{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","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"},{"sourceId":1313369,"sourceType":"kernelVersion"},{"sourceId":12859356,"sourceType":"kernelVersion"}],"dockerImageVersionId":30761,"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)\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 ","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-09-11T05:54:07.764117Z","iopub.execute_input":"2024-09-11T05:54:07.764526Z","iopub.status.idle":"2024-09-11T05:54:08.209599Z","shell.execute_reply.started":"2024-09-11T05:54:07.764483Z","shell.execute_reply":"2024-09-11T05:54:08.208446Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom matplotlib import pyplot as plt\ndata = pd.read_csv('/kaggle/input/digit-recognizer/train.csv' )#'/kaggle/input/mnist-dataset-digit-recognizer/mnist_submission.csv')\ndata.head()\ndata= 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]\n\n\n\n","metadata":{"execution":{"iopub.status.busy":"2024-09-11T05:54:08.211760Z","iopub.execute_input":"2024-09-11T05:54:08.212375Z","iopub.status.idle":"2024-09-11T05:54:13.317671Z","shell.execute_reply.started":"2024-09-11T05:54:08.212320Z","shell.execute_reply":"2024-09-11T05:54:13.316501Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def init_params():\n    W1 = np.random.randn(10, 784) - 0.5\n    b1 = np.random.randn(10,1) - 0.5\n    W2 = np.random.randn(10, 10) - 0.5\n    b2 = np.random.randn(10,1) - 0.5\n    return W1, b1, W2, b2\n\ndef ReLu(Z):\n    return np.maximum(0,Z)\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, W1, 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":"2024-09-11T05:54:13.319015Z","iopub.execute_input":"2024-09-11T05:54:13.319372Z","iopub.status.idle":"2024-09-11T05:54:13.333872Z","shell.execute_reply.started":"2024-09-11T05:54:13.319333Z","shell.execute_reply":"2024-09-11T05:54:13.332777Z"},"trusted":true},"outputs":[],"execution_count":null},{"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, 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(\"interations \" , i)\n            print (\"accuracy \" ,get_accuracy(get_predictions(A2) , Y))\n        return W1, b1, W2, b2","metadata":{"execution":{"iopub.status.busy":"2024-09-11T05:54:13.337064Z","iopub.execute_input":"2024-09-11T05:54:13.337665Z","iopub.status.idle":"2024-09-11T05:54:13.355469Z","shell.execute_reply.started":"2024-09-11T05:54:13.337609Z","shell.execute_reply":"2024-09-11T05:54:13.354292Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"W1, b1, W2, b2 = gradient_descent(X_train , Y_train, 500, 0.10)","metadata":{"execution":{"iopub.status.busy":"2024-09-11T05:54:13.357195Z","iopub.execute_input":"2024-09-11T05:54:13.357611Z","iopub.status.idle":"2024-09-11T05:54:13.716487Z","shell.execute_reply.started":"2024-09-11T05:54:13.357569Z","shell.execute_reply":"2024-09-11T05:54:13.715078Z"},"trusted":true},"outputs":[],"execution_count":null},{"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(\"predictions : \", 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":"2024-09-11T05:54:13.718503Z","iopub.execute_input":"2024-09-11T05:54:13.719909Z","iopub.status.idle":"2024-09-11T05:54:13.732661Z","shell.execute_reply.started":"2024-09-11T05:54:13.719839Z","shell.execute_reply":"2024-09-11T05:54:13.731191Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_prediction(10, W1, b1, W2, b2 )","metadata":{"execution":{"iopub.status.busy":"2024-09-11T05:54:46.253542Z","iopub.execute_input":"2024-09-11T05:54:46.254508Z","iopub.status.idle":"2024-09-11T05:54:46.438485Z","shell.execute_reply.started":"2024-09-11T05:54:46.254455Z","shell.execute_reply":"2024-09-11T05:54:46.437312Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"","metadata":{}}]}