Update README.md

README.md

@@ -1,2 +1,91 @@
+---
+license: bsd-3-clause
+datasets:
+- Kingsman2125/Spam-MailClassification-Dataset
+language:
+- en
+metrics:
+- accuracy
+- precision
+pipeline_tag: text-classification
+tags:
+- spamClassification
+---
 # email-spam-classifier-new
 End to end code for the email spam classifier project
+-----------------------------------------------------
+<!-- TABLE OF CONTENTS -->
+<details>
+  <summary>Table of Contents</summary>
+  <ol>
+    <li>
+      <a href="#Quickstart">Quickstart</a>
+    </li>
+  </ol>
+</details>
+
+<!-- Quickstar -->
+## Quickstart
+```py
+import streamlit as st
+import pickle
+import string
+import pickle
+from nltk.corpus import stopwords
+import nltk
+from nltk.stem.porter import PorterStemmer
+nltk.download('stopwords')   # Downloading stopwords data
+nltk.download('punkt')       # Downloading tokenizer data
+
+ps = PorterStemmer()
+
+
+def transform_text(text):
+    text = text.lower()
+    text = nltk.word_tokenize(text)
+
+    y = []
+    for i in text:
+        if i.isalnum():
+            y.append(i)
+
+    text = y[:]
+    y.clear()
+
+    for i in text:
+        if i not in stopwords.words('english') and i not in string.punctuation:
+            y.append(i)
+
+    text = y[:]
+    y.clear()
+
+    for i in text:
+        y.append(ps.stem(i))
+
+    return " ".join(y)
+
+tfidf = pickle.load(open('vectorizer.pkl','rb'))
+model = pickle.load(open('model.pkl','rb'))
+
+st.title("Email/SMS Spam Classifier")
+
+input_sms = st.text_area("Enter the message")
+
+if st.button('Predict'):
+
+    # 1. preprocess
+    transformed_sms = transform_text(input_sms)
+    # 2. vectorize
+    vector_input = tfidf.transform([transformed_sms])
+    # 3. predict
+    result = model.predict(vector_input)[0]
+    # 4. Display
+    if result == 1:
+        st.header("Spam")
+    else:
+        st.header("Not Spam")
+
+```
+
+<p align="right">(<a href="#readme-top">back to top</a>)</p>
+