Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Make JSON the default full serialization format. (#6027)

Browse Source
This commit is contained in:
Jiaming Yuan
2020-08-19 09:57:43 +08:00
committed by GitHub
parent f58e41bad8
commit 90355b4f00
3 changed files with 8 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/xgboost/generic_parameters.h
View File

@@ -27,7 +27,7 @@ struct GenericParameter : public XGBoostParameter<GenericParameter> {
int gpu_id;
// gpu page size in external memory mode, 0 means using the default.
size_t gpu_page_size;
bool enable_experimental_json_serialization {false};
bool enable_experimental_json_serialization {true};
bool validate_parameters {false};
void CheckDeprecated() {
@@ -68,7 +68,7 @@ struct GenericParameter : public XGBoostParameter<GenericParameter> {
.set_lower_bound(0)
.describe("GPU page size when running in external memory mode.");
DMLC_DECLARE_FIELD(enable_experimental_json_serialization)
.set_default(false)
.set_default(true)
.describe("Enable using JSON for memory serialization (Python Pickle, "
"rabit checkpoints etc.).");
DMLC_DECLARE_FIELD(validate_parameters)

38
tests/cpp/test_serialization.cc
View File

@@ -179,7 +179,6 @@ TEST_F(SerializationTest, Exact) {
{"nthread", "1"},
{"base_score", "3.14195265"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "exact"}},
fmap_, p_dmat_);
@@ -189,7 +188,6 @@ TEST_F(SerializationTest, Exact) {
{"base_score", "3.14195265"},
{"max_depth", "2"},
{"num_parallel_tree", "4"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "exact"}},
fmap_, p_dmat_);
@@ -198,7 +196,6 @@ TEST_F(SerializationTest, Exact) {
{"nthread", "1"},
{"base_score", "3.14195265"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "exact"}},
fmap_, p_dmat_);
}
@@ -208,7 +205,6 @@ TEST_F(SerializationTest, Approx) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "approx"}},
fmap_, p_dmat_);
@@ -217,7 +213,6 @@ TEST_F(SerializationTest, Approx) {
{"nthread", "1"},
{"max_depth", "2"},
{"num_parallel_tree", "4"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "approx"}},
fmap_, p_dmat_);
@@ -225,7 +220,6 @@ TEST_F(SerializationTest, Approx) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "approx"}},
fmap_, p_dmat_);
}
@@ -235,7 +229,6 @@ TEST_F(SerializationTest, Hist) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "hist"}},
fmap_, p_dmat_);
@@ -244,7 +237,6 @@ TEST_F(SerializationTest, Hist) {
{"nthread", "1"},
{"max_depth", "2"},
{"num_parallel_tree", "4"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "hist"}},
fmap_, p_dmat_);
@@ -252,7 +244,6 @@ TEST_F(SerializationTest, Hist) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "hist"}},
fmap_, p_dmat_);
}
@@ -261,7 +252,6 @@ TEST_F(SerializationTest, CPUCoordDescent) {
TestLearnerSerialization({{"booster", "gblinear"},
{"seed", "0"},
{"nthread", "1"},
{"enable_experimental_json_serialization", "1"},
{"updater", "coord_descent"}},
fmap_, p_dmat_);
}
@@ -270,7 +260,6 @@ TEST_F(SerializationTest, CPUCoordDescent) {
TEST_F(SerializationTest, GpuHist) {
TestLearnerSerialization({{"booster", "gbtree"},
{"seed", "0"},
{"enable_experimental_json_serialization", "1"},
{"nthread", "1"},
{"max_depth", "2"},
{"tree_method", "gpu_hist"}},
@@ -278,7 +267,6 @@ TEST_F(SerializationTest, GpuHist) {
TestLearnerSerialization({{"booster", "gbtree"},
{"seed", "0"},
{"enable_experimental_json_serialization", "1"},
{"nthread", "1"},
{"max_depth", "2"},
{"num_parallel_tree", "4"},
@@ -287,7 +275,6 @@ TEST_F(SerializationTest, GpuHist) {
TestLearnerSerialization({{"booster", "dart"},
{"seed", "0"},
{"enable_experimental_json_serialization", "1"},
{"nthread", "1"},
{"max_depth", "2"},
{"tree_method", "gpu_hist"}},
@@ -345,7 +332,6 @@ TEST_F(SerializationTest, GPUCoordDescent) {
TestLearnerSerialization({{"booster", "gblinear"},
{"seed", "0"},
{"nthread", "1"},
{"enable_experimental_json_serialization", "1"},
{"updater", "gpu_coord_descent"}},
fmap_, p_dmat_);
}
@@ -380,7 +366,6 @@ TEST_F(LogitSerializationTest, Exact) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "exact"}},
fmap_, p_dmat_);
@@ -389,7 +374,6 @@ TEST_F(LogitSerializationTest, Exact) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "exact"}},
fmap_, p_dmat_);
}
@@ -400,7 +384,6 @@ TEST_F(LogitSerializationTest, Approx) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "approx"}},
fmap_, p_dmat_);
@@ -409,7 +392,6 @@ TEST_F(LogitSerializationTest, Approx) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "approx"}},
fmap_, p_dmat_);
}
@@ -420,7 +402,6 @@ TEST_F(LogitSerializationTest, Hist) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "hist"}},
fmap_, p_dmat_);
@@ -429,7 +410,6 @@ TEST_F(LogitSerializationTest, Hist) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "hist"}},
fmap_, p_dmat_);
}
