{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "3441299d-7a3c-a067-cd39-ef05c82569d2" }, "outputs": [], "source": [ "from __future__ import print_function\n", "import numpy as np\n", "import pandas as pd\n", "np.random.seed(1337) # for reproducibility\n", "%matplotlib inline\n", "import matplotlib.pyplot as plt\n", "\n", "from sklearn.model_selection import train_test_split\n", "from keras.models import Sequential\n", "from keras.layers import Dense, Dropout, Activation, Flatten\n", "from keras.layers import Convolution2D, MaxPooling2D\n", "from keras.utils import np_utils\n", "from keras import backend as K" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "fbe0f166-842f-d2af-9997-c2cb293dc7f1" }, "outputs": [], "source": [ "# getting the datasets\n", "train = pd.read_csv(\"../input/train.csv\")\n", "test = pd.read_csv(\"../input/test.csv\")\n", "print(train.shape)\n", "print(test.shape)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "ec005123-85c5-dfa5-99a4-a27a40b099c3" }, "outputs": [], "source": [ "# plot some digits\n", "for i in range(9):\n", " plt.subplot(3,3,i+1)\n", " data =train.ix[i, 'pixel0':'pixel783'].reshape(28,28)\n", " plt.imshow(data, cmap='gray')\n", " plt.axis('off')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "e7eb2102-d104-bd18-2de2-18cab1d5031c" }, "outputs": [], "source": [ "# separate predictors and labels, transform to ndarrays\n", "y = train[[0]].values.ravel() # labels/target\n", "X = train.iloc[:,1:].values # Predictors(pixels that form the image)\n", "test = test.values" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "dadd7c31-f050-a643-938c-7dfbc8004aae" }, "outputs": [], "source": [ "batch_size = 128\n", "nb_classes = 10\n", "nb_epoch = 12\n", "\n", "# input image dimensions: 28x28 = 784 pixels (exactly what we have in training dataset)\n", "img_rows, img_cols = 28, 28\n", "# number of convolutional filters to use\n", "nb_filters = 32\n", "# size of pooling area for max pooling\n", "pool_size = (2, 2)\n", "# convolution kernel size\n", "kernel_size = (3, 3)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "baa82608-4108-3346-646a-bbb9cef70f20" }, "outputs": [], "source": [ "# Split our data into train and test, this way will be able to evaluate the perfomance of the model\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)\n", "\n", "if K.set_image_dim_ordering == 'th':\n", " X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)\n", " X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)\n", " test = test.reshape(test.shape[0], 1, img_rows, img_cols)\n", " input_shape = (1, img_rows, img_cols)\n", "else:\n", " X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1)\n", " X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1)\n", " test = test.reshape(test.shape[0], img_rows, img_cols, 1)\n", " input_shape = (img_rows, img_cols, 1)\n", "\n", "# convert to array, specify data type, and reshape\n", "X_train = X_train.astype('float32')\n", "X_test = X_test.astype('float32')\n", "test = test.astype('float32')\n", "\n", "# Normalize data to have zero mean and unit variance. \n", "X_train /= 255\n", "X_test /= 255\n", "test /= 255\n", "\n", "print('X_train shape:', X_train.shape)\n", "print(X_train.shape[0], 'train samples')\n", "print(X_test.shape[0], 'test samples')\n", "\n", "# convert class vectors to binary class matrices\n", "y_train = np_utils.to_categorical(y_train, nb_classes)\n", "y_test = np_utils.to_categorical(y_test, nb_classes)\n", "print(\"One hot encoding: {}\".format(y_train[0, :]))" ] }, { "cell_type": "markdown", "metadata": { "_cell_guid": "aeea550b-a381-f8db-3cae-9205d935b463" }, "source": [ "**CNN Model definition**" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "cb500ee4-09f1-9b51-f2a6-d2f4f8b83e64" }, "outputs": [], "source": [ "# The Sequential model is a linear stack of layers\n", "model = Sequential()\n", "\n", "# in the first layer, you must specify the expected input data shape\n", "# input: 28x28 images with 1 channel -> (1, 28, 28) tensors.\n", "# this applies 32 (nb_filters) convolution filters of size 3x3 each.\n", "model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],\n", " border_mode='valid',\n", " input_shape=input_shape))\n", "model.add(Activation('relu'))\n", "model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1]))\n", "model.add(Activation('relu'))\n", "model.add(MaxPooling2D(pool_size=pool_size))\n", "model.add(Dropout(0.25))\n", "\n", "model.add(Flatten())\n", "\n", "# Dense(128) is a fully-connected layer with 128 hidden units.\n", "model.add(Dense(128))\n", "model.add(Activation('relu'))\n", "model.add(Dropout(0.5))\n", "model.add(Dense(nb_classes))\n", "model.add(Activation('softmax'))\n", "\n", "\n", "# a loss function. This is the objective that the model will try to minimize.\n", "# It can be the string identifier of an existing loss function (such as categorical_crossentropy or mse),\n", "# or it can be an objective function\n", "model.compile(loss='categorical_crossentropy',\n", " optimizer='adadelta',\n", " metrics=['accuracy'])" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "3e9a5553-f909-6729-bd0c-ad3f79cbb0d7" }, "outputs": [], "source": [ "# train the model, iterating on the data in batches\n", "# of 128 samples(batch_size declared above)\n", "model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=nb_epoch,\n", " verbose=1, validation_data=(X_test, y_test))\n", "score = model.evaluate(X_test, y_test, verbose=0)\n", "print('Test score:', score[0])\n", "print('Test accuracy:', score[1])" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "5fba7d40-047c-92b5-9ce1-b8cf641687dd" }, "outputs": [], "source": [ "# Make new predictions with the model on the kaggle test dataset\n", "predictions = model.predict_classes(test, batch_size=batch_size)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "fd1cb1ef-4ee1-af83-0f0d-11e49d240806" }, "outputs": [], "source": [ "submission = pd.DataFrame({\n", " \"ImageId\": np.arange(1,len(test)+1),\n", " \"Label\": predictions\n", " })\n", "submission.to_csv('submission_cnn.csv', index=False)" ] } ], "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": "3.5.2" } }, "nbformat": 4, "nbformat_minor": 0 }