Commit 372c5d01 authored by leswing's avatar leswing
Browse files

Mark Tests

parent 287ada79

devtools/jenkins/test_notebooks.sh

+8 −7
Original line number Diff line number Diff line
@@ -5,13 +5,14 @@ export python_version=2.7 
bash scripts/install_deepchem_conda.sh $envname

source activate $envname

python setup.py install

conda install jupyter

conda install nbconvert

conda install jupyter_client

conda install ipykernel

conda install matplotlib

pip install nglview

conda install ipywidgets

conda install -y jupyter

conda install -y nbconvert

conda install -y jupyter_client

conda install -y ipykernel

conda install -y matplotlib

yes | pip install nglview

conda install -y ipywidgets

yes | pip uninstall tensorflow



cd examples/notebooks

nosetests --with-timer tests.py --with-xunit --xunit-file=notebook_tests.xml|| true

examples/notebooks/BACE.ipynb

+253 −273

File changed.

Preview size limit exceeded, changes collapsed.

examples/notebooks/Multitask Networks on MUV.ipynb→examples/notebooks/Multitask_Networks_on_MUV.ipynb

+208 −29
Original line number Diff line number Diff line 
%% Cell type:markdown id: tags:



This notebook walks through the creation of multitask models on MUV. The goal is to demonstrate that multitask methods outperform singletask methods on MUV.



%% Cell type:code id: tags:



``` python

%reload_ext autoreload

%autoreload 2

%pdb off

reload = True

```



%% Output



    Automatic pdb calling has been turned OFF



%% Cell type:code id: tags:



``` python

import deepchem as dc



dataset_file= "../../datasets/muv.csv.gz"

dataset = dc.utils.save.load_from_disk(dataset_file)

print("Columns of dataset: %s" % str(dataset.columns.values))

print("Number of examples in dataset: %s" % str(dataset.shape[0]))

```



%% Output



    /home/leswing/anaconda3/envs/deepchem27/lib/python2.7/site-packages/sklearn/cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.

      "This module will be removed in 0.20.", DeprecationWarning)



    Columns of dataset: ['MUV-466' 'MUV-548' 'MUV-600' 'MUV-644' 'MUV-652' 'MUV-689' 'MUV-692'

     'MUV-712' 'MUV-713' 'MUV-733' 'MUV-737' 'MUV-810' 'MUV-832' 'MUV-846'

     'MUV-852' 'MUV-858' 'MUV-859' 'mol_id' 'smiles']

    Number of examples in dataset: 93127



%% Cell type:markdown id: tags:



Now, let's visualize some compounds from our dataset



%% Cell type:code id: tags:



``` python

from rdkit import Chem

from rdkit.Chem import Draw

from itertools import islice

from IPython.display import Image, display, HTML



def display_images(filenames):

    """Helper to pretty-print images."""

    imagesList=''.join(

        ["<img style='width: 140px; margin: 0px; float: left; border: 1px solid black;' src='%s' />"

         % str(s) for s in sorted(filenames)])

    display(HTML(imagesList))



def mols_to_pngs(mols, basename="test"):

    """Helper to write RDKit mols to png files."""

    filenames = []

    for i, mol in enumerate(mols):

        filename = "%s%d.png" % (basename, i)

        Draw.MolToFile(mol, filename)

        filenames.append(filename)

    return filenames



num_to_display = 12

molecules = []

for _, data in islice(dataset.iterrows(), num_to_display):

    molecules.append(Chem.MolFromSmiles(data["smiles"]))

display_images(mols_to_pngs(molecules))

```



%% Output





%% Cell type:code id: tags:



``` python

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

             'MUV-548', 'MUV-852', 'MUV-600', 'MUV-810', 'MUV-712',

             'MUV-737', 'MUV-858', 'MUV-713', 'MUV-733', 'MUV-652',

             'MUV-466', 'MUV-832']



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

loader = dc.data.CSVLoader(

      tasks=MUV_tasks, smiles_field="smiles",

      featurizer=featurizer)

dataset = loader.featurize(dataset_file)

```



%% Output



    Loading raw samples now.

    shard_size: 8192

    About to start loading CSV from ../../datasets/muv.csv.gz

    Loading shard 1 of size 8192.

