提交 b4b967a7 编写于 作者: D dzhwinter 提交者: GitHub

Merge pull request #2053 from dzhwinter/develop_mq2007

enrich paddle built-in learning to rank dataset with the mq2007 dataset
上级 8b6f374f 590c6038
develop 1.8.5 2.0.1-rocm-post 2.4.1 Ligoml-patch-1 OliverLPH-patch-1 OliverLPH-patch-2 PaddlePM-patch-1 PaddlePM-patch-2 ZHUI-patch-1 add_default_att add_kylinv10 add_model_benchmark_ci add_some_yaml_config addfile all_new_design_exec ascendrc ascendrelease bugfix-eval-frame-leakgae cherry-pick-fix-customOP-random-fail cherry_undefined_var compile_windows cp_2.4_fix_numpy delete_2.0.1-rocm-post delete_add_default_att delete_all_new_design_exec delete_ascendrc delete_compile_windows delete_delete_addfile delete_disable_iterable_dataset_unittest delete_fix_dataloader_memory_leak delete_fix_imperative_dygraph_error delete_fix_retry_ci delete_fix_undefined_var delete_improve_sccache delete_incubate/lite delete_paddle_tiny_install delete_paralleltest delete_prv-disable-more-cache delete_revert-31068-fix_conv3d_windows delete_revert-31562-mean delete_revert-33630-bug-fix delete_revert-34159-add_npu_bce_logical_dev delete_revert-34910-spinlocks_for_allocator delete_revert-35069-revert-34910-spinlocks_for_allocator delete_revert-36057-dev/read_flags_in_ut dingjiaweiww-patch-1 disable_iterable_dataset_unittest dy2static enable_eager_model_test final_state_gen_python_c final_state_intermediate fix-numpy-issue fix-run-program-grad-node-mem fix_check fix_concat_slice fix_custom_device_copy_sync fix_dataloader_memory_leak fix_dlpack_for fix_imperative_dygraph_error fix_newexe_gc fix_npu_ci fix_op_flops fix_retry_ci fix_rnn_docs fix_tensor_type fix_undefined_var fix_var_stop_gradient_error fixiscan fixiscan1 fixiscan2 fixiscan3 github/fork/123malin/netifaces github/fork/123malin/tdm_abacus github/fork/AshburnLee/dev_unique github/fork/ForFishes/fix_memory_matmul github/fork/ForFishes/rm_fluid github/fork/LielinJiang/move-2.0-api github/fork/LielinJiang/visual-dl-cb github/fork/LiuChiachi/add-transformer-generate-square-subsequent-mask-api github/fork/LiuChiachi/fix-example-code-for-hapi-Model github/fork/LiuChiachi/remove-input-requirment-in-dygraph-Model github/fork/MrChengmo/fix_ps_profiler github/fork/MrChengmo/update_ps_heter github/fork/PWhiddy/patch-1 github/fork/Shixiaowei02/dev/save_load_upgrade github/fork/TCChenlong/fix_hapi github/fork/TCChenlong/fix_inden github/fork/Thunderbrook/xpu_slice github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_2 github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_3 github/fork/XieYunshen/timeout_20S_ut github/fork/ZeyuChen/remove-nltk github/fork/arlesniak/arlesniak/selective__mkldnn_flags github/fork/baiyfbupt/code_doc_mig github/fork/chalsliu/set_timeout github/fork/chen-zhiyu/develop github/fork/chenwhql/ci/try_to_find_test_buffer_shared_memory_reuse_pass_error github/fork/chenwhql/dygraph/remove_scale_loss_and_apply_collective_grads github/fork/chenwhql/saveload/add_get_inference_program github/fork/chenwhql/saveload/remove_save_load_config github/fork/cryoco/pass-compatibility-trt github/fork/danleifeng/isempty_api2.0 github/fork/frankwhzhang/api_transfer github/fork/hbwx24/error_msg/cuda_kernel_error_msg github/fork/heavengate/cherry_yolo_box github/fork/heavengate/update_yolo_box github/fork/iclementine/rnn_fix github/fork/iducn/testestse github/fork/jczaja/prv-25537-fix github/fork/jeff41404/release/1.8 github/fork/jiweibo/api_2.0 github/fork/jiweibo/fix_lite_resnet50_test github/fork/juncaipeng/fix_doc_1 github/fork/lfchener/sample_code github/fork/littletomatodonkey/fix_reg_doc github/fork/liym27/dy2stat_update_assign_to_rc20 github/fork/luotao1/profiler_ut github/fork/mapingshuo/add_wait