{"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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-11-04T21:07:54.732998Z","iopub.execute_input":"2022-11-04T21:07:54.733451Z","iopub.status.idle":"2022-11-04T21:07:54.739560Z","shell.execute_reply.started":"2022-11-04T21:07:54.733417Z","shell.execute_reply":"2022-11-04T21:07:54.738405Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-11-04T21:07:54.741744Z","iopub.execute_input":"2022-11-04T21:07:54.742074Z","iopub.status.idle":"2022-11-04T21:07:56.379620Z","shell.execute_reply.started":"2022-11-04T21:07:54.742042Z","shell.execute_reply":"2022-11-04T21:07:56.378236Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data.shape","metadata":{"execution":{"iopub.status.busy":"2022-11-04T21:07:56.382008Z","iopub.execute_input":"2022-11-04T21:07:56.382719Z","iopub.status.idle":"2022-11-04T21:07:56.389739Z","shell.execute_reply.started":"2022-11-04T21:07:56.382665Z","shell.execute_reply":"2022-11-04T21:07:56.388542Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = np.array(data)\nm, n = data.shape\nnp.random.shuffle(data)\n\ndata_dev = data[0:1000].T\nY_dev = data_dev[0]\nX_dev = data_dev[1:n]\n\ndata_train = data[1000:m].T\nY_train = data_train[0]\nX_train = data_train[1:n]\nX_train = X_train / 255.","metadata":{"execution":{"iopub.status.busy":"2022-11-04T21:07:56.390704Z","iopub.execute_input":"2022-11-04T21:07:56.390991Z","iopub.status.idle":"2022-11-04T21:07:56.829716Z","shell.execute_reply.started":"2022-11-04T21:07:56.390966Z","shell.execute_reply":"2022-11-04T21:07:56.828238Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train","metadata":{"execution":{"iopub.status.busy":"2022-11-04T21:07:56.832601Z","iopub.execute_input":"2022-11-04T21:07:56.833149Z","iopub.status.idle":"2022-11-04T21:07:56.841008Z","shell.execute_reply.started":"2022-11-04T21:07:56.833010Z","shell.execute_reply":"2022-11-04T21:07:56.839841Z"},"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    return np.exp(Z) / sum(np.exp(Z))\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 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 deriv_ReLU(Z):\n    return Z > 0\n    \ndef back_prop(Z1, A1, Z2, A2, W2, X, Y):\n    m = Y.size\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) * deriv_ReLU(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":"2022-11-04T21:07:56.842543Z","iopub.execute_input":"2022-11-04T21:07:56.842839Z","iopub.status.idle":"2022-11-04T21:07:56.856896Z","shell.execute_reply.started":"2022-11-04T21:07:56.842814Z","shell.execute_reply":"2022-11-04T21:07:56.855291Z"},"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, iterations, alpha):\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 = back_prop(Z1, A1, Z2, A2, 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":"2022-11-04T21:07:56.858390Z","iopub.execute_input":"2022-11-04T21:07:56.858844Z","iopub.status.idle":"2022-11-04T21:07:56.874963Z","shell.execute_reply.started":"2022-11-04T21:07:56.858803Z","shell.execute_reply":"2022-11-04T21:07:56.873309Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"W1, b1, W2, b2 = gradient_descent(X_train, Y_train, 500, 0.1)","metadata":{"execution":{"iopub.status.busy":"2022-11-04T21:07:56.877154Z","iopub.execute_input":"2022-11-04T21:07:56.877648Z","iopub.status.idle":"2022-11-04T21:08:33.049589Z","shell.execute_reply.started":"2022-11-04T21:07:56.877606Z","shell.execute_reply":"2022-11-04T21:08:33.048783Z"},"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":"2022-11-04T21:08:33.053696Z","iopub.execute_input":"2022-11-04T21:08:33.055723Z","iopub.status.idle":"2022-11-04T21:08:33.063858Z","shell.execute_reply.started":"2022-11-04T21:08:33.055690Z","shell.execute_reply":"2022-11-04T21:08:33.063112Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for i in range(10):\n    test_prediction(i, W1, b1, W2,b2)","metadata":{"execution":{"iopub.status.busy":"2022-11-04T21:08:33.068302Z","iopub.execute_input":"2022-11-04T21:08:33.070571Z","iopub.status.idle":"2022-11-04T21:08:34.404873Z","shell.execute_reply.started":"2022-11-04T21:08:33.070535Z","shell.execute_reply":"2022-11-04T21:08:34.403845Z"},"trusted":true},"execution_count":null,"outputs":[]}]}