{"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\nimport numpy as np \nimport pandas as pd \nimport matplotlib.pyplot as plt\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\nfrom sklearn.model_selection import train_test_split\nfrom keras.models import Sequential\nfrom keras.layers import Dense , Dropout , Lambda, Flatten\nfrom keras.optimizers import Adam ,RMSprop\nfrom keras.layers.convolutional import Conv2D\nfrom keras.layers.convolutional import MaxPooling2D\nfrom keras.utils import np_utils\n\n%matplotlib inline\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# load the data        \ntrain_data = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ntest_data = pd.read_csv('/kaggle/input/digit-recognizer/test.csv')\n\n# splitting the training data into train and validation data\ntrain, valid = train_test_split(train_data, train_size=0.5)\n\n# reshaping and normalization of the test data\nX_test = (test_data/255).astype(float)\nX_test =  X_test.values.reshape(X_test.shape[0], 28, 28, 1)\n\n# reshaping and normalization of the training data\nX_train = (train.drop(columns='label')/255).astype(float)\nX_train = X_train.values.reshape(X_train.shape[0], 28, 28, 1)\ny_train = train.label.astype(int)\n\n# reshaping and normalization of the validation data\nX_valid = (valid.drop(columns='label')/255).astype(float)\nX_valid = X_valid.values.reshape(X_valid.shape[0], 28, 28, 1)\ny_valid = valid.label.astype(int)\n\n# convert to 10 numerical classes\ny_train = tf.keras.utils.to_categorical(y_train, num_classes=10)\ny_valid = tf.keras.utils.to_categorical(y_valid, num_classes=10)\n\n# model creation\ndef model():\n    model = Sequential()\n    model.add(Conv2D(32, (5, 5), input_shape=(28, 28, 1), activation='relu'))\n    model.add(Dense(128, input_shape=(28, 28, 1), activation='relu'))\n    model.add(MaxPooling2D())\n    model.add(Dropout(0.2))\n    model.add(Flatten())\n    model.add(Dense(128, activation='relu'))\n    model.add(Dense(10, activation='softmax'))\n\n    model.compile(\n    optimizer = 'adam',\n    loss='binary_crossentropy',\n    metrics=['binary_accuracy']\n    )\n    return model\n\n# build the model\nmodel = model()\n\n# modelfitting \nhistory = model.fit(\n    X_train, y_train,\n    validation_data=(X_valid, y_valid),\n    batch_size=128,\n    epochs=10,\n    verbose=1 \n)\n\nscore = model.evaluate(X_valid, y_valid)\nprint('Test loss:', score[0])\nprint('Test accuracy:', score[1])\n\ntarget = model.predict(X_test)\ntarget_classes = np.argmax(target,axis = 1) \n\nresults = pd.Series(target_classes,name=\"Label\")\nsubmission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\nsubmission.to_csv(\"digit_recognition.csv\",index=False)\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":"","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}