import?java.io.File;
import?java.io.FileInputStream;
import?java.io.FileNotFoundException;
import?java.util.ArrayList;
import?java.util.List;
import?java.util.Scanner;

/**
?*?Created?with?IntelliJ?IDEA.
?*?User:?Wangyu
?*?Date:?10/13/16
?*?Time:?16:28?
?*?將從文本讀入的數據進行結構化處理
?*?
?*/
public?class?DataSet?{

????public?static?List?readDataSet（String?file）?throws?FileNotFoundException?{
????????List?dataset?=?new?ArrayList（）;
????????Scanner?scanner?=?new?Scanner（new?File（file））;
????????//按行讀入
????????while（scanner.hasNextLine（））?{
????????????String?line?=?scanner.nextLine（）;
????????????//第一行用于說明，不讀取
????????????if?（line.startsWith（“#“））?{
????????????????continue;
????????????}
????????????//String[]?columns?=?line.split（“\\s+“）;
????????????String[]?columns?=?line.split（““）;//用逗號分割字符串
????????????//?skip?first?column?and?last?column?is?the?label
????????????/*int?i?=?1;
????????????double[]?data?=?new?double[columns.length-2];
????????????for?（i=1;?i????????????int?i?=?0;//前面是數據，最后一列是標簽
????????????double?[]?data?=?new?double?[columns.length?-?1];
????????????for（i?=?0;i?????????????????//data[i-1]?=?Integer.parseInt（columns[i]）;
????????????	data[i]?=?Double.parseDouble（columns[i]）;//將字符串轉換成double
????????????}
????????????//int?label?=?Integer.parseInt（columns[i]）;
????????????int?label?=?Integer.parseInt（columns[columns.length-1]）;//將最后一列的標簽轉換成整數
????????????Instance?instance?=?new?Instance（label?data）;
????????????dataset.add（instance）;
????????}
????????return?dataset;
????}
}

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2016-10-14?11:52??LogRegression\
?????文件?????????301??2016-10-13?14:12??LogRegression\.classpath
?????文件?????????389??2016-10-13?14:12??LogRegression\.project
?????目錄???????????0??2016-10-14?11:52??LogRegression\.settings\
?????文件?????????598??2016-10-13?14:12??LogRegression\.settings\org.eclipse.jdt.core.prefs
?????文件??????????96??2012-06-28?09:53??LogRegression\README.md
?????目錄???????????0??2016-10-14?11:52??LogRegression\bin\
?????文件????????1677??2016-10-13?16:54??LogRegression\bin\DataSet.class
?????文件?????????510??2016-10-13?16:54??LogRegression\bin\Instance.class
?????文件????????2883??2016-10-13?17:10??LogRegression\bin\Logistic.class
?????文件????????1015??2016-10-13?14:55??LogRegression\bin\iris.txt
?????文件????????1011??2016-10-13?16:32??LogRegression\iris.txt
?????目錄???????????0??2016-10-14?11:52??LogRegression\src\
?????文件????????1736??2016-10-13?16:54??LogRegression\src\DataSet.java
?????文件?????????445??2016-10-13?16:54??LogRegression\src\Instance.java
?????文件????????2889??2016-10-13?17:10??LogRegression\src\Logistic.java
?????文件????????1015??2016-10-13?14:55??LogRegression\src\iris.txt