    Featurizing sample 0

    Featurizing sample 1000

    Featurizing sample 2000

    Featurizing sample 3000

    Featurizing sample 4000

    Featurizing sample 5000

    Featurizing sample 6000

    Featurizing sample 7000

    Featurizing sample 8000

    TIMING: featurizing shard 0 took 15.158 s

    Loading shard 2 of size 8192.

    Featurizing sample 0

    Featurizing sample 1000

    Featurizing sample 2000

    Featurizing sample 3000

    Featurizing sample 4000

    Featurizing sample 5000

    Featurizing sample 6000

    Featurizing sample 7000

    Featurizing sample 8000

    TIMING: featurizing shard 1 took 15.454 s

    Loading shard 3 of size 8192.

    Featurizing sample 0

    Featurizing sample 1000

    Featurizing sample 2000

    Featurizing sample 3000

    Featurizing sample 4000

    Featurizing sample 5000

    Featurizing sample 6000

    Featurizing sample 7000

    Featurizing sample 8000

    TIMING: featurizing shard 2 took 15.119 s

    Loading shard 4 of size 8192.

    Featurizing sample 0

    Featurizing sample 1000

    Featurizing sample 2000

    Featurizing sample 3000

    Featurizing sample 4000

    Featurizing sample 5000

    Featurizing sample 6000

    Featurizing sample 7000

    Featurizing sample 8000

    TIMING: featurizing shard 3 took 15.337 s

    Loading shard 5 of size 8192.

    Featurizing sample 0

    Featurizing sample 1000

    Featurizing sample 2000

    Featurizing sample 3000

    Featurizing sample 4000

    Featurizing sample 5000

    Featurizing sample 6000

    Featurizing sample 7000

    Featurizing sample 8000

    TIMING: featurizing shard 4 took 15.104 s

    Loading shard 6 of size 8192.

    Featurizing sample 0

    Featurizing sample 1000

    Featurizing sample 2000

    Featurizing sample 3000

    Featurizing sample 4000

    Featurizing sample 5000

    Featurizing sample 6000

    Featurizing sample 7000

    Featurizing sample 8000

    TIMING: featurizing shard 5 took 15.349 s

    Loading shard 7 of size 8192.

    Featurizing sample 0

    Featurizing sample 1000

    Featurizing sample 2000

    Featurizing sample 3000

    Featurizing sample 4000

    Featurizing sample 5000

    Featurizing sample 6000

    Featurizing sample 7000

    Featurizing sample 8000

    TIMING: featurizing shard 6 took 15.181 s

    Loading shard 8 of size 8192.

    Featurizing sample 0

    Featurizing sample 1000

    Featurizing sample 2000

    Featurizing sample 3000

    Featurizing sample 4000

    Featurizing sample 5000

    Featurizing sample 6000

    Featurizing sample 7000

    Featurizing sample 8000

    TIMING: featurizing shard 7 took 15.062 s

    Loading shard 9 of size 8192.

    Featurizing sample 0

    Featurizing sample 1000

    Featurizing sample 2000

    Featurizing sample 3000

    Featurizing sample 4000

    Featurizing sample 5000

    Featurizing sample 6000

    Featurizing sample 7000

    Featurizing sample 8000

    TIMING: featurizing shard 8 took 14.960 s

    Loading shard 10 of size 8192.

    Featurizing sample 0

    Featurizing sample 1000

    Featurizing sample 2000

    Featurizing sample 3000

    Featurizing sample 4000

    Featurizing sample 5000

    Featurizing sample 6000

    Featurizing sample 7000

    Featurizing sample 8000

    TIMING: featurizing shard 9 took 15.355 s

    Loading shard 11 of size 8192.

    Featurizing sample 0

    Featurizing sample 1000

    Featurizing sample 2000

    Featurizing sample 3000

    Featurizing sample 4000

    Featurizing sample 5000

    Featurizing sample 6000

    Featurizing sample 7000

    Featurizing sample 8000

    TIMING: featurizing shard 10 took 15.209 s

    Loading shard 12 of size 8192.

    Featurizing sample 0

    Featurizing sample 1000

    Featurizing sample 2000

    Featurizing sample 3000

    TIMING: featurizing shard 11 took 5.511 s

    TIMING: dataset construction took 176.355 s

    Loading dataset from disk.



