Commit e815db76 authored by ZHENQIN WU's avatar ZHENQIN WU
Browse files

update of time data

parent 6e02cd6e

README.md

+13 −13
Original line number Diff line number Diff line
@@ -206,20 +206,20 @@ different subclasses of ``Featurizer`` for convenience: 
|Dataset    |Model               |Train score/ROC-AUC|Valid score/ROC-AUC|Time(loading)/s |Time(running)/s|

|-----------|--------------------|-------------------|-------------------|----------------|---------------| 

|tox21      |logistic regression |0.910              |0.759              |30              |30             |

|           |tensorflow(MT-NN)   |0.987              |0.800              |                |               |

|           |graph convolution   |0.930              |0.819              |                |               |

|           |tensorflow(MT-NN)   |0.987              |0.800              |                |30             |

|           |graph convolution   |0.930              |0.819              |                |40             |

|muv        |logistic regression |0.910              |0.744              |400             |800            |

|           |tensorflow(MT-NN)   |0.980              |0.710              |                |               |

|           |graph convolution   |0.881              |0.832              |                |               |

|pcba       |logistic regression |0.741        	     |0.719              |1800            |7200           |                                         

|           |tensorflow(MT-NN)	 |0.949        	     |0.791              |                |               |                                         

|           |graph convolution   |0.866        	     |0.836              |                |               |                                         

|sider      |logistic regression |0.900        	     |0.620              |20              |60             |                                         

|           |tensorflow(MT-NN)	 |0.931        	     |0.647              |                |               |                                         

|           |graph convolution   |0.845        	     |0.646              |                |               |                                         

|toxcast    |logistic regression |0.762        	     |0.622              |80              |2400           |                                         

|           |tensorflow(MT-NN)	 |0.926        	     |0.705              |                |               |                                         

|           |graph convolution   |0.906        	     |0.725              |                |               |                                         

|           |tensorflow(MT-NN)   |0.980              |0.710              |                |800            |

|           |graph convolution   |0.881              |0.832              |                |1200           |

|pcba       |logistic regression |0.759        	     |0.736              |1800            |5400           |                                         

|           |tensorflow(MT-NN)	 |0.949        	     |0.791              |                |7200           |                                         

|           |graph convolution   |0.866        	     |0.836              |                |20000          |                                         

|sider      |logistic regression |0.900        	     |0.620              |20              |40             |                                         

|           |tensorflow(MT-NN)	 |0.931        	     |0.647              |                |60             |                                         

|           |graph convolution   |0.845        	     |0.646              |                |60             |                                         

|toxcast    |logistic regression |0.762        	     |0.622              |80              |2000           |                                         

|           |tensorflow(MT-NN)	 |0.926        	     |0.705              |                |2400           |                                         

|           |graph convolution   |0.906        	     |0.725              |                |3000           |                                         





## Contributing to DeepChem

examples/benchmark.py

+3 −3
Original line number Diff line number Diff line
@@ -74,10 +74,10 @@ def benchmark_loading_datasets(base_dir_o, hyper_parameters, 
    raise ValueError('Dataset not supported')

                          

  if model in ['graphconv']:

    method = 'GraphConv'

    featurize = 'GraphConv'

    n_features = 71

  elif model in ['tf','logreg','rf']:

    method = 'ECFP'

    featurize = 'ECFP'

    n_features = 1024

  else:

    raise ValueError('Model not supported')
@@ -100,7 +100,7 @@ def benchmark_loading_datasets(base_dir_o, hyper_parameters, 
    

    time_start = time.time()

    #loading datasets     

    tasks,datasets,transformers = loading_functions[dname](method = method)

    tasks,datasets,transformers = loading_functions[dname](featurize=featurize)

    train_dataset, valid_dataset, test_dataset = datasets

    time_finish_loading = time.time()

    #time_finish_loading-time_start is the time(s) used for dataset loading

examples/muv/muv_datasets.py

+6 −6
Original line number Diff line number Diff line
@@ -10,7 +10,7 @@ import numpy as np 
import shutil

import deepchem as dc



def load_muv(method = 'ECFP'):

def load_muv(featurizer='ECFP'):

  """Load MUV datasets. Does not do train/test split"""

  # Load MUV dataset

  print("About to load MUV dataset.")
@@ -20,10 +20,10 @@ def load_muv(method = 'ECFP'): 
  # Featurize MUV dataset

  print("About to featurize MUV dataset.")



