mirror of
https://github.com/Doctorado-ML/Stree_datasets.git
synced 2025-08-24 03:46:08 +00:00
Commit Inicial
This commit is contained in:
2
data/tanveer/ozone/conxuntos.dat
Executable file
2
data/tanveer/ozone/conxuntos.dat
Executable file
File diff suppressed because one or more lines are too long
8
data/tanveer/ozone/conxuntos_kfold.dat
Executable file
8
data/tanveer/ozone/conxuntos_kfold.dat
Executable file
File diff suppressed because one or more lines are too long
33
data/tanveer/ozone/le_datos.m
Executable file
33
data/tanveer/ozone/le_datos.m
Executable file
@@ -0,0 +1,33 @@
|
||||
printf('lendo problema %s ...\n', problema);
|
||||
|
||||
n_entradas= 72; n_clases= 2; n_fich= 1; fich{1}= 'onehr.data'; n_patrons(1)= 2536;
|
||||
|
||||
n_max= max(n_patrons);
|
||||
x = zeros(n_fich, n_max, n_entradas); cl= zeros(n_fich, n_max);
|
||||
|
||||
n_patrons_total = sum(n_patrons); n_iter=0;
|
||||
|
||||
for i_fich=1:n_fich
|
||||
f=fopen(fich{i_fich}, 'r');
|
||||
if -1==f
|
||||
error('erro en fopen abrindo %s\n', fich{i_fich});
|
||||
end
|
||||
for i=1:n_patrons(i_fich)
|
||||
fprintf(2,'%5.1f%%\r', 100*n_iter++/n_patrons_total);
|
||||
fscanf(f,'%s',1);
|
||||
% printf('%i: ', i)
|
||||
for j = 1:n_entradas
|
||||
t= fscanf(f,'%s',1);
|
||||
if strcmp(t, '?')
|
||||
x(i_fich,i,j) = 0;
|
||||
else
|
||||
x(i_fich,i,j) = str2double(t);
|
||||
end
|
||||
% printf('%g ', x(i_fich,i,j))
|
||||
end
|
||||
cl(i_fich,i) = fscanf(f,'%g',1); % lectura da clase
|
||||
% printf('cl= %i\n', cl(i_fich,i))
|
||||
% if i==2 exit end
|
||||
end
|
||||
fclose(f);
|
||||
end
|
2536
data/tanveer/ozone/onehr.data
Executable file
2536
data/tanveer/ozone/onehr.data
Executable file
File diff suppressed because it is too large
Load Diff
128
data/tanveer/ozone/onehr.names
Executable file
128
data/tanveer/ozone/onehr.names
Executable file
@@ -0,0 +1,128 @@
|
||||
1. Title: Ozone Level Detection
|
||||
|
||||
|
||||
2. Source:
|
||||
|
||||
Kun Zhang
|
||||
zhang.kun05 '@' gmail.com
|
||||
Department of Computer Science,
|
||||
Xavier University of Lousiana
|
||||
|
||||
Wei Fan
|
||||
wei.fan '@' gmail.com
|
||||
IBM T.J.Watson Research
|
||||
|
||||
XiaoJing Yuan
|
||||
xyuan '@' uh.edu
|
||||
Engineering Technology Department,
|
||||
College of Technology, University of Houston
|
||||
|
||||
|
||||
3. Past Usage:
|
||||
|
||||
Forecasting skewed biased stochastic ozone days: analyses, solutions and beyond, Knowledge and Information Systems, Vol. 14, No. 3, 2008.
|
||||
Discusses details about the dataset, its use as well as various experiments (both cross-validation and streaming) using many state-of-the-art methods.
|
||||
|
||||
A shorter version of the paper (does not contain some detailed experiments as the journal paper above) is in:
|
||||
Forecasting Skewed Biased Stochastic Ozone Days: Analyses and Solutions. ICDM 2006: 753-764
|
||||
|
||||
|
||||
4. Relevant Information:
|
||||
|
||||
The following are specifications for several most important attributes
|
||||
that are highly valued by Texas Commission on Environmental Quality (TCEQ).
|
||||
More details can be found in the two relevant papers.
