Upload 14 files

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+static/spam.webp filter=lfs diff=lfs merge=lfs -text

Procfile

@@ -0,0 +1 @@
+web: gunicorn app:app

README.md

@@ -1,10 +1,10 @@
----
-title: Spam Message Predictor
-emoji: 🐢
-colorFrom: purple
-colorTo: blue
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Spam SMS Classification - Deployment
+![Kaggle](https://img.shields.io/badge/Dataset-Kaggle-blue.svg) ![Python 3.6](https://img.shields.io/badge/Python-3.6-brightgreen.svg) ![NLTK](https://img.shields.io/badge/Library-NLTK-orange.svg)
+
+• This repository consists of files required to deploy a ___Machine Learning Web App___ created with ___Flask___ on ___Heroku___ platform.
+
+• If you want to view the deployed model, click on the following link:<br />
+Deployed at: https://spam-message-predictor21.herokuapp.com/
+
+
+• Please do ⭐ the repository, if it helped you in anyway.

Spam SMS Classifier - Deployment.py

@@ -0,0 +1,66 @@
+# Importing essential libraries
+import pandas as pd
+import pickle
+
+# Loading the dataset
+df = pd.read_csv('Spam SMS Collection', sep='\t', names=['label', 'message'])
+
+# Importing essential libraries for performing Natural Language Processing on 'SMS Spam Collection' dataset
+import nltk
+import re
+nltk.download('stopwords')
+from nltk.corpus import stopwords
+from nltk.stem.porter import PorterStemmer
+
+# Cleaning the messages
+corpus = []
+ps = PorterStemmer()
+
+for i in range(0,df.shape[0]):
+
+  # Cleaning special character from the message
+  message = re.sub(pattern='[^a-zA-Z]', repl=' ', string=df.message[i])
+
+  # Converting the entire message into lower case
+  message = message.lower()
+
+  # Tokenizing the review by words
+  words = message.split()
+
+  # Removing the stop words
+  words = [word for word in words if word not in set(stopwords.words('english'))]
+
+  # Stemming the words
+  words = [ps.stem(word) for word in words]
+
+  # Joining the stemmed words
+  message = ' '.join(words)
+
+  # Building a corpus of messages
+  corpus.append(message)
+  
+# Creating the Bag of Words model
+from sklearn.feature_extraction.text import CountVectorizer
+cv = CountVectorizer(max_features=2500)
+X = cv.fit_transform(corpus).toarray()
+
+# Extracting dependent variable from the dataset
+y = pd.get_dummies(df['label'])
+y = y.iloc[:, 1].values
+
+# Creating a pickle file for the CountVectorizer
+pickle.dump(cv, open('cv-transform.pkl', 'wb'))
+
+# Model Building
+
+from sklearn.model_selection import train_test_split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=0)
+
+# Fitting Naive Bayes to the Training set
+from sklearn.naive_bayes import MultinomialNB
+classifier = MultinomialNB(alpha=0.3)
+classifier.fit(X_train, y_train)
+
+# Creating a pickle file for the Multinomial Naive Bayes model
+filename = 'spam-sms-mnb-model.pkl'
+pickle.dump(classifier, open(filename, 'wb'))

app.py

@@ -0,0 +1,25 @@
+# Importing essential libraries
+from flask import Flask, render_template, request
+import pickle
+
+# Load the Multinomial Naive Bayes model and CountVectorizer object from disk
+filename = 'spam-sms-mnb-model.pkl'
+classifier = pickle.load(open(filename, 'rb'))
+cv = pickle.load(open('cv-transform.pkl','rb'))
+app = Flask(__name__)
+
+@app.route('/')
+def home():
+	return render_template('home.html')
+
+@app.route('/predict',methods=['POST'])
+def predict():
+    if request.method == 'POST':
+    	message = request.form['message']
+    	data = [message]
+    	vect = cv.transform(data).toarray()
+    	my_prediction = classifier.predict(vect)
+    	return render_template('result.html', prediction=my_prediction)
+
+if __name__ == '__main__':
+	app.run(debug=True)

cv-transform.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6850efa9440ff2b4cc6346f16adb34412101d83be2129c9ea7ce159f0487341e
+size 179663

requirements.txt

@@ -0,0 +1,11 @@
+Flask==1.1.1
+gunicorn==19.9.0
+itsdangerous==1.1.0
+Jinja2==2.10.1
+MarkupSafe==1.1.1
+Werkzeug==0.15.5
+numpy>=1.9.2
+scipy>=0.15.1
+scikit-learn>=0.18
+matplotlib>=1.4.3
+pandas>=0.19

spam-sms-mnb-model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6cc509111cefe1d973976508cb26039511b2d8a4b7d7832a407cd3333dfe342
+size 80636

