[LON-CAPA-cvs] cvs: modules /gerd/harvesting seq_taxonomy.pl taxonomy.dat

[www]

www		Fri Sep  9 02:44:17 2011 EDT

  Added files:                 
    /modules/gerd/harvesting	seq_taxonomy.pl taxonomy.dat 
  Log:
  Work in progress: classification of assignments
  
  

Index: modules/gerd/harvesting/seq_taxonomy.pl
+++ modules/gerd/harvesting/seq_taxonomy.pl
use strict;

my @cats=();
my @iss=();
my @isnots=();
my @equivs=();
my %catidx=();
open(IN,'taxonomy.dat');
my $i=0;
while (my $line=<IN>) {
   chomp($line);
   my ($cat,$is,$isnot,$equiv)=split(/\t/,$line);
   $cats[$i]=$cat;
   $iss[$i]=$is;
   $isnots[$i]=$isnot;
   if ($equiv=~/\w/) {
      $iss[$i]=$iss[$catidx{$equiv}];
      $isnots[$i]=$isnots[$catidx{$equiv}];
   }
   $catidx{$cat}=$i;
   print $i." ".$cat."\n";
   $i++;
}
close(IN);

my $j=0;
open(IN,'seq_subj_keyw.dat');
while (my $line=<IN>) {
   chomp($line);
   my ($seq,$subs,$keys)=split(/\t/,$line);

   print "-------$subs $keys\n";

   my %keysw=();
   foreach my $keyc (split(/\,/,$keys)) {
      my ($key,$cnt)=split(/\:/,$keyc);
      $keysw{$key}=$cnt;
   }
   my %successes=();
   foreach my $subc (split(/\,/,$subs)) {
      my ($sub,$cnt)=split(/\:/,$subc);
      for (my $i=0;$i<=$#cats;$i++) {
          if ($cats[$i]=~/^$sub\:/) {
             my $totalcount=0;
             foreach my $snot (split(/\,/,$isnots[$i])) {
                 $totalcount-=$keysw{$snot};
             }
             foreach my $sbe (split(/\,/,$iss[$i])) {
                 $totalcount+=$keysw{$sbe};
             }
             if ($totalcount>=$cnt/4.) {
                $successes{$cats[$i]}=$totalcount; 
             }
          } 
      }
   }
   my $max=0;
   my $winner='';
   foreach my $suc (keys(%successes)) {
      if ($successes{$suc}>$max) {
         $max=$successes{$suc};
         $winner=$suc;
      }
   }
   print "Winner: $winner\n";
   $j++;
   if ($j>200) {last;}
}
close(IN);

Index: modules/gerd/harvesting/taxonomy.dat
+++ modules/gerd/harvesting/taxonomy.dat
physics:introduction:mathematics	vector,vectors,derivative,integral	energy,momentum,force,wave
physics:introduction:units	unit,measurement,system	energy,momentum
physics:mechanics:linearkinematics	speed,velocity,acceleration,distance,displacement,position	angular,angle,force,work,atom,quantum,momentum,inertia
physics:mechanics:rotationalkinematics	angular,speed,velocity,acceleration,angle	work,force,torque,atom,quantum	
physics:mechanics:lineardynamics	force,acceleration,mass,newton	torque,angle,angular,charge,magnetic,atom,quantum,work
physics:mechanics:rotationaldynamics	torque,angular,acceleration,inertia	atom,quantum,momentum
physics:mechanics:linearmomentum	momentum,velocity,mass,collision,collisions,elastic,inelastic	angular,atom,quantum
physics:mechanics:angularmomentum	momentum,velocity,angular,inertia	atom,quantum
physics:mechanics:energy	energy,force,distance,work,potential,kinetic,gravitational,gravity	entropy,charge,atom,quantum,electric
physics:mechanics:oscillation	period,frequency,resonance,amplitude,harmonic,spring	wavelength,current
physics:mechanics:wave	period,frequency,wavelength,speed	sound,doppler
physics:mechanics:sound	sound,frequency,wavelength,speed,doppler,pressure,air,hear,water,longitudinal	magnetic,electric,field
physics:thermodynamics	energy,work,pressure,temperature,gas,ideal,entropy,gas,volume
physics:electromagnetism:electrostatics	electric,charge,coulomb,coulombs,field	magnet,capacitor
physics:electromagnetism:potentials	voltage,potential,field	current,ampere,amperes
physics:electromagnetism:capacitance	capacitance,capacitor,charge,plate,farad
physics:electromagnetism:magnetism	magnetic,current,ampere,amperes,field,magnet,solenoid	wave,quantum
physics:electromagnetism:inductance	magnetic,induction,inductance,coil,mutual,loop,emf
physics:electromagnetism:dccircuits	current,battery,voltage,potential,voltage,resistor,resistance,ampere,resistor	frequency,phase,resonance
physics:electromagnetism:accircuits	current,voltage,frequency,resonance,phase,ac,oscillator,inductor,inductance,resistor,resistance,capacitor,capacitance	pressure,sound,air,wave
physics:electromagnetism:emwaves	magnetic,electric,field,speed,wavelength,frequency,amplitude,color,pressure,radiation,intensity	lens,interference,sound,air,emf
physics:optics:mirrorslenses	light,lens,mirror,lenses,mirrors,focal,concave,convex,virtual,ray,reflection,diffraction
physics:optics:opticalinstruments	telescope,microscope,glasses
physics:optics:interference	slit,pattern,diffraction,interference	quantum
physics:modern:relativity	frame,relative,dilation,contraction,time,space,transform,light,observer,speed
physics:modern:quantum	spin,quantum,level,energy,atom,atoms,electron,electrons,wave,state,states,line	isotope,nuclear,neutron,neutrons
physics:modern:nuclear	nucleus,proton,neutron,decay,halflife,atoms,atomic,protons,neutrons,isotope,radioactive,beta,gamma,activity,nuclear,mass,radiation
chemistry:atomsmolecules:nuclear			physics:modern:nuclear
chemistry:atomsmolecules:shell			physics:modern:quantum
chemistry:atomsmolecules:binding	binding,covalent,bond,bonding,ionic
chemistry:thermodynamics			physics:thermodynamics
chemistry:phases:transitions	phase,temperature,liquid,gas,solid,molecule,pressure
chemistry:phases:solid		crystal,solid,structure,lattice
statistics:descriptive:means	mean,standard,deviation,value,proability,number,measure,measurement,median,formula
mathematics:functions:trigonometric	function,functions,cosine,sine,tangent,sin,cos,period,pi
mathematics:functions:exponential	function,functions,exponent,exponential,power
mathematics:functions:logarithmic	function,functions,logarithm,logarithmic,hyperbolic
mathematics:functions:extrema		function,minimum,maximum,minima,maxima,extrema,local,global,derivative