{"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\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom keras.utils.np_utils import to_categorical \nprint(tf.__version__)\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 5GB 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":"train=pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ntest=pd.read_csv('/kaggle/input/digit-recognizer/test.csv')\nsample=pd.read_csv('/kaggle/input/digit-recognizer/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=train.drop(['label'], axis=1)/255\nX_test=test/255\nX_train=X_train.values.reshape(-1, 28,28,1)\nX_test=X_test.values.reshape(-1, 28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train[1].shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"im1=train.drop(['label'], axis=1).loc[10].values.reshape(28,28)\nplt.imshow(im1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train=to_categorical(train['label'], num_classes=10)\nY_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.imshow(X_train[1000,:,:,0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model =keras.Sequential([\n    keras.layers.Conv2D(filters=32, kernel_size=(5,5), activation='relu', input_shape=(28,28,1)),\n    keras.layers.Conv2D(filters=32, kernel_size=(5,5), activation='relu'),\n    keras.layers.MaxPool2D(pool_size=(2,2)),\n    keras.layers.Dropout(0.25),\n    keras.layers.Conv2D(filters = 64, kernel_size = (3,3), activation ='relu'),\n    keras.layers.Conv2D(filters = 64, kernel_size = (3,3), activation ='relu'),\n    keras.layers.MaxPool2D(pool_size=(2,2), strides=(2,2)),\n    keras.layers.Dropout(0.25),\n    keras.layers.Flatten(),\n    keras.layers.Dense(256, activation = \"relu\"),\n    keras.layers.Dropout(0.5),\n    keras.layers.Dense(10, activation = \"softmax\")    \n])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer='adam',\n              loss=\"categorical_crossentropy\",\n              metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Xtrain.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nXtrain, X_val, Ytrain, Y_val = train_test_split(X_train, Y_train, \n                                                  test_size = 0.1, random_state=2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(Xtrain, Ytrain, epochs=5, validation_data=(X_val, Y_val), verbose=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results=model.predict(X_test)\nresults=results.argmax(axis=1)\nsub=pd.DataFrame({'ImageId':sample['ImageId'], 'Label': results})\nsub.to_csv('sub_mnist.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}