Skip to content

B
BiTransDPI
提交 44a442cd 作者: 朱学凯
操作

add z-score data

上级 256bf696
正在显示 包含 54 行增加 和 32 行删除
.idea/CPI.iml
...@@ -2,7 +2,7 @@ ...@@ -2,7 +2,7 @@
<module type="PYTHON_MODULE" version="4"> <module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager"> <component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$" /> <content url="file://$MODULE_DIR$" />
<orderEntry type="jdk" jdkName="Python 3.6 (code)" jdkType="Python SDK" /> <orderEntry type="jdk" jdkName="Python 3.6 (py3.6)" jdkType="Python SDK" />
<orderEntry type="sourceFolder" forTests="false" /> <orderEntry type="sourceFolder" forTests="false" />
</component> </component>
<component name="PyDocumentationSettings"> <component name="PyDocumentationSettings">
......
.idea/misc.xml
<?xml version="1.0" encoding="UTF-8"?> <?xml version="1.0" encoding="UTF-8"?>
<project version="4"> <project version="4">
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.6 (code)" project-jdk-type="Python SDK" /> <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.6 (py3.6)" project-jdk-type="Python SDK" />
</project> </project>
\ No newline at end of file
.idea/workspace.xml
...@@ -2,7 +2,12 @@ ...@@ -2,7 +2,12 @@
<project version="4"> <project version="4">
<component name="ChangeListManager"> <component name="ChangeListManager">
<list default="true" id="f877ac68-9cea-46d8-9125-207eebe5b5d6" name="Default Changelist" comment=""> <list default="true" id="f877ac68-9cea-46d8-9125-207eebe5b5d6" name="Default Changelist" comment="">
<change beforePath="$PROJECT_DIR$/.idea/CPI.iml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/CPI.iml" afterDir="false" />
<change beforePath="$PROJECT_DIR$/.idea/misc.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/misc.xml" afterDir="false" />
<change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" /> <change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
<change beforePath="$PROJECT_DIR$/run_interaction.py" beforeDir="false" afterPath="$PROJECT_DIR$/run_interaction.py" afterDir="false" />
<change beforePath="$PROJECT_DIR$/train.sh" beforeDir="false" afterPath="$PROJECT_DIR$/train.sh" afterDir="false" />
<change beforePath="$PROJECT_DIR$/utils/normalize_data.py" beforeDir="false" afterPath="$PROJECT_DIR$/utils/normalize_data.py" afterDir="false" />
</list> </list>
<option name="SHOW_DIALOG" value="false" /> <option name="SHOW_DIALOG" value="false" />
<option name="HIGHLIGHT_CONFLICTS" value="true" /> <option name="HIGHLIGHT_CONFLICTS" value="true" />
...@@ -49,7 +54,7 @@ ...@@ -49,7 +54,7 @@
<recent name="$PROJECT_DIR$/experment_result/learning_rate" /> <recent name="$PROJECT_DIR$/experment_result/learning_rate" />
</key> </key>
</component> </component>
<component name="RunManager" selected="Python.normalize_data"> <component name="RunManager" selected="Python.run_interaction">
<configuration default="true" type="PythonConfigurationType" factoryName="Python"> <configuration default="true" type="PythonConfigurationType" factoryName="Python">
<module name="CPI" /> <module name="CPI" />
<option name="INTERPRETER_OPTIONS" value="" /> <option name="INTERPRETER_OPTIONS" value="" />
...@@ -120,9 +125,6 @@ ...@@ -120,9 +125,6 @@
<module name="CPI" /> <module name="CPI" />
<option name="INTERPRETER_OPTIONS" value="" /> <option name="INTERPRETER_OPTIONS" value="" />
<option name="PARENT_ENVS" value="true" /> <option name="PARENT_ENVS" value="true" />
<envs>
<env name="PYTHONUNBUFFERED" value="1" />
</envs>
<option name="SDK_HOME" value="" /> <option name="SDK_HOME" value="" />
<option name="WORKING_DIRECTORY" value="$PROJECT_DIR$/utils" /> <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$/utils" />
<option name="IS_MODULE_SDK" value="true" /> <option name="IS_MODULE_SDK" value="true" />
...@@ -184,8 +186,8 @@ ...@@ -184,8 +186,8 @@
</configuration> </configuration>
<recent_temporary> <recent_temporary>
<list> <list>
<item itemvalue="Python.normalize_data" />
<item itemvalue="Python.run_interaction" /> <item itemvalue="Python.run_interaction" />
<item itemvalue="Python.normalize_data" />
<item itemvalue="Python.test" /> <item itemvalue="Python.test" />
<item itemvalue="Python.dataset" /> <item itemvalue="Python.dataset" />
<item itemvalue="Python.eval" /> <item itemvalue="Python.eval" />
...@@ -232,10 +234,10 @@ ...@@ -232,10 +234,10 @@
</breakpoint-manager> </breakpoint-manager>
</component> </component>
<component name="com.intellij.coverage.CoverageDataManagerImpl"> <component name="com.intellij.coverage.CoverageDataManagerImpl">
<SUITE FILE_PATH="coverage/CPI$dataset.coverage" NAME="dataset Coverage Results" MODIFIED="1618641059668" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
<SUITE FILE_PATH="coverage/CPI$test.coverage" NAME="test Coverage Results" MODIFIED="1618643206375" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" /> <SUITE FILE_PATH="coverage/CPI$test.coverage" NAME="test Coverage Results" MODIFIED="1618643206375" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
<SUITE FILE_PATH="coverage/CPI$normalize_data.coverage" NAME="normalize_data Coverage Results" MODIFIED="1619675786375" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/utils" /> <SUITE FILE_PATH="coverage/CPI$normalize_data.coverage" NAME="normalize_data Coverage Results" MODIFIED="1619667621484" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$/utils" />
<SUITE FILE_PATH="coverage/CPI$run_interaction.coverage" NAME="run_interaction Coverage Results" MODIFIED="1619685403006" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
<SUITE FILE_PATH="coverage/CPI$eval.coverage" NAME="eval Coverage Results" MODIFIED="1618396849549" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" /> <SUITE FILE_PATH="coverage/CPI$eval.coverage" NAME="eval Coverage Results" MODIFIED="1618396849549" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
<SUITE FILE_PATH="coverage/CPI$run_interaction.coverage" NAME="run_interaction Coverage Results" MODIFIED="1619081693342" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" /> <SUITE FILE_PATH="coverage/CPI$dataset.coverage" NAME="dataset Coverage Results" MODIFIED="1618641059668" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
</component> </component>
</project> </project>
\ No newline at end of file
data/train_z_100_ic50 0 → 100644
This source diff could not be displayed because it is too large. You can view the blob instead.
data/train_z_10_ic50 0 → 100644
This source diff could not be displayed because it is too large. You can view the blob instead.
run_interaction.py
...@@ -10,11 +10,6 @@ from tqdm import tqdm ...@@ -10,11 +10,6 @@ from tqdm import tqdm
torch.set_default_tensor_type(torch.DoubleTensor) torch.set_default_tensor_type(torch.DoubleTensor)
def get_task(task_name): def get_task(task_name):
if task_name.lower() == 'train':
df_train = {"sps": './data/train_sps',
"smile": './data/train_smile',
"affinity": './data/train_ic50',
}
tokenizer_config = {"vocab_file": './config/vocab.txt', tokenizer_config = {"vocab_file": './config/vocab.txt',
"vocab_pair": './config/drug_codes_chembl.txt', "vocab_pair": './config/drug_codes_chembl.txt',
...@@ -22,21 +17,42 @@ def get_task(task_name): ...@@ -22,21 +17,42 @@ def get_task(task_name):
"separate_id": "[SEP]", "separate_id": "[SEP]",
"max_len": 256 "max_len": 256
} }
if task_name.lower() == 'train':
df_train = {"sps": './data/train_sps',
"smile": './data/train_smile',
"affinity": './data/train_ic50',
}
return df_train, tokenizer_config return df_train, tokenizer_config
elif task_name.lower() == 'test': elif task_name.lower() == 'test':
df_test = {"sps": './data/test_sps', df_test = {"sps": './data/test_sps',
"smile": './data/test_smile', "smile": './data/test_smile',
"affinity": './data/test_ic50', "affinity": './data/test_ic50',
} }
tokenizer_config = {"vocab_file": './config/vocab.txt',
"vocab_pair": './config/drug_codes_chembl.txt',
"begin_id": '[CLS]',
"separate_id": "[SEP]",
"max_len": 256
}
return df_test, tokenizer_config return df_test, tokenizer_config
elif task_name.lower() == 'train_z_10':
df = {"sps": './data/train_sps',
"smile": './data/train_smile',
"affinity": './data/train_z_10_ic50',
}
return df, tokenizer_config
elif task_name.lower() == 'train_z_100':
df = {"sps": './data/train_sps',
"smile": './data/train_smile',
"affinity": './data/train_z_100_ic50',
}
return df, tokenizer_config
def train(args, model, dataset): def train(args, model, dataset):
data_loder_para = {'batch_size': args.batch_size, data_loder_para = {'batch_size': args.batch_size,
'shuffle': True, 'shuffle': True,
...@@ -136,7 +152,7 @@ def main(args): ...@@ -136,7 +152,7 @@ def main(args):
print('model name : BertAffinity') print('model name : BertAffinity')
print('task name : {}'.format(args.task)) print('task name : {}'.format(args.task))
if args.task == 'train': if args.task in ['train', 'train_z_10', 'train_z_100']:
train(args, model, dataset) train(args, model, dataset)
elif args.task in ['test']: elif args.task in ['test']:
...@@ -178,11 +194,11 @@ if __name__ == '__main__': ...@@ -178,11 +194,11 @@ if __name__ == '__main__':
# local test # local test
# args.task = 'train' args.task = 'train_z_10'
# args.savedir = 'local_test_train' args.savedir = 'local_test_train'
# args.epochs = 10 args.epochs = 10
# args.lr = 1e-5 args.lr = 1e-5
# args.config = './config/config_layer_3.json' args.config = './config/config_layer_3.json'
......
train.sh
CUDA_VISIBLE_DEVICES=4 python run_interaction.py --b=32 --task=train --epochs=10 --lr=1e-5 --savedir=lr-1e-5-batch-32-e-10-layer9-0420 --config=./config/config_layer_9.json CUDA_VISIBLE_DEVICES=4 python run_interaction.py --b=32 --task=train_z --epochs=10 --lr=1e-5 --savedir=lr-1e-5-batch-32-e-10-layer9-0420 --config=./config/config_layer_9.json
\ No newline at end of file \ No newline at end of file
utils/normalize_data.py
import numpy as np import numpy as np
from tqdm import tqdm
def z_score(data, save, enlarge): def z_score(data, save, enlarge):
with open(data, 'r') as f: with open(data, 'r') as f:
...@@ -14,7 +15,7 @@ def z_score(data, save, enlarge): ...@@ -14,7 +15,7 @@ def z_score(data, save, enlarge):
new_affinity *= enlarge new_affinity *= enlarge
new_affinity = list(new_affinity) new_affinity = list(new_affinity)
with open(save, 'w') as f: with open(save, 'w') as f:
for aff in new_affinity: for aff in tqdm(new_affinity):
f.write(str(aff) + '\n') f.write(str(aff) + '\n')
...@@ -22,7 +23,7 @@ def z_score(data, save, enlarge): ...@@ -22,7 +23,7 @@ def z_score(data, save, enlarge):
if __name__ == '__main__': if __name__ == '__main__':
data = '../data/test_ic50' data = '../data/train_ic50'
save = '../data/test_z_ic50' save = '../data/train_z_100_ic50'
enlarge = 100 enlarge = 100
z_score(data, save, enlarge) z_score(data, save, enlarge)
\ No newline at end of file
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论