{"cells":[{"metadata":{},"cell_type":"markdown","source":"## This is a simple keras model to begin with . I will keep updating it .\nUpdate 1 -  Playing with number of epochs & thought of combining dig mnist validation data with train data to increase data for training but combining dig mnist is not improving score infact it is reducing the score so  going ahead with only train data . "},{"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)\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow.python import keras\nfrom tensorflow.python.keras.models import Sequential\nfrom tensorflow.python.keras.layers import Dense, Flatten, Conv2D, Dropout\nfrom sklearn.metrics import accuracy_score\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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"img_rows, img_cols = 28, 28\nnum_classes = 10","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def data_prep(raw):\n    out_y = keras.utils.to_categorical(raw.label, num_classes)\n\n    num_images = raw.shape[0]\n    x_as_array = raw.values[:,1:]\n    x_shaped_array = x_as_array.reshape(num_images, img_rows, img_cols, 1)\n    out_x = x_shaped_array / 255\n    return out_x, out_y","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_file = \"../input/Kannada-MNIST/train.csv\"\n#dmnist  = pd.read_csv(\"../input/Kannada-MNIST/Dig-MNIST.csv\")\nraw_data = pd.read_csv(train_file)\n#raw_data = pd.concat([train,dmnist])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"raw_data.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x,y = data_prep(raw_data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(200, kernel_size=(3, 3),\n                 activation='relu',\n                 input_shape=(img_rows, img_cols, 1)))\nmodel.add(Conv2D(200, kernel_size=(3, 3), activation='relu'))\nmodel.add(Flatten())\nmodel.add(Dense(1280, activation='relu'))\nmodel.add(Dense(num_classes, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss=keras.losses.categorical_crossentropy,\n              optimizer='adam',\n              metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(x, y,\n          batch_size=1000,\n          epochs=10,\n          validation_split = 0.2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_file = \"../input/Kannada-MNIST/test.csv\"\ntest_data = pd.read_csv(test_file)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"num_images_t = test_data.shape[0]\ntx_as_array = test_data.values[:,1:]\ntx_shaped_array = tx_as_array.reshape(num_images_t, img_rows, img_cols, 1)\ntest_x = tx_shaped_array / 255","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred = model.predict_classes(test_x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.read_csv(\"../input/Kannada-MNIST/sample_submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.label =pred","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.to_csv(\"KannadaMnist1.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}