{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom matplotlib import pyplot as plt\n\ndata = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ntest_data = pd.read_csv('../input/digit-recognizer/test.csv')","metadata":{"execution":{"iopub.status.busy":"2022-08-03T12:42:27.659828Z","iopub.execute_input":"2022-08-03T12:42:27.660243Z","iopub.status.idle":"2022-08-03T12:42:31.866590Z","shell.execute_reply.started":"2022-08-03T12:42:27.660210Z","shell.execute_reply":"2022-08-03T12:42:31.865427Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = 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\n","metadata":{"execution":{"iopub.status.busy":"2022-08-03T12:38:03.502896Z","iopub.execute_input":"2022-08-03T12:38:03.503818Z","iopub.status.idle":"2022-08-03T12:38:04.571972Z","shell.execute_reply.started":"2022-08-03T12:38:03.503759Z","shell.execute_reply":"2022-08-03T12:38:04.570571Z"},"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":"2022-08-03T12:38:04.573769Z","iopub.execute_input":"2022-08-03T12:38:04.574549Z","iopub.status.idle":"2022-08-03T12:38:04.587890Z","shell.execute_reply.started":"2022-08-03T12:38:04.574512Z","shell.execute_reply":"2022-08-03T12:38:04.586949Z"},"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\n","metadata":{"execution":{"iopub.status.busy":"2022-08-03T12:38:04.589957Z","iopub.execute_input":"2022-08-03T12:38:04.590491Z","iopub.status.idle":"2022-08-03T12:38:04.602841Z","shell.execute_reply.started":"2022-08-03T12:38:04.590451Z","shell.execute_reply":"2022-08-03T12:38:04.601667Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"W1, b1, W2, b2 = gradient_descent(X_train, Y_train, 0.10, 500)","metadata":{"execution":{"iopub.status.busy":"2022-08-03T12:38:51.235798Z","iopub.execute_input":"2022-08-03T12:38:51.236288Z","iopub.status.idle":"2022-08-03T12:40:15.659488Z","shell.execute_reply.started":"2022-08-03T12:38:51.236254Z","shell.execute_reply":"2022-08-03T12:40:15.657678Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def make_predictions(X, W1, b1, W2, b2):\n    _, _, _, A2 = forward_prop(W1, b1, W2, b2, X)\n    predictions = get_predictions(A2)\n    return predictions\n\ndef test_prediction(index, W1, b1, W2, b2):\n    current_image = X_train[:, index, None]\n    prediction = make_predictions(X_train[:, index, None], W1, b1, 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":{"execution":{"iopub.status.busy":"2022-08-03T13:27:47.690936Z","iopub.execute_input":"2022-08-03T13:27:47.691403Z","iopub.status.idle":"2022-08-03T13:27:47.728908Z","shell.execute_reply.started":"2022-08-03T13:27:47.691307Z","shell.execute_reply":"2022-08-03T13:27:47.727734Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_prediction(101, W1, b1, W2, b2)\ntest_prediction(32, W1, b1, W2, b2)\ntest_prediction(42, W1, b1, W2, b2)\ntest_prediction(3, W1, b1, W2, b2)","metadata":{"execution":{"iopub.status.busy":"2022-08-03T12:40:21.774969Z","iopub.execute_input":"2022-08-03T12:40:21.775378Z","iopub.status.idle":"2022-08-03T12:40:23.098562Z","shell.execute_reply.started":"2022-08-03T12:40:21.775346Z","shell.execute_reply":"2022-08-03T12:40:23.096953Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dev_predictions = make_predictions(X_dev, W1, b1, W2, b2)\nget_accuracy(dev_predictions, Y_dev)","metadata":{"execution":{"iopub.status.busy":"2022-08-03T12:41:01.456175Z","iopub.execute_input":"2022-08-03T12:41:01.456776Z","iopub.status.idle":"2022-08-03T12:41:01.492688Z","shell.execute_reply.started":"2022-08-03T12:41:01.456734Z","shell.execute_reply":"2022-08-03T12:41:01.491133Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"* *83.6% Overall on the dev_dataset and 83.0% on the training set","metadata":{"execution":{"iopub.status.busy":"2022-08-03T12:51:07.765669Z","iopub.execute_input":"2022-08-03T12:51:07.766164Z","iopub.status.idle":"2022-08-03T12:51:08.034353Z","shell.execute_reply.started":"2022-08-03T12:51:07.766130Z","shell.execute_reply":"2022-08-03T12:51:08.032814Z"}}}]}