github/fork/mapingshuo/doc_2.0 github/fork/mapingshuo/zero-0.5 github/fork/miraiwk/dev github/fork/pangyoki/add-Categorical-class-branch github/fork/pangyoki/add-multinomial-op-branch github/fork/pangyoki/fix-test_distritbution-CI github/fork/qjing666/doublegrad github/fork/qjing666/fix_hdfs_download github/fork/sandyhouse/add_gather_etc github/fork/sandyhouse/add_send_recv_alltoall_etc github/fork/sandyhouse/pipeline_exe_run github/fork/seiriosPlus/feature/large_scale_kv_save_delta github/fork/seiriosPlus/fix/paddle_errors_fix github/fork/seiriosPlus/fix/paddle_op_errors github/fork/shangzhizhou/fix_test_activation_op_random_bug github/fork/smallv0221/yxp0924 github/fork/smallv0221/yxp0925 github/fork/swtkiwi/del-matplotlib github/fork/tianshuo78520a/kunlun_test github/fork/tianshuo78520a/update_dockerfile github/fork/wanghaoshuang/bert_fuse github/fork/wanghaoshuang/label_smooth github/fork/wanghuancoder/develop_CUDASynchronize github/fork/wanghuancoder/develop_Layer_doc github/fork/wanghuancoder/develop_ParameterList_doc github/fork/wanghuancoder/develop_Sequential_doc github/fork/wanghuancoder/develop_bilinear_tensor_product github/fork/wanghuancoder/develop_coverage_build_sh github/fork/wanghuancoder/develop_in_dynamic_mode_doc github/fork/wanghuancoder/develop_unique_name_doc github/fork/wangxicoding/fleet_meta_combine github/fork/wawltor/error_message_fix_5 github/fork/willthefrog/remove_l2_norm github/fork/windstamp/momentum_op github/fork/windstamp/mv_op_5 github/fork/windstamp/normal_api github/fork/wojtuss/wojtuss/fusion_gru_quantization github/fork/wojtuss/wojtuss/quantization-with-shift github/fork/wzzju/fix_err_info github/fork/wzzju/pure_fp16 github/fork/xiemoyuan/op_error_message github/fork/xiemoyuan/optimize_error_message github/fork/yaoxuefeng6/fix_doc github/fork/yaoxuefeng6/mod_dataset_v2 github/fork/yongqiangma/lod github/fork/ysh329/fix-clip-by-norm-error github/fork/ysh329/fix-error-clip-by-value github/fork/yukavio/error_info github/fork/zhangting2020/conv_filter_grad github/fork/zhangting2020/is_compile_with_cuda github/fork/zhangting2020/place_doc github/fork/zhangting2020/program github/fork/zhhsplendid/fix_any github/fork/zhhsplendid/refine_api2 github/fork/zhhsplendid/refine_api2_test github/fork/zhhsplendid/refine_api_test_ptb_lm github/fork/zhhsplendid/refine_api_test_resnet github/fork/zhhsplendid/refine_api_test_simnet github/fork/zhiqiu/dev/refine_initializer github/fork/zhiqiu/dev/remove_inplace_argument github/fork/zlsh80826/nvinfer_plugin_var_len_cuda11 hack_event improve_sccache incuabte/new_frl incubate/frl_train_eval incubate/infrt incubate/lite incubate/new_frl incubate/new_frl_rc incubate/stride inplace_addto layer_norm make_flag_adding_easier master matmul_double_grad move_embedding_to_phi move_histogram_to_pten move_sgd_to_phi move_slice_to_pten move_temporal_shift_to_phi move_yolo_box_to_phi npu_fix_alloc numel operator_opt paddle_tiny_install paralleltest pass-compile-eval-frame preln_ernie prv-disable-more-cache prv-md-even-more prv-onednn-2.5 prv-reshape-mkldnn-ut2 pten_tensor_refactor release-deleted/2.5 release-rc/2.5 release/0.11.0 release/0.12.0 release/0.13.0 release/0.14.0 release/0.15.0 release/1.0.0 release/1.1 release/1.2 release/1.3 release/1.4 release/1.5 release/1.6 release/1.7 release/1.8 release/2.0 release/2.0-alpha release/2.0-beta release/2.0-rc release/2.0-rc1 release/2.1 release/2.2 release/2.3 release/2.3-fc-ernie-fix release/2.4 release/2.5 release/lite-0.1 release/llm_2.5 revert-24981-add_device_attr_for_regulization revert-26856-strategy_example2 revert-27520-disable_pr revert-31068-fix_conv3d_windows revert-31562-mean