Commit c011725e authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

Factors files

parent 23e59acb

examples/factors/FACTORS_correlations.py

0 → 100644
+43 −0
Original line number Diff line number Diff line 
"""

Script that computes correlations of FACTORS tasks. 

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import os

import numpy as np

import tempfile

import shutil

import deepchem as dc

import pandas as pd

from FACTORS_datasets import load_factors



###Load data###

np.random.seed(123)

shard_size = 2000

print("About to load FACTORS data.")

FACTORS_tasks, datasets, transformers = load_factors(shard_size=shard_size)

train_dataset, valid_dataset, test_dataset = datasets



y_train = train_dataset.y

n_tasks = y_train.shape[1]



all_results = []

for task in range(n_tasks):

  y_task = y_train[:, task]

  task_results = []

  for other_task in range(n_tasks):

    if task == other_task:

      task_results.append(1.)

      continue

    y_other = y_train[:, other_task]

    r2 = dc.metrics.pearson_r2_score(y_task, y_other)

    #print("r2 for %s-%s is %f" % (task, other_task, r2))

    task_results.append(r2)

  print("Task %d" % task)

  print(task_results)

  all_results.append(task_results)

print("Writing results to factors_corr.csv")

df = pd.DataFrame(all_results)

df.to_csv("factors_corr.csv")

examples/factors/FACTORS_tf_progressive.py

+63 −30
Original line number Diff line number Diff line
@@ -11,17 +11,16 @@ import tempfile 
import shutil

import numpy as np

import deepchem as dc

from MERCK_datasets import load_factors

from FACTORS_datasets import load_factors



# Set numpy seed

np.random.seed(123)



###Load data###

shard_size = 2000

num_shards_per_batch = 4

print("About to load MERCK data.")

FACTORS_tasks, datasets, transformers = load_factors(

    shard_size=shard_size, num_shards_per_batch=num_shards_per_batch)

num_trials = 5

print("About to load FACTORS data.")

FACTORS_tasks, datasets, transformers = load_factors(shard_size=shard_size)

train_dataset, valid_dataset, test_dataset = datasets



print("Number of compounds in train set")
@@ -31,6 +30,8 @@ print(len(valid_dataset)) 
print("Number of compounds in test set")

print(len(test_dataset))



all_results = []

for trial in range(num_trials):

  ###Create model###

  n_layers = 3

  nb_epoch = 50
@@ -40,26 +41,58 @@ model = dc.models.ProgressiveMultitaskRegressor( 
      alpha_init_stddevs=[.02]*n_layers, weight_init_stddevs=[.02]*n_layers,

      bias_init_consts=[1.]*n_layers, learning_rate=.0003,

      penalty=.0001, penalty_type="l2", optimizer="adam", batch_size=100,

    seed=123, verbosity="high")



      seed=123)



  #Use R2 classification metric

  metric = dc.metrics.Metric(dc.metrics.pearson_r2_score, task_averager=np.mean)



  print("Training model")

  model.fit(train_dataset, nb_epoch=nb_epoch)

#model.old_fit(train_dataset, nb_epoch=nb_epoch)



train_scores = model.evaluate(train_dataset, [metric], transformers)

valid_scores = model.evaluate(valid_dataset, [metric], transformers)

#Only use for final evaluation

test_scores = model.evaluate(test_dataset, [metric], transformers)

  print("Evaluating models")

  train_score, train_task_scores = model.evaluate(

      train_dataset, [metric], transformers, per_task_metrics=True)

  valid_score, valid_task_scores = model.evaluate(

      valid_dataset, [metric], transformers, per_task_metrics=True)

  test_score, test_task_scores = model.evaluate(

      test_dataset, [metric], transformers, per_task_metrics=True)



  all_results.append((train_score, train_task_scores,

                      valid_score, valid_task_scores,

                      test_score, test_task_scores))



  print("Scores for trial %d" % trial)

  print("----------------------------------------------------------------")

  print("train_task_scores")

  print(train_task_scores)

  print("Mean Train score")

  print(train_score)

  print("valid_task_scores")

  print(valid_task_scores)

  print("Mean Validation score")

  print(valid_score)

  print("test_task_scores")

  print(test_task_scores)

  print("Mean Test score")

  print(test_score)



print("Train scores")

print(train_scores)

print("####################################################################")



print("Validation scores")

print(valid_scores)

for trial in range(num_trials):

  (train_score, train_task_scores, valid_score, valid_task_scores,

   test_score, test_task_scores) = all_results[trial]



print("Test scores")

print(test_scores)
 
  print("Scores for trial %d" % trial)

  print("----------------------------------------------------------------")

  print("train_task_scores")

  print(train_task_scores)

  print("Mean Train score")

  print(train_score)

  print("valid_task_scores")

  print(valid_task_scores)

  print("Mean Validation score")

  print(valid_score)

  print("test_task_scores")

  print(test_task_scores)

  print("Mean Test score")

  print(test_score)

examples/factors/FACTORS_tf_robust.py

+64 −31
Original line number Diff line number Diff line 
"""

Script that trains Tensorflow Robust Multitask models on FACTORS datasets.