static/styles.css

@@ -0,0 +1,126 @@
+html{
+	height: 100%;
+	margin: 0;
+}
+
+body{
+	font-family: Arial, Helvetica,sans-serif;
+    text-align: center;
+    margin: 0;
+    padding: 0;
+    width: 100%;
+	height: 100%;
+	display: flex;
+  	flex-direction: column;
+}
+
+/* Website Title */
+.container{
+	padding: 30px;
+	position: relative;
+	background: linear-gradient(45deg, #ffffff, #ffffff, #f9f9f9, #eeeeee, #e0e4e1, #d7e1ec);
+	background-size: 500% 500%;
+	animation: change-gradient 10s ease-in-out infinite;
+}
+@keyframes change-gradient {
+	0%{
+		background-position: 0 50%;
+	}
+	50%{
+		background-position: 100% 50%;
+	}
+	100%{
+		background-position: 0 50%;
+	}
+}
+
+.container-heading{
+    margin: 0;
+}
+
+.container span{
+    color: #ff0000;
+}
+
+.description p{
+    font-style: italic;
+    font-size: 14px;
+    margin: 3px 0 0;
+}
+
+/* Text Area */
+.ml-container{
+    margin: 30px 0;
+	flex: 1 0 auto;
+}
+
+.message-box{
+    margin-bottom: 20px;
+}
+
+/* Predict Button */
+.my-cta-button{
+    background: #f9f9f9;
+    border: 2px solid #000000;
+    border-radius: 1000px;
+    box-shadow: 3px 3px #8c8c8c;
+    padding: 10px 36px;
+    color: #000000;
+    display: inline-block;
+    font: italic bold 20px/1 "Calibri", sans-serif;
+    text-align: center;
+}
+
+.my-cta-button:hover{
+    color: #ff0000;
+    border: 2px solid #ff0000;
+}
+
+.my-cta-button:active{
+    box-shadow: 0 0;
+}
+
+
+/* Footer */
+.footer{
+    font-size: 14px;
+	padding: 20px;
+	flex-shrink: 0;
+	position: relative;
+	background: linear-gradient(45deg, #ffffff, #ffffff, #f9f9f9, #eeeeee, #e0e4e1, #d7e1ec);
+	background-size: 500% 500%;
+	animation: change-gradient 10s ease-in-out infinite;
+}
+
+.contact-icon{
+	color: #000000;
+	padding: 7px;
+}
+
+
+.contact-icon:hover{
+	color: #8c8c8c;
+}
+
+.footer-description{
+	margin: 0;
+	font-size: 12px;
+}
+
+/* Result */
+.results{
+    padding: 30px 0 0;
+	flex: 1 0 auto;
+}
+
+.danger{
+    color: #ff0000;
+}
+
+.safe{
+    color: green;
+}
+
+.gif{
+	width: 30%;
+}

templates/home.html

@@ -0,0 +1,40 @@
+<!DOCTYPE html>
+
+<html lang="en" dir="ltr">
+    <head>
+        <meta charset="utf-8">
+        <title>Spam message predictor</title>
+        <link rel="shortcut icon" href="{{ url_for('static', filename='spam-favicon.ico') }}">
+        <link rel="stylesheet" type="text/css" href="{{ url_for('static', filename='styles.css') }}">
+        <script src="https://kit.fontawesome.com/5f3f547070.js" crossorigin="anonymous"></script>
+    </head>
+
+    <body>
+
+        <!-- Website Title -->
+    	<div class="container">
+    		<h2 class='container-heading'><span>Spam Detector</span> for Short Message Service (SMS)</h2>
+            <div class='description'>
+    			<p>A Machine Learning Web App, Built with Flask, Deployed using Heroku.</p>
+    		</div>
+    	</div>
+
+        <!-- Text Area -->
+    	<div class="ml-container">
+    		<form action="{{ url_for('predict') }}" method="POST">
+        		<textarea class='message-box' name="message" rows="15" cols="75" placeholder="Enter Your Message Here..."></textarea><br/>
+        		<input type="submit" class="my-cta-button" value="Predict">
+        	</form>
+    	</div>
+
+        <!-- Footer -->
+        <div class='footer'>
+            <div class="contact">
+                <a target="_blank" href="https://github.com/ArchitSharma21/Spam-message-predictor"><i class="fab fa-github fa-lg contact-icon"></i></a>
+                <a target="_blank" href="https://www.linkedin.com/in/thearchitsharma/"><i class="fab fa-linkedin fa-lg contact-icon"></i></a>
+            </div>
+            <p class='footer-description'>Made with ❤️ by Archit Sharma.</p>
+        </div>
+
+    </body>
+</html>

templates/result.html

@@ -0,0 +1,43 @@
+<!DOCTYPE html>
+
+<html lang="en" dir="ltr">
+	<head>
+		<meta charset="utf-8">
+		<title>Spam message predictor</title>
+		<link rel="shortcut icon" href="{{ url_for('static', filename='spam-favicon.ico') }}">
+		<link rel="stylesheet" type="text/css" href="{{ url_for('static', filename='styles.css') }}">
+		<script src="https://kit.fontawesome.com/5f3f547070.js" crossorigin="anonymous"></script>
+	</head>
+
+	<body>
+
+		<!-- Website Title -->
+		<div class="container">
+			<h2 class='container-heading'><span>Spam Detector</span> for Short Message Service (SMS)</h2>
+	        	<div class='description'>
+				<p>A Machine Learning Web App, Built with Flask, Deployed using Heroku.</p>
+			</div>
+		</div>
+
+		<!-- Result -->
+		<div class="results">
+			{% if prediction==1 %}
+				<h1>Prediction: <span class='danger'>Gotcha! This is a SPAM message.</span></h1>
+				<img class="gif" src="{{ url_for('static', filename='spam.webp') }}" alt="SPAM Image">
+			{% elif prediction==0 %}
+				<h1>Prediction: <span class='safe'>Great! This is NOT a spam message.</span></h1>
+				<img class="gif" src="{{ url_for('static', filename='not-spam.webp') }}" alt="Not a spam image">
+			{% endif %}
+		</div>
+
+		<!-- Footer -->
+        <div class='footer'>
+            <div class="contact">
+                <a target="_blank" href="https://github.com/ArchitSharma21/Spam-message-predictor"><i class="fab fa-github fa-lg contact-icon"></i></a>
+                <a target="_blank" href="https://www.linkedin.com/in/thearchitsharma/"><i class="fab fa-linkedin fa-lg contact-icon"></i></a>
+            </div>
+            <p class='footer-description'>Made with ❤️ by Archit Sharma.</p>
+        </div>
+
+	</body>
+</html>