{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":3004,"databundleVersionId":861823,"sourceType":"competition"}],"dockerImageVersionId":30786,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# 1. Import necessary libraries <a class=\"anchor\" id=\"2\"></a>\n\n","metadata":{}},{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\n# conda install  TensorFlow\n# The Official Keras Deep Neural Network Example for CNN \n###############################\n# Setting Seed Random Number for Reproducibility\nimport numpy as np # linear algebra\nnp.random.seed(123)  # for reproducibility\n\n# Setting Seed Random Number for the TensorFlow Backend\nimport tensorflow as tf\ntf.random.set_seed(123) # for reproducibility\n\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt # plotting library\n#%matplotlib inline\n\nfrom tensorflow import keras\nfrom keras import  backend as K","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:02:15.075119Z","iopub.execute_input":"2024-12-09T19:02:15.075579Z","iopub.status.idle":"2024-12-09T19:02:15.084092Z","shell.execute_reply.started":"2024-12-09T19:02:15.075535Z","shell.execute_reply":"2024-12-09T19:02:15.082469Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 2. Loading MNIST dataset <a class=\"anchor\" id=\"3\"></a>\n","metadata":{}},{"cell_type":"code","source":"# import dataset\nfrom keras.datasets import mnist\n\n# load dataset\n(x_train, y_train),(x_test, y_test) = mnist.load_data() # ouput numpy arrays\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:02:17.712706Z","iopub.execute_input":"2024-12-09T19:02:17.713141Z","iopub.status.idle":"2024-12-09T19:02:18.039865Z","shell.execute_reply.started":"2024-12-09T19:02:17.713103Z","shell.execute_reply":"2024-12-09T19:02:18.038601Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 3. Data exploration and visualization <a class=\"anchor\" id=\"4\"></a>","metadata":{}},{"cell_type":"code","source":"print(type(x_train))\nprint(\"x_train shape:\", x_train.shape )\nprint(\"x_test shape:\",x_test.shape )\nprint(\"y_train shape:\",y_train.shape )\nprint(\"y_test shape:\",y_test.shape )\n\nprint(\"labels: \",np.unique(y_train)) # multi-classification\n\n# count the number of unique train labels\ncategory_name, counts = np.unique(y_train, return_counts=True)\nprint(\"Train labels: \", dict(zip(category_name, counts)))\n\n# count the number of unique test labels\ncategory_name, counts = np.unique(y_test, return_counts=True)\nprint(\"\\nTest labels: \", dict(zip(category_name, counts)))\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:02:19.815897Z","iopub.execute_input":"2024-12-09T19:02:19.816341Z","iopub.status.idle":"2024-12-09T19:02:19.829785Z","shell.execute_reply.started":"2024-12-09T19:02:19.816304Z","shell.execute_reply":"2024-12-09T19:02:19.827964Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# sample 9 mnist digits from train dataset\nindexes = np.random.randint(0, x_train.shape[0], size=9)\nimages = x_train[indexes]\nlabels = y_train[indexes]\n\n# plot the 9 mnist digits\nplt.figure(figsize=(3,3))\nfor i in range(len(indexes)):\n    plt.subplot(3, 3, i + 1)\n    image = images[i]\n    plt.imshow(image, cmap='gray')\n    plt.axis('off')\n    \nplt.show()\nplt.savefig(\"mnist-samples.png\")\nplt.close('all')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:02:22.494119Z","iopub.execute_input":"2024-12-09T19:02:22.494551Z","iopub.status.idle":"2024-12-09T19:02:22.841475Z","shell.execute_reply.started":"2024-12-09T19:02:22.494515Z","shell.execute_reply":"2024-12-09T19:02:22.839312Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 4 Data Preprocessing <a class=\"anchor\" id=\"4\"></a>","metadata":{}},{"cell_type":"markdown","source":"### 4.1 One-Hot Encode the Labels <a class=\"anchor\" id=\"5.2\"></a>\n\nThe number of labels is computed as:","metadata":{}},{"cell_type":"code","source":"np.unique(y_train)\n\n# compute the number of labels\nnum_labels = len(np.unique(y_train))\nprint(num_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:02:25.775294Z","iopub.execute_input":"2024-12-09T19:02:25.775714Z","iopub.status.idle":"2024-12-09T19:02:25.786247Z","shell.execute_reply.started":"2024-12-09T19:02:25.775680Z","shell.execute_reply":"2024-12-09T19:02:25.784421Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.utils import to_categorical, plot_model\n# convert to one-hot vector\nY_train = to_categorical(y_train)\nY_test = to_categorical(y_test)\n\nprint (\"A sample output before encoding: \",y_train[0])\nprint (\"A sample output after encoding: \",Y_train[0])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:02:27.712426Z","iopub.execute_input":"2024-12-09T19:02:27.712838Z","iopub.status.idle":"2024-12-09T19:02:27.723146Z","shell.execute_reply.started":"2024-12-09T19:02:27.712803Z","shell.execute_reply":"2024-12-09T19:02:27.721887Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 4.2 Reshape the Data\n","metadata":{},"attachments":{"5f951dc9-409c-4fda-a2fc-25241876f700.png":{"image/png":"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"}}},{"cell_type":"code","source":"# image dimensions\nimage_height = x_train.shape[1]\ninput_width = x_train.shape[2]\ninput_size = image_height * input_width\nprint(input_size)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:02:29.703791Z","iopub.execute_input":"2024-12-09T19:02:29.704209Z","iopub.status.idle":"2024-12-09T19:02:29.710679Z","shell.execute_reply.started":"2024-12-09T19:02:29.704154Z","shell.execute_reply":"2024-12-09T19:02:29.709222Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Resize the images\nX_train = np.reshape(x_train, [-1, input_size])\nX_test = np.reshape(x_test, [-1, input_size])\n\nprint(\"x_train shape before the re-shaping:\", x_train.shape )\nprint(\"x_train shape after flattening:\", X_train.shape )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:02:31.359301Z","iopub.execute_input":"2024-12-09T19:02:31.359713Z","iopub.status.idle":"2024-12-09T19:02:31.367740Z","shell.execute_reply.started":"2024-12-09T19:02:31.359678Z","shell.execute_reply":"2024-12-09T19:02:31.366373Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 4.3 Normalize the Data","metadata":{}},{"cell_type":"code","source":"# Preprocess input data\nprint(\"Range of X_train data before re-scaling: [ \", max(X_train[0].round(2)), ',', min(X_train[0]), ' ]' )\n# Scale image data to the [0, 1] range\nX_train_ = X_train.astype('float32') / 255\nX_test_ = X_test.astype('float32') / 255\n\nprint(\"Range of X_train data after re-scaling: [ \", max(X_train_[0].round(2)), ',', min(X_train[0]), ' ]' )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:02:33.083896Z","iopub.execute_input":"2024-12-09T19:02:33.084317Z","iopub.status.idle":"2024-12-09T19:02:33.183534Z","shell.execute_reply.started":"2024-12-09T19:02:33.084283Z","shell.execute_reply":"2024-12-09T19:02:33.182228Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 5. Designing ANN model architecture using Sci-learn ML Library <a class=\"anchor\" id=\"5\"></a>","metadata":{}},{"cell_type":"markdown","source":"### 5.1 Design ANN model <a class=\"anchor\" id=\"5.5\"></a>\n\n- Now, we will set the network parameters as follows:","metadata":{}},{"cell_type":"code","source":"from sklearn.neural_network import MLPClassifier\n# ('identity', 'logistic', 'tanh', 'relu')\n\n# ('identity', 'logistic', 'tanh', 'relu')\n# Design an ANN model\nANN = MLPClassifier(hidden_layer_sizes=350, \n                    solver='adam', \n                    activation=\"relu\", \n                    random_state=1, \n                    alpha=1e-04,  \n                    max_iter=1000, \n                    early_stopping=True, \n                    n_iter_no_change =1000, \n                    validation_fraction=0.1 )\n\n\n# Hidden layer activation functions {‘identity’, ‘logistic’, ‘tanh’, ‘relu’}, default=’relu’\n# Activation function for the all hidden layers is the same\n# solver{‘lbfgs’, ‘sgd’, ‘adam’}, default=’adam’\n# MLPClassifier uses the Average Cross-Entropy loss function. In the current version you can not set this parameter.