revert-32290-develop-hardlabel revert-33037-forci revert-33475-fix_cifar_label_dimension revert-33630-bug-fix revert-34159-add_npu_bce_logical_dev revert-34406-add_copy_from_tensor revert-34910-spinlocks_for_allocator revert-35069-revert-34910-spinlocks_for_allocator revert-36057-dev/read_flags_in_ut revert-36201-refine_fast_threaded_ssa_graph_executor revert-36985-add_license revert-37318-refactor_dygraph_to_eager revert-37926-eager_coreops_500 revert-37956-revert-37727-pylayer_support_tuple revert-38100-mingdong revert-38301-allocation_rearrange_pr revert-38703-numpy_bf16_package_reupload revert-38732-remove_useless_header_in_elementwise_mul_grad revert-38959-Reduce_Grad revert-39143-adjust_empty revert-39227-move_trace_op_to_pten revert-39268-dev/remove_concat_fluid_kernel revert-40170-support_partial_grad revert-41056-revert-40727-move_some_activaion_to_phi revert-41065-revert-40993-mv_ele_floordiv_pow revert-41068-revert-40790-phi_new revert-41944-smaller_inference_api_test revert-42149-do-not-reset-default-stream-for-stream-safe-cuda-allocator revert-43155-fix_ut_tempfile revert-43882-revert-41944-smaller_inference_api_test revert-45808-phi/simplify_size_op revert-46827-deform_comment revert-47325-remove_cudnn_hardcode revert-47645-add_npu_storage_dims revert-48815-set_free_when_no_cache_hit_default_value_true revert-49499-test_ninja_on_ci revert-49654-prim_api_gen revert-49673-modify_get_single_cov revert-49763-fix_static_composite_gen revert-50158-fix_found_inf_bug_for_custom_optimizer revert-50188-refine_optimizer_create_accumulators revert-50335-fix_optminizer_set_auxiliary_var_bug revert-51676-flag_delete revert-51850-fix_softmaxce_dev revert-52175-dev_peak_memory revert-52186-deve revert-52523-test_py38 revert-52912-develop revert-53248-set_cmake_policy revert-54029-fix_windows_compile_bug revert-54068-support_translating_op_attribute revert-54214-modify_cmake_dependencies revert-54370-offline_pslib revert-54391-fix_cmake_md5error revert-54411-fix_cpp17_compile revert-54466-offline_pslib revert-54480-cmake-rocksdb revert-55568-fix_BF16_bug1 revert-56328-new_ir_support_vector_type_place_transfer revert-56366-fix_openssl_bug revert-56545-revert-56366-fix_openssl_bug revert-56620-fix_new_ir_ocr_bug revert-56925-check_inputs_grad_semantic revert-57005-refine_stride_flag rocm_dev_0217 sd_conv_linear_autocast semi-auto/rule-base support-0D-sort support_weight_transpose test_benchmark_ci test_feature_precision_test_c test_for_Filtetfiles test_model_benchmark test_model_benchmark_ci zhiqiu-patch-1 v2.5.1 v2.5.0 v2.5.0-rc1 v2.5.0-rc0 v2.4.2 v2.4.1 v2.4.0 v2.4.0-rc0 v2.3.2 v2.3.1 v2.3.0 v2.3.0-rc0 v2.2.2 v2.2.1 v2.2.0 v2.2.0-rc0 v2.2.0-bak0 v2.1.3 v2.1.2 v2.1.1 v2.1.0 v2.1.0-rc0 v2.0.2 v2.0.1 v2.0.0 v2.0.0-rc1 v2.0.0-rc0 v2.0.0-beta0 v2.0.0-alpha0 v1.8.5 v1.8.4 v1.8.3 v1.8.2 v1.8.1 v1.8.0 v1.7.2 v1.7.1 v1.7.0 v1.6.3 v1.6.2 v1.6.1 v1.6.0 v1.6.0-rc0 v1.5.2 v1.5.1 v1.5.0 v1.4.1 v1.4.0 v1.3.2 v1.3.1 v1.3.0 v1.2.1 v1.2.0 v1.1.0 v1.0.2 v1.0.1 v1.0.0 v1.0.0-rc0 v0.15.0 v0.15.0-rc0 v0.14.0 v0.13.0 v0.12.0 v0.11.1a2 v0.11.1a1 v0.11.0 lite-v0.1
6 合并请求!11636[IMPORTANT] MKLDNN layout: Support for sum operator,!8482Release/0.11.0,!8190Release/0.11.0,!8189Release/0.11.0,!6633给线性回归的get-started代码加上了预测的示例~~,!4615Feature/tensor array add python binding
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
MQ2007 dataset
MQ2007 is a query set from Million Query track of TREC 2007. There are about 1700 queries in it with labeled documents. In MQ2007, the 5-fold cross
validation strategy is adopted and the 5-fold partitions are included in the package. In each fold, there are three subsets for learning: training set,
validation set and testing set.
