📄 page_139.html
字号:
<HTML> <HEAD> <!--SCRIPT LANGUAGE="JavaScript" SRC="http://a1835.g.akamai.net/f/1835/276/3h/www.netlibrary.com/include/js/dictionary_library.js"></SCRIPT> <SCRIPT LANGUAGE="JavaScript"> if (!opener){document.onkeyup=parent.turnBookPage;} </SCRIPT!--> <META HTTP-EQUIV="Cache-Control" CONTENT="no-cache"> <META HTTP-EQUIV="Pragma" CONTENT="no-cache"> <META HTTP-EQUIV="Expires" CONTENT="-1"><META http-equiv="Content-Type" content="text/html; charset=windows-1252"><SCRIPT>var PrevPage="Page_138";var NextPage="Page_140";var CurPage="Page_139";var PageOrder="149";</SCRIPT> <TITLE>Document</TITLE> </HEAD> <BODY BGCOLOR="#FFFFFF"><CENTER><TABLE BORDER=0 WIDTH=100% CELLPADDING=0><TR><TD ALIGN=CENTER> <TABLE BORDER=0 CELLPADDING=2 CELLSPACING=0 WIDTH=100%> <TR> <TD ALIGN=LEFT><A HREF='Page_138.html'>Previous</A></TD> <TD ALIGN=RIGHT><A HREF='Page_140.html'>Next</A></TD> </TR> </TABLE></TD></TR><TR><TD ALIGN=LEFT><P><A NAME='JUMPDEST_Page_139'/><A NAME='{4B8}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0 WIDTH='100%'><TR><TD ALIGN=RIGHT><FONT FACE='Times New Roman, Times, Serif' SIZE=2 COLOR=#FF0000>Page 139</FONT></TD></TR></TABLE><A NAME='{4B9}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3>some form of visualization aid, such as histogram of errors by business graphs, or can its market segments be mapped to geographic maps? Is the tool designed to work on a desktop or in a client/server environment? Size is not a true measurement of the complexity it can handle—quite simply the only thing a tool's architecture may indicate is the amount of data it can process and not the complexity it can mine.</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{4BA}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3><B><I>Solutions</I></B></FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{4BB}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3>A data mining tool should help you understand the results of its analysis by providing simple yet exact measurements, such as predicted error rates, level of significance, and/or rate of accuracy. What kind of output (solutions) does the tool generate: decision tree, C code, IF/THEN rules, narrative reports, graphs, visualization, SQL syntax? Some tools produce results that are relatively easy to interpret, such as decision trees that can be expressed as rules. Other tools, such as a back-propagation neural network, may make good predictions but may be difficult to understand. Ideally, both understanding and accuracy should be balanced in the format of the tool's solution.</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{4BC}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3>The tool should also incorporate adequate instruments to allow the user to perform a sensitivity analysis on its output results. Does the tool include some interface for exporting the results of its models to other visualization or OLAP tools? What kind of GUI is provided for model building? Does the tool provide an API, which can be used embedded in a production system, in C, Visual Basic, or PowerBuilder?</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{4BD}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3><B><I>Preprocessing</I></B></FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{4BE}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD><FONT FACE='Times New Roman, Times, Serif' SIZE=3>Preparing the data for analysis is one of the most time-consuming aspects of data mining. Your web server log files generally are comma-delimited, so the tool you select should be able to read this format without difficulty. Your forms database is most likely housed in some relational database, which again your tool should be able to connect to. Any special features a tool can perform to ease this process will greatly expedite the development of knowledge extraction and the construction of your predictive models. Some preprocessing functions to consider in evaluating a tool should include its ability to do some of the following:</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{4BF}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD><FONT FACE='Symbol' SIZE=3>·</FONT><FONT FACE='Times New Roman, Times, Serif' SIZE=3> data cleaning</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{4C0}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD><FONT FACE='Symbol' SIZE=3>·</FONT><FONT FACE='Times New Roman, Times, Serif' SIZE=3> data selection</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{4C1}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD><FONT FACE='Symbol' SIZE=3>·</FONT><FONT FACE='Times New Roman, Times, Serif' SIZE=3> data description</FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{4C2}'/><TABLE BORDER=0 CELLSPACING=0 CELLPADDING=0><TR> <TD ROWSPAN=5></TD> <TD COLSPAN=3 HEIGHT=12></TD> <TD ROWSPAN=5></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR><TD></TD> <TD><FONT FACE='Symbol' SIZE=3>·</FONT><FONT FACE='Times New Roman, Times, Serif' SIZE=3> data transformation</FONT><FONT FACE='Times New Roman, Times, Serif' SIZE=3 COLOR=#FFFF00><!-- break --></FONT></TD><TD></TD></TR><TR> <TD COLSPAN=3></TD></TR><TR> <TD COLSPAN=3 HEIGHT=1></TD></TR></TABLE><A NAME='{4C3}'/></FORM></P></TD></TR></TABLE><P><FONT SIZE=0 COLOR=WHITE></CENTER><A NAME="bottom"> </A><!-- netLibrary.com Copyright Notice --> </BODY></HTML>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -