{"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\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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data = pd.read_csv('../input/digit-recognizer/train.csv')\ntest_data = pd.read_csv('../input/digit-recognizer/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train_data.shape)\nprint(test_data.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.head","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = train_data['label']\nx = train_data.drop(['label'], axis=1, inplace=True)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data = train_data.values.reshape(42000,28,28,1)\ntest_data = test_data.values.reshape(28000,28,28,1)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.shape,test_data.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nplt.imshow(train_data[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(20,20))\nfor i in range(10):\n    plt.subplot(2, 10, i+1)\n    plt.imshow(train_data[i])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = np.array(train_data)\ny = np.array(y)\ntest = np.array(test_data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import seaborn as sns\nsns.countplot(y)\nplt.title('digit count')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import keras\nfrom keras.utils.np_utils import to_categorical\nfrom keras import layers, models, optimizers\nfrom keras.datasets import mnist\nfrom keras.models import Sequential \nfrom keras.layers import Dense, Dropout, Flatten\nfrom keras.layers import Conv2D, MaxPooling2D","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = to_categorical(y,num_classes=10)\ny.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nx_train, x_val, y_train, y_val = train_test_split(train, y, test_size = 0.2, random_state = 42)\nnum_classes = 10","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train.astype(\"float32\")\nx_val = x_val.astype(\"float32\")\n\n#images from dark(black) to white denoted by [0,255]\nx_train /= 255 \nx_val /= 255 \nprint(x_train.dtype,x_val.dtype)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n#construct CNN\n#As i have multiple outputs layers from 0 to 9 , i should use Sequential model\nmodel = Sequential()\n\n# add number of filters , filter size , strides,padding =valid means no padding and p=same means same dimension will remain of input , input\n#relu is important because it introduces non-linearity and gives modified version of image\n#now input is multiplied with weights and add bias ...entering into hidden layer\nmodel.add(Conv2D(32,kernel_size=(3,3),strides=(1,1),padding='Same',activation='relu',input_shape=(28,28,1)))\n\nmodel.add(Conv2D(64,3,activation='relu'))\n\n#pooling is important to reduce the dimension of input and does not reduce the dimension of filters...(2,2) is filter which multiplies with input mask size\nmodel.add(MaxPooling2D(pool_size=(2,2)))\n\n\nmodel.add(Conv2D(64,3,padding='Same',activation='relu'))\n\nmodel.add(MaxPooling2D(pool_size=(2,2)))\n\nmodel.add(Conv2D(64,3,padding='Same',activation='relu'))\n\nmodel.add(MaxPooling2D(pool_size=(2,2)))\n#dropout is use to randomly on off the neurons in network\nmodel.add(Dropout(0.25))\n\n#flatten : to pass pooling layer to fully-connected layer(dense) in 1-dimension array\nmodel.add(Flatten())\n\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dense(num_classes, activation='softmax'))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = optimizers.Adam(learning_rate=0.001)\nmodel.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])\n#train CNN\nmodel.fit(x_train, y_train,batch_size=128,epochs=10,verbose=1,validation_data=(x_val, y_val))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_result = model.predict(test)\nprint('Prediction Shape is {}'.format(y_result.shape))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = np.argmax(y_result, axis=1)\nresults = pd.Series(results,name=\"Label\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"My_submission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nMy_submission.to_csv(\"submission.csv\",index=False)","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":4}