MQ2007 dataset from website
http://research.microsoft.com/en-us/um/beijing/projects/letor/LETOR4.0/Data/MQ2007.rar and parse training set and test set into paddle reader creators
"""
import os
import random
import functools
import rarfile
from common import download
import numpy as np
# URL = "http://research.microsoft.com/en-us/um/beijing/projects/letor/LETOR4.0/Data/MQ2007.rar"
URL = "http://www.bigdatalab.ac.cn/benchmark/upload/download_source/7b6dbbe2-842c-11e4-a536-bcaec51b9163_MQ2007.rar"
MD5 = "7be1640ae95c6408dab0ae7207bdc706"
def __initialize_meta_info__():
"""
download and extract the MQ2007 dataset
"""
fn = fetch()
rar = rarfile.RarFile(fn)
dirpath = os.path.dirname(fn)
rar.extractall(path=dirpath)
return dirpath
class Query(object):
"""
queries used for learning to rank algorithms. It is created from relevance scores, query-document feature vectors
Parameters:
----------
query_id : int
query_id in dataset, mapping from query to relevance documents
relevance_score : int
relevance score of query and document pair
feature_vector : array, dense feature
feature in vector format
description : string
comment section in query doc pair data
"""
def __init__(self,
query_id=-1,
relevance_score=-1,
feature_vector=None,
description=""):
self.query_id = query_id
self.relevance_score = relevance_score
if feature_vector is None:
self.feature_vector = []
else:
self.feature_vector = feature_vector
self.description = description
def __str__(self):
string = "%s %s %s" % (str(self.relevance_score), str(self.query_id),
" ".join(str(f) for f in self.feature_vector))
return string
# @classmethod
def _parse_(self, text):
"""
parse line into Query
"""
comment_position = text.find('#')
line = text[:comment_position].strip()
self.description = text[comment_position + 1:].strip()
parts = line.split()
if len(parts) != 48:
sys.stdout.write("expect 48 space split parts, get %d" %
(len(parts)))
return None
# format : 0 qid:10 1:0.000272 2:0.000000 ....
self.relevance_score = int(parts[0])
self.query_id = int(parts[1].split(':')[1])
for p in parts[2:]:
pair = p.split(':')
self.feature_vector.append(float(pair[1]))
return self
class QueryList(object):
"""
group query into list, every item in list is a Query
"""
def __init__(self, querylist=None):
self.query_id = -1
if querylist is None:
self.querylist = []
else:
self.querylist = querylist
for query in self.querylist:
if self.query_id == -1:
self.query_id = query.query_id
else:
if self.query_id != query.query_id:
raise ValueError("query in list must be same query_id")
def __iter__(self):
for query in self.querylist:
yield query
def __len__(self):
return len(self.querylist)
def __getitem__(self, i):
return self.querylist[i]
def _correct_ranking_(self):
if self.querylist is None:
return
self.querylist.sort(key=lambda x: x.relevance_score, reverse=True)
def _add_query(self, query):
if self.query_id == -1:
self.query_id = query.query_id
else:
if self.query_id != query.query_id:
raise ValueError("query in list must be same query_id")
self.querylist.append(query)
def gen_plain_txt(querylist):
"""
gen plain text in list for other usage
Paramters:
--------
querylist : querylist, one query match many docment pairs in list, see QueryList
return :
------
query_id : np.array, shape=(samples_num, )
label : np.array, shape=(samples_num, )
querylist : np.array, shape=(samples_num, feature_dimension)
"""
if not isinstance(querylist, QueryList):
querylist = QueryList(querylist)
querylist._correct_ranking_()
for query in querylist:
yield querylist.query_id, query.relevance_score, np.array(
query.feature_vector)
def gen_point(querylist):
"""
gen item in list for point-wise learning to rank algorithm
Paramters:
--------
querylist : querylist, one query match many docment pairs in list, see QueryList
return :
------
label : np.array, shape=(samples_num, )
querylist : np.array, shape=(samples_num, feature_dimension)
"""
if not isinstance(querylist, QueryList):
querylist = QueryList(querylist)
querylist._correct_ranking_()
for query in querylist:
yield query.relevance_score, np.array(query.feature_vector)
def gen_pair(querylist, partial_order="full"):
"""
gen pair for pair-wise learning to rank algorithm
Paramters:
--------
querylist : querylist, one query match many docment pairs in list, see QueryList
pairtial_order : "full" or "neighbour"