%% Cell type:code id: tags:



``` python

splitter = dc.splits.RandomSplitter(dataset_file)

train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(

    dataset)

#NOTE THE RENAMING:

valid_dataset, test_dataset = test_dataset, valid_dataset

```



%% Output



    Computing train/valid/test indices

    TIMING: dataset construction took 3.757 s

    Loading dataset from disk.

    TIMING: dataset construction took 1.717 s

    Loading dataset from disk.

    TIMING: dataset construction took 1.707 s

    Loading dataset from disk.



%% Cell type:code id: tags:



``` python

import numpy as np

import numpy.random



params_dict = {"activation": ["relu"],

               "momentum": [.9],

               "batch_size": [50],

               "init": ["glorot_uniform"],

               "data_shape": [train_dataset.get_data_shape()],

               "learning_rate": [1e-3],

               "decay": [1e-6],

               "nb_epoch": [1],

               "nesterov": [False],

               "dropouts": [(.5,)],

               "nb_layers": [1],

               "batchnorm": [False],

               "layer_sizes": [(1000,)],

               "weight_init_stddevs": [(.1,)],

               "bias_init_consts": [(1.,)],

               "penalty": [0.],

              }





n_features = train_dataset.get_data_shape()[0]

def model_builder(model_params, model_dir):

  model = dc.models.TensorflowMultiTaskClassifier(

    len(MUV_tasks), n_features, **model_params)

  return model



metric = dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean)

optimizer = dc.hyper.HyperparamOpt(model_builder)

best_dnn, best_hyperparams, all_results = optimizer.hyperparam_search(

    params_dict, train_dataset, valid_dataset, [], metric)

```



%% Output



    Fitting model 1/1

    hyperparameters: {'learning_rate': 0.001, 'layer_sizes': (1000,), 'data_shape': (1024,), 'dropouts': (0.5,), 'activation': 'relu', 'decay': 1e-06, 'batch_size': 50, 'penalty': 0.0, 'nesterov': False, 'init': 'glorot_uniform', 'bias_init_consts': (1.0,), 'weight_init_stddevs': (0.1,), 'batchnorm': False, 'nb_layers': 1, 'nb_epoch': 1, 'momentum': 0.9}

    Training for 1 epochs

    On batch 0

    On batch 50

    On batch 100

    On batch 150

    On batch 200

    On batch 250

    On batch 300

    On batch 350

    On batch 400

    On batch 450

    On batch 500

    On batch 550

    On batch 600

    On batch 650

    On batch 700

    On batch 750

    On batch 800

    On batch 850

    On batch 900

    On batch 950

    On batch 1000

    On batch 1050

    On batch 1100

    On batch 1150

    On batch 1200

    On batch 1250

    On batch 1300

    On batch 1350

    On batch 1400

    On batch 1450

    Ending epoch 0: Average loss 0.0512837

    On batch 0

    TIMING: model fitting took 21.154 s True

    computed_metrics: [0.82459677419354838, 0.57987551867219911, 0.87625923438549358, 0.40115904700579524, 0.85100593667546176, 0.84176720285969608, 0.81982616866337787, 0.92716408268733852, 0.90555555555555556, 0.93358568479008941, 0.84312370421561855, 0.5993421052631579, 0.40930420711974114, 0.53205995041694831, 0.99836708033964727, 0.6931528662420382, 0.89704918032786884]

    Model 1/1, Metric mean-roc_auc_score, Validation set 0: 0.760776

    	best_validation_score so far: 0.760776

    computed_metrics: [0.88035724476402444, 0.92499356167911406, 0.98634926369263543, 0.86291516863550766, 0.95042120575284494, 0.97632672092234651, 0.9834740792000799, 0.91723021876461464, 0.9288788241326269, 0.9427229610525234, 0.9281144552776599, 0.94111351509505148, 0.90709998845843109, 0.93500087572450941, 0.95015000422547113, 0.92490461101880572, 0.97988502677604972]

    Best hyperparameters: (1e-06, (1024,), 1, 'relu', (1000,), 50, 0.0, False, 'glorot_uniform', (1.0,), (0.1,), 1, False, (0.5,), 0.001, 0.9)

    train_score: 0.936467

    validation_score: 0.760776

examples/notebooks/mnist.ipynb

0 → 100644
+312 −0

File added.

