{"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":"# 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\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom matplotlib import pyplot as plt\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2021-09-12T16:49:39.571995Z","iopub.execute_input":"2021-09-12T16:49:39.572364Z","iopub.status.idle":"2021-09-12T16:49:39.597262Z","shell.execute_reply.started":"2021-09-12T16:49:39.572273Z","shell.execute_reply":"2021-09-12T16:49:39.596394Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ndata","metadata":{"execution":{"iopub.status.busy":"2021-09-12T16:49:39.599110Z","iopub.execute_input":"2021-09-12T16:49:39.600234Z","iopub.status.idle":"2021-09-12T16:49:43.252431Z","shell.execute_reply.started":"2021-09-12T16:49:39.600186Z","shell.execute_reply":"2021-09-12T16:49:43.251631Z"},"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","metadata":{"execution":{"iopub.status.busy":"2021-09-12T16:49:43.253736Z","iopub.execute_input":"2021-09-12T16:49:43.254021Z","iopub.status.idle":"2021-09-12T16:49:44.035755Z","shell.execute_reply.started":"2021-09-12T16:49:43.253982Z","shell.execute_reply":"2021-09-12T16:49:44.034915Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Y_train","metadata":{"execution":{"iopub.status.busy":"2021-09-12T16:49:44.038134Z","iopub.execute_input":"2021-09-12T16:49:44.039015Z","iopub.status.idle":"2021-09-12T16:49:44.045942Z","shell.execute_reply.started":"2021-09-12T16:49:44.038944Z","shell.execute_reply":"2021-09-12T16:49:44.045163Z"},"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":"2021-09-12T16:49:44.047357Z","iopub.execute_input":"2021-09-12T16:49:44.047663Z","iopub.status.idle":"2021-09-12T16:49:44.063902Z","shell.execute_reply.started":"2021-09-12T16:49:44.047624Z","shell.execute_reply":"2021-09-12T16:49:44.063067Z"},"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":"2021-09-12T16:49:44.065506Z","iopub.execute_input":"2021-09-12T16:49:44.065857Z","iopub.status.idle":"2021-09-12T16:49:44.081307Z","shell.execute_reply.started":"2021-09-12T16:49:44.065797Z","shell.execute_reply":"2021-09-12T16:49:44.080331Z"},"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":"2021-09-12T16:49:44.083057Z","iopub.execute_input":"2021-09-12T16:49:44.083394Z","iopub.status.idle":"2021-09-12T16:51:04.104698Z","shell.execute_reply.started":"2021-09-12T16:49:44.083356Z","shell.execute_reply":"2021-09-12T16:51:04.103727Z"},"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":"2021-09-12T16:51:04.106465Z","iopub.execute_input":"2021-09-12T16:51:04.107029Z","iopub.status.idle":"2021-09-12T16:51:04.117192Z","shell.execute_reply.started":"2021-09-12T16:51:04.106988Z","shell.execute_reply":"2021-09-12T16:51:04.116357Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_prediction(0, W1, b1, W2, b2)\ntest_prediction(1, W1, b1, W2, b2)\ntest_prediction(2, W1, b1, W2, b2)\ntest_prediction(3, W1, b1, W2, b2)\ntest_prediction(4, W1, b1, W2, b2)\ntest_prediction(5, W1, b1, W2, b2)\ntest_prediction(6, W1, b1, W2, b2)\ntest_prediction(7, W1, b1, W2, b2)\ntest_prediction(8, W1, b1, W2, b2)","metadata":{"execution":{"iopub.status.busy":"2021-09-12T16:52:34.825287Z","iopub.execute_input":"2021-09-12T16:52:34.825586Z","iopub.status.idle":"2021-09-12T16:52:36.015737Z","shell.execute_reply.started":"2021-09-12T16:52:34.825557Z","shell.execute_reply":"2021-09-12T16:52:36.015157Z"},"trusted":true},"execution_count":null,"outputs":[]}]}