Commit Inicial

data/tanveer/spambase/le_datos.m

@@ -0,0 +1,23 @@
+printf('lendo problema %s ...\n', problema);
+
+n_entradas= 57; n_clases= 2; n_fich= 1; fich{1}= 'spambase.data'; n_patrons(1)= 4601;
+
+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);
+	for j = 1:n_entradas
+	  x(i_fich,i,j) = fscanf(f,'%g',1);
+	end	
+	cl(i_fich,i) = fscanf(f,'%i',1);  	% lectura da clase
+  end
+  fclose(f);
+end

data/tanveer/spambase/spambase.cost

@@ -0,0 +1,5 @@
+% Rows	Columns
+2	2
+% Matrix elements
+ 0.0	 1.0	
+ 1.0	 0.0	

data/tanveer/spambase/spambase.names

@@ -0,0 +1,90 @@
+| SPAM E-MAIL DATABASE ATTRIBUTES (in .names format)
+|
+| 48 continuous real [0,100] attributes of type word_freq_WORD 
+| = percentage of words in the e-mail that match WORD,
+| i.e. 100 * (number of times the WORD appears in the e-mail) / 
+| total number of words in e-mail.  A "word" in this case is any 
+| string of alphanumeric characters bounded by non-alphanumeric 
+| characters or end-of-string.
+|
+| 6 continuous real [0,100] attributes of type char_freq_CHAR
+| = percentage of characters in the e-mail that match CHAR,
+| i.e. 100 * (number of CHAR occurences) / total characters in e-mail
+|
+| 1 continuous real [1,...] attribute of type capital_run_length_average
+| = average length of uninterrupted sequences of capital letters
+|
+| 1 continuous integer [1,...] attribute of type capital_run_length_longest
+| = length of longest uninterrupted sequence of capital letters
+|
+| 1 continuous integer [1,...] attribute of type capital_run_length_total
+| = sum of length of uninterrupted sequences of capital letters
+| = total number of capital letters in the e-mail
+|
+| 1 nominal {0,1} class attribute of type spam
+| = denotes whether the e-mail was considered spam (1) or not (0), 
+| i.e. unsolicited commercial e-mail.  
+|
+| For more information, see file 'spambase.DOCUMENTATION' at the
+| UCI Machine Learning Repository: http://www.ics.uci.edu/~mlearn/MLRepository.html
+
+
+1, 0.    | spam, non-spam classes
+
+word_freq_make:         continuous.
+word_freq_address:      continuous.
+word_freq_all:          continuous.
+word_freq_3d:           continuous.
+word_freq_our:          continuous.
+word_freq_over:         continuous.
+word_freq_remove:       continuous.
+word_freq_internet:     continuous.
+word_freq_order:        continuous.
+word_freq_mail:         continuous.
+word_freq_receive:      continuous.
+word_freq_will:         continuous.
+word_freq_people:       continuous.
+word_freq_report:       continuous.
+word_freq_addresses:    continuous.
+word_freq_free:         continuous.
+word_freq_business:     continuous.
+word_freq_email:        continuous.
+word_freq_you:          continuous.
+word_freq_credit:       continuous.
+word_freq_your:         continuous.
+word_freq_font:         continuous.
+word_freq_000:          continuous.
+word_freq_money:        continuous.
+word_freq_hp:           continuous.
+word_freq_hpl:          continuous.
+word_freq_george:       continuous.
+word_freq_650:          continuous.
+word_freq_lab:          continuous.
+word_freq_labs:         continuous.
+word_freq_telnet:       continuous.
+word_freq_857:          continuous.
+word_freq_data:         continuous.
+word_freq_415:          continuous.
+word_freq_85:           continuous.
+word_freq_technology:   continuous.
+word_freq_1999:         continuous.
+word_freq_parts:        continuous.
+word_freq_pm:           continuous.
+word_freq_direct:       continuous.
+word_freq_cs:           continuous.
+word_freq_meeting:      continuous.
+word_freq_original:     continuous.
+word_freq_project:      continuous.
+word_freq_re:           continuous.
+word_freq_edu:          continuous.
+word_freq_table:        continuous.
+word_freq_conference:   continuous.
+char_freq_;:            continuous.
+char_freq_(:            continuous.
+char_freq_[:            continuous.
+char_freq_!:            continuous.
+char_freq_$:            continuous.
+char_freq_#:            continuous.
+capital_run_length_average: continuous.
+capital_run_length_longest: continuous.
+capital_run_length_total:   continuous.

data/tanveer/spambase/spambase.txt

@@ -0,0 +1,8 @@
+n_entradas= 57
+n_clases= 2
+n_arquivos= 1
+fich1= spambase_R.dat
+n_patrons1= 4601
+n_patrons_entrena= 2301
+n_patrons_valida= 2300
+n_conxuntos= 1