{"nbformat_minor": 0, "cells": [{"outputs": [], "metadata": {"_execution_state": "busy", "trusted": false, "_cell_guid": "69c77a6c-e632-4dc3-8d6f-3e75bf6fb3c4", "_uuid": "fed2bcf437f87190c300de998034d720af9c184f"}, "execution_count": null, "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 \nimport pandas as pd \nfrom keras.models import Sequential\nfrom keras.layers import Dense , Dropout , Lambda, Flatten\nfrom keras.optimizers import Adam ,RMSprop\nfrom sklearn.model_selection import train_test_split\nfrom keras.models import Sequential\nfrom keras.layers import Dense , Dropout\nfrom keras.optimizers import RMSprop\n\n\ntrain = pd.read_csv(\"../input/train.csv\")\ntest_images = (pd.read_csv(\"../input/test.csv\").values).astype('float32')\ntrain_images = (train.ix[:,1:].values).astype('float32')\ntrain_labels = train.ix[:,0].values.astype('int32')\ntrain_images = train_images / 255\ntest_images = test_images / 255\n\n\nfrom keras.utils.np_utils import to_categorical\ntrain_labels = to_categorical(train_labels)\nnum_classes = train_labels.shape[1]\n\nseed = 43\nnp.random.seed(seed)\n\nmodel = Sequential()\nmodel.add(Dense(64, activation='relu',input_dim=(28 * 28)))\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dense(64, activation='relu'))\nmodel.add(Dense(10, activation='softmax'))\n\nmodel.compile(optimizer=RMSprop(lr=0.0001), loss='categorical_crossentropy',\n metrics=['accuracy'])\n\nmodel.fit(train_images, train_labels, \n\t        nb_epoch=1, batch_size=64,verbose=1)\npredictions = model.predict_classes(test_images, verbose=1)\nsubmissions=pd.DataFrame({\"ImageId\": list(range(1,len(predictions)+1)),\n\t                         \"Label\": predictions})\nsubmissions.to_csv(\"DR\"+str(i)+\".csv\", index=False, header=True)", "cell_type": "code"}], "metadata": {"language_info": {"name": "python", "version": "3.6.1", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "file_extension": ".py", "mimetype": "text/x-python", "codemirror_mode": {"name": "ipython", "version": 3}}, "kernelspec": {"name": "python3", "display_name": "Python 3", "language": "python"}}, "nbformat": 4}