{"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":"import tensorflow as tf\nimport matplotlib.pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"load train data"},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/Kannada-MNIST/train.csv')\ntest = pd.read_csv('/kaggle/input/Kannada-MNIST/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head(3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head(3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Получаем метки значений как массив y_train\n\ny_train = train['label'].values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Удаляем колонку со значениями чтобы преобразовать данные в массив\n\nx_train = train.drop(columns=['label'])\nx_test = test.drop(columns=['id'])\n\nx_train = x_train.to_numpy(copy = True)\nx_test = x_test.to_numpy(copy = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Изменение формы массивов для нормальной работы с API Keras\n\nx_train = x_train.reshape(len(x_train), 28, 28, 1)\nx_test = x_test.reshape(len(x_test), 28, 28, 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Убедиться, что значения являются плавающими\nx_train = x_train.astype('float32')\nx_test = x_test.astype('float32')\n\n# Нормализация кодов RGB путем деления его на максимальное значение RGB.\nx_train /= 255\nx_test /= 255\nprint('x_train shape:', x_train.shape)\nprint('Number of images in x_train', x_train.shape[0])\nprint('Number of images in x_test', x_test.shape[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Импорт необходимых Keras модулей, содержащих модель и слои\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Conv2D, Dropout, Flatten, MaxPooling2D","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"input_shape = (28, 28, 1)\n# Создание последовательной модели и доавление слоев\nmodel = Sequential()\n\n# Добавление слоя извлечения признаков\nmodel.add(Conv2D(28, kernel_size=(3,3), input_shape=input_shape))\n# Добавление слоя объединения\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n# Добавление слоя сглаживания двумерных массивов в одномерный перед построением полностью связанных слоев\nmodel.add(Flatten())\n# Добавление плотного слоя\nmodel.add(Dense(128, activation=tf.nn.relu))\nmodel.add(Dropout(0.2))\nmodel.add(Dense(10,activation=tf.nn.softmax))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer='adam', \n              loss='sparse_categorical_crossentropy', \n              metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(x=x_train,y=y_train, epochs=5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"image_index = 4423\nplt.imshow(x_test[image_index].reshape(28, 28),cmap='Greys')\npred = model.predict(x_test[image_index].reshape(1, 28, 28, 1))\nprint(pred.argmax())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.read_csv('/kaggle/input/Kannada-MNIST/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"d = {i: model.predict(x_test[i].reshape(1, 28, 28, 1)).argmax() for i in test['id']}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"(pd.DataFrame.from_dict(data=d, orient='index')\n   .to_csv('submission.csv', header=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}