there is redudant in all possiable pair combinations, which can be simplifed
gen pairs for neighbour items or the full partial order pairs
return :
------
label : np.array, shape=(1)
query_left : np.array, shape=(1, feature_dimension)
query_right : same as left
"""
if not isinstance(querylist, QueryList):
querylist = QueryList(querylist)
querylist._correct_ranking_()
labels = []
docpairs = []
# C(n,2)
for i in range(len(querylist)):
query_left = querylist[i]
for j in range(i + 1, len(querylist)):
query_right = querylist[j]
if query_left.relevance_score > query_right.relevance_score:
labels.append(1)
docpairs.append([
np.array(query_left.feature_vector),
np.array(query_right.feature_vector)
])
elif query_left.relevance_score < query_right.relevance_score:
labels.append(1)
docpairs.append([
np.array(query_right.feature_vector),
np.array(query_left.feature_vector)
])
for label, pair in zip(labels, docpairs):
yield label, pair[0], pair[1]
def gen_list(querylist):
"""
gen item in list for list-wise learning to rank algorithm
Paramters:
--------
querylist : querylist, one query match many docment pairs in list, see QueryList
return :
------
label : np.array, shape=(samples_num, )
querylist : np.array, shape=(samples_num, feature_dimension)
"""
if not isinstance(querylist, QueryList):
querylist = QueryList(querylist)
querylist._correct_ranking_()
relevance_score_list = [query.relevance_score for query in querylist]
feature_vector_list = [query.feature_vector for query in querylist]
yield np.array(relevance_score_list).T, np.array(feature_vector_list)
def query_filter(querylists):
"""
filter query get only document with label 0.
label 0, 1, 2 means the relevance score document with query
parameters :
querylist : QueyList list
return :
querylist : QueyList list
"""
filter_query = []
for querylist in querylists:
relevance_score_list = [query.relevance_score for query in querylist]
if sum(relevance_score_list) != .0:
filter_query.append(querylist)
return filter_query
def load_from_text(filepath, shuffle=True, fill_missing=-1):
"""
parse data file into querys
"""
prev_query_id = -1
querylists = []
querylist = None
fn = __initialize_meta_info__()
with open(os.path.join(fn, filepath)) as f:
for line in f:
query = Query()
query = query._parse_(line)
if query == None:
continue
if query.query_id != prev_query_id:
if querylist is not None:
querylists.append(querylist)
querylist = QueryList()
prev_query_id = query.query_id
querylist._add_query(query)
if querylist is not None:
querylists.append(querylist)
if shuffle == True:
random.shuffle(querylists)
return querylists
def __reader__(filepath, format="pairwise", shuffle=True, fill_missing=-1):
"""
Parameters
--------
filename : string
shuffle : shuffle query-doc pair under the same query
fill_missing : fill the missing value. default in MQ2007 is -1
Returns
------
yield
label query_left, query_right # format = "pairwise"
label querylist # format = "listwise"
"""
querylists = query_filter(
load_from_text(
filepath, shuffle=shuffle, fill_missing=fill_missing))
for querylist in querylists:
if format == "plain_txt":
yield next(gen_plain_txt(querylist))
elif format == "pointwise":
yield next(gen_point(querylist))
elif format == "pairwise":
for pair in gen_pair(querylist):
yield pair
elif format == "listwise":
yield next(gen_list(querylist))
train = functools.partial(__reader__, filepath="MQ2007/MQ2007/Fold1/train.txt")
test = functools.partial(__reader__, filepath="MQ2007/MQ2007/Fold1/test.txt")
def fetch():
return download(URL, "MQ2007", MD5)
if __name__ == "__main__":
fetch()
mytest = functools.partial(
__reader__, filepath="MQ2007/MQ2007/Fold1/sample", format="listwise")
for label, query in mytest():
print label, query
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import paddle.v2.dataset.mq2007
import unittest
class TestMQ2007(unittest.TestCase):
def test_pairwise(self):
for label, query_left, query_right in paddle.v2.dataset.mq2007.test(
format="pairwise"):
self.assertEqual(query_left.shape(), (46, ))
self.assertEqual(query_right.shape(), (46, ))
def test_listwise(self):
for label_array, query_array in paddle.v2.dataset.mq2007.test(
format="listwise"):
self.assertEqual(len(label_array), len(query_array))
if __name__ == "__main__":
unittest.main()
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册
反馈
建议
客服 返回
顶部