@@ -438,7 +418,6 @@ TEST_F(LogitSerializationTest, CPUCoordDescent) {
TestLearnerSerialization({{"booster", "gblinear"},
{"seed", "0"},
{"nthread", "1"},
{"enable_experimental_json_serialization", "1"},
{"updater", "coord_descent"}},
fmap_, p_dmat_);
}
@@ -450,14 +429,12 @@ TEST_F(LogitSerializationTest, GpuHist) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "gpu_hist"}},
fmap_, p_dmat_);
TestLearnerSerialization({{"booster", "gbtree"},
{"objective", "binary:logistic"},
{"seed", "0"},
{"enable_experimental_json_serialization", "1"},
{"nthread", "1"},
{"max_depth", "2"},
{"num_parallel_tree", "4"},
@@ -469,7 +446,6 @@ TEST_F(LogitSerializationTest, GpuHist) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", "2"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "gpu_hist"}},
fmap_, p_dmat_);
}
@@ -479,7 +455,6 @@ TEST_F(LogitSerializationTest, GPUCoordDescent) {
{"objective", "binary:logistic"},
{"seed", "0"},
{"nthread", "1"},
{"enable_experimental_json_serialization", "1"},
{"updater", "gpu_coord_descent"}},
fmap_, p_dmat_);
}
@@ -515,7 +490,6 @@ TEST_F(MultiClassesSerializationTest, Exact) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", std::to_string(kClasses)},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "exact"}},
fmap_, p_dmat_);
@@ -525,7 +499,6 @@ TEST_F(MultiClassesSerializationTest, Exact) {
{"nthread", "1"},
{"max_depth", std::to_string(kClasses)},
{"num_parallel_tree", "4"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "exact"}},
fmap_, p_dmat_);
@@ -534,7 +507,6 @@ TEST_F(MultiClassesSerializationTest, Exact) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", std::to_string(kClasses)},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "exact"}},
fmap_, p_dmat_);
}
@@ -545,7 +517,6 @@ TEST_F(MultiClassesSerializationTest, Approx) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", std::to_string(kClasses)},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "approx"}},
fmap_, p_dmat_);
@@ -554,7 +525,6 @@ TEST_F(MultiClassesSerializationTest, Approx) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", std::to_string(kClasses)},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "approx"}},
fmap_, p_dmat_);
}
@@ -565,7 +535,6 @@ TEST_F(MultiClassesSerializationTest, Hist) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", std::to_string(kClasses)},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "hist"}},
fmap_, p_dmat_);
@@ -574,7 +543,6 @@ TEST_F(MultiClassesSerializationTest, Hist) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", std::to_string(kClasses)},
{"enable_experimental_json_serialization", "1"},
{"num_parallel_tree", "4"},
{"tree_method", "hist"}},
fmap_, p_dmat_);
@@ -584,7 +552,6 @@ TEST_F(MultiClassesSerializationTest, Hist) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", std::to_string(kClasses)},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "hist"}},
fmap_, p_dmat_);
}
@@ -593,7 +560,6 @@ TEST_F(MultiClassesSerializationTest, CPUCoordDescent) {
TestLearnerSerialization({{"booster", "gblinear"},
{"seed", "0"},
{"nthread", "1"},
{"enable_experimental_json_serialization", "1"},
{"updater", "coord_descent"}},
fmap_, p_dmat_);
}
@@ -609,7 +575,6 @@ TEST_F(MultiClassesSerializationTest, GpuHist) {
// different result (1e-7) with CPU predictor for some
// entries.
{"predictor", "gpu_predictor"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "gpu_hist"}},
fmap_, p_dmat_);
@@ -621,7 +586,6 @@ TEST_F(MultiClassesSerializationTest, GpuHist) {
// GPU_Hist has higher floating point error. 1e-6 doesn't work
// after num_parallel_tree goes to 4
{"num_parallel_tree", "3"},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "gpu_hist"}},
fmap_, p_dmat_);
@@ -630,7 +594,6 @@ TEST_F(MultiClassesSerializationTest, GpuHist) {
{"seed", "0"},
{"nthread", "1"},
{"max_depth", std::to_string(kClasses)},
{"enable_experimental_json_serialization", "1"},
{"tree_method", "gpu_hist"}},
fmap_, p_dmat_);
}
@@ -640,7 +603,6 @@ TEST_F(MultiClassesSerializationTest, GPUCoordDescent) {
{"num_class", std::to_string(kClasses)},
{"seed", "0"},
{"nthread", "1"},
{"enable_experimental_json_serialization", "1"},
{"updater", "gpu_coord_descent"}},
fmap_, p_dmat_);
}

9
tests/python/test_cli.py
View File

@@ -47,9 +47,12 @@ eval[test] = {data_path}
seed = 1994
with tempfile.TemporaryDirectory() as tmpdir:
model_out_cli = os.path.join(tmpdir, 'test_load_cli_model-cli.bin')
model_out_py = os.path.join(tmpdir, 'test_cli_model-py.bin')
config_path = os.path.join(tmpdir, 'test_load_cli_model.conf')
model_out_cli = os.path.join(
tmpdir, 'test_load_cli_model-cli.json')
model_out_py = os.path.join(
tmpdir, 'test_cli_model-py.json')
config_path = os.path.join(
tmpdir, 'test_load_cli_model.conf')
train_conf = self.template.format(data_path=data_path,
seed=seed,