{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Kannada MNIST\nA competição [Kannada MNIST](https://www.kaggle.com/c/Kannada-MNIST/)\n    é uma versão da famosa tarefa MNIST para reconhecimento de dígitos escritos a mão.\nEntretanto, \na Kannada consiste de dígitos escritos na língua indiana [Cararim](https://pt.wikipedia.org/wiki/L%C3%ADngua_canaresa).\nOs exemplos são imagens monocromáticas com resolução de 28x28 pixels, \n    totalizando 784 pixels por imagem.\nCada pixel é representado por um número de 0 a 255 indicando o nível de cinza do pixel\n    (0 indica preto e 255 indica branco).\nUtilizaremos a plataforma de competição [Kaggle](https://www.kaggle.com).\nMais informações sobre a tarefa podem ser encontradas na [página oficial da competição no Kaggle](https://www.kaggle.com/c/Kannada-MNIST/)."},{"metadata":{},"cell_type":"markdown","source":"## Plataforma Kaggle\nA plataforma Kaggle provê inúmeras competições de Aprendizado de Máquina.\nEsta plataforma provê vários recursos relacionados às tarefas.\nOs mais importantes são:\n\n- "},{"metadata":{},"cell_type":"markdown","source":"## Dados\nOs dados "},{"metadata":{},"cell_type":"markdown","source":""},{"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":4}