Spaces:
Sleeping
Sleeping
| from flask import Flask, request, render_template | |
| import numpy as np | |
| import pickle | |
| app = Flask(__name__) | |
| # Cloud Computing Weights and Max Marks | |
| cc_weights = { | |
| 'A1': 1, 'Q1': 1.5, 'A2': 1, 'Q2': 1.5, 'A3': 1, | |
| 'A4': 4, 'Q3': 1.5, 'Mid': 35, 'AWS Labs': 3, | |
| 'Q4': 1.25, 'A5': 4, 'Q5': 1.25, 'A6': 4, 'Final': 40 | |
| } | |
| cc_max_marks = { | |
| 'A1': 10, 'Q1': 21, 'A2': 10, 'Q2': 30, 'A3': 100, | |
| 'A4': 10, 'Q3': 41, 'Mid': 35, 'AWS Labs': 10, | |
| 'Q4': 40, 'A5': 100, 'Q5': 20, 'A6': 100, 'Final': 40 | |
| } | |
| # ICT Weights and Max Marks | |
| ict_weights = { | |
| 'Q1': 2.625, 'Q2': 2.625, 'A1': 2, 'Q3': 2.625, 'Q4': 2.625, | |
| 'Midterm': 35, 'Q5': 2.625, 'A2': 2, 'Q6': 2.625, 'Q7': 2.625, | |
| 'Q8': 2.625, 'Final': 40 | |
| } | |
| ict_max_marks = { | |
| 'Q1': 30, 'Q2': 49, 'A1': 100, 'Q3': 30, 'Q4': 15, | |
| 'Midterm': 35, 'Q5': 45, 'A2': 100, 'Q6': 32, 'Q7': 24, | |
| 'Q8': 40, 'Final': 100 | |
| } | |
| def normalize_input(input_activities, weights, max_marks): | |
| """ | |
| Normalize the input activities based on weights and max marks. | |
| """ | |
| normalized_activities = [] | |
| for activity, score in input_activities.items(): | |
| if score > 0: # Ignore zeros | |
| normalized_score = (score / max_marks[activity]) * weights[activity] | |
| normalized_activities.append(normalized_score) | |
| return normalized_activities | |
| def predict_final_score(input_activities, weights, max_marks, model_prefix): | |
| """ | |
| Predict the final score based on input activities after normalization. | |
| """ | |
| normalized_activities = normalize_input(input_activities, weights, max_marks) | |
| n = len(normalized_activities) | |
| if n == 0: | |
| return "No valid activities entered. Please provide scores greater than 0." | |
| try: | |
| with open(f"{model_prefix}_model_{n}_activities.pkl", "rb") as file: | |
| model = pickle.load(file) | |
| except FileNotFoundError: | |
| return f"No model available for {n} activities. Train the model first." | |
| input_array = np.array(normalized_activities).reshape(1, -1) | |
| predicted_score = model.predict(input_array)[0] | |
| return round(predicted_score, 2) | |
| def home(): | |
| cc_predicted_score = None | |
| ict_predicted_score = None | |
| if request.method == 'POST': | |
| # Identify the form (Cloud Computing or ICT) | |
| form_type = request.form.get('form_type') | |
| if form_type == 'cloud_computing': | |
| input_activities = { | |
| activity: float(request.form.get(activity, 0) or 0) # Default to 0 for empty inputs | |
| for activity in cc_weights.keys() | |
| } | |
| cc_predicted_score = predict_final_score(input_activities, cc_weights, cc_max_marks, "cloud_computing") | |
| elif form_type == 'ict': | |
| input_activities = { | |
| activity: float(request.form.get(activity, 0) or 0) # Default to 0 for empty inputs | |
| for activity in ict_weights.keys() | |
| } | |
| ict_predicted_score = predict_final_score(input_activities, ict_weights, ict_max_marks, "ict") | |
| return render_template( | |
| 'index.html', | |
| cc_max_marks=cc_max_marks, | |
| ict_max_marks=ict_max_marks, | |
| cc_predicted_score=cc_predicted_score, | |
| ict_predicted_score=ict_predicted_score | |
| ) | |
| if __name__ == '__main__': | |
| app.run(debug=False, port=5000) | |