{"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\n\n\nimport pandas as pd\nimport matplotlib.pyplot as plt\n%matplotlib inline\nfrom sklearn.model_selection import train_test_split\nfrom keras.utils.np_utils import to_categorical\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D\nfrom keras.optimizers import RMSprop\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ReduceLROnPlateau, CSVLogger\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 5GB 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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"img_size = 28\nimg_width, img_ht = img_size, img_size\nverbosity = 1\nbatch_size = 512\nclasses = 10\nchannels = 1\nvalidation_ratio = 0.1\n\ntrain_set = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntest_set = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\n\ny_train = train_set[\"label\"].values\nx_train = train_set.drop(labels=[\"label\"], axis=1).values\n\nx_train = x_train.reshape(-1, 28, 28, 1)\ntest_set = test_set.values.reshape(-1, 28, 28, 1)\n\n\n\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### **One Hot Encoding for Softmax To work**\n","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# x_train = x_train.values.reshape(-1, 28, 28, 1)\n# test_set = test_set.values.reshape(-1, 28, 28, 1)\n\n# # One-Hot encoding\ny_train = to_categorical(y_train, num_classes=10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nfrom sklearn.model_selection import train_test_split\nx_training, x_validation, y_training, y_validation = train_test_split(x_train,\n                                                                      y_train,\n                                                                      test_size=validation_ratio,\n                                                                      shuffle = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"input_shape=(28,28,1)\nmodel=Sequential()\nmodel.add(Conv2D(filters=32,\n                kernel_size=(5,5),\n               padding='Same',\n               activation='relu',\n               input_shape=input_shape))\n\nmodel.add(Conv2D(filters=32,\n                kernel_size=(5,5),\n               padding='Same',\n               activation='relu',\n               input_shape=input_shape))\n\nmodel.add(Conv2D(filters=32,\n                kernel_size=(5,5),\n               padding='Same',\n               activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.5))\n\n\nmodel.add(Conv2D(filters=64, kernel_size=(3,3),padding='Same', \n                 activation='relu'))\nmodel.add(Conv2D(filters=64, kernel_size=(3,3),padding='Same', \n                 activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\nmodel.add(Dropout(0.5))\n\nmodel.add(Flatten())\nmodel.add(Dense(8192, activation='relu'))\nmodel.add(Dropout(0.5))\n\nmodel.add(Dense(2048, activation='relu'))\nmodel.add(Dropout(0.5))\n\nmodel.add(Dense(10, activation=\"softmax\"))\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer=RMSprop(lr=0.0001,\n                                rho=0.9,\n                                epsilon=1e-08,\n                                decay=0.00001),\n              loss=\"categorical_crossentropy\",\n              metrics=[\"accuracy\"])\n\ndata_generator = ImageDataGenerator(rescale=1./255,\n                                    rotation_range=1,\n                                    zoom_range=0.1, \n                                    width_shift_range=0.05,\n                                    height_shift_range=0.05)\ndata_generator.fit(x_training)\n\nhistory = model.fit_generator(data_generator.flow(x_training,\n                                                  y_training,\n                                                  batch_size=512),\n                              epochs=10,\n                              validation_data=(x_validation, y_validation),\n                              verbose=1,\n                              steps_per_epoch=x_training.shape[0]// 32,\n                             )\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_x=test_set[:,:]\ntest_y=model.predict(test_x)\n# print(test_y)\n# y_test_y=test_y.argmax(axis=1)\n# print(y_test_y)\nids=[]\nfor x in range(len(test_set)):\n    ids.append(x)\n    \n# print(ids)\nmysubmission=pd.DataFrame({\"ImageId\": ids,\"Label\":test_y.argmax(axis=-1)})\nmysubmission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"mysubmission.to_csv('submission.csv', index=False)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# kaggle competitions submit -c digit-recognizer -f submission.csv -m \"Message\"","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}