Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
tianlh
LightGBM-DCU
Commits
63b122ca
Commit
63b122ca
authored
Nov 09, 2016
by
Guolin Ke
Browse files
fix array index cross when met unknown features indices.
parent
4a451b89
Changes
2
Show whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
6 additions
and
1 deletion
+6
-1
include/LightGBM/dataset.h
include/LightGBM/dataset.h
+3
-1
src/io/dataset_loader.cpp
src/io/dataset_loader.cpp
+3
-0
No files found.
include/LightGBM/dataset.h
View file @
63b122ca
...
@@ -249,7 +249,7 @@ public:
...
@@ -249,7 +249,7 @@ public:
~
Dataset
();
~
Dataset
();
inline
void
PushOneRow
(
int
tid
,
data_size_t
row_idx
,
const
std
::
vector
<
double
>&
feature_values
)
{
inline
void
PushOneRow
(
int
tid
,
data_size_t
row_idx
,
const
std
::
vector
<
double
>&
feature_values
)
{
for
(
size_t
i
=
0
;
i
<
feature_values
.
size
();
++
i
)
{
for
(
size_t
i
=
0
;
i
<
feature_values
.
size
()
&&
i
<
num_total_features_
;
++
i
)
{
int
feature_idx
=
used_feature_map_
[
i
];
int
feature_idx
=
used_feature_map_
[
i
];
if
(
feature_idx
>=
0
)
{
if
(
feature_idx
>=
0
)
{
features_
[
feature_idx
]
->
PushData
(
tid
,
row_idx
,
feature_values
[
i
]);
features_
[
feature_idx
]
->
PushData
(
tid
,
row_idx
,
feature_values
[
i
]);
...
@@ -259,6 +259,7 @@ public:
...
@@ -259,6 +259,7 @@ public:
inline
void
PushOneRow
(
int
tid
,
data_size_t
row_idx
,
const
std
::
vector
<
std
::
pair
<
int
,
double
>>&
feature_values
)
{
inline
void
PushOneRow
(
int
tid
,
data_size_t
row_idx
,
const
std
::
vector
<
std
::
pair
<
int
,
double
>>&
feature_values
)
{
for
(
auto
&
inner_data
:
feature_values
)
{
for
(
auto
&
inner_data
:
feature_values
)
{
if
(
inner_data
.
first
>=
num_total_features_
)
{
continue
;
}
int
feature_idx
=
used_feature_map_
[
inner_data
.
first
];
int
feature_idx
=
used_feature_map_
[
inner_data
.
first
];
if
(
feature_idx
>=
0
)
{
if
(
feature_idx
>=
0
)
{
features_
[
feature_idx
]
->
PushData
(
tid
,
row_idx
,
inner_data
.
second
);
features_
[
feature_idx
]
->
PushData
(
tid
,
row_idx
,
inner_data
.
second
);
...
@@ -267,6 +268,7 @@ public:
...
@@ -267,6 +268,7 @@ public:
}
}
inline
void
PushOneColumn
(
int
tid
,
data_size_t
col_idx
,
const
std
::
vector
<
std
::
pair
<
int
,
double
>>&
feature_values
)
{
inline
void
PushOneColumn
(
int
tid
,
data_size_t
col_idx
,
const
std
::
vector
<
std
::
pair
<
int
,
double
>>&
feature_values
)
{
if
(
col_idx
>=
num_total_features_
)
{
return
;
}
int
feature_idx
=
used_feature_map_
[
col_idx
];
int
feature_idx
=
used_feature_map_
[
col_idx
];
if
(
feature_idx
>=
0
)
{
if
(
feature_idx
>=
0
)
{
for
(
auto
&
inner_data
:
feature_values
)
{
for
(
auto
&
inner_data
:
feature_values
)
{
...
...
src/io/dataset_loader.cpp
View file @
63b122ca
...
@@ -729,6 +729,7 @@ void DatasetLoader::ExtractFeaturesFromMemory(std::vector<std::string>& text_dat
...
@@ -729,6 +729,7 @@ void DatasetLoader::ExtractFeaturesFromMemory(std::vector<std::string>& text_dat
// text_reader_->Lines()[i].shrink_to_fit();
// text_reader_->Lines()[i].shrink_to_fit();
// push data
// push data
for
(
auto
&
inner_data
:
oneline_features
)
{
for
(
auto
&
inner_data
:
oneline_features
)
{
if
(
inner_data
.
first
>=
dataset
->
num_total_features_
)
{
continue
;
}
int
feature_idx
=
dataset
->
used_feature_map_
[
inner_data
.
first
];
int
feature_idx
=
dataset
->
used_feature_map_
[
inner_data
.
first
];
if
(
feature_idx
>=
0
)
{
if
(
feature_idx
>=
0
)
{
// if is used feature
// if is used feature
...
@@ -764,6 +765,7 @@ void DatasetLoader::ExtractFeaturesFromMemory(std::vector<std::string>& text_dat
...
@@ -764,6 +765,7 @@ void DatasetLoader::ExtractFeaturesFromMemory(std::vector<std::string>& text_dat
// text_reader_->Lines()[i].shrink_to_fit();
// text_reader_->Lines()[i].shrink_to_fit();
// push data
// push data
for
(
auto
&
inner_data
:
oneline_features
)
{
for
(
auto
&
inner_data
:
oneline_features
)
{
if
(
inner_data
.
first
>=
dataset
->
num_total_features_
)
{
continue
;
}
int
feature_idx
=
dataset
->
used_feature_map_
[
inner_data
.
first
];
int
feature_idx
=
dataset
->
used_feature_map_
[
inner_data
.
first
];
if
(
feature_idx
>=
0
)
{
if
(
feature_idx
>=
0
)
{
// if is used feature
// if is used feature
...
@@ -814,6 +816,7 @@ void DatasetLoader::ExtractFeaturesFromFile(const char* filename, const Parser*
...
@@ -814,6 +816,7 @@ void DatasetLoader::ExtractFeaturesFromFile(const char* filename, const Parser*
dataset
->
metadata_
.
SetLabelAt
(
start_idx
+
i
,
static_cast
<
float
>
(
tmp_label
));
dataset
->
metadata_
.
SetLabelAt
(
start_idx
+
i
,
static_cast
<
float
>
(
tmp_label
));
// push data
// push data
for
(
auto
&
inner_data
:
oneline_features
)
{
for
(
auto
&
inner_data
:
oneline_features
)
{
if
(
inner_data
.
first
>=
dataset
->
num_total_features_
)
{
continue
;
}
int
feature_idx
=
dataset
->
used_feature_map_
[
inner_data
.
first
];
int
feature_idx
=
dataset
->
used_feature_map_
[
inner_data
.
first
];
if
(
feature_idx
>=
0
)
{
if
(
feature_idx
>=
0
)
{
// if is used feature
// if is used feature
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment