{"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\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 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 20GB 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":"# Načítanie dátovej množiny\ndf_train = pd.read_csv('../input/digit-recognizer/train.csv')\ndf_test = pd.read_csv('../input/digit-recognizer/test.csv')\ns_sub = pd.read_csv('../input/digit-recognizer/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Odstránenie stĺpca \"label\"\ndf_train_y = df_train['label']\ndf_train_x = df_train.drop(columns=['label'])/255\ndf_test = df_test/255","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Transformácia na 28x28\ndf_train_x = df_train_x.values.reshape(-1,28,28,1)\ndf_test = df_test.values.reshape(-1,28,28,1)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Model siete - konvolúcia (jadro 3x3) , združovanie (jadro 2x2) a dropout\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D\nfrom keras.optimizers import Adam\n\nmodel = Sequential()\n\nmodel.add(Conv2D(filters=32, kernel_size=(3,3), padding='Same',\n                activation='relu', input_shape=(28,28,1)))\nmodel.add(Conv2D(filters=32, kernel_size=(3,3), padding='Same',\n                activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.33))\n\n\nmodel.add(Conv2D(filters=32, kernel_size=(3,3), padding='Same',\n                activation='relu'))\nmodel.add(Conv2D(filters=32, kernel_size=(3,3), padding='Same',\n                activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.33))\n\n\n\nmodel.add(Conv2D(filters=32, kernel_size=(3,3), padding='Same',\n                activation='relu'))\nmodel.add(Conv2D(filters=32, kernel_size=(3,3), padding='Same',\n                activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.33))\n\n\n\nmodel.add(Conv2D(filters=32, kernel_size=(3,3), padding='Same',\n                activation='relu'))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.33))\n\n\nmodel.add(Dense(512,activation='relu'))\nmodel.add(Flatten())\nmodel.add(Dense(10,activation='softmax'))  # 10 -> klasifikujeme 10 číslic\n\n# model.summary() -> zobrazenie štruktúry modelu\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer='adam', loss='SparseCategoricalCrossentropy', metrics=['accuracy'])\n# pri numerických -> loss=SparseCategoricalCrossentropy  \n# pri kategorických -> loss=categorical_crossentropy","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Učenie modelu\nmodel.fit(df_train_x,df_train_y, batch_size=100, epochs = 6, validation_split = 0.2, shuffle = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = model.predict(df_test) # Aplikovanie modelu na testovacie dáta\nsub = np.argmax(sub,axis = 1) # Transformácia na \"one hot\" vektor\n\n\nsubmission = pd.DataFrame()\nsubmission['ImageId'] = s_sub['ImageId']\nsubmission['Label'] = sub\nsubmission.to_csv('submission.csv',index=False)","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}