{"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":"code","source":"import numpy as np\nimport pandas as pd\nfrom matplotlib import pyplot as plt","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2024-12-02T05:46:22.287016Z","iopub.execute_input":"2024-12-02T05:46:22.287851Z","iopub.status.idle":"2024-12-02T05:46:22.679779Z","shell.execute_reply.started":"2024-12-02T05:46:22.287811Z","shell.execute_reply":"2024-12-02T05:46:22.678734Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"data = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\n\ndata = np.array(data)\nm, n = data.shape\nnp.random.shuffle(data) # shuffle before splitting into dev and training sets\n\ndata_dev = data[0:1000].T\nY_dev = data_dev[0]\nX_dev = data_dev[1:n]\nX_dev = X_dev / 255.\n\ndata_train = data[1000:m].T\nY_train = data_train[0]\nX_train = data_train[1:n]\nX_train = X_train / 255.\n_,m_train = X_train.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-02T05:46:24.377394Z","iopub.execute_input":"2024-12-02T05:46:24.377894Z","iopub.status.idle":"2024-12-02T05:46:28.818045Z","shell.execute_reply.started":"2024-12-02T05:46:24.377859Z","shell.execute_reply":"2024-12-02T05:46:28.816911Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def init_params():\n    W1 = np.random.rand(535, 784) - 0.5\n    b1 = np.random.rand(535, 1) - 0.5\n    W13 = np.random.rand(10, 535) - 0.5\n    b13 = np.random.rand(10, 1) - 0.5\n    W2 = np.random.rand(10, 10) - 0.5\n    b2 = np.random.rand(10, 1) - 0.5\n    return W1, b1, W13, b13, W2, b2\n\ndef ReLU(Z):\n    return np.maximum(Z, 0)\n\ndef softmax(Z):\n    A = np.exp(Z) / sum(np.exp(Z))\n    return A\n\ndef tanh(x):\n    t=(np.exp(x)-np.exp(-x))/(np.exp(x)+np.exp(-x))\n    return t\n\ndef tanh_deriv(x):\n    t=(np.exp(x)-np.exp(-x))/(np.exp(x)+np.exp(-x))\n    dt=1-t**2\n    return dt\n\ndef forward_prop(W1, b1, W13, b13, W2, b2, X):\n    Z1 = W1.dot(X) + b1\n    A1 = tanh(Z1)\n    Z13 = W13.dot(A1) + b13\n    A13 = tanh(Z13)\n    Z2 = W2.dot(A13) + b2\n    A2 = softmax(Z2)\n    return Z1, A1, Z13, A13, Z2, A2\n\ndef ReLU_deriv(Z):\n    return Z > 0\n\ndef one_hot(Y):\n    one_hot_Y = np.zeros((Y.size, Y.max() + 1))\n    one_hot_Y[np.arange(Y.size), Y] = 1\n    one_hot_Y = one_hot_Y.T\n    return one_hot_Y\n\ndef backward_prop(Z1, A1, Z13, A13, Z2, A2, W1, W13, W2, X, Y):\n    one_hot_Y = one_hot(Y)\n    dZ2 = A2 - one_hot_Y\n    dW2 = 1 / m * dZ2.dot(A13.T)\n    db2 = 1 / m * np.sum(dZ2)\n    \n    dZ13 = W2.T.dot(dZ2) * tanh_deriv(Z13)\n    dW13 = 1 / m * dZ13.dot(A1.T)\n    db13 = 1 / m * np.sum(dZ13)\n    \n    dZ1 = W13.T.dot(dZ13) * tanh_deriv(Z1)\n    dW1 = 1 / m * dZ1.dot(X.T)\n    db1 = 1 / m * np.sum(dZ1)\n    return dW1, db1, dW13, db13, dW2, db2\n\ndef update_params(W1, b1, W13, b13, W2, b2, dW1, db1, dW13, db13, dW2, db2, alpha):\n    W1 = W1 - alpha * dW1\n    b1 = b1 - alpha * db1\n    W13 = W13 - alpha * dW13\n    b13 = b13 - alpha * db13\n    W2 = W2 - alpha * dW2  \n    b2 = b2 - alpha * db2    \n    return W1, b1, W13, b13, W2, b2","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-02T06:49:41.722603Z","iopub.execute_input":"2024-12-02T06:49:41.722989Z","iopub.status.idle":"2024-12-02T06:49:41.738815Z","shell.execute_reply.started":"2024-12-02T06:49:41.722957Z","shell.execute_reply":"2024-12-02T06:49:41.737601Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def