File size: 2,121 Bytes
378aae4 | 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 | #!/usr/local/bin/python3.9
import streamlit as st
import datetime
print(datetime.datetime.now(),"Program start.")
#import nltk
#from nltk.corpus import stopwords
import re
#import pandas as pd
#import nltk
import pickle
#import re
#import string
import numpy as np
#import pandas as pd
#from sklearn.preprocessing import LabelEncoder
#from sklearn.model_selection import train_test_split
#from tensorflow.keras.utils import to_categorical
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
#from tensorflow.keras.optimizers import Adam
#from tensorflow.keras.models import Sequential
#from tensorflow.keras.callbacks import EarlyStopping
#from tensorflow.keras.layers import Dense, LSTM, Embedding, Bidirectional
if "model_loaded" not in st.session_state:
with open('model.pkl', 'rb') as f:
clf2 = pickle.load(f)
st.session_state.model_loaded=clf2
else:
clf2=st.session_state.model_loaded
print(datetime.datetime.now(),"Finished import.")
st.text("Hate Speech Detector")
sentence=st.text_input('Sentence to analyze')
labels=['Homophobe', 'Sexist', 'OtherHate', 'NotHate', 'Religion', 'Racist']
# LIB LIB str_punc = string.punctuation.replace(',', '').replace("'",'')
def clean(text):
global str_punc
text = re.sub(r'[^a-zA-Z ]', '', text)
text = text.lower()
return text
tokenizer = Tokenizer()
# LIB LIB le = LabelEncoder()
print(datetime.datetime.now(),"Program. About to load the model.")
print(datetime.datetime.now(),"Program. Finished loading the model.")
if sentence:
print("*************\nSentence:",sentence)
sentence = clean(sentence)
sentence = tokenizer.texts_to_sequences([sentence])
sentence = pad_sequences(sentence, maxlen=256, truncating='pre')
p=clf2.predict(sentence)
print("Prediction:",p)
a=np.argmax(p)
print("ArgMax:",a)
result=labels[a]
#result = le.inverse_transform(np.argmax(clf2.predict(sentence), axis=-1))[0]
proba = np.max(clf2.predict(sentence))
print(f"{result} : {proba}\n\n")
st.text(f"{result}")
print(datetime.datetime.now(),"Program end.")
|