LRN
File structure
The *.lrn
file contains the input data as tab separated values. Features in columns, datasets in rows. The first column should be a unique integer key. The optional header contains descriptions of the columns.
# comment
#
% n
% m
% s1 s2 .. sm
% var_name1 var_name2 .. var_namem
x11 x12 .. x1m
x21 x22 .. x2m
. . . .
. . . .
xn1 xn2 .. xnm
Element | Description |
---|---|
$n$ | Number of datasets |
$m$ | Number of columns (including index) |
$s_i$ | Type of column: 9 for unique key, 1 for data, 0 to ignore column |
$var\_name_i$ | Name for the i-th feature |
$x_{ij}$ | Elements of the data matrix. Decimal numbers denoted by '.', not by ',' |
Writing and Reading
DataIO.writeLRN
— FunctionwriteLRN(filename::String, lrn::LRNData, directory=pwd())
Write the contents of a LRNData
struct into a file.
DataIO.readLRN
— FunctionreadLRN(filename::String, directory=pwd())
Read the contents of a *.lrn
and return a LRNData
struct.
Types and Constructors
DataIO.LRNData
— TypeLRNData
LRNData
represents the contents of a *.lrn
file with the following fields:
data::Matrix{Float64}
Matrix of data, cases in rows, variables in columns
column_types::Array{LRNCType, 1}
Column types, see
LRNCType
key::Array{Integer, 1}
Unique key for each line
names::Array{String, 1}
Column names
key_name::String
Name for key column
comment::String
Comments about the data
DataIO.LRNData
— MethodLRNData(data::AbstractMatrix{Float64})
Convenience constructor for LRNData
. Uses sensible defaults:
column_types=[9,1,1...]
key=[1,2,3...]
names=["C1","C2","C3"...]
key_name="Key"
comment=""
Missing docstring for LRNCType
. Check Documenter's build log for details.