Spaces:

behlil
/

email-spam-classifier

Sleeping

App Files Files Community

behlil commited on 13 days ago

Commit

66df09f

verified ·

1 Parent(s): 84c0919

add files

Browse files

Files changed (7) hide show

__pycache__/utils.cpython-38.pyc +0 -0
app.py +31 -0
models/model.pkl +3 -0
requirements.txt +3 -0
static/style.css +77 -0
templates/index.html +70 -0
utils.py +30 -0

__pycache__/utils.cpython-38.pyc ADDED Viewed

Binary file (760 Bytes). View file

app.py ADDED Viewed

	@@ -0,0 +1,31 @@

+# app.py
+from flask import Flask, render_template, request, jsonify
+from utils import model_predict
+app = Flask(__name__)
+@app.route("/", methods=["GET"])
+def index():
+    """
+    Serve the main HTML page.
+    """
+    return render_template("index.html")
+@app.route("/predict", methods=["POST"])
+def predict():
+    """
+    Handle POST requests for email classification.
+    """
+    data = request.json
+    email_content = data.get("email", "").strip()
+    if not email_content:
+        return jsonify({"error": "Please enter some text to classify."}), 400
+    prediction = model_predict(email_content)
+    result = "SPAM" if prediction == 1 else "NOT SPAM"
+    return jsonify({"result": result})
+if __name__ == "__main__":
+    app.run(debug=True)

models/model.pkl ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e267bcbe204f9d95acebc0f8680e73f1c7d390b54d70162835b811c3691a36e7
+size 1560707

requirements.txt ADDED Viewed

	@@ -0,0 +1,3 @@

+flask==2.3.2
+scikit-learn
+numpy

static/style.css ADDED Viewed

	@@ -0,0 +1,77 @@

+/* General Styling */
+body {
+    font-family: Arial, sans-serif;
+    background-color: #f4f4f9;
+    margin: 0;
+    padding: 0;
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    height: 100vh;
+}
+.container {
+    background-color: #ffffff;
+    border-radius: 10px;
+    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
+    padding: 30px 50px;
+    width: 100%;
+    max-width: 500px;
+    text-align: center;
+}
+h1 {
+    color: #333333;
+    margin-bottom: 20px;
+}
+textarea {
+    width: 100%;
+    height: 150px;
+    padding: 10px;
+    font-size: 16px;
+    border: 1px solid #cccccc;
+    border-radius: 5px;
+    margin-bottom: 20px;
+    resize: none;
+}
+button {
+    background-color: #007bff;
+    color: #ffffff;
+    border: none;
+    padding: 10px 20px;
+    font-size: 16px;
+    border-radius: 5px;
+    cursor: pointer;
+    transition: background-color 0.3s ease;
+}
+button:hover {
+    background-color: #0056b3;
+}
+a.reset-link {
+    margin-left: 10px;
+    color: #007bff;
+    text-decoration: none;
+    font-size: 16px;
+}
+a.reset-link:hover {
+    text-decoration: underline;
+}
+.result {
+    margin-top: 20px;
+    font-size: 18px;
+    font-weight: bold;
+}
+.spam {
+    color: #ff5252; /* Red for spam */
+}
+.not-spam {
+    color: #28a745; /* Green for not spam */
+}

templates/index.html ADDED Viewed

	@@ -0,0 +1,70 @@

+<!-- templates/index.html -->
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Email Spam Classifier</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='style.css') }}">
+</head>
+<body>
+    <div class="container">
+        <h1>Email Spam Classifier</h1>
+        <!-- Form for entering email -->
+        <textarea id="emailInput" rows="6" cols="50" placeholder="Enter email content here..."></textarea>
+        <div>
+            <button id="checkButton">Check</button>
+            <button id="resetButton">Reset</button>
+        </div>
+        <!-- Display error message or prediction -->
+        <p id="outputMessage" class="message"></p>
+    </div>
+    <script>
+        // JavaScript to handle form submission and reset functionality
+        document.getElementById("checkButton").addEventListener("click", async () => {
+            const emailContent = document.getElementById("emailInput").value.trim();
+            const outputMessage = document.getElementById("outputMessage");
+            // Clear previous results
+            outputMessage.textContent = "";
+            if (!emailContent) {
+                outputMessage.textContent = "Please enter some text to classify.";
+                outputMessage.style.color = "red";
+                return;
+            }
+            try {
+                // Send email content to the Flask backend for prediction
+                const response = await fetch("/predict", {
+                    method: "POST",
+                    headers: { "Content-Type": "application/json" },
+                    body: JSON.stringify({ email: emailContent }),
+                });
+                const result = await response.json();
+                if (response.ok) {
+                    outputMessage.textContent = `This email is ${result.result}.`;
+                    outputMessage.style.color = result.result === "SPAM" ? "red" : "green";
+                } else {
+                    outputMessage.textContent = result.error || "An error occurred.";
+                    outputMessage.style.color = "red";
+                }
+            } catch (error) {
+                outputMessage.textContent = "An error occurred while processing your request.";
+                outputMessage.style.color = "red";
+            }
+        });
+        // Reset button functionality
+        document.getElementById("resetButton").addEventListener("click", () => {
+            document.getElementById("emailInput").value = "";
+            document.getElementById("outputMessage").textContent = "";
+        });
+    </script>
+</body>
+</html>

utils.py ADDED Viewed

	@@ -0,0 +1,30 @@

+# utils.py (Helper Functions)
+import pickle
+import numpy as np
+def load_model():
+    """
+    Loads the trained model from file.
+    """
+    with open("models/model.pkl", "rb") as file:
+        model = pickle.load(file)  # Use pickle to load the model
+    return model
+def model_predict(email):
+    """
+    Predicts using the loaded model.
+    """
+    model = load_model()  # Load the model before predicting
+    prediction = model.predict([email])  # Use the predict method to make predictions
+    # If the email is spam, prediction should be 1, otherwise 0
+    # Convert the prediction to 1 or -1 as specified
+    prediction = 1 if prediction[0] == 1 else -1
+    return prediction
+with open("models/model.pkl", "rb") as file:
+    model = pickle.load(file)
+print("Model loaded successfully!")