{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","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":30635,"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":{"execution":{"iopub.status.busy":"2024-01-15T13:28:53.226798Z","iopub.execute_input":"2024-01-15T13:28:53.227529Z","iopub.status.idle":"2024-01-15T13:28:53.749647Z","shell.execute_reply.started":"2024-01-15T13:28:53.227490Z","shell.execute_reply":"2024-01-15T13:28:53.748065Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')","metadata":{"execution":{"iopub.status.busy":"2024-01-15T13:33:38.206816Z","iopub.execute_input":"2024-01-15T13:33:38.207275Z","iopub.status.idle":"2024-01-15T13:33:43.355554Z","shell.execute_reply.started":"2024-01-15T13:33:38.207241Z","shell.execute_reply":"2024-01-15T13:33:43.354267Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data.head()","metadata":{"execution":{"iopub.status.busy":"2024-01-15T13:33:44.009909Z","iopub.execute_input":"2024-01-15T13:33:44.010321Z","iopub.status.idle":"2024-01-15T13:33:44.030374Z","shell.execute_reply.started":"2024-01-15T13:33:44.010290Z","shell.execute_reply":"2024-01-15T13:33:44.029475Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = np.array(data)\nm, n = data.shape\nprint(m, n)","metadata":{"execution":{"iopub.status.busy":"2024-01-15T13:33:46.614411Z","iopub.execute_input":"2024-01-15T13:33:46.615018Z","iopub.status.idle":"2024-01-15T13:33:46.760687Z","shell.execute_reply.started":"2024-01-15T13:33:46.614987Z","shell.execute_reply":"2024-01-15T13:33:46.759477Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"np.random.shuffle(data) \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":{"execution":{"iopub.status.busy":"2024-01-15T14:03:08.695932Z","iopub.execute_input":"2024-01-15T14:03:08.697178Z","iopub.status.idle":"2024-01-15T14:03:09.572473Z","shell.execute_reply.started":"2024-01-15T14:03:08.697110Z","shell.execute_reply":"2024-01-15T14:03:09.571133Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def init_params():\n    W1 = np.random.rand(10, 784) - 0.5\n    b1 = 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, 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 forward_prop(W1, b1, W2, b2, X):\n    Z1 = W1.dot(X) + b1\n    A1 = ReLU(Z1)\n    Z2 = W2.dot(A1) + b2\n    A2 = softmax(Z2)\n    return Z1, A1, 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, Z2, A2, W1, W2, X, Y):\n    one_hot_Y = one_hot(Y)\n    dZ2 = A2 - one_hot_Y\n    dW2 = 1 / m * dZ2.dot(A1.T)\n    db2 = 1 / m * np.sum(dZ2)\n    dZ1 = W2.T.dot(dZ2) * ReLU_deriv(Z1)\n    dW1 = 1 / m * dZ1.dot(X.T)\n    db1 = 1 / m * np.sum(dZ1)\n    return dW1, db1, dW2, db2\n\ndef update_params(W1, b1, W2, b2, dW1, db1, dW2, db2, alpha):\n    W1 = W1 - alpha * dW1\n    b1 = b1 - alpha * db1    \n    W2 = W2 - alpha * dW2  \n    b2 = b2 - alpha * db2    \n    return W1, b1, W2, b2","metadata":{"execution":{"iopub.status.busy":"2024-01-15T14:03:12.514507Z","iopub.execute_input":"2024-01-15T14:03:12.514981Z","iopub.status.idle":"2024-01-15T14:03:12.531280Z","shell.execute_reply.started":"2024-01-15T14:03:12.514944Z","shell.execute_reply":"2024-01-15T14:03:12.529853Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_predictions(A2):\n    return np.argmax(A2, 0)\n\ndef get_accuracy(predictions, Y):\n    print(predictions, Y)\n    return np.sum(predictions == Y) / Y.size\n\ndef gradient_descent(X, Y, alpha, iterations):\n    W1, b1, W2, b2 = init_params()\n    for i in range(iterations):\n        Z1, A1, Z2, A2 = forward_prop(W1, b1, W2, b2, X)\n        dW1, db1, dW2, db2 = backward_prop(Z1, A1, Z2, A2, W1, W2, X, Y)\n        W1, b1, W2, b2 = update_params(W1, b1, W2, b2, dW1, db1, dW2, db2, alpha)\n        if i % 10 == 0:\n            print(\"Iteration: \", i)\n            predictions = get_predictions(A2)\n            print(get_accuracy(predictions, Y))\n    return W1, b1, W2, b2","metadata":{"execution":{"iopub.status.busy":"2024-01-15T14:03:12.794146Z","iopub.execute_input":"2024-01-15T14:03:12.794645Z","iopub.status.idle":"2024-01-15T14:03:12.805983Z","shell.execute_reply.started":"2024-01-15T14:03:12.794611Z","shell.execute_reply":"2024-01-15T14:03:12.804441Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"W1, b1, W2, b2 = gradient_descent(X_train, Y_train, 0.10, 600)","metadata":{"scrolled":true,"execution":{"iopub.status.busy":"2024-01-15T14:04:45.880050Z","iopub.execute_input":"2024-01-15T14:04:45.880553Z","iopub.status.idle":"2024-01-15T14:06:27.925789Z","shell.execute_reply.started":"2024-01-15T14:04:45.880514Z","shell.execute_reply":"2024-01-15T14:06:27.924038Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}