{"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)\nimport tensorflow as tf\n\nfrom keras.layers import Dense\nfrom keras.datasets import mnist\nfrom keras.layers import Dropout\nfrom keras.utils import np_utils\nfrom keras.models import Sequential\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom sklearn.model_selection import train_test_split\n\n\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 the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trainset = pd.read_csv('../input/train.csv')\ntestset = pd.read_csv('../input/test.csv')\n\nprint(trainset.shape)\nprint(testset.shape)\n\n# split dataset into tainset and cross-validation set\ntrainset, valset= train_test_split(trainset, test_size = 0.1)\n\n# get pix from trainset\nx_train = trainset.loc[:, \"pixel0\" : \"pixel783\"]\nx_train = x_train.values\n# get label from trainset\ny_train = trainset.loc[:,\"label\"]\ny_train = pd.get_dummies(y_train).values\n\n# get pix from valset\nx_cv = valset.loc[:, \"pixel0\" : \"pixel783\"]\nx_cv = x_cv.values\n# get label from valset\ny_cv = valset.loc[:,\"label\"]\ny_cv = pd.get_dummies(y_cv).values\n\nx_test = testset.values\n\nprint(\"Number of training examples: \" + str(x_train.shape[1]))\nprint(\"Number of cross-validation examples = \" + str(x_cv.shape[1]))\nprint (\"x_train shape: \" + str(x_train.shape))\nprint (\"y_train shape: \" + str(y_train.shape))\nprint (\"y_train sample0: \" + str(y_train[0]))\nprint (\"x_test shape: \" + str(x_test.shape))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# define baseline model\ndef network():\n    # create model\n    model = Sequential()\n    model.add(Dense(256, input_dim=784, kernel_initializer=tf.contrib.layers.xavier_initializer(), bias_initializer=tf.zeros_initializer(),activation='relu'))\n    model.add(Dense(128, kernel_initializer=tf.contrib.layers.xavier_initializer(), bias_initializer=tf.zeros_initializer(), activation='relu'))\n    model.add(Dense(64, kernel_initializer=tf.contrib.layers.xavier_initializer(), bias_initializer=tf.zeros_initializer(), activation='relu'))\n    model.add(Dense(32, kernel_initializer=tf.contrib.layers.xavier_initializer(), bias_initializer=tf.zeros_initializer(), activation='relu'))\n    model.add(Dense(15, kernel_initializer=tf.contrib.layers.xavier_initializer(), bias_initializer=tf.zeros_initializer(), activation='relu'))\n    model.add(Dense(10, kernel_initializer=tf.contrib.layers.xavier_initializer(), bias_initializer=tf.zeros_initializer(), activation='softmax'))\n    # Compile model\n    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# build the model\nmodel = network()\n# Fit the model\nmodel.fit(x_train, y_train, validation_data=(x_cv, y_cv), epochs=30, batch_size=64, verbose=1)\n# Final evaluation of the model\nscores = model.evaluate(x_cv, y_cv, verbose=0)\nprint(\"Baseline Error: %.2f%%\" % (100-scores[1]*100))\nprint(\"Baseline acc: \",scores[1]*100) ","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}