├── README.md
└── generate_html.py


/README.md:
--------------------------------------------------------------------------------
 1 | 1. Set Up Python on Your System
 2 |    - Install Python 3.x from the [official Python website](https://www.python.org/).  
 3 |    - During installation, ensure the option Add Python to PATH is selected.  
 4 | 
 5 | 2. Install Required Libraries 
 6 |    - After Python is installed, open the terminal or command prompt.  
 7 |    - Install the necessary libraries using the following commands:
 8 |      - pip install numpy
 9 |      - pip install scikit-learn
10 |      - pip install matplotlib
11 |    - These libraries are essential for data handling, model training, and visualization.
12 | 
13 | 3. Prepare the Project Files  
14 |    - Place all project files in a single folder for easy access.
15 |    - Ensure the script file, Digit Recognition Training.py, is included in this folder.
16 | 
17 | 4. Run the Training Script
18 |    - Open the terminal or command prompt.  
19 |    - Use the cd command to navigate to the folder containing the project files. For example:
20 |      bash
21 |      cd path/to/your/project-folder
22 |      
23 |    - Run the training script using:
24 |      bash
25 |      python "Digit Recognition Training.py"
26 |      
27 |    - The script will perform the following:
28 |      - Load the digits dataset from scikit-learn.
29 |      - Split the data into training and testing sets.
30 |      - Train a Support Vector Machine (SVM) classifier.
31 |      - Predict outcomes on the test set.
32 |      - Save example predictions as image files.
33 |      - Generate an HTML file displaying the model's accuracy and prediction images.
34 | 
35 | 5. View the Results  
36 |    - After execution, check the project folder for:
37 |      - Several image files (digit_0.png, digit_1.png, etc.) showing test predictions.
38 |      - An HTML file named digit_recognition.html.
39 |    - Open the HTML file in any web browser to view:
40 |      - The accuracy of the model.
41 |      - Images of predicted digits along with their labels.
42 | 
43 | 6. Verify and Adjust 
44 |    - Review the accuracy displayed in the browser.  
45 |    - If needed, modify the script parameters (e.g., kernel type in SVM) to optimize the model performance.  
46 |    - Re-run the script to test the changes.
47 | 
48 | 7. Next Steps (Optional) 
49 |    - Save the trained SVM model for later use.
50 |    - Modify the HTML to allow real-time user input for new digit predictions
51 | 


--------------------------------------------------------------------------------
/generate_html.py:
--------------------------------------------------------------------------------
 1 | import numpy as np
 2 | from sklearn import datasets
 3 | from sklearn.model_selection import train_test_split
 4 | from sklearn.preprocessing import StandardScaler
 5 | from sklearn.svm import SVC
 6 | from sklearn.metrics import accuracy_score
 7 | import matplotlib.pyplot as plt
 8 | 
 9 | # Load the digits dataset
10 | digits = datasets.load_digits()
11 | 
12 | # Split data into training and testing sets
13 | X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target, test_size=0.3, random_state=42)
14 | 
15 | # Standardize the data
16 | scaler = StandardScaler()
17 | X_train_scaled = scaler.fit_transform(X_train)
18 | X_test_scaled = scaler.transform(X_test)
19 | 
20 | # Train an SVM classifier
21 | svm_clf = SVC(kernel='linear')
22 | svm_clf.fit(X_train_scaled, y_train)
23 | 
24 | # Make predictions on the test set
25 | y_pred = svm_clf.predict(X_test_scaled)
26 | 
27 | # Calculate accuracy
28 | accuracy = accuracy_score(y_test, y_pred)
29 | 
30 | # Save test images with predictions
31 | n_images = 5
32 | image_filenames = []
33 | for i in range(n_images):
34 |     filename = f"digit_{i}.png"
35 |     image_filenames.append(filename)
36 |     plt.figure()
37 |     plt.imshow(X_test[i].reshape(8, 8), cmap="gray")
38 |     plt.title(f"Pred: {y_pred[i]}")
39 |     plt.axis("off")
40 |     plt.savefig(filename)
41 |     plt.close()
42 | 
43 | # Generate the HTML content
44 | html_content = f"""
45 | <!DOCTYPE html>
46 | <html lang="en">
47 | <head>
48 |     <meta charset="UTF-8">
49 |     <meta name="viewport" content="width=device-width, initial-scale=1.0">
50 |     <title>Digit Recognition</title>
51 |     <style>
52 |         body {{
53 |             font-family: Arial, sans-serif;
54 |             text-align: center;
55 |             padding: 20px;
56 |         }}
57 |         .images {{
58 |             display: flex;
59 |             justify-content: center;
60 |             flex-wrap: wrap;
61 |         }}
62 |         img {{
63 |             border: 1px solid #ddd;
64 |             padding: 10px;
65 |             width: 100px;
66 |             height: 100px;
67 |             margin: 10px;
68 |         }}
69 |     </style>
70 | </head>
71 | <body>
72 |     <h1>Digit Recognition</h1>
73 |     <p>Model Accuracy: <strong>{accuracy * 100:.2f}%</strong></p>
74 |     <div class="images">
75 |         {"".join([f'<img src="{filename}" alt="Digit Prediction">' for filename in image_filenames])}
76 |     </div>
77 | </body>
78 | </html>
79 | """
80 | 
81 | # Save the HTML file
82 | with open("digit_recognition.html", "w") as file:
83 |     file.write(html_content)
84 | 
85 | print("HTML file 'digit_recognition.html' and associated images have been created. Open the HTML file in a browser to view the results.")
86 | 


--------------------------------------------------------------------------------