: Positive
RESULT:
Thus the python code for language processing for social media was executed
successfully.
CSE/NM/NN&DL / 513322104048/SHANMUGASUNDARAM K
EX NO:
CHATBOT FOR CUSTOMER SERVICES
DATE:
AIM:
To write a python code for chatbot for customer services.
ALGORITHM:
Step 1: Import the required libraries.
Step 2: Gather dataset common customer service interaction.
Step 3: Process data an using training neutral networks.
Step 4: Testing ensure chatbots retrability and accuracy.
PROGRAM:
Import math
import random
def calculator_chatbot():
print ("?? Hello! I am MathBot")
greetings = [ "Hello! Ask me any math problem!"]
allowed_functions = {
"sqrt": math.sqrt, "pow": math.pow, "sin": math.sin, "cos": math.cos,
"tan": math.tan, "log": math.log, "pi": math.pi, "e": math.e
while True:
user_input = inpt ("You: ").strip ().lower()
if user_input == "exit":
print ("Chatbot: It was great talking to you! Have a fantastic day! ??")
break
elif user_input in ["hi", "hello", "hey"]:
CSE/NM/NN&DL / 513322104048/SHANMUGASUNDARAM K
print ("Chatbot:", random.choice(greetings))
elif user_input in ["how are you?"]:
print ("Chatbot: I'm feeling great! How about you?")
else:
try:
print (f"Chatbot: {eval(user_input, {'__builtins__': None}, allowed_functions)}")
except:
print ("Chatbot: I can only solve math problems! ")
calculator_chatbot()
OUTPUT:
Hello: I am mathbot
You: Hi
Chatbot: Hello! Ask me any math problem!
You:4*8
Chartbot: 32
You: Sqrt(64)
Chatbot: 8.0
You: How are you!
Chatbot: I’m feeling great?How about you?
You: Exit
Chatbot: It was talking to you?Have a fantastic day!??
RESULT:
Thus the python code for chatbot for customer services was executed
successfully.
CSE/NM/NN&DL / 513322104048/SHANMUGASUNDARAM K
EX NO:
MUSIC GENERATION
DATE:
AIM:
To write a python code for music generation.
ALGORITHM:
Step 1: Import the required libraries.
Step 2: then gathering of data from collect dataset.
Step 3: Convert the musical data into suitable format training the rnn.
Step 4: Design and build an rnn model generating mp3 file.
PROGRAM:
! pip install pydub
import numpy as np
from scipy.io.wavfile import write
from pydub import AudioSegment
sample_rate = 44100
duration = 2
freq = 440.0
t = np.linspace(0, duration, int(sample_rate * duration), False)
wave = 0.5 * np.sin(2 * np.pi * freq * t)
wave = (wave * 32767) .astype(np.int16)
wav_filename = "simple_tone.wav"
write (wav_filename, sample_rate, wave)
mp3_filename = "simple_tone.mp3"
sound = AudioSegment.from_wav(wav_filename)
sound.export(mp3_filename, format="mp3")
CSE/NM/NN&DL / 513322104048/SHANMUGASUNDARAM K
print (f"MP3 file saved as '{mp3_filename}'.")
OUTPUT:
MP3 file saves as ‘simple_tone.mp3’
RESULT:
Thus the python code for music generation was executed Successfully.
CSE/NM/NN&DL / 513322104048/SHANMUGASUNDARAM K
CSE/NM/NN&DL / 513322104048/SHANMUGASUNDARAM K
RESULT:
Thus the python code for chatbot for customer services was executed
successfully.
CSE/NM/NN&DL / 513322104048/SHANMUGASUNDARAM K
