Spaces:
Sleeping
Sleeping
File size: 5,091 Bytes
dfe58cd |
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 |
from flask import Flask, render_template, request, url_for
import numpy as np
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.preprocessing.text import Tokenizer
import pickle
import json
import re
app = Flask(__name__, static_folder='static')
cls_biLSTM = load_model("Classification/biLSTM_model.h5")
cls_LSTM = load_model("Classification/LSTM_model.h5")
cls_GRU = load_model("Classification/GRU_model.h5")
gen_biLSTM = load_model("Generation/bilstm_model.h5")
gen_LSTM = load_model("Generation/lstm_model.h5")
gen_GRU = load_model("Generation/gru_model.h5")
# Post-process Texts
def postprocess_text(text):
# Remove leading and trailing whitespace, consecutive spaces, and ensure a space after punctuation marks
text = re.sub(r"\s+", " ", text.strip())
text = re.sub(r"(\w)([.!?])(\w)", r"\1\2 \3", text)
# Capitalize the first letter of the sentence
text = text[0].upper() + text[1:]
# # Add a period at the end if missing
# if not text.endswith("."):
# text += "."
return text
@app.route('/')
def index():
return render_template('index.html')
@app.route('/classifier')
def classifier():
return render_template('classifier.html')
@app.route('/classification', methods=['GET', 'POST'])
def classification():
if request.method == 'POST':
sentence = request.form['sentence']
with open('Classification/data.json', 'r') as file:
data = json.load(file)
max_length = data['max_length']
padding_type = data['padding_type']
trunc_type = data['trunc_type']
threshold = data['threshold']
tokenizer = pickle.load(open('Classification/tokenizer.pkl', 'rb'))
sequences = tokenizer.texts_to_sequences([sentence])
padded = pad_sequences(sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)
biLSTM_pred = cls_biLSTM.predict(padded)
LSTM_pred = cls_LSTM.predict(padded)
GRU_pred = cls_GRU.predict(padded)
biLSTM_label = "Positive" if biLSTM_pred > threshold else "Negative"
LSTM_label = "Positive" if LSTM_pred > threshold else "Negative"
GRU_label = "Positive" if GRU_pred > threshold else "Negative"
biLSTM_pred = "{:.9f}".format(biLSTM_pred[0][0])
LSTM_pred = "{:.9f}".format(LSTM_pred[0][0])
GRU_pred = "{:.9f}".format(GRU_pred[0][0])
return render_template('classification.html', sentence=sentence,
biLSTM_pred=biLSTM_pred, biLSTM_label=biLSTM_label,
LSTM_pred=LSTM_pred, LSTM_label=LSTM_label,
GRU_pred=GRU_pred, GRU_label=GRU_label)
return render_template('classification.html')
@app.route("/generation", methods=['GET', 'POST'])
def generation():
if request.method == 'POST':
sentence = postprocess_text(request.form['sentence'])
next_words = int(request.form['valueradio'])
# Generate text using LSTM
LSTM_Pred = generate_text(sentence, next_words, "lstm")
# Generate text using GRU
GRU_Pred = generate_text(sentence, next_words, "gru")
# Generate text using BiLSTM
BILSTM_Pred = generate_text(sentence, next_words, "bilstm")
return render_template("generation.html", sentence=sentence, next_words=next_words, LSTM_Pred=LSTM_Pred + ".", GRU_Pred=GRU_Pred + ".", BILSTM_Pred=BILSTM_Pred +".", valueradio=next_words)
else:
return render_template("generation.html")
def generate_text(sentence, next_words, model_name):
models = {
"lstm": gen_LSTM,
"gru": gen_GRU,
"bilstm": gen_biLSTM
}
model = models[model_name]
with open('Classification/Reviews.json', 'r') as f:
data = json.load(f)
reviews = [item['Reviews'] for item in data]
tokenizer = Tokenizer()
tokenizer.fit_on_texts(reviews)
total_words = len(tokenizer.word_index) + 1
input_sequences = []
for line in reviews:
token_list = tokenizer.texts_to_sequences([line])[0]
for i in range(1, len(token_list)):
n_gram_sequence = token_list[:i+1]
input_sequences.append(n_gram_sequence)
max_sequence_len = max([len(x) for x in input_sequences])
input_sequences = np.array(pad_sequences(input_sequences, maxlen=max_sequence_len, padding='pre'))
generated_text = sentence
for _ in range(next_words):
token_list = tokenizer.texts_to_sequences([generated_text])[0]
token_list = pad_sequences([token_list], maxlen=max_sequence_len-1, padding='pre')
predicted = np.argmax(model.predict(token_list), axis=1)
output_word = " "
for word, index in tokenizer.word_index.items():
if index == predicted:
output_word = word
break
generated_text += " " + output_word
return generated_text
if __name__ == '__main__':
app.run(debug=True, port=8000) |