  if method == 'ECFP':

      featurizer = dc.feat.CircularFingerprint(size=1024)

  elif method == 'GraphConv':

      featurizer = dc.feat.ConvMolFeaturizer()

  if featurizer == 'ECFP':

      featurizer_func = dc.feat.CircularFingerprint(size=1024)

  elif featurizer == 'GraphConv':

      featurizer_func = dc.feat.ConvMolFeaturizer()

      

  MUV_tasks = sorted(['MUV-692', 'MUV-689', 'MUV-846', 'MUV-859', 'MUV-644',

                      'MUV-548', 'MUV-852', 'MUV-600', 'MUV-810', 'MUV-712',
@@ -32,7 +32,7 @@ def load_muv(method = 'ECFP'): 


  loader = dc.load.DataLoader(

      tasks=MUV_tasks, smiles_field="smiles",

      featurizer=featurizer, verbosity="high")

      featurizer=featurizer_func, verbosity="high")

  dataset = loader.featurize(dataset_file)



  # Initialize transformers

examples/nci/nci_datasets.py

+6 −6
Original line number Diff line number Diff line
@@ -13,7 +13,7 @@ import numpy as np 
import shutil

import deepchem as dc



def load_nci(method = 'ECFP', shard_size=1000, num_shards_per_batch=4):

def load_nci(featurizer='ECFP', shard_size=1000, num_shards_per_batch=4):



  current_dir = os.path.dirname(os.path.realpath(__file__))
@@ -29,10 +29,10 @@ def load_nci(method = 'ECFP', shard_size=1000, num_shards_per_batch=4): 


  # Featurize nci dataset

  print("About to featurize nci dataset.")

  if method == 'ECFP':

      featurizer = dc.feat.CircularFingerprint(size=1024)

  elif method == 'GraphConv':

      featurizer = dc.feat.ConvMolFeaturizer()

  if featurizer == 'ECFP':

      featurizer_func = dc.feat.CircularFingerprint(size=1024)

  elif featurizer == 'GraphConv':

      featurizer_func = dc.feat.ConvMolFeaturizer()



  all_nci_tasks = (['CCRF-CEM', 'HL-60(TB)', 'K-562', 'MOLT-4', 'RPMI-8226',

                    'SR', 'A549/ATCC', 'EKVX', 'HOP-62', 'HOP-92', 'NCI-H226',
@@ -49,7 +49,7 @@ def load_nci(method = 'ECFP', shard_size=1000, num_shards_per_batch=4): 


  loader = dc.load.DataLoader(tasks=all_nci_tasks,

                     	      smiles_field="smiles",

	                      featurizer=featurizer,

	                      featurizer=featurizer_func,

        	              verbosity='high')



  dataset = loader.featurize(dataset_paths, shard_size=shard_size,

examples/pcba/pcba_datasets.py

+6 −6
Original line number Diff line number Diff line
@@ -10,7 +10,7 @@ import numpy as np 
import shutil

import deepchem as dc



def load_pcba(method = 'ECFP'):

def load_pcba(featurizer='ECFP'):

  """Load PCBA datasets. Does not do train/test split"""

  

  current_dir = os.path.dirname(os.path.realpath(__file__))
@@ -19,10 +19,10 @@ def load_pcba(method = 'ECFP'): 
  

  # Featurize PCBA dataset

  print("About to featurize PCBA dataset.")

  if method == 'ECFP':

      featurizer = dc.feat.CircularFingerprint(size=1024)

  elif method == 'GraphConv':

      featurizer = dc.feat.ConvMolFeaturizer()

  if featurizer == 'ECFP':

      featurizer_func = dc.feat.CircularFingerprint(size=1024)

  elif featurizer == 'GraphConv':

      featurizer_func = dc.feat.ConvMolFeaturizer()

  PCBA_tasks = [

      'PCBA-1030','PCBA-1379','PCBA-1452','PCBA-1454','PCBA-1457',

      'PCBA-1458','PCBA-1460','PCBA-1461','PCBA-1468','PCBA-1469',
@@ -52,7 +52,7 @@ def load_pcba(method = 'ECFP'): 


  loader = dc.load.DataLoader(tasks=PCBA_tasks,

                      	      smiles_field="smiles",

	                      featurizer=featurizer)

	                      featurizer=featurizer_func)

  

  dataset = loader.featurize(dataset_file)

  # Initialize transformers

CRA Git | Maintained and supported by SUSTech CRA and CCSE