Preview size limit exceeded, changes collapsed.

examples/notebooks/quantum_machine_gdb1k.ipynb

+16 −37
Original line number Diff line number Diff line 
%% Cell type:markdown id: tags:



Setting up imports



%% Cell type:code id: tags:



``` python

%load_ext autoreload

%autoreload 2

%pdb off

"""

Not Currently Working

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



__author__ = "Joseph Gomes"

__copyright__ = "Copyright 2016, Stanford University"

__license__ = "LGPL"



import os

import unittest

import tempfile

import shutil



import numpy as np

import numpy.random



from deepchem import metrics

from deepchem.datasets import Dataset

from deepchem.data.datasets import Dataset

from deepchem.featurizers.featurize import DataFeaturizer

from deepchem.featurizers.featurize import FeaturizedSamples

from deepchem.hyperparameters import HyperparamOpt

from deepchem.metrics import Metric

from deepchem.models import Model

from deepchem.models.sklearn_models import SklearnModel

from deepchem.transformers import NormalizationTransformer

from deepchem.utils.evaluate import Evaluator

from sklearn.ensemble import RandomForestRegressor

from sklearn.kernel_ridge import KernelRidge

```



%% Output



    The autoreload extension is already loaded. To reload it, use:

      %reload_ext autoreload

    Automatic pdb calling has been turned OFF



    ---------------------------------------------------------------------------

    ImportError                               Traceback (most recent call last)

    <ipython-input-2-a6ac7c9c202f> in <module>()

         20 from deepchem import metrics

         21 from deepchem.data.datasets import Dataset

    ---> 22 from deepchem.featurizers.featurize import DataFeaturizer

         23 from deepchem.featurizers.featurize import FeaturizedSamples

         24 from deepchem.hyperparameters import HyperparamOpt

    ImportError: No module named featurizers.featurize



%% Cell type:markdown id: tags:



Creating temporary directories



%% Cell type:code id: tags:



``` python

feature_dir = tempfile.mkdtemp()

samples_dir = tempfile.mkdtemp()

train_dir = tempfile.mkdtemp()

valid_dir = tempfile.mkdtemp()

test_dir = tempfile.mkdtemp()

model_dir = tempfile.mkdtemp()

```



%% Cell type:markdown id: tags:



Setting up model variables



%% Cell type:code id: tags:



``` python

from deepchem.featurizers.coulomb_matrices import CoulombMatrixEig

compound_featurizers = [CoulombMatrixEig(23, remove_hydrogens=False)]

complex_featurizers = []

tasks = ["atomization_energy"]

task_type = "regression"

task_types = {task: task_type for task in tasks}

input_file = "../datasets/gdb1k.sdf"

smiles_field = "smiles"

mol_field = "mol"

```



%% Cell type:markdown id: tags:



Load featurized data



%% Cell type:code id: tags:



``` python

featurizers = compound_featurizers + complex_featurizers

featurizer = DataFeaturizer(tasks=tasks,

                            smiles_field=smiles_field,

                            mol_field=mol_field,

                            compound_featurizers=compound_featurizers,

                            complex_featurizers=complex_featurizers, verbosity="high")

```



%% Cell type:code id: tags:



``` python

featurized_samples = featurizer.featurize(input_file, feature_dir, samples_dir)

```



%% Output



    Loading raw samples now.

    Reading structures from ../datasets/gdb1k.sdf.

    Loaded raw data frame from file.

    About to preprocess samples.

