#training model for TF
from __future__ import print_function
from __future__ import division
from __future__ import unicode_literals
import os
import tempfile
import shutil
import numpy as np
import deepchem as dc
from kaggle_datasets import load_kaggle
sh_size = 2000
num_trials = 2
KAGGLE_tasks, datasets, transformers = load_kaggle(sh_size=sh_size)
train_dataset, valid_dataset, test_dataset = datasets
print("Number of compounds in train set")
print(len(train_dataset))
print("Number of compounds in validation set")
print(len(valid_dataset))
print("Number of compounds in test set")
print(len(test_dataset))
all_results = []
for trial in range(num_trials):
#create the actual model
n_layers = 3
nb_epoch = 100
model = dc.models.TensorflowMultiTaskRegressor(
from __future__ import unicode_literals
import os
import numpy as np
import tempfile
import shutil
import deepchem as dc
from sklearn.ensemble import RandomForestRegressor
from kaggle_datasets import load_kaggle
###Load data###
np.random.seed(123)
shard_size = 2000
num_shards_per_batch = 4
print("About to load KAGGLE data.")
KAGGLE_tasks, datasets, transformers = load_kaggle(
shard_size=shard_size, num_shards_per_batch=num_shards_per_batch)
train_dataset, valid_dataset, test_dataset = datasets
print("Number of compounds in train set")
print(len(train_dataset))
print("Number of compounds in validation set")
print(len(valid_dataset))
print("Number of compounds in test set")
print(len(test_dataset))
num_features = train_dataset.get_data_shape()[0]
print("Num features: %d" % num_features)
def task_model_builder(model_dir):
sklearn_model = RandomForestRegressor(
n_estimators=100, max_features=int(num_features/3),
from __future__ import division
from __future__ import unicode_literals
import os
import numpy as np
import tempfile
import shutil
import deepchem as dc
from kaggle_datasets import load_kaggle
###Load data###
shard_size = 2000
num_trials = 2
print("About to load KAGGLE data.")
KAGGLE_tasks, datasets, transformers = load_kaggle(shard_size=shard_size)
train_dataset, valid_dataset, test_dataset = datasets
print("Number of compounds in train set")
print(len(train_dataset))
print("Number of compounds in validation set")
print(len(valid_dataset))
print("Number of compounds in test set")
print(len(test_dataset))
metric = dc.metrics.Metric(dc.metrics.pearson_r2_score, task_averager=np.mean)
###Create model###
n_layers = 3
nb_epoch = 100
n_features = train_dataset.get_data_shape()[0]