Commit e91d3bfe authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

Initial commit of low-data RFs

parent 89f095ce

deepchem/models/tf_keras_models/support_classifier.py

+18 −0
Original line number Diff line number Diff line
@@ -136,6 +136,24 @@ class SupportGenerator(object): 
  each task, and returns in a randomized order

  """

  def __init__(self, dataset, tasks, n_pos, n_neg, n_trials, replace):

    """

    Parameters

    ----------

    dataset: deepchem.datasets.Dataset

      Holds dataset from which support sets will be sampled.

    tasks: list

      Indices of tasks from which supports are sampled.

      TODO(rbharath): Can this be removed.

    n_pos: int

      Number of positive samples

    n_neg: int

      Number of negative samples.

    n_trials: int

      Number of support sets to sample from dataset.

    replace: bool

      Whether to use sampling with or without replacement.

    """

      

    self.tasks = tasks

    self.n_tasks = len(tasks)

    self.n_trials = n_trials

examples/bace/bace_datasets.py

+1 −1
Original line number Diff line number Diff line
@@ -123,7 +123,7 @@ def load_bace(mode="regression", transform=True, split="20-80"): 
  transformers = input_transformers + output_transformers

  for dataset in [train_dataset, valid_dataset, test_dataset, crystal_dataset]:

    for transformer in transformers:

        transformer.transform(dataset)

        dataset = transformer.transform(dataset)



  return (bace_tasks, train_dataset, valid_dataset, test_dataset,

          crystal_dataset, output_transformers)

examples/low_data/tox_rf_K_fold.py

0 → 100644
+84 −0
Original line number Diff line number Diff line 
"""

Train low-data models on random forests.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import tempfile

import numpy as np

import deepchem as dc

from datasets import load_tox21_ecfp

from sklearn.ensemble import RandomForestClassifier

from deepchem.metrics import Metric

from deepchem.splits.task_splitter import merge_fold_datasets

from deepchem.splits.task_splitter import TaskSplitter

from deepchem.models.sklearn_models import SklearnModel

from deepchem.models.tf_keras_models.support_classifier import SupportGenerator

from deepchem.models.tf_keras_models.support_classifier import get_task_dataset_minus_support



model_dir = tempfile.mkdtemp()



# 4-fold splits

K = 4

# 10 positive/negative ligands

n_pos = 10

n_neg = 10

# 10 trials on test-set

n_trials = 10

# Sample supports without replacement (all pos/neg should be different)

replace = False



tox21_tasks, dataset, transformers = load_tox21_ecfp()



# Define metric

metric = Metric(dc.metrics.roc_auc_score, verbosity="high",

                mode="classification")



task_splitter = TaskSplitter()

fold_datasets = task_splitter.k_fold_split(dataset, K)



all_scores = {}

for fold in range(K):

  train_inds = list(set(range(K)) - set([fold]))

  train_folds = [fold_datasets[ind] for ind in train_inds]

  train_dataset = merge_fold_datasets(train_folds)

  test_dataset = fold_datasets[fold]



  fold_tasks = range(fold * len(test_dataset.get_task_names()),

                     (fold+1) * len(test_dataset.get_task_names()))



  # Get supports on test-set

  support_generator = SupportGenerator(

      test_dataset, range(len(test_dataset.get_task_names())), n_pos, n_neg,

      n_trials, replace)



  # Compute accuracies

  task_scores = {task: [] for task in range(len(test_dataset.get_task_names()))}

  for (task, support) in support_generator:

    # Train model on support

    sklearn_model = RandomForestClassifier(

        class_weight="balanced", n_estimators=50)

    model = SklearnModel(sklearn_model, model_dir)

    model.fit(support)



    # Test model

    task_dataset = get_task_dataset_minus_support(test_dataset, support, task)

    y_pred = model.predict_proba(task_dataset)

    score = metric.compute_metric(

        task_dataset.y, y_pred, task_dataset.w)

    #print("Score on task %s is %s" % (str(task), str(score)))

    task_scores[task].append(score)



  # Join information for all tasks.

  mean_task_scores = {}

  for task in range(len(test_dataset.get_task_names())):

    mean_task_scores[task] = np.mean(np.array(task_scores[task]))

  print("Fold %s" % str(fold))

  print(mean_task_scores)



  for (fold_task, task) in zip(fold_tasks, range(len(test_dataset.get_task_names()))):

    all_scores[fold_task] = mean_task_scores[task]



print("All scores")

print(all_scores)

examples/low_data/tox_rf_one_fold.py

0 → 100644
+71 −0
Original line number Diff line number Diff line 
"""

Train low-data models on random forests.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import tempfile

import numpy as np

import deepchem as dc

from datasets import load_tox21_ecfp

from sklearn.ensemble import RandomForestClassifier

from deepchem.metrics import Metric

from deepchem.splits.task_splitter import merge_fold_datasets

from deepchem.splits.task_splitter import TaskSplitter

from deepchem.models.sklearn_models import SklearnModel

from deepchem.models.tf_keras_models.support_classifier import SupportGenerator

from deepchem.models.tf_keras_models.support_classifier import get_task_dataset_minus_support



model_dir = tempfile.mkdtemp()



# 4-fold splits

K = 4

# 10 positive/negative ligands

n_pos = 10

n_neg = 10

# 10 trials on test-set

n_trials = 10

# Sample supports without replacement (all pos/neg should be different)

replace = False



tox21_tasks, dataset, transformers = load_tox21_ecfp()



# Define metric

metric = Metric(dc.metrics.roc_auc_score, verbosity="high",

                mode="classification")



task_splitter = TaskSplitter()

fold_datasets = task_splitter.k_fold_split(dataset, K)



train_folds = fold_datasets[:-1] 

train_dataset = merge_fold_datasets(train_folds)

test_dataset = fold_datasets[-1]



# Get supports on test-set

support_generator = SupportGenerator(

    test_dataset, range(len(test_dataset.get_task_names())), n_pos, n_neg,

    n_trials, replace)



# Compute accuracies

task_scores = {task: [] for task in range(len(test_dataset.get_task_names()))}

for (task, support) in support_generator:

  # Train model on support

  sklearn_model = RandomForestClassifier(

      class_weight="balanced", n_estimators=50)

  model = SklearnModel(sklearn_model, model_dir)

  model.fit(support)



  # Test model

  task_dataset = get_task_dataset_minus_support(test_dataset, support, task)

  y_pred = model.predict_proba(task_dataset)

  score = metric.compute_metric(

      task_dataset.y, y_pred, task_dataset.w)

  #print("Score on task %s is %s" % (str(task), str(score)))

  task_scores[task].append(score)



# Join information for all tasks.

mean_task_scores = {}

for task in range(len(test_dataset.get_task_names())):

  mean_task_scores[task] = np.mean(np.array(task_scores[task]))

print(mean_task_scores)

examples/muv/muv_datasets.py

+1 −1
Original line number Diff line number Diff line
@@ -67,7 +67,7 @@ def load_muv(base_dir, reload=True, frac_train=.8): 
  if regen:

    print("About to transform data")

    for transformer in transformers:

        transformer.transform(dataset)

        dataset = transformer.transform(dataset)



  X, y, w, ids = (dataset.X, dataset.y, dataset.w, dataset.ids)

  num_tasks = 17

CRA Git | Maintained and supported by SUSTech CRA and CCSE