|
||||
|
||||
-- O 3 - Local ozone peak prediction
|
||||
-- Upwind - Upwind ozone background level
|
||||
-- EmFactor - Precursor emissions related factor
|
||||
-- Tmax - Maximum temperature in degrees F
|
||||
-- Tb - Base temperature where net ozone production begins (50 F)
|
||||
-- SRd - Solar radiation total for the day
|
||||
-- WSa - Wind speed near sunrise (using 09-12 UTC forecast mode)
|
||||
-- WSp - Wind speed mid-day (using 15-21 UTC forecast mode)
|
||||
|
||||
|
||||
5. Number of Instances: 2536
|
||||
|
||||
|
||||
6. Number of Attributes: 73
|
||||
|
||||
|
||||
7. Attribute Information:
|
||||
|
||||
1,0 | two classes 1: ozone day, 0: normal day
|
||||
|
||||
Date: ignore.
|
||||
WSR0: continuous.
|
||||
WSR1: continuous.
|
||||
WSR2: continuous.
|
||||
WSR3: continuous.
|
||||
WSR4: continuous.
|
||||
WSR5: continuous.
|
||||
WSR6: continuous.
|
||||
WSR7: continuous.
|
||||
WSR8: continuous.
|
||||
WSR9: continuous.
|
||||
WSR10: continuous.
|
||||
WSR11: continuous.
|
||||
WSR12: continuous.
|
||||
WSR13: continuous.
|
||||
WSR14: continuous.
|
||||
WSR15: continuous.
|
||||
WSR16: continuous.
|
||||
WSR17: continuous.
|
||||
WSR18: continuous.
|
||||
WSR19: continuous.
|
||||
WSR20: continuous.
|
||||
WSR21: continuous.
|
||||
WSR22: continuous.
|
||||
WSR23: continuous.
|
||||
WSR_PK: continuous.
|
||||
WSR_AV: continuous.
|
||||
T0: continuous.
|
||||
T1: continuous.
|
||||
T2: continuous.
|
||||
T3: continuous.
|
||||
T4: continuous.
|
||||
T5: continuous.
|
||||
T6: continuous.
|
||||
T7: continuous.
|
||||
T8: continuous.
|
||||
T9: continuous.
|
||||
T10: continuous.
|
||||
T11: continuous.
|
||||
T12: continuous.
|
||||
T13: continuous.
|
||||
T14: continuous.
|
||||
T15: continuous.
|
||||
T16: continuous.
|
||||
T17: continuous.
|
||||
T18: continuous.
|
||||
T19: continuous.
|
||||
T20: continuous.
|
||||
T21: continuous.
|
||||
T22: continuous.
|
||||
T23: continuous.
|
||||
T_PK: continuous.
|
||||
T_AV: continuous.
|
||||
T85: continuous.
|
||||
RH85: continuous.
|
||||
U85: continuous.
|
||||
V85: continuous.
|
||||
HT85: continuous.
|
||||
T70: continuous.
|
||||
RH70: continuous.
|
||||
U70: continuous.
|
||||
V70: continuous.
|
||||
HT70: continuous.
|
||||
T50: continuous.
|
||||
RH50: continuous.
|
||||
U50: continuous.
|
||||
V50: continuous.
|
||||
HT50: continuous.
|
||||
KI: continuous.
|
||||
TT: continuous.
|
||||
SLP: continuous.
|
||||
SLP_: continuous.
|
||||
Precp: continuous.
|
2611
data/tanveer/ozone/ozone.arff
Executable file
2611
data/tanveer/ozone/ozone.arff
Executable file
File diff suppressed because it is too large
Load Diff
5
data/tanveer/ozone/ozone.cost
Executable file
5
data/tanveer/ozone/ozone.cost
Executable file
@@ -0,0 +1,5 @@
|
||||
% Rows Columns
|
||||
2 2
|
||||
% Matrix elements
|
||||
0.0 1.0
|
||||
1.0 0.0
|
8
data/tanveer/ozone/ozone.txt
Executable file
8
data/tanveer/ozone/ozone.txt
Executable file
@@ -0,0 +1,8 @@
|
||||
n_entradas= 72
|
||||
n_clases= 2
|
||||
n_arquivos= 1
|
||||
fich1= ozone_R.dat
|
||||
n_patrons1= 2536
|
||||
n_patrons_entrena= 1268
|
||||
n_patrons_valida= 1268
|
||||
n_conxuntos= 1
|
2537
data/tanveer/ozone/ozone_R.dat
Executable file
2537
data/tanveer/ozone/ozone_R.dat
Executable file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user