www.pudn.com > firev0.01.rar > cloogluster.py

#!/usr/bin/python
print "Content-Type: text/html\n\n"
print
print "
"
import cgi
import re
import sys
import traceback
import os
from types import *
sys.stderr=sys.stdout

## Settings
TemplateFile="/u/deselaers/ir/src/cgi/cloogluster.html"
basepath="/u/deselaers/data/google/tn/"
WordList="namelist"
clustertest="ssh ununbium /u/deselaers/ir/src/bin/clustertest"

def Display(Content):
   print """
   
   
   
   
   
   
   
   Warning: This cgi is only for testing purposes and not in any stable state
   """
   print Content
   print """
   """

#    print Content
#    TemplateHandle = open(TemplateFile, "r")  # open in read only mode
    # read the entire file as a string
#    TemplateInput = TemplateHandle.read() 
#    TemplateHandle.close()                    # close the file

    # this defines an exception string in case our
    # template file is messed up
#    BadTemplateException = "There was a problem with the HTML template."
#    SubResult = re.subn("INSERT CONTENT HERE",Content,TemplateInput)
    
 #   if SubResult[1] == 0:
 #       raise BadTemplateException

#    print SubResult[0]

def readList(filename,word):
    output=""
    listHandle=open(filename,"r")
    listInput=listHandle.read()
    listHandle.close()
    output=output+"""
    
    """
    for i in re.split("\n",listInput):
        if(i==word):
            selected=" selected"
        else:
            selected=""
        output=output+""+i+"\n"

    output=output+"WANG db\n"
    output=output+"\n"
    return output


def processParams(listname):
    output=""
    featuresToUse=[]

    if(form.has_key("suffix")):
        field=form["suffix"]
        if type(field) == ListType:
            for subfield in field:
                featuresToUse.append(subfield.value)
        else:
            featuresToUse.append(field.value)

    if(form.has_key("suffixstring")):
        featuresToUse.append(form["suffixstring"].value)
        
    if(form.has_key("poolMode")):
        poolMode=form["poolMode"].value
    else:
        poolMode="noPooling"

    if(form.has_key("disturbMode")):
        disturbMode=form["disturbMode"].value
    else:
        disturbMode="varianceDisturb"

    if(form.has_key("algorithm")):
        algorithm=form["algorithm"].value
    else:
        algorithm="kmeans"
    
    if(form.has_key("iterations")):
        iterations=form["iterations"].value
    else:
        iterations="10"

    if(form.has_key("clusters")):
        clusters=form["clusters"].value
    else:
        clusters="10"

    if(form.has_key("maxSplits")):
        maxSplits=form["maxSplits"].value
    else:
        maxSplits="10"

    if(form.has_key("iterBetween")):
        iterBetween=form["iterBetween"].value
    else:
        iterBetween="10"

    if(form.has_key("minObs")):
        minObs=form["minObs"].value
    else:
        minObs="4"

    if(form.has_key("epsilon")):
        epsilon=form["epsilon"].value
    else:
        epsilon="0.001"

    if(form.has_key("word")):
        word=form["word"].value
    else:
        word=""
        
    if(form.has_key("distance")):
        distance=form["distance"].value
    else:
        distance=""

    output=output+"
\n"
    output=output+"\n"
    output=output+""
    
    output=output+"\n"
    output=output+"\n"
    output=output+"\n"

    output=output+"\n"
    output=output+"\n"
    output=output+"\n"
    output=output+"\n"
    output=output+"\n"

    output=output+"\n"


    output=output+"\n\n"
    output=output+"\n\n"
    output=output+""
    output=output+"
Algorithm
"
    output=output+""
    for i in ["kmeans","em"]:
        if i==algorithm:
            selected=" selected"
        else:
            selected=""
        output=output+""+i+""
    output=output+"
kMeans Parameters
Iterations
Clusters
EM Parameters
maxSplits
Iterations between Splits
minObs
epsilon
poolMode
"
    for i in ["noPooling","clusterPooling","dimensionPooling","bothPooling"]:
        if i==poolMode:
            selected=" selected"
        else:
            selected=""
        output=output+""+i+""
    output=output+""

    output=output+"
disturbMode
"
    for i in ["constDisturb","meanDisturb","varianceDisturb","meanDisturb2"]:
        if i==disturbMode:
            selected=" selected"
        else:
            selected=""
        output=output+""+i+""
    output=output+""

    output=output+"
General Parameters
Distance
"
    for i in ["euclidean","jsd","kld","chisquare","his"]:
        if i==distance:
            selected=" selected"
        else:
            selected=""
        output=output+""+i+""
    output=output+""



    output=output+"
Word
"
    output=output+readList(listname,word)
    output=output+"
Features
(selecting none selects all available)
\n"
    for suffix in [".rgbfeat.gz", ".tamurafeature.gz", ".X40X08-rgbfeat.gz" ]:
        output=output+"
"+suffix+"
\n"
    output=output+""
    output=output+"
"
    output=output+"
\n"
    output=output+"
\n"
    cmdline=""
    if len(word) >0:
        if word[0]=="/":
            cmdline=" -rgb "+word+" -c "+algorithm+" -d "+distance
        else:
            cmdline=" -rgb "+basepath+word+"/list -c "+algorithm+" -d "+distance
    
    if len(featuresToUse)!=0:
            features=reduce(lambda x,y: x+":"+y,featuresToUse)
            cmdline=cmdline+" -suffix="+features
            
    if(algorithm=="em"):
        cmdline=cmdline+" -maxSplits "+maxSplits+" -iter "+iterBetween+" -minObs "+minObs+" -epsilon "+epsilon
    else:
        cmdline=cmdline+" -iterations "+iterations+" -nOfClusters "+clusters
    return output,cmdline

def clustering(params):
    output=""
    output=output+"Clustering with params: "+params
    cmdline=clustertest+" "+params
    #    print cmdline
    clusterInfo=""

    
    clusterHandle=os.popen(cmdline)

    clusterInfo=clusterHandle.read()
    clusterHandle.close()



    output=output+"\n
0:
"
    oldcluster=""
    
    for line in re.split("\n",clusterInfo):
        if(re.search("^.1.",line)):
           lineList=re.split("[ ]*",line)
           if(lineList[2]=="clustermember"):
#               print lineList
               no=lineList[3]
               cluster=lineList[4]
               filename=lineList[5]
#               print cluster
#              print oldcluster
        
               if cluster != oldcluster:
                   if oldcluster != "":
                       output=output+"
\n\n"
                       output=output+"\n\n\n"
                   oldcluster=cluster
                           
                           #               output=output+"\n\n"
               filename=re.sub("\.X.*rgbfeat","",filename)
               filename=re.sub("\.rgbfeat","",filename)
               filename=re.sub(".gz","",filename)
               output=output+"\n"

    output=output+"\n
"+cluster+"
"+no+"
"+cluster+"
\n\n"

    output=output+"
 Shell output from "+cmdline+"
"
    output=output+"
\n"+clusterInfo+"\n
\n"

    return output

form=cgi.FieldStorage()

paramForm,cmdline=processParams(basepath+WordList)

clusterresult=""
if  form.has_key("word"):
    if(form["word"] != ""):
        clusterresult=clustering(cmdline)

print "
"
    
Display(paramForm+clusterresult)