\n# MLPClassifier uses softmax transfer function as output activation function for Multiclass-Classification. In the current version you can not set this parameter.\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:06:39.708096Z","iopub.execute_input":"2024-12-09T19:06:39.708507Z","iopub.status.idle":"2024-12-09T19:06:39.716966Z","shell.execute_reply.started":"2024-12-09T19:06:39.708473Z","shell.execute_reply":"2024-12-09T19:06:39.714806Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 5.2 Train the ANN model <a class=\"anchor\" id=\"5.5\"></a>","metadata":{}},{"cell_type":"code","source":"# Train the ANN model\nANN.fit(X_train_, Y_train)\n\nprint(ANN.out_activation_)\nprint(ANN.n_outputs_)\nprint(ANN.n_features_in_)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:07:09.890558Z","iopub.execute_input":"2024-12-09T19:07:09.890994Z","iopub.status.idle":"2024-12-09T19:07:15.382546Z","shell.execute_reply.started":"2024-12-09T19:07:09.890956Z","shell.execute_reply":"2024-12-09T19:07:15.381389Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 5.3 Evaluate the ANN model <a class=\"anchor\" id=\"5.5\"></a>","metadata":{}},{"cell_type":"code","source":"# Find out and display the test and training accuracies\ntrain_accuracy = ANN.score(X_train_, Y_train)\ntest_accuracy = ANN.score(X_test_, Y_test)\n\nprint(\"Training Accuracy: {:.2f}%\".format(train_accuracy * 100))\nprint(\"Test Accuracy: {:.2f}%\".format(test_accuracy * 100))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:07:18.569488Z","iopub.execute_input":"2024-12-09T19:07:18.569879Z","iopub.status.idle":"2024-12-09T19:07:19.204630Z","shell.execute_reply.started":"2024-12-09T19:07:18.569848Z","shell.execute_reply":"2024-12-09T19:07:19.203148Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Visualize Evaluation Metrics of ML Models\nfrom sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n# Make predictions\nY_pred = ANN.predict(X_test_)\nY_pred_categorical = np.argmax(Y_pred, axis=1) # convert softmax output (ANN prediction) into the categorical label\nY_test_categorical = np.argmax(Y_test, axis=1) # convert one-hot encoded label into the categorical label\n\n# Compute the confusion matrix\ncm = confusion_matrix(Y_test_categorical, Y_pred_categorical)\n\n# Plot the confusion matrix\ndisp = ConfusionMatrixDisplay(confusion_matrix=cm)\ndisp.plot(cmap=plt.cm.Blues)\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:07:21.664538Z","iopub.execute_input":"2024-12-09T19:07:21.664934Z","iopub.status.idle":"2024-12-09T19:07:22.292534Z","shell.execute_reply.started":"2024-12-09T19:07:21.664899Z","shell.execute_reply":"2024-12-09T19:07:22.291286Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 5.4 Monitoring the training process <a class=\"anchor\" id=\"5.5\"></a>","metadata":{}},{"cell_type":"code","source":"print('Number of the training: {}'.format(ANN.n_iter_)) # Default value for the max_iter parameter is 200","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:07:25.131018Z","iopub.execute_input":"2024-12-09T19:07:25.131468Z","iopub.status.idle":"2024-12-09T19:07:25.137164Z","shell.execute_reply.started":"2024-12-09T19:07:25.131430Z","shell.execute_reply":"2024-12-09T19:07:25.135981Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print('Number of the training: {}'.format(ANN.n_iter_))\ntrn_loss= ANN.loss_curve_ #errors\n#validation_scores = ANN.validation_scores_ #validation_scores_ is not available if early_stopping=False\n\nimport matplotlib.pyplot