Script that trains Tensorflow Bypass Multitask models on FACTORS datasets.

"""



from __future__ import print_function
@@ -11,18 +11,16 @@ import numpy as np 
import tempfile

import shutil

import deepchem as dc

from MERCK_datasets import load_factors

from FACTORS_datasets import load_factors



# Set numpy seed

np.random.seed(123)



###Load data###

shard_size = 2000

num_cores = 1

num_shards_per_batch = 4

print("About to load MERCK data.")

FACTORS_tasks, datasets, transformers = load_factors(

    shard_size=shard_size, num_shards_per_batch=num_shards_per_batch)

num_trials = 5

print("About to load FACTORS data.")

FACTORS_tasks, datasets, transformers = load_factors(shard_size=shard_size)

train_dataset, valid_dataset, test_dataset = datasets



print("Number of compounds in train set")
@@ -34,8 +32,13 @@ print(len(test_dataset)) 


n_layers = 3

n_bypass_layers = 3

#nb_epoch = 150

nb_epoch = 125



#Use R2 classification metric

metric = dc.metrics.Metric(dc.metrics.pearson_r2_score, task_averager=np.mean)



all_results = []

for trial in range(num_trials):

  model = dc.models.RobustMultitaskRegressor(

      len(FACTORS_tasks), train_dataset.get_data_shape()[0],

      layer_sizes=[1000]*n_layers, bypass_layer_sizes=[100]*n_bypass_layers,
@@ -44,25 +47,55 @@ model = dc.models.RobustMultitaskRegressor( 
      bypass_weight_init_stddevs=[.02]*n_bypass_layers,

      bypass_bias_init_consts=[1.]*n_bypass_layers,

      learning_rate=.0003, penalty=.0001, penalty_type="l2",

    optimizer="adam", batch_size=100, seed=123, verbosity="high")



#Use R2 classification metric

metric = dc.metrics.Metric(dc.metrics.pearson_r2_score, task_averager=np.mean,

                           mode="regression")

      optimizer="adam", batch_size=100, seed=123)



  print("Fitting Model")

  model.fit(train_dataset, nb_epoch=nb_epoch)



train_scores = model.evaluate(train_dataset, [metric], transformers)

valid_scores = model.evaluate(valid_dataset, [metric], transformers)

#Only use for final evaluation

test_scores = model.evaluate(test_dataset, [metric], transformers)

  print("Evaluating models")

  train_score, train_task_scores = model.evaluate(

      train_dataset, [metric], transformers, per_task_metrics=True)

  valid_score, valid_task_scores = model.evaluate(

      valid_dataset, [metric], transformers, per_task_metrics=True)

  test_score, test_task_scores = model.evaluate(

      test_dataset, [metric], transformers, per_task_metrics=True)



  all_results.append((train_score, train_task_scores,

                      valid_score, valid_task_scores,

                      test_score, test_task_scores))



  print("Scores for trial %d" % trial)

  print("----------------------------------------------------------------")

  print("train_task_scores")

  print(train_task_scores)

  print("Mean Train score")

  print(train_score)

  print("valid_task_scores")

  print(valid_task_scores)

  print("Mean Validation score")

  print(valid_score)

  print("test_task_scores")

  print(test_task_scores)

  print("Mean Test score")

  print(test_score)



print("Train scores")

print(train_scores)

print("####################################################################")



print("Validation scores")

print(valid_scores)

for trial in range(num_trials):

  (train_score, train_task_scores, valid_score, valid_task_scores,

   test_score, test_task_scores) = all_results[trial]



print("Test scores")

print(test_scores)
 
  print("Scores for trial %d" % trial)

  print("----------------------------------------------------------------")

  print("train_task_scores")

  print(train_task_scores)

  print("Mean Train score")

  print(train_score)

  print("valid_task_scores")

  print(valid_task_scores)

  print("Mean Validation score")

  print(valid_score)

  print("test_task_scores")

  print(test_task_scores)

  print("Mean Test score")

  print(test_score)

examples/factors/FACTORS_tf_singletask.py

+1 −3
Original line number Diff line number Diff line 
"""

Script that trains Tensorflow Multitask models on FACTORS dataset.

Script that trains Tensorflow Singletask models on FACTORS dataset.

"""

from __future__ import print_function

from __future__ import division
@@ -34,7 +34,6 @@ metric = dc.metrics.Metric(dc.metrics.pearson_r2_score, task_averager=np.mean) 


###Create model###

n_layers = 3

#nb_epoch = 1

nb_epoch = 125

n_features = train_dataset.get_data_shape()[0]

def task_model_builder(m_dir):
@@ -53,7 +52,6 @@ for trial in range(num_trials): 
  print("Fitting Model")

  model.fit(train_dataset, nb_epoch=nb_epoch)





  print("Evaluating models")

  train_score, train_task_scores = model.evaluate(

      train_dataset, [metric], transformers, per_task_metrics=True)

CRA Git | Maintained and supported by SUSTech CRA and CCSE