{"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)\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 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":"#%tensorflow_version 1.x\nimport tensorflow\nprint(tensorflow.__version__)\nimport tensorflow.keras as keras\nprint(keras.__version__)\nimport pandas\n\ncsvfile = pandas.read_csv(\"/kaggle/input/Kannada-MNIST/train.csv\")\narray = csvfile.values\nsourcelabels, source = array[:, :1], array[:, 1:]\n\ncsvfile = pandas.read_csv(\"/kaggle/input/Kannada-MNIST/test.csv\")\narray = csvfile.values\ntestlabels, test = array[:, :1], array[:, 1:]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import sklearn.preprocessing\n\nscaler = sklearn.preprocessing.MinMaxScaler((-1, 1), False)\n\nscaler.fit(source)\nssource = scaler.transform(source)\n\nscaler = sklearn.preprocessing.MinMaxScaler((-1, 1), False)\n\nscaler.fit(test)\ntest = scaler.transform(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train, valid, trainlabels, validlabels = ssource[:50000], ssource[50000:],sourcelabels[:50000], sourcelabels[50000:]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.layers import *\nfrom keras.models import Model\nfrom keras.callbacks import CSVLogger, ModelCheckpoint\n\nx = Input(shape=(784,))\ny = Dense(20, activation=None)(x)\ny = Activation('elu')(y)\ny = Dropout(rate=0.3)(y)\ny = Dense(20, activation=None)(y)\ny = Activation('elu')(y)\nprediction = Dense(10, activation='softmax')(y)\n\nmodel = Model(inputs=[x], output=[prediction])\n\nmodel.compile(optimizer='sgd',\n              loss='sparse_categorical_crossentropy',\n              metrics=['accuracy'])\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(train, trainlabels,\n          batch_size=16,\n          epochs=20,\n          verbose=1,\n          validation_data=(valid, validlabels),\n          callbacks=[CSVLogger('logs.csv'), ModelCheckpoint('model', save_best_only=True)])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = keras.models.load_model('model')\n\npred = model.predict(test, batch_size=16)\n\nprediction = pred.argmax(axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"f = open(\"submission.csv\", \"w\")\n\nimport csv\nwith f:\n  writer = csv.writer(f)\n    \n  fnames = [\"id\", \"label\"]\n  writer = csv.DictWriter(f, fieldnames=fnames) \n  writer.writeheader()\n\n  for pos, value in enumerate(prediction):\n    writer.writerow({\"id\" : pos, \"label\": value})","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}