Spaces:
Runtime error
Runtime error
File size: 3,167 Bytes
e03530d 071cb1b f4db971 afb9463 3ea613d 19ded2a afb9463 f4db971 3ea613d f4db971 3ea613d dc1bf57 86f79dd dc2ae70 86f79dd 071cb1b 115ff0b 360bf8a 071cb1b 360bf8a 86f79dd 3ea613d 071cb1b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
import streamlit as st
import pandas as pd
import twint
import nest_asyncio
import multiprocessing.pool
import functools
from transformers import AutoModelForSequenceClassification
from transformers import TFAutoModelForSequenceClassification
from transformers import AutoTokenizer
import numpy as np
from scipy.special import softmax
import csv
import urllib.request
import IPython.display as ipd
# Preprocess text (username and link placeholders)
def preprocess(text):
new_text = []
for t in text.split(" "):
t = '@user' if t.startswith('@') and len(t) > 1 else t
t = 'http' if t.startswith('http') else t
new_text.append(t)
return " ".join(new_text)
# Loading pretrained model
MODEL = 'cardiffnlp/twitter-roberta-base-sentiment'
tokenizer = AutoTokenizer.from_pretrained(MODEL)
model = AutoModelForSequenceClassification.from_pretrained(MODEL)
model.save_pretrained(MODEL)
# Func to get a score using the above model
def combined_score(text):
text = preprocess(text)
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
scores = output[0][0].detach().numpy()
scores = softmax(scores)
return -scores[0] + scores[2] # scores = [negative, neutral, positive]
# https://stackoverflow.com/questions/492519/timeout-on-a-function-call
def timeout(max_timeout):
"""Timeout decorator, parameter in seconds."""
def timeout_decorator(item):
"""Wrap the original function."""
@functools.wraps(item)
def func_wrapper(*args, **kwargs):
"""Closure for function."""
pool = multiprocessing.pool.ThreadPool(processes=1)
async_result = pool.apply_async(item, args, kwargs)
# raises a TimeoutError if execution exceeds max_timeout
return async_result.get(max_timeout)
return func_wrapper
return timeout_decorator
# Getting tweets from a user
@timeout(120.0)
def get_tweets(username, limit=500, save_name=None):
#nest_asyncio.apply() # Helps avoid RuntimeError: This event loop is already running
# Setup config
c = twint.Config() # Create a config object to store our settings
c.Limit = limit # Max number of tweets to fetch (increments of 20)
c.Username = username # User of interest
c.Pandas = True # Store tweets in a dataframe
c.Hide_output = True # Avoid printing out tweets
# Run the seearch
twint.run.Search(c)
# Get the results and optionally save to a file as well
df = twint.storage.panda.Tweets_df
if save_name != None:
df.to_csv(save_name)
return df
st.title('Test')
with st.form("my_form"):
st.write("Inside the form")
user = st.text_input("Twitter Username")
n_tweets = st.slider('How Many Tweets', 20, 2000, 20)
# Every form must have a submit button.
submitted = st.form_submit_button("Submit")
if submitted:
st.write("Fetching user", user, "n_tweets", n_tweets)
tweets = get_tweets(user, limit=n_tweets)
st.write(st.dataframe(tweets.head()))
tweets['sentiment'] = tweets['tweet'].map(lambda s: combined_score(s))
st.write(st.dataframe(tweets[['tweet', 'sentiment']].head()))
st.write("Outside the form") |