    Sharding and standardizing into shard-1 / 1 shards

    Currently featurizing feature_type: CoulombMatrixEig

    Featurizing sample 0

    Saving compounds to disk



%% Cell type:markdown id: tags:



Perform Train, Validation, and Testing Split



%% Cell type:code id: tags:



``` python

from deepchem.splits import RandomSplitter

random_splitter = RandomSplitter()

train_samples, valid_samples, test_samples = random_splitter.train_valid_test_split(featurized_samples,

    train_dir, valid_dir, test_dir)

```



%% Cell type:markdown id: tags:



Creating datasets



%% Cell type:code id: tags:



``` python

train_dataset = Dataset(data_dir=train_dir, samples=train_samples,

                        featurizers=featurizers, tasks=tasks)

valid_dataset = Dataset(data_dir=valid_dir, samples=valid_samples,

                        featurizers=featurizers, tasks=tasks)

test_dataset = Dataset(data_dir=test_dir, samples=test_samples,

                       featurizers=featurizers, tasks=tasks)

```



%% Output



    /home/joegomes/deepchem/deepchem/datasets/__init__.py:402: UnicodeWarning: Unicode equal comparison failed to convert both arguments to Unicode - interpreting them as being unequal

      if features[feature_ind] == "":

    /home/joegomes/deepchem/deepchem/datasets/__init__.py:411: UnicodeWarning: Unicode equal comparison failed to convert both arguments to Unicode - interpreting them as being unequal

      if y[ind, task] == "":



%% Cell type:markdown id: tags:



Transforming datasets



%% Cell type:code id: tags:



``` python

input_transformers = [NormalizationTransformer(transform_X=True, dataset=train_dataset)]

output_transformers = [NormalizationTransformer(transform_y=True, dataset=train_dataset)]

transformers = input_transformers + output_transformers

for transformer in transformers:

    transformer.transform(train_dataset)

for transformer in transformers:

    transformer.transform(valid_dataset)

for transformer in transformers:

    transformer.transform(test_dataset)

```



%% Cell type:markdown id: tags:



Fit Random Forest with hyperparameter search



%% Cell type:code id: tags:



``` python

def rf_model_builder(tasks, task_types, params_dict, model_dir, verbosity=None):

    """Builds random forests given hyperparameters.



    """

    n_estimators = params_dict["n_estimators"]

    max_features = params_dict["max_features"]

    return SklearnModel(

        tasks, task_types, params_dict, model_dir,

        mode="regression",

        model_instance=RandomForestRegressor(n_estimators=n_estimators,

                                             max_features=max_features))



params_dict = {

    "n_estimators": [10, 100],

    "data_shape": [train_dataset.get_data_shape()],

    "max_features": ["auto"],

    }



metric = Metric(metrics.mean_absolute_error)

optimizer = HyperparamOpt(rf_model_builder, tasks, task_types, verbosity="low")

best_model, best_hyperparams, all_results = optimizer.hyperparam_search(

    params_dict, train_dataset, valid_dataset, output_transformers,

    metric, use_max="False", logdir=None)

```



%% Output



    Model 1/2, Metric mean_absolute_error, Validation set 0: 27.577397

    	best_validation_score so far: 27.577397

    Model 2/2, Metric mean_absolute_error, Validation set 1: 24.751563

    	best_validation_score so far: 27.577397

    Best hyperparameters: (10, (23,), u'auto')

    train_score: 10.962967

    validation_score: 27.577397



%% Cell type:code id: tags:



``` python

def kr_model_builder(tasks, task_types, params_dict, model_dir, verbosity=None):

    """Builds random forests given hyperparameters.



    """

    kernel = params_dict["kernel"]

    alpha = params_dict["alpha"]

    gamma = params_dict["gamma"]

    return SklearnModel(

        tasks, task_types, params_dict, model_dir,

        mode="regression",

        model_instance=KernelRidge(alpha=alpha,kernel=kernel,gamma=gamma))



params_dict = {

    "kernel": ["laplacian"],

    "alpha": [0.0001],

    "gamma": [0.0001]

    }



metric = Metric(metrics.mean_absolute_error)

optimizer = HyperparamOpt(kr_model_builder, tasks, task_types, verbosity="low")

best_model, best_hyperparams, all_results = optimizer.hyperparam_search(

    params_dict, train_dataset, valid_dataset, output_transformers,

    metric, use_max="False", logdir=None)

```



%% Output



    Model 1/1, Metric mean_absolute_error, Validation set 0: 11.888263

    	best_validation_score so far: 11.888263

    Best hyperparameters: (u'laplacian', 0.0001, 0.0001)

    train_score: 8.300859

    validation_score: 11.888263



%% Cell type:code id: tags:



``` python

```

CRA Git | Maintained and supported by SUSTech CRA and CCSE