{"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)\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":"2022-09-26T10:52:10.885873Z","iopub.execute_input":"2022-09-26T10:52:10.886743Z","iopub.status.idle":"2022-09-26T10:52:10.920268Z","shell.execute_reply.started":"2022-09-26T10:52:10.886612Z","shell.execute_reply":"2022-09-26T10:52:10.919240Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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')","metadata":{"execution":{"iopub.status.busy":"2022-09-26T10:52:10.921904Z","iopub.execute_input":"2022-09-26T10:52:10.922966Z","iopub.status.idle":"2022-09-26T10:52:14.869444Z","shell.execute_reply.started":"2022-09-26T10:52:10.922926Z","shell.execute_reply":"2022-09-26T10:52:14.867861Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data.head","metadata":{"execution":{"iopub.status.busy":"2022-09-26T10:52:14.872135Z","iopub.execute_input":"2022-09-26T10:52:14.873320Z","iopub.status.idle":"2022-09-26T10:52:14.902065Z","shell.execute_reply.started":"2022-09-26T10:52:14.873263Z","shell.execute_reply":"2022-09-26T10:52:14.900542Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = np.array(data) #since working with numpy arrays\nm, n = data.shape\nnp.random.shuffle(data) # shuffle before splitting into dev and training sets\n\n#divide into dev and training\n\ndata_dev = data[0:1000].T #.T is transpose\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":"2022-09-26T10:52:14.904155Z","iopub.execute_input":"2022-09-26T10:52:14.904734Z","iopub.status.idle":"2022-09-26T10:52:15.758002Z","shell.execute_reply.started":"2022-09-26T10:52:14.904693Z","shell.execute_reply":"2022-09-26T10:52:15.756642Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Y_train","metadata":{"execution":{"iopub.status.busy":"2022-09-26T10:52:15.761089Z","iopub.execute_input":"2022-09-26T10:52:15.761908Z","iopub.status.idle":"2022-09-26T10:52:15.770459Z","shell.execute_reply.started":"2022-09-26T10:52:15.761852Z","shell.execute_reply":"2022-09-26T10:52:15.769027Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def init_params(): #defining all parameters\n    W1 = np.random.rand(10, 784) - 0.5 #rand makes dist between 0 to but randn makes it bw -0.5 to 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 #dot product since numpy we can do matrix operations\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):# we need to undo activation func in bakcward propagation\n    return Z > 0 \n\ndef one_hot(Y):#creates correctly sized matrix\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":"2022-09-26T10:52:15.772207Z","iopub.execute_input":"2022-09-26T10:52:15.772823Z","iopub.status.idle":"2022-09-26T10:52:15.786031Z","shell.execute_reply.started":"2022-09-26T10:52:15.772788Z","shell.execute_reply":"2022-09-26T10:52:15.784870Z"},"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:#every 10th iteration print accuracy on A2 from forward prop and Y\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":"2022-09-26T10:52:15.787561Z","iopub.execute_input":"2022-09-26T10:52:15.787955Z","iopub.status.idle":"2022-09-26T10:52:15.802746Z","shell.execute_reply.started":"2022-09-26T10:52:15.787923Z","shell.execute_reply":"2022-09-26T10:52:15.801559Z"},"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":"2022-09-26T10:52:15.804746Z","iopub.execute_input":"2022-09-26T10:52:15.805224Z","iopub.status.idle":"2022-09-26T10:53:25.819021Z","shell.execute_reply.started":"2022-09-26T10:52:15.805187Z","shell.execute_reply":"2022-09-26T10:53:25.817727Z"},"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":"2022-09-26T10:53:25.820946Z","iopub.execute_input":"2022-09-26T10:53:25.821790Z","iopub.status.idle":"2022-09-26T10:53:25.831592Z","shell.execute_reply.started":"2022-09-26T10:53:25.821742Z","shell.execute_reply":"2022-09-26T10:53:25.830503Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_prediction(22, W1, b1, W2, b2)","metadata":{"execution":{"iopub.status.busy":"2022-09-26T11:03:37.744724Z","iopub.execute_input":"2022-09-26T11:03:37.745155Z","iopub.status.idle":"2022-09-26T11:03:37.911057Z","shell.execute_reply.started":"2022-09-26T11:03:37.745116Z","shell.execute_reply":"2022-09-26T11:03:37.909885Z"},"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)\n#testing dataset accuracy prediction","metadata":{"execution":{"iopub.status.busy":"2022-09-26T10:53:26.050204Z","iopub.execute_input":"2022-09-26T10:53:26.050633Z","iopub.status.idle":"2022-09-26T10:53:26.074363Z","shell.execute_reply.started":"2022-09-26T10:53:26.050597Z","shell.execute_reply":"2022-09-26T10:53:26.073191Z"},"trusted":true},"execution_count":null,"outputs":[]}]}