Spaces:
Runtime error
Runtime error
File size: 5,137 Bytes
64f1623 0cf6beb 53df561 0cf6beb 53df561 0cf6beb 53df561 |
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 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 |
# utilities
import re
import pickle
import numpy as np
import pandas as pd
# plotting
import seaborn as sns
from wordcloud import WordCloud
import matplotlib.pyplot as plt
# nltk
from nltk.stem import WordNetLemmatizer
# sklearn
from sklearn.svm import LinearSVC
from sklearn.naive_bayes import BernoulliNB
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics import confusion_matrix, classification_report
from datasets import load_dataset
dataset = load_dataset('Twitter_Emoticon_Analysis_NLP/training.1600000.processed.noemoticon.csv')
DATASET_COLUMNS = ["sentiment", "ids", "date", "flag", "user", "text"]
DATASET_ENCODING = "ISO-8859-1"
dataset = pd.read_csv('training.1600000.processed.noemoticon.csv',
encoding=DATASET_ENCODING , names=DATASET_COLUMNS)
# Removing the unnecessary columns.
dataset = dataset[['sentiment','text']]
# Replacing the values to ease understanding.
dataset['sentiment'] = dataset['sentiment'].replace(4,1)
# Storing data in lists.
text, sentiment = list(dataset['text']), list(dataset['sentiment'])
def preprocess(textdata):
processedText = []
# Create Lemmatizer and Stemmer.
wordLemm = WordNetLemmatizer()
# Defining regex patterns.
urlPattern = r"((http://)[^ ]*|(https://)[^ ]*|( www\.)[^ ]*)"
userPattern = '@[^\s]+'
alphaPattern = "[^a-zA-Z0-9]"
sequencePattern = r"(.)\1\1+"
seqReplacePattern = r"\1\1"
for tweet in textdata:
tweet = tweet.lower()
# Replace all URls with 'URL'
tweet = re.sub(urlPattern,' URL',tweet)
# Replace all emojis.
for emoji in emojis.keys():
tweet = tweet.replace(emoji, "EMOJI" + emojis[emoji])
# Replace @USERNAME to 'USER'.
tweet = re.sub(userPattern,' USER', tweet)
# Replace all non alphabets.
tweet = re.sub(alphaPattern, " ", tweet)
# Replace 3 or more consecutive letters by 2 letter.
tweet = re.sub(sequencePattern, seqReplacePattern, tweet)
tweetwords = ''
for word in tweet.split():
# Checking if the word is a stopword.
#if word not in stopwordlist:
if len(word)>1:
# Lemmatizing the word.
word = wordLemm.lemmatize(word)
tweetwords += (word+' ')
processedText.append(tweetwords)
return processedText
def preprocess(textdata):
processedText = []
# Create Lemmatizer and Stemmer.
wordLemm = WordNetLemmatizer()
# Defining regex patterns.
urlPattern = r"((http://)[^ ]*|(https://)[^ ]*|( www\.)[^ ]*)"
userPattern = '@[^\s]+'
alphaPattern = "[^a-zA-Z0-9]"
sequencePattern = r"(.)\1\1+"
seqReplacePattern = r"\1\1"
for tweet in textdata:
tweet = tweet.lower()
# Replace all URls with 'URL'
tweet = re.sub(urlPattern,' URL',tweet)
# Replace all emojis.
for emoji in emojis.keys():
tweet = tweet.replace(emoji, "EMOJI" + emojis[emoji])
# Replace @USERNAME to 'USER'.
tweet = re.sub(userPattern,' USER', tweet)
# Replace all non alphabets.
tweet = re.sub(alphaPattern, " ", tweet)
# Replace 3 or more consecutive letters by 2 letter.
tweet = re.sub(sequencePattern, seqReplacePattern, tweet)
tweetwords = ''
for word in tweet.split():
# Checking if the word is a stopword.
#if word not in stopwordlist:
if len(word)>1:
# Lemmatizing the word.
word = wordLemm.lemmatize(word)
tweetwords += (word+' ')
processedText.append(tweetwords)
return processedText
import gradio as gr
import nltk
from nltk.sentiment.vader import SentimentIntensityAnalyzer
# Download required NLTK resources
nltk.download('vader_lexicon')
# Load the pre-trained sentiment intensity analyzer
sia = SentimentIntensityAnalyzer()
def get_sentiment(tweet):
# Preprocess the tweet
processed_tweet = preprocess([tweet])
# Get the sentiment score using VADER sentiment analyzer
sentiment_score = sia.polarity_scores(processed_tweet[0])
# Determine the sentiment label based on the compound score
compound_score = sentiment_score['compound']
if compound_score >= 0.05:
sentiment = 'Positive'
elif compound_score <= -0.05:
sentiment = 'Negative'
else:
sentiment = 'Neutral'
return sentiment
# Create a Gradio interface
iface = gr.Interface(
fn=get_sentiment,
inputs='text',
outputs='text',
title='Tweet Sentiment Analyzer',
description='Enter a tweet with text or emoticon or both, and get the sentiment prediction.',
examples=[['I love this movie!', 'This weather is terrible.']],
theme='Soft'
)
# Launch the interface
iface.launch(share = True) |