{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "_cell_guid": "6f12b2ff-578e-e40d-ca6a-63c60451d4b1" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "test.csv\n", "train.csv\n", "\n" ] } ], "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": 2, "metadata": { "_cell_guid": "fa440bad-3115-3cf3-12d7-f08aba65c68a" }, "outputs": [], "source": [ "import os\n", "os.getcwd()\n", "os.chdir(\"../input\")" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "_cell_guid": "a01cd6cd-2ade-6c1d-f44f-c180c08fe41f" }, "outputs": [ { "data": { "text/plain": [ "['test.csv', 'train.csv']" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "os.listdir()" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "_cell_guid": "d9c93124-035b-9798-adf4-3898fc95bdda" }, "outputs": [], "source": [ "train_frame = pd.read_csv(\"train.csv\")\n", "test_frame = pd.read_csv(\"test.csv\")" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "_cell_guid": "0427b066-33a7-4dcb-9db2-57c935b428fc" }, "outputs": [], "source": [ "train_label = train_frame.iloc[:,0]" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "_cell_guid": "593bef87-1699-04ee-cb28-5a3665d6f7dc" }, "outputs": [], "source": [ "train_feature = train_frame.iloc[:,1:]\n", "from sklearn import svm" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "_cell_guid": "be50e22f-8e56-b145-66d2-06e35023e600" }, "outputs": [], "source": [ "from sklearn.decomposition import PCA" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "_cell_guid": "e73d6a8a-5b11-51dd-a956-3bd085230871" }, "outputs": [ { "data": { "text/plain": [ "PCA(copy=True, iterated_power='auto', n_components=100, random_state=None,\n", " svd_solver='auto', tol=0.0, whiten=False)" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pca = PCA(n_components=100)\n", "pca.fit(train_feature)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "_cell_guid": "2b02f75e-a742-e549-73ac-951299b76957" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[ 0.09748938 0.07160266 0.06145903 0.05379302 0.04894262 0.04303214\n", " 0.03277051 0.02892103 0.02766902 0.02348871 0.02099325 0.02059001\n", " 0.01702553 0.01692787 0.01581126 0.0148324 0.01319688 0.01282727\n", " 0.01187976 0.01152755 0.01072191 0.01015199 0.00964902 0.00912846\n", " 0.00887641 0.00838766 0.00811856 0.00777406 0.00740635 0.00686661\n", " 0.00657982 0.00638799 0.00599367 0.00588913 0.00564335 0.00540967\n", " 0.00509222 0.00487505 0.00475569 0.00466545 0.00452952 0.00444989\n", " 0.00418255 0.00397506 0.00384542 0.00374919 0.00361013 0.00348522\n", " 0.00336487 0.00320737 0.00315466 0.00309144 0.00293708 0.00286538\n", " 0.00280751 0.00269607 0.00265828 0.00256293 0.00253803 0.00246174\n", " 0.00239712 0.00238735 0.00227555 0.00221498 0.00213916 0.00206082\n", " 0.00202803 0.00195957 0.0019356 0.00188422 0.00186702 0.00181558\n", " 0.00176731 0.0017244 0.00165787 0.00163127 0.00160229 0.00154287\n", " 0.00145995 0.00141934 0.00140863 0.00139564 0.00138477 0.0013513\n", " 0.00131825 0.00129862 0.00128521 0.00123274 0.00121642 0.00117731\n", " 0.00114796 0.00112347 0.00111165 0.00109022 0.00106429 0.00105147\n", " 0.00101502 0.00099917 0.00098879 0.00095485]\n" ] } ], "source": [ "print(pca.explained_variance_ratio_)" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "_cell_guid": "1bd4cec2-d583-f07d-b4a8-694d56c6d460" }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
pixel1pixel2pixel3pixel4pixel5pixel6pixel7pixel8pixel9pixel10...pixel190pixel191pixel192pixel193pixel194pixel195pixel196pixel197pixel198pixel199
10000000000...0000000000
20000000000...0000000000
30000000000...0000000000
40000000000...0000000000
\n", "

4 rows × 199 columns

\n", "
" ], "text/plain": [ " pixel1 pixel2 pixel3 pixel4 pixel5 pixel6 pixel7 pixel8 pixel9 \\\n", "1 0 0 0 0 0 0 0 0 0 \n", "2 0 0 0 0 0 0 0 0 0 \n", "3 0 0 0 0 0 0 0 0 0 \n", "4 0 0 0 0 0 0 0 0 0 \n", "\n", " pixel10 ... pixel190 pixel191 pixel192 pixel193 pixel194 \\\n", "1 0 ... 0 0 0 0 0 \n", "2 0 ... 0 0 0 0 0 \n", "3 0 ... 0 0 0 0 0 \n", "4 0 ... 0 0 0 0 0 \n", "\n", " pixel195 pixel196 pixel197 pixel198 pixel199 \n", "1 0 0 0 0 0 \n", "2 0 0 0 0 0 \n", "3 0 0 0 0 0 \n", "4 0 0 0 0 0 \n", "\n", "[4 rows x 199 columns]" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train_feature.iloc[1:5,1:200]" ] } ], "metadata": { "_change_revision": 71, "_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 }