Update app.py

app.py

@@ -5,13 +5,41 @@ import streamlit.components.v1 as components
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.model_selection import train_test_split
 import pandas as pd
+import nltk
+import re
+nltk.download('stopwords')
+stemmer = nltk.SnowballStemmer("english")
+from nltk.corpus import stopwords
+import string
+stopword=set(stopwords.words('english'))
 # Separate target and feature column in X and y variable
 df = pd.read_csv('stress.csv')
 # X will be the features
+def clean(text):
+    text = str(text).lower()
+    text = re.sub('\[.*?\]', '', text)
+    text = re.sub('https?://\S+|www\.\S+', '', text)
+    text = re.sub('<.*?>+', '', text)
+    text = re.sub('[%s]' % re.escape(string.punctuation), '', text)
+    text = re.sub('\n', '', text)
+    text = re.sub('\w*\d\w*', '', text)
+    text = [word for word in text.split(' ') if word not in stopword]
+    text=" ".join(text)
+    text = [stemmer.stem(word) for word in text.split(' ')]
+    text=" ".join(text)
+    return text
+
+
+df["text"] = df["text"].apply(clean)
 X = np.array(df["text"])
 
 # y will be the target variable
 y = np.array(df["label"])
+
+
+
+df["text"] = df["text"].apply(clean)
+
 cv = CountVectorizer()
 # Load the pickled model
 
@@ -40,7 +68,7 @@ def app_design():
     features = text # add features according to notebook
     
     # Make a prediction when the user clicks the "Predict" button
-    if st.button('Predict Sarcasm'):  
+    if st.button('Predict Stress'):  
         predicted_value = model_prediction(features)
         if predicted_value == "['Stress']":
             st.success("Your message contains Stress")