get_predictions(A2):\n    return np.argmax(A2, 0)\n\ndef get_accuracy(predictions, Y):\n    return np.sum(predictions == Y) / Y.size\n\ndef gradient_descent(X, Y, alpha, iterations):\n    W1, b1, W13, b13, W2, b2 = init_params()\n    for i in range(iterations+1):\n        Z1, A1, Z13, A13, Z2, A2 = forward_prop(W1, b1, W13, b13, W2, b2, X)\n        dW1, db1, dW13, db13, dW2, db2 = backward_prop(Z1, A1, Z13, A13, Z2, A2, W1, W13, W2, X, Y)\n        W1, b1, W13, b13, W2, b2 = update_params(W1, b1, W13, b13, W2, b2, dW1, db1, dW13, db13, dW2, db2, alpha)\n        if i % 100 == 0:\n            print(\"Iteration: \", i)\n            predictions = get_predictions(A2)\n            print(get_accuracy(predictions, Y))\n    return W1, b1, W13, b13, W2, b2","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-02T06:20:21.273045Z","iopub.execute_input":"2024-12-02T06:20:21.273412Z","iopub.status.idle":"2024-12-02T06:20:21.281835Z","shell.execute_reply.started":"2024-12-02T06:20:21.273380Z","shell.execute_reply":"2024-12-02T06:20:21.280545Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"W1, b1, W13, b13, W2, b2 = gradient_descent(X_train, Y_train, 0.10, 500)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-02T06:49:45.970322Z","iopub.execute_input":"2024-12-02T06:49:45.970740Z","iopub.status.idle":"2024-12-02T07:23:06.171855Z","shell.execute_reply.started":"2024-12-02T06:49:45.970690Z","shell.execute_reply":"2024-12-02T07:23:06.170358Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def make_predictions(X, W1, b1, W13, b13, W2, b2):\n    _, _, _,_,_, A2 = forward_prop(W1, b1, W13, b13, W2, b2, X)\n    predictions = get_predictions(A2)\n    return predictions\n\ndef test_prediction(index, W1, b1, W13, b13, W2, b2):\n    current_image = X_train[:, index, None]\n    prediction = make_predictions(X_train[:, index, None], W1, b1, W13, b13, W2, b2)\n    label = Y_train[index]\n    print(\"Prediction: \", prediction)\n    print(\"Label: \", label)\n    \n    current_image = current_image.reshape((28, 28)) * 255\n    plt.gray()\n    plt.imshow(current_image, interpolation='nearest')\n    plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-02T06:48:12.843436Z","iopub.execute_input":"2024-12-02T06:48:12.843825Z","iopub.status.idle":"2024-12-02T06:48:12.851701Z","shell.execute_reply.started":"2024-12-02T06:48:12.843792Z","shell.execute_reply":"2024-12-02T06:48:12.850529Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_prediction(0, W1, b1, W13, b13, W2, b2)\ntest_prediction(1, W1, b1, W13, b13, W2, b2)\ntest_prediction(2, W1, b1, W13, b13, W2, b2)\ntest_prediction(3, W1, b1, W13, b13, W2, b2)\n\ndev_predictions = make_predictions(X_dev, W1, b1, W13, b13, W2, b2)\nget_accuracy(dev_predictions, Y_dev)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-02T06:48:15.434908Z","iopub.execute_input":"2024-12-02T06:48:15.435531Z","iopub.status.idle":"2024-12-02T06:48:16.506094Z","shell.execute_reply.started":"2024-12-02T06:48:15.435405Z","shell.execute_reply":"2024-12-02T06:48:16.503417Z"}},"outputs":[],"execution_count":null}]}