{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","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":30698,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-04-19T17:56:53.443560Z","iopub.execute_input":"2024-04-19T17:56:53.443962Z","iopub.status.idle":"2024-04-19T17:56:53.785524Z","shell.execute_reply.started":"2024-04-19T17:56:53.443931Z","shell.execute_reply":"2024-04-19T17:56:53.784184Z"},"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":"2024-04-19T17:56:54.604026Z","iopub.execute_input":"2024-04-19T17:56:54.604932Z","iopub.status.idle":"2024-04-19T17:56:58.477159Z","shell.execute_reply.started":"2024-04-19T17:56:54.604889Z","shell.execute_reply":"2024-04-19T17:56:58.476089Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data.head()","metadata":{"execution":{"iopub.status.busy":"2024-04-19T17:57:02.560733Z","iopub.execute_input":"2024-04-19T17:57:02.561127Z","iopub.status.idle":"2024-04-19T17:57:02.592757Z","shell.execute_reply.started":"2024-04-19T17:57:02.561095Z","shell.execute_reply":"2024-04-19T17:57:02.591419Z"},"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]\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":"2024-04-19T17:59:46.927608Z","iopub.execute_input":"2024-04-19T17:59:46.928043Z","iopub.status.idle":"2024-04-19T17:59:47.690045Z","shell.execute_reply.started":"2024-04-19T17:59:46.927998Z","shell.execute_reply":"2024-04-19T17:59:47.688746Z"},"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":"2024-04-19T17:59:50.879178Z","iopub.execute_input":"2024-04-19T17:59:50.879635Z","iopub.status.idle":"2024-04-19T17:59:50.891583Z","shell.execute_reply.started":"2024-04-19T17:59:50.879599Z","shell.execute_reply":"2024-04-19T17:59:50.890295Z"},"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            print(\"Accuracy: \", get_accuracy(get_predictions(A2), Y))\n    return W1, b1, W2, b2","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:05:03.361885Z","iopub.execute_input":"2024-04-19T18:05:03.362501Z","iopub.status.idle":"2024-04-19T18:05:03.372949Z","shell.execute_reply.started":"2024-04-19T18:05:03.362451Z","shell.execute_reply":"2024-04-19T18:05:03.371612Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"W1, b1, W2, b2 = gradient_descent(X_train, Y_train, 500, 0.2)","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:25:55.592602Z","iopub.execute_input":"2024-04-19T18:25:55.593058Z","iopub.status.idle":"2024-04-19T18:26:50.318109Z","shell.execute_reply.started":"2024-04-19T18:25:55.593027Z","shell.execute_reply":"2024-04-19T18:26:50.316727Z"},"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":"2024-04-19T18:28:36.115886Z","iopub.execute_input":"2024-04-19T18:28:36.116377Z","iopub.status.idle":"2024-04-19T18:28:36.125557Z","shell.execute_reply.started":"2024-04-19T18:28:36.116346Z","shell.execute_reply":"2024-04-19T18:28:36.124115Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_prediction(0, W1, b1, W2, b2)","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:28:37.907277Z","iopub.execute_input":"2024-04-19T18:28:37.907681Z","iopub.status.idle":"2024-04-19T18:28:38.134346Z","shell.execute_reply.started":"2024-04-19T18:28:37.907654Z","shell.execute_reply":"2024-04-19T18:28:38.133183Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_prediction(1, W1, b1, W2, b2)","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:28:40.766869Z","iopub.execute_input":"2024-04-19T18:28:40.767328Z","iopub.status.idle":"2024-04-19T18:28:40.991860Z","shell.execute_reply.started":"2024-04-19T18:28:40.767283Z","shell.execute_reply":"2024-04-19T18:28:40.990657Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_prediction(2, W1, b1, W2, b2)\ntest_prediction(3, W1, b1, W2, b2)\ntest_prediction(4, W1, b1, W2, b2)","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:28:44.123876Z","iopub.execute_input":"2024-04-19T18:28:44.124555Z","iopub.status.idle":"2024-04-19T18:28:44.765564Z","shell.execute_reply.started":"2024-04-19T18:28:44.124513Z","shell.execute_reply":"2024-04-19T18:28:44.764037Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}