as plt\nplt.rcParams['figure.figsize'] = 5, 5\nplt.plot( trn_loss, label='Losses') # errors plot\nplt.legend()\nplt.xlabel('Iterations')\nplt.ylabel('Losses')\nplt.title('Training Losses over Iterations')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:07:27.017484Z","iopub.execute_input":"2024-12-09T19:07:27.017902Z","iopub.status.idle":"2024-12-09T19:07:27.330411Z","shell.execute_reply.started":"2024-12-09T19:07:27.017867Z","shell.execute_reply":"2024-12-09T19:07:27.329224Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# II - Designing ANN model using Keras DL Library <a class=\"anchor\" id=\"5\"></a>","metadata":{}},{"cell_type":"code","source":"from tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Input, Activation, Dropout\nfrom tensorflow.keras.utils import to_categorical, plot_model\n\n# network parameters\nbatch_size = 128","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:07:30.914967Z","iopub.execute_input":"2024-12-09T19:07:30.915419Z","iopub.status.idle":"2024-12-09T19:07:30.921652Z","shell.execute_reply.started":"2024-12-09T19:07:30.915382Z","shell.execute_reply":"2024-12-09T19:07:30.920300Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 1. Designing ANN model using Keras DL Library <a class=\"anchor\" id=\"5\"></a>","metadata":{}},{"cell_type":"markdown","source":"### 1.1 Designing the model architecture <a class=\"anchor\" id=\"5.6\"></a>","metadata":{}},{"cell_type":"code","source":"# Design an ANN model with a 3-layer and  ReLU using the Keras\nmodel = Sequential([\n    Input(shape=(28 * 28,)),\n    Dense(128, activation='relu'),\n    Dropout(0.3),\n    Dense(64, activation='relu'),\n    Dropout(0.2),\n    Dense(10, activation='softmax')\n])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:07:40.227825Z","iopub.execute_input":"2024-12-09T19:07:40.228276Z","iopub.status.idle":"2024-12-09T19:07:40.332820Z","shell.execute_reply.started":"2024-12-09T19:07:40.228237Z","shell.execute_reply":"2024-12-09T19:07:40.331510Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 1.2 View model summary <a class=\"anchor\" id=\"5.7\"></a>\n\n- Keras library provides us **summary()** method to check the model description.","metadata":{}},{"cell_type":"code","source":"model.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:07:43.407391Z","iopub.execute_input":"2024-12-09T19:07:43.407790Z","iopub.status.idle":"2024-12-09T19:07:43.432840Z","shell.execute_reply.started":"2024-12-09T19:07:43.407756Z","shell.execute_reply":"2024-12-09T19:07:43.431688Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"- The above listing shows the model summary of the proposed network. It requires a total of 269,322 parameters.\n\n- This is substantial considering that we have a simple task of classifying MNIST digits. So, MLPs are not parameter efficient. \n\n- The total number of parameters required can be computed as follows:\n\n  - From input to Dense layer: 784 × 256 + 256 = 200,960. \n  \n  - From first Dense to second Dense: 256 × 256 + 256 = 65,792. \n  \n  - From second Dense to the output layer: 10 × 256 + 10 = 2,570. \n  \n  - The total is 200,690 + 65,972 + 2,570 = 269,322.","metadata":{}},{"cell_type":"markdown","source":"- Another way of verifying the network is by calling the **plot_model()** method as follows:","metadata":{}},{"cell_type":"code","source":"plot_model(model, to_file='mlp-mnist_plot.png', \n           show_shapes=True, \n           show_layer_names=True, \n           dpi=50, \n           show_layer_activations=True,\n           show_trainable=True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:07:47.234033Z","iopub.execute_input":"2024-12-09T19:07:47.235048Z","iopub.status.idle":"2024-12-09T19:07:47.540586Z","shell.execute_reply.started":"2024-12-09T19:07:47.235002Z","shell.execute_reply":"2024-12-09T19:07:47.539394Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 