{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "901d90d4-3778-8fa2-c6cc-3f76ab6480dd" }, "outputs": [], "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", "\n", "import numpy as np # linear algebra\n", "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\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", "\n", "from subprocess import check_output\n", "print(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n", "\n", "# Any results you write to the current directory are saved as output." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "591b9ff6-359c-d4d2-cc5f-da05c362aaae" }, "outputs": [], "source": [ "train= pd.read_csv(\"../input/train.csv\")\n", "train.head(5)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "15a29882-ec73-bb06-2d31-701f087556bc" }, "outputs": [], "source": [ "test= pd.read_csv(\"../input/test.csv\")\n", "test.head(5)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "f5c583ac-7161-eac1-b288-f36843cafacc" }, "outputs": [], "source": [ "print(train.shape, test.shape)" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "13567f77-a375-7fc2-f7e8-32fca2ed5ce8" }, "source": "" }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "31e9760f-baf0-9d08-0893-df3af952654e" }, "outputs": [], "source": [ "X_train= train.drop(['label'], axis=1)\n", "X_train.head(5)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "9bf6c6c9-f610-7bac-1191-0da02b18542b" }, "outputs": [], "source": [ "y_train= train['label']" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "5a245d13-b3fd-74c7-e989-347bb287062e" }, "outputs": [], "source": [ "X_train.shape[0]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "8281aac0-41e6-25ec-e849-1a5e70f34270" }, "outputs": [], "source": [ "from keras.models import Sequential\n", "from keras.layers.core import Dense, Dropout, Activation, Flatten, Reshape\n", "from keras.optimizers import SGD, RMSprop\n", "from keras.utils import np_utils\n", "from keras.regularizers import l2\n", "from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D, AveragePooling2D\n", "from keras.callbacks import EarlyStopping\n", "from keras.preprocessing.image import ImageDataGenerator\n", "from keras.layers.normalization import BatchNormalization\n", "from keras import backend as K\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "87d7d95f-7e54-a767-10c8-d1b51db8f758" }, "outputs": [], "source": [ "x_train = train.drop(['label'], axis=1).values.astype('float32')\n", "Y_train = train['label'].values.astype('float32')\n", "x_test = test.values.astype('float32')\n", "\n", "img_width, img_height = 28, 28\n", "\n", "n_train = x_train.shape[0]\n", "n_test = x_test.shape[0]\n", "\n", "n_classes = 10 \n", "\n", "x_train = x_train.reshape(n_train,1,img_width,img_height)\n", "x_test = x_test.reshape(n_test,1,img_width,img_height)\n", "\n", "x_train = x_train/255 #normalize from [0,255] to [0,1]\n", "x_test = x_test/255 \n", "\n", "y_train = np_utils.to_categorical(Y_train)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "83f9847e-15c2-695d-6d2c-349700c94866" }, "outputs": [], "source": [ "%matplotlib inline\n", "import matplotlib.pyplot as plt\n", "\n", "imgplot = plt.imshow(x_train[100,0,:,:,],cmap='gray')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "5feb51f8-df29-1aad-77d2-2995212675cf" }, "outputs": [], "source": [ "from keras.models import Sequential\n", "from keras.layers.convolutional import *\n", "from keras.layers.core import Dropout, Dense, Flatten, Activation\n", "\n", "n_filters = 64\n", "filter_size1 = 3\n", "filter_size2 = 2\n", "pool_size1 = 3\n", "pool_size2 = 1\n", "n_dense = 128\n", "\n", "K.set_image_dim_ordering('th')\n", "\n", "model = Sequential()\n", "\n", "model.add(Convolution2D(n_filters, filter_size1, filter_size1, batch_input_shape=(None, 1, img_width, img_height), activation='relu', border_mode='valid'))\n", "\n", "model.add(MaxPooling2D(pool_size=(pool_size1, pool_size1)))\n", "\n", "model.add(Convolution2D(n_filters, filter_size2, filter_size2, activation='relu', border_mode='valid'))\n", "\n", "model.add(MaxPooling2D(pool_size=(pool_size2, pool_size2)))\n", "\n", "model.add(Dropout(0.25))\n", "\n", "model.add(Flatten())\n", "\n", "model.add(Dense(n_dense))\n", "\n", "model.add(Activation('relu'))\n", "\n", "model.add(Dropout(0.5))\n", "\n", "model.add(Dense(n_classes))\n", "\n", "model.add(Activation('softmax'))\n", "\n", "model.compile(optimizer='adam',\n", " loss='categorical_crossentropy',\n", " metrics=['accuracy'])" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b52b76ab-4d9a-b8e3-e4d3-d43be6ca5083" }, "outputs": [], "source": [ "model.compile(optimizer='Adam', loss='categorical_crossentropy', metrics=['accuracy'])" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "5c81980c-173c-bf4a-5e71-abde0816faa2" }, "outputs": [], "source": [ "model.fit(x_train,\n", " y_train,\n", " batch_size=128,\n", " nb_epoch=2,verbose=1,\n", " validation_split=.2\n", " )" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "96268201-d16d-b94e-0de9-f3412e493c63" }, "outputs": [], "source": [ "yPred = model.predict_classes(x_test,batch_size=32,verbose=1)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b107fd4e-a81c-6f00-68c7-0087cd849fff" }, "outputs": [], "source": [ "pd.DataFrame({\"ImageId\": list(range(1,len(x_test)+1)), \n", " \"Label\": yPred}).to_csv('MNIST-submission_1.csv', index=False,header=True)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "2b5da420-14da-fbe3-e9b9-7267b667f867" }, "outputs": [], "source": "" } ], "metadata": { "_change_revision": 0, "_is_fork": false, "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.0" } }, "nbformat": 4, "nbformat_minor": 0 }