Uploading necessary files

app.py

@@ -0,0 +1,41 @@
+# import necessary libraries
+import joblib
+import numpy as np
+from flask import Flask, render_template, request, jsonify
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.linear_model import LogisticRegression
+from pre_processing import preprocess_text
+
+app = Flask(__name__)
+
+# specify path for model and vectorizer
+model_path = "log_model_final.pkl"
+vectorizer_path = "vectorizer.pkl"
+
+# Load the pre-trained model
+model = joblib.load(model_path)
+vectorizer = joblib.load(vectorizer_path)
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    # predict
+    try:
+        # Get input text from the form
+        input_text = request.get_json(force=True)['input']
+        print(input_text)
+        test_data =  vectorizer.transform([input_text])
+        y_pred = model.predict(test_data)
+        print(y_pred)
+                # Return the prediction as JSON
+        return jsonify({'prediction': y_pred[0]})
+    
+    except Exception as e:
+        return jsonify({'error': str(e)})
+    
+    
+if __name__ == '__main__':
+    app.run(port=5000, debug=True)

log_model_final.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba33944b346a7546c899dd218b63a6703c0f5f1e7be0e1fc52d0d24b776d7ae9
+size 1093696

pre_processing.py

@@ -0,0 +1,60 @@
+# import necessary libraries
+
+
+import numpy as np
+import re
+import string
+
+# create a function for basic pre-processing
+
+stopwords= set(['br', 'the', 'i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', "you're", "you've",\
+            "you'll", "you'd", 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', \
+            'she', "she's", 'her', 'hers', 'herself', 'it', "it's", 'its', 'itself', 'they', 'them', 'their',\
+            'theirs', 'themselves', 'what', 'which', 'who', 'whom', 'this', 'that', "that'll", 'these', 'those', \
+            'am', 'is', 'are', 'was', 'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do', 'does', \
+            'did', 'doing', 'a', 'an', 'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while', 'of', \
+            'at', 'by', 'for', 'with', 'about', 'against', 'between', 'into', 'through', 'during', 'before', 'after',\
+            'above', 'below', 'to', 'from', 'up', 'down', 'in', 'out', 'on', 'off', 'over', 'under', 'again', 'further',\
+            'then', 'once', 'here', 'there', 'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each', 'few', 'more',\
+            'most', 'other', 'some', 'such', 'only', 'own', 'same', 'so', 'than', 'too', 'very', \
+            's', 't', 'can', 'will', 'just', 'don', "don't", 'should', "should've", 'now', 'd', 'll', 'm', 'o', 're', \
+            've', 'y', 'ain', 'aren', "aren't", 'couldn', "couldn't", 'didn', "didn't", 'doesn', "doesn't", 'hadn',\
+            "hadn't", 'hasn', "hasn't", 'haven', "haven't", 'isn', "isn't", 'ma', 'mightn', "mightn't", 'mustn',\
+            "mustn't", 'needn', "needn't", 'shan', "shan't", 'shouldn', "shouldn't", 'wasn', "wasn't", 'weren', "weren't", \
+            'won', "won't", 'wouldn', "wouldn't"])
+
+def decontracted(phrase):
+    # specific
+    phrase = re.sub(r"won't", "will not", phrase)
+    phrase = re.sub(r"can\'t", "can not", phrase)
+
+    # general
+    phrase = re.sub(r"n\'t", " not", phrase)
+    phrase = re.sub(r"\'re", " are", phrase)
+    phrase = re.sub(r"\'s", " is", phrase)
+    phrase = re.sub(r"\'d", " would", phrase)
+    phrase = re.sub(r"\'ll", " will", phrase)
+    phrase = re.sub(r"\'t", " not", phrase)
+    phrase = re.sub(r"\'ve", " have", phrase)
+    phrase = re.sub(r"\'m", " am", phrase)
+    return phrase
+
+
+def preprocess_text(text):
+    text = text.lower()
+    text = re.sub(r"\n", " ", text)
+    text = re.sub(r"\d", " ", text)
+    text = re.sub(r"<.*?>+", "", text)
+    text = re.sub("\[.*?\]", "", text)
+    text = re.sub("https?://S+|www.\.\S+", "", text)
+    text = text.translate(str.maketrans("", "", string.punctuation))
+    text = re.sub(r'xx', '', text)
+    text = decontracted(text)
+    words = text.split()
+    words = [word for word in words if not word in stopwords]
+    words = [re.sub(r"(.)\1{1,}", r"\1\1", word) for word in words]
+    words = [word.strip() for word in words if len(word.strip()) > 1]
+    text = " ".join(words)
+    return text
+    
+    

templates/index.html

@@ -0,0 +1,92 @@
+<!-- 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>Logistic Regression Predictor</title>
+    <style>
+        body {
+            font-family: 'Arial', sans-serif;
+            margin: 20px;
+            text-align: center;
+        }
+
+        h1 {
+            color: #333;
+        }
+
+        form {
+            margin-top: 20px;
+            display: flex;
+            flex-direction: column;
+            align-items: center;
+        }
+
+        label {
+            margin-bottom: 10px;
+        }
+
+        input {
+            padding: 8px;
+            margin-bottom: 10px;
+            width: 300px;
+            box-sizing: border-box;
+        }
+
+        button {
+            padding: 10px;
+            background-color: #4CAF50;
+            color: white;
+            border: none;
+            cursor: pointer;
+            font-size: 16px;
+        }
+
+        button:hover {
+            background-color: #45a049;
+        }
+
+        #predictionResult {
+            margin-top: 20px;
+            font-size: 18px;
+        }
+    </style>
+</head>
+<body>
+    <h1>Logistic Regression Predictor</h1>
+    
+    <form id="predictionForm">
+        <label for="inputText">Input Text:</label>
+        <input type="text" id="inputText" name="inputText" required>
+        <button type="button" onclick="predict()">Submit</button>
+    </form>
+
+    <p id="predictionResult"></p>
+
+    <script>
+        function predict() {
+            var inputText = document.getElementById('inputText').value;
+
+            // Make a POST request to the Flask API
+            fetch('/predict', {
+                method: 'POST',
+                headers: {
+                    'Content-Type': 'application/json',
+                },
+                body: JSON.stringify({
+                    'input': inputText,
+                }),
+            })
+            .then(response => response.json())
+            .then(data => {
+                document.getElementById('predictionResult').innerText = 'Prediction: ' + data.prediction;
+            })
+            .catch(error => {
+                console.error('Error:', error);
+                document.getElementById('predictionResult').innerText = 'Error occurred. Please try again.';
+            });
+        }
+    </script>
+</body>
+</html>

vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:280f67b47eb1ae3e7386047de966646e9515468bed9eb62dc0fdada533961c22
+size 4573659