Create app.py

app.py

@@ -0,0 +1,85 @@
+import os
+os.system('pip install nltk')
+os.system('pip install sklearn')
+
+import nltk
+
+nltk.download('punkt')
+nltk.download('stopwords')
+nltk.download('wordnet')
+nltk.download('omw-1.4')
+
+# importing relevant python packages
+import streamlit as st
+import pandas as pd
+import numpy as np
+import pickle
+import joblib
+from PIL import Image
+# preprocessing
+import re
+import string
+import nltk
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer 
+from sklearn.feature_extraction.text import TfidfVectorizer
+# modeling
+from sklearn import svm
+# sentiment analysis
+
+
+# creating page sections
+site_header = st.container()
+business_context = st.container()
+data_desc = st.container()
+performance = st.container()
+tweet_input = st.container()
+model_results = st.container()
+sentiment_analysis = st.container()
+contact = st.container()
+
+with site_header:
+    st.title('Toxic Comment Detection')
+   
+
+with tweet_input:
+    st.header('Is Your Tweet Considered Hate Speech?')
+    st.write("""*Please note that this prediction is based on how the model was trained, so it may not be an accurate representation.*""")
+    # user input here
+    user_text = st.text_input('Enter Tweet', max_chars=280) # setting input as user_text
+
+with model_results:    
+    st.subheader('Prediction:')
+    if user_text:
+    # processing user_text
+        # removing punctuation
+        user_text = re.sub('[%s]' % re.escape(string.punctuation), '', user_text)
+        # tokenizing
+        stop_words = set(stopwords.words('english'))
+        tokens = nltk.word_tokenize(user_text)
+        # removing stop words
+        stopwords_removed = [token.lower() for token in tokens if token.lower() not in stop_words]
+        # taking root word
+        lemmatizer = WordNetLemmatizer() 
+        lemmatized_output = []
+        for word in stopwords_removed:
+            lemmatized_output.append(lemmatizer.lemmatize(word))
+
+        # instantiating count vectorizor
+        tfidf = TfidfVectorizer(stop_words=stop_words)
+        X_train = joblib.load(open('X_train.pickle', 'rb'))
+        X_test = lemmatized_output
+        X_train_count = tfidf.fit_transform(X_train)
+        X_test_count = tfidf.transform(X_test)
+
+        # loading in model
+        final_model = joblib.load(open('final_bayes.pickle', 'rb'))
+
+        # apply model to make predictions
+        prediction = final_model.predict(X_test_count[0])
+
+        if prediction == 0:
+            st.subheader('**Not Hate Speech**')
+        else:
+            st.subheader('**Hate Speech**')
+        st.text('')