Create app.py

app.py

@@ -0,0 +1,43 @@
+import pandas as pd
+import numpy as np
+df = pd.read_csv('NLP/CrimeVsNoCrimeArticles.csv')
+titles = np.array(df['title'].to_list())
+labels = np.array(df['is_crime_report'].to_list())
+import gradio as gr
+import re
+import nltk
+from nltk.corpus import stopwords
+from nltk.tokenize import TreebankWordTokenizer
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense,LSTM,Embedding
+stop_word = set(stopwords.words('english'))
+word_tokenizer = TreebankWordTokenizer()
+def preprocess(text):
+    text = text.lower()
+    text = re.sub(r'[^a-z\s]','',text)
+    tokens = word_tokenizer.tokenize(text)
+    filtered = [word for word in tokens if word not in stop_word]
+    return ' '.join(filtered)
+preprocess_doc = [preprocess(doc) for doc in titles]
+num_tokenizer = Tokenizer(num_words=10000,oov_token='<OOV>')
+num_tokenizer.fit_on_texts(preprocess_doc)
+seq= num_tokenizer.texts_to_sequences(preprocess_doc)
+padded_seq = pad_sequences(seq,maxlen=10,padding='post')
+model = Sequential([
+    Embedding(input_dim=10000,output_dim=16),
+    LSTM(32),
+    Dense(1,activation='sigmoid')
+])
+model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
+model.fit(padded_seq,labels,epochs=50)
+def pre_sentiment(user_input):
+    user = preprocess(user_input)
+    seq_input = num_tokenizer.texts_to_sequences([user])
+    padded_input = pad_sequences(seq_input,maxlen=10,padding='post')
+    prediction  = model.predict(padded_input).item()
+    result = 'CRIMINAL' if prediction>=0.5 else 'NOT CRIMINAL'
+    return(f'{result} - Score: {prediction}')
+demo = gr.Interface(fn=pre_sentiment,inputs='text',outputs='text',title='Sentiment Analyst')
+demo.launch()