{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 in \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 \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":" ## Import the dataset"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\n%matplotlib inline \n\nfrom sklearn.model_selection import train_test_split\nimport cv2\nimport keras\nfrom matplotlib import pyplot as plt\nfrom keras.models import Sequential \nfrom keras.layers import Conv2D,MaxPooling2D, Dense,Flatten, Dropout\nfrom keras.datasets import mnist \nimport matplotlib.pyplot as plt\nfrom keras.utils import np_utils\nfrom keras.optimizers import SGD","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/digit-recognizer/train.csv')\nvalidation = pd.read_csv('../input/digit-recognizer/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"validation.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train.drop(['label'],axis = 1 )\ny = train['label']\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig = plt.figure(figsize = (8,8))\nrow, column = 5,5\n\nfor i in range(1, row * column + 1):\n    im = X_train.iloc[i]\n    im = np.array(im)\n    fig.add_subplot(row,column, i)\n    plt.imshow(im.reshape((28,28)))\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"count =train.groupby(['label']).size()\nprint(count)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(X_train.shape)\nprint(y_test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = np.array(X_train.iloc[:,:])\nX_train = np.array([np.reshape(i, (28,28)) for i in X_train])\n\nX_test = np.array(X_test.iloc[:,:])\nX_test = np.array([np.reshape(i, (28,28)) for i in X_test])\n\nnum_classes = 10\ny_train = np.array(y_train).reshape(-1)\n\ny_train = np.eye(num_classes)[y_train]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(X_train.shape)\nprint(X_test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.reshape((33600, 28, 28, 1))\nX_test = X_test.reshape((8400, 28, 28, 1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(32, kernel_size=(3, 3),activation='relu',input_shape=(28,28,1)))\n\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(Dropout(0.25))\n#flatten since too many dimensions, we only want a classification output\nmodel.add(Flatten())\n#fully connected to get all relevant data\nmodel.add(Dense(128, activation='relu'))\n#one more dropout for convergence' sake :) \nmodel.add(Dropout(0.5))\n#output a softmax to squash the matrix into output probabilities\nmodel.add(Dense(10, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\nmodel.fit(X_train, y_train, epochs= 50, batch_size=32)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"valid = np.array(validation.iloc[:,:])\nvalid = np.array([np.reshape(i, (28,28)) for i in valid])\nvalid = valid.reshape((28000, 28, 28, 1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = model.predict(valid)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_pred = np.argmax(y_pred,axis = 1)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_pred","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = pd.Series(Y_pred,name=\"Label\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nsubmission.to_csv(\"digit.csv\",index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":1}