doc: Man page for configuration file addedHEADmain

The only concern I have with this file is having the program version
matching with the actual program, but it is not critical

6 files changed, 186 insertions, 7 deletions

diff --git a/.gitignore b/.gitignore
index 3faff71..3be73ec 100644
--- a/.gitignore
+++ b/.gitignore
@@ -5,7 +5,8 @@ objs/
 doc/*
 !doc/*.pdf
 !doc/*.tex
-!doc/*.1
+!doc/ml.1
+!doc/ml_config.5
 *.gdb
 utils/*.gpi
 *.bin
diff --git a/Makefile b/Makefile
index b8efec3..4d54e2c 100644
--- a/Makefile
+++ b/Makefile
@@ -38,6 +38,7 @@ install: all
 	@#man page
 	install -d $(MANPREFIX)/man1
 	install -m 644 doc/ml.1 $(MANPREFIX)/man1/ml.1
+	install -m 644 doc/ml_config.5 $(MANPREFIX)/man5/ml_config.5
 
 install_config:
 	mkdir -p ~/.config/ml
@@ -46,6 +47,7 @@ install_config:
 uninstall:
 	rm -v $(BINPREFIX)/${BIN}
 	rm -v $(MANPREFIX)/man1/ml.1
+	rm -v $(MANPREFIX)/man5/ml_config.5
 
 man: build
 	help2man -N ./ml -I doc/man.txt > doc/ml.1
diff --git a/doc/ml.1 b/doc/ml.1
index d10de6f..4a9926f 100644
--- a/doc/ml.1
+++ b/doc/ml.1
@@ -1,7 +1,7 @@
 .\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.49.3.
-.TH ML "1" "September 2024" "ml 0.2.0" "User Commands"
+.TH ML "1" "September 2024" "ml 0.5.0" "User Commands"
 .SH NAME
-ml \- manual page for ml 0.2.0
+ml \- manual page for ml 0.5.0
 .SH SYNOPSIS
 .B ml
 [\fI\,re\/\fR]\fI\,train \/\fR[\fI\,Options\/\fR] \fI\,FILE\/\fR
diff --git a/doc/ml_config.5 b/doc/ml_config.5
new file mode 100644
index 0000000..f50d568
--- /dev/null
+++ b/doc/ml_config.5
@@ -0,0 +1,179 @@
+.TH ML_CONFIG "5" "September 2024" "ml 0.5.0" "Configuration file"
+
+.SH NAME
+ml_config - ml configuration file
+
+.SH DESCRIPTION
+.PP
+ml configuration file format consists of lines of key-value options grouped in
+multiple sections as is shown below in the demo configuration file:
+.PP
+
+.EX
+.RS 4
+; comments
+[net]
+loss = square ; options (square)
+epochs = 500 ; comment
+batch = 32
+alpha = 1
+weights_path = utils/weights.bin
+inputs = sepal_length,sepal_width,petal_length,petal_width
+labels = species
+
+
+[categorical_fields]
+species=setosa,versicolor,virginica
+
+[preprocessing]
+onehot=species
+
+
+[layer]
+neurons=10
+; options (relu, sigmoid, softplus, leaky_relu, linear, tanh)
+activation=sigmoid
+
+[outlayer]
+activation = sigmoid
+.RE
+.EE
+
+.SS [net]
+.PP
+In this section you describe general network configurations more specifically
+its training parameter, weights filepath and input and output columns.
+
+.TS
+box nospaces center tab(|);
+L L L
+Lb L L.
+Key | Description | Type
+_
+alpha           | learning rate     | decimal
+loss            | loss function     | option (string)
+epochs          | training epochs   | integer
+batch           | batch size        | integer
+weights_path    | weights filepath  | string
+inputs          | input fields      | list (string)
+labels          | label fields      | list (string)
+.TE
+
+.SS [preprocessing]
+Indicate preprocessing operations for input or label fields
+
+
+.TS
+box nospaces center tab(|);
+L L L
+Lb L L.
+Key | Description | Type
+_
+onehot  | onehot columns | list (string)
+.TE
+
+.PP
+Categorical preprocessing like operations
+.B onehot
+require to have their fields specified in
+.B [categorical_fields].
+otherwise the program will prompt you an error message.
+
+
+.SS [categorical_fields]
+.PP
+This section is kind of special, here you must set the possible values a field
+can take. taking the first example as reference:
+
+.EX
+.RS
+[categorical_fields]
+species=setosa,versicolor,virginica
+.RE
+.EE
+
+the column
+.B species
+can only take the values
+.B setosa,versicolor
+and
+.B virginica,
+if the program encounters a different value it will stop its execution.
+
+.SS [layer]
+.SS [outlayer]
+.PP
+Create a layer component.
+.B [outlayer]
+section does not require
+.B neurons
+parameter.
+.TS
+box nospaces center tab(:);
+L L L
+Lb L L.
+Key : Description : Type
+_
+neurons     :  number of neurons            : integer
+activation  :  activation function          : option (string)
+.TE
+
+.PP
+The topology of the network depends of the order in which
+.B [layer]
+, is put on the file, the program will load each
+.B [layer]
+section sequentially. For instance the following example:
+.PP
+
+.EX
+.RS
+[layer]
+neurons=10
+activation=relu
+
+[layer]
+neurons=20
+activation=sigmoid
+
+[outlayer]
+activation = sigmoid
+.RE
+.EE
+
+will produce a network with the following topology
+.TS
+nospaces center tab(:);
+Lb | Lb
+L | L.
+Activation : Dimension
+_
+ReLu        : in \[mu] 10
+Sigmoid     : 10 \[mu] 20
+outlayers   : 20 \[mu] out
+.TE
+
+.SH FILES
+.PP
+The configuration file is searched in the following order:
+.PP
+.PD 0
+.IP \(bu 4
+CLI filepath
+.IP \(bu 4
+ML_CONFIG_PATH env variable
+.IP \(bu 4 
+$HOME/.\&config/ml/ml.cfg
+.PP
+
+.SH AUTHOR
+Written by jvech
+
+.SH COPYRIGHT
+Copyright \(co 2024  jvech
+
+.PP
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
diff --git a/src/main.c b/src/main.c
index 7918706..6d1d433 100644
--- a/src/main.c
+++ b/src/main.c
@@ -31,9 +31,6 @@
 
 #define MAX_FILE_SIZE 536870912 //1<<29; 0.5 GiB
 
-#define ARRAY_SIZE(x, type) sizeof(x) / sizeof(type)
-
-
 void load_config(struct Configs *cfg, int n_args, ...)
 {
     char *filepath;
diff --git a/src/util.c b/src/util.c
index ad14632..13d963a 100644
--- a/src/util.c
+++ b/src/util.c
@@ -80,7 +80,7 @@ char *e_strdup(const char *s)
 
 void version()
 {
-    printf("ml 0.2.0\n");
+    printf("ml 0.5.0\n");
     printf( "Copyright (C) 2023  jvech\n\n"
             "This program is free software: you can redistribute it and/or modify\n"
             "it under the terms of the GNU General Public License as published by\n"