{"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)\nimport matplotlib.pyplot as plt \nimport matplotlib.image as mpimg\nimport seaborn as sns\n\nnp.random.seed(2)\n\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix\nimport itertools\n\n\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 the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"# Basic modules for NN\nfrom keras.models import  Sequential \nfrom keras.layers import Dense\nfrom keras.utils import to_categorical\nfrom keras.optimizers import RMSprop","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Modules for CNN\n\nfrom keras.layers.convolutional import Conv2D\nfrom keras.layers.convolutional import MaxPooling2D\nfrom keras.layers import Flatten, Dropout\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"../input/train.csv\")\ntest = pd.read_csv(\"../input/test.csv\")\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train = train[\"label\"]\nX_train = train.drop(labels = [\"label\"], axis = 1)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.values.reshape(-1, 28, 28 ,1)\ntest = test.values.reshape(-1,28,28, 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train/255.0\ntest= test/255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train = to_categorical(Y_train, num_classes = 10)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Spliting and validation set\n#Set the random Seed\nrandom_seed = 2\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# splitting and validating set for the fitting\nX_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size = 0.1 ,random_state = random_seed)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"g = plt.imshow(X_train[0][:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def convolutional_model():\n    model = Sequential()\n    model.add(Conv2D(16,(5,5), strides= (1,1), activation ='relu', input_shape = (28,28,1)))\n    model.add(MaxPooling2D(pool_size = (2,2), strides = (2,2)))\n    \n    model.add(Flatten())\n    model.add(Dense(100, activation ='relu'))\n    model.add(Dense(10, activation = 'softmax'))\n    \n    #compile model\n    model.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model= convolutional_model()\n\nmodel.fit(X_train,Y_train, validation_data = (X_val, Y_val), epochs = 10, batch_size = 100, verbose = 2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = model.predict(test)\nresults = np.argmax(results,axis = 1)\nresults = pd.Series(results, 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)\nsubmission.to_csv(\"cnn_mnist_datagen.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":4}