1.3 Compile the model with compile() method <a class=\"anchor\" id=\"6.1\"></a>\n\n\n- Compilation of model can be done as follows:","metadata":{}},{"cell_type":"code","source":"model.compile(loss='categorical_crossentropy', \n              optimizer='adam',\n              metrics=['accuracy'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:07:53.019636Z","iopub.execute_input":"2024-12-09T19:07:53.020397Z","iopub.status.idle":"2024-12-09T19:07:53.039254Z","shell.execute_reply.started":"2024-12-09T19:07:53.020351Z","shell.execute_reply":"2024-12-09T19:07:53.037553Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 1.4 Train the model with fit() method <a class=\"anchor\" id=\"6.2\"></a>","metadata":{}},{"cell_type":"code","source":"# Fit your model\nhistory = model.fit(X_train_, Y_train,\n                    batch_size=batch_size,\n                    epochs=20,\n                    validation_split=0.1,\n                    verbose=1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:07:54.463609Z","iopub.execute_input":"2024-12-09T19:07:54.464690Z","iopub.status.idle":"2024-12-09T19:08:37.457251Z","shell.execute_reply.started":"2024-12-09T19:07:54.464647Z","shell.execute_reply":"2024-12-09T19:08:37.455998Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 1.5 Evaluating model performance with evaluate() method <a class=\"anchor\" id=\"6.3\"></a>","metadata":{}},{"cell_type":"code","source":"loss, acc = model.evaluate(X_train_, Y_train, batch_size=batch_size)\nprint(\"\\nTraining accuracy: %.1f%%\" % (100.0 * acc))\n\nloss, acc = model.evaluate(X_test_, Y_test, batch_size=batch_size)\nprint(\"\\nTest accuracy: %.1f%%\" % (100.0 * acc))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:09:03.028161Z","iopub.execute_input":"2024-12-09T19:09:03.028633Z","iopub.status.idle":"2024-12-09T19:09:04.664908Z","shell.execute_reply.started":"2024-12-09T19:09:03.028594Z","shell.execute_reply":"2024-12-09T19:09:04.663679Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### 1.6 Monitoring the training process <a class=\"anchor\" id=\"6.3\"></a>","metadata":{}},{"cell_type":"code","source":"pd.DataFrame(history.history).head()\n\nplt.title('Loss')\nplt.plot(history.history['loss'], label='train loss')\nplt.plot(history.history['val_loss'], label='validation loss')\n# Set x-axis ticks to be integers\nplt.xticks(np.arange(0, len(history.history['loss']), step=5))  # This sets ticks from 0 to 10\nplt.ylabel('Errors')  \nplt.xlabel('Iterarions')  \nplt.legend()\nplt.show()\n\nplt.title('accuracy')\nplt.plot(history.history['accuracy'], label='train accuracy')\nplt.plot(history.history['val_accuracy'], label='val accuracy')\n# Set x-axis ticks to be integers\nplt.xticks(np.arange(0, len(history.history['loss']), step=5))  # This sets ticks from 0 to 10\nplt.ylabel('Accuracies')  \nplt.xlabel('Iterarions')  \nplt.legend()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:09:07.702440Z","iopub.execute_input":"2024-12-09T19:09:07.702813Z","iopub.status.idle":"2024-12-09T19:09:08.127086Z","shell.execute_reply.started":"2024-12-09T19:09:07.702782Z","shell.execute_reply":"2024-12-09T19:09:08.125819Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 2. Results and Conclusion <a class=\"anchor\" id=\"8\"></a>\n\n","metadata":{}},{"cell_type":"code","source":"# Visualize Evaluation Metrics of ML Models\nfrom sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n# Make predictions\nY_pred = model.predict(X_test_)\nY_pred_categorical = np.argmax(Y_pred, axis=1)\nY_test_categorical = np.argmax(Y_test, axis=1)\n\n# Compute the confusion matrix\ncm = confusion_matrix(Y_test_categorical, Y_pred_categorical)\n\n# Plot the confusion matrix\ndisp = ConfusionMatrixDisplay(confusion_matrix=cm)\ndisp.plot(cmap=plt.cm.Blues)\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:09:12.866452Z","iopub.execute_input":"2024-12-09T19:09:12.866936Z","iopub.status.idle":"2024-12-09T19:09:14.090536Z","shell.execute_reply.started":"2024-12-09T19:09:12.866896Z","shell.execute_reply":"2024-12-09T19:09:14.089316Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn import metrics\nprint(metrics.classification_report(Y_test_categorical, Y_pred_categorical))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:09:16.936093Z","iopub.execute_input":"2024-12-09T19:09:16.936564Z","iopub.status.idle":"2024-12-09T19:09:16.977114Z","shell.execute_reply.started":"2024-12-09T19:09:16.936519Z","shell.execute_reply":"2024-12-09T19:09:16.975709Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Developing a User Interface to interact with the trained model\n# 3. Using the trained model in the production environment","metadata":{}},{"cell_type":"markdown","source":"*Draw a digit on the black background* using the Paint application and save it as **png** image. As seen the following example:\n\n![image.png](attachment:77f091c0-cd1b-4401-8fdd-ccea49830f20.png)","metadata":{},"attachments":{"77f091c0-cd1b-4401-8fdd-ccea49830f20.png":{"image/png":"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"}}},{"cell_type":"code","source":"# Draw a number on the black background using the Paint application and save it as png image. As seen in the example above:\n# Execute this cell to make available the upload button and upload your image from your computer to the kaggle notebook. \nimport ipywidgets as widgets\nfrom ipywidgets import interact\n# Define the widget\nfile_upload = widgets.FileUpload(\n    accept='.png',   # The type of files to accept\n    multiple=False    # Whether to allow to upload multiple files or not\n)\n\n# Display the widget\ndisplay(file_upload)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:12:15.392498Z","iopub.execute_input":"2024-12-09T19:12:15.392916Z","iopub.status.idle":"2024-12-09T19:12:15.595102Z","shell.execute_reply.started":"2024-12-09T19:12:15.392880Z","shell.execute_reply":"2024-12-09T19:12:15.594124Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#Run this cell to see the prediction for your uploaded image.\n\nif  len(file_upload.data)!=0:\n    import io\n    rawdata = file_upload.data[0]\n    #When you need to handle binary data (like images or files) without saving them to disk, io.BytesIO can be very handy\n    img = io.BytesIO(rawdata)\n    # loading and displaying the sample image\n    from PIL import Image\n    import numpy as np\n    import matplotlib.pyplot as plt \n    img=Image.open(img).convert('L').resize((28, 28))\n    \n    # convert('L') loads the image as gray scale image.\n    img=np.array(img) # convert the image into the Numpy array.\n    \n    # Plot the image\n    plt.figure(figsize=(2, 2))  # Width: 2 inches, Height: 2 inches\n    plt.imshow(img, cmap='gray')\n    plt.axis('off')  # Hide the axis\n    plt.show()\n    # Print the Shape of image as it is a Numpy Array\n    print(\"Image is reshaped into:\", img.shape)\n\n    # Scalling the image so that all pixel values can fall into \n    # the range of 1 to 0 \n    # Same as our training samples\n    img=img/255\n    # reshape our image data matrix \n    # so that match input shape of the our trained perceptron network \n    img=img.reshape(-1, 28*28)\n    print('Flattened image shape:\\n',img.shape)\n    prediction = model.predict(img)\n    prediction = np.argmax(prediction, axis=1)\n    print(\"Prediction for the uploaded image is: \", prediction)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-09T19:12:25.662661Z","iopub.execute_input":"2024-12-09T19:12:25.663558Z","iopub.status.idle":"2024-12-09T19:12:25.670735Z","shell.execute_reply.started":"2024-12-09T19:12:25.663519Z","shell.execute_reply":"2024-12-09T19:12:25.669568Z"}},"outputs":[],"execution_count":null}]}