File size: 3,570 Bytes
f4e514f 2f6e3a1 1e322be b0d355a b3e4112 1409c20 57410b1 1e322be 57410b1 8bdae34 |
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 |
import streamlit as st
import os
import tensorflow as tf
from transformers import AutoTokenizer, TFBertModel
from tensorflow.keras.layers import Input, Dense
import numpy as np
import re
import emoji
import nltk
from nltk.corpus import stopwords
from nltk.stem.wordnet import WordNetLemmatizer
nltk.download('stopwords')
nltk.download('wordnet')
lmtzr = WordNetLemmatizer()
stop_words = stopwords.words("english")
max_len = 35
def clean_text(text):
# Put text into lower case
text = text.lower()
# Remove URLs
text = re.sub(r'https?:\/\/.*[\r\n]*', '', text)
# Remove Hashtags
text = re.sub(r"#", "", text)
# Remove Mentions
text = re.sub(r"@\S+", "", text)
# Handling Emojis/Emoticons
text = emoji.demojize(text)
emoticons = dict()
emoticons['EMOT_SMILEY'] = [':-)', ':)', '(:', '(-:', ';p', ':-d', ':d', ]
emoticons['EMOT_LAUGH'] = [':-D', ':D', 'X-D', 'XD', 'xD']
emoticons['EMOT_LOVE'] = ['<3', ':\*', ]
emoticons['EMOT_CRY'] = [':,(', ':\'(', ':"(', ':((']
emoticons['EMOT_WINK'] = [';-)', ';)', ';-D', ';D', '(;', '(-;']
emoticons['EMOT_FROWN'] = [':-(', ':(']
for label, emot in emoticons.items():
for word in text.split():
if word in emot:
text = text.replace(word, label)
# Lemmatazation
text = ' '.join([lmtzr.lemmatize(word, 'v') for word in text.split()])
return text
st.title('Welcome to my twitter airline sentiment analysis !', anchor='center')
airline_tweet = st.text_input('Enter your english airline tweet here, press the prediction button and wait for the model to predict the sentiment of your review:', '@AmericanAirline My flight was awful, the flight was late and you lost my luggage!')
tokenizer = AutoTokenizer.from_pretrained('distilbert-base-uncased', num_labels=2)
encoded_input = tokenizer(
text=airline_tweet,
add_special_tokens=True,
max_length=max_len,
truncation=True,
padding='max_length',
return_tensors='tf',
return_token_type_ids=False,
return_attention_mask=True,
verbose=False)
bert = TFBertModel.from_pretrained('distilbert-base-uncased', num_labels=2)
input_ids = Input(shape=(max_len,), dtype=tf.int32, name='input_ids')
input_mask = Input(shape=(max_len,), dtype=tf.int32, name='attention_mask')
bert_inputs = {'input_ids': input_ids, 'input_mask': input_mask}
embeddings = bert.bert(input_ids, attention_mask=input_mask)[0] #Here 0 is the last hidden states
out = tf.keras.layers.GlobalMaxPool1D()(embeddings)
out = Dense(512, activation='relu')(out)
out = tf.keras.layers.Dropout(0.1)(out)
# out = Dense(512, activation='relu')(out)
# Last layer
y = Dense(2, activation = 'softmax')(out) #Here 2 because we got 2 categories to predict and softmax because we want probabilities
# y = Dense(1, activation = 'sigmoid')(out)
model = tf.keras.Model(inputs=bert_inputs, outputs=y)
model.load_weights('sentiment_weights.h5')
if st.button('Predict sentiment'):
prediction = model.predict({'input_ids': encoded_input['input_ids'], 'input_mask': encoded_input['attention_mask']})
encoded_dict = {0: 'negative', 1: 'positive'}
if np.argmax(prediction) == 0:
st.write(f'Sentiment predicted : {encoded_dict[np.argmax(prediction)]}')
st.write(f'I\'m sorry you had a bad experience with our company :( , please accept our apologies')
else:
st.write(f'Sentiment predicted : {encoded_dict[np.argmax(prediction)]}')
st.write('Glad your flight was good ! Hope to see you soon :)')
|