def test_gp_bagging(self):
df = pd.read_csv(os.path.join(CAMD_TEST_FILES, 'test_df.csv'))
df_sub = df[df['N_species'] <= 3]
n_seed = 200 # Starting sample size
agent = BaggedGaussianProcessStabilityAgent(
n_query=10,
hull_distance=0.05,
alpha=0.5, # Fraction of std to include in expected improvement
n_estimators=2,
max_samples=195,
parallel=False)
analyzer = StabilityAnalyzer(hull_distance=0.05, parallel=False)
experiment = ATFSampler(df_sub)
candidate_data = df_sub
new_loop = Campaign(candidate_data,
agent,
experiment,
analyzer,
create_seed=n_seed)
new_loop.initialize()
self.assertTrue(new_loop.initialized)
new_loop.auto_loop(6)
self.assertTrue(True)
def test_sync(self):
with ScratchDir('.'):
df = pd.read_csv(os.path.join(CAMD_TEST_FILES, 'test_df.csv'))
# Construct and start campaign
new_campaign = Campaign(df,
AgentStabilityML5(),
ATFSampler(df),
StabilityAnalyzer(),
create_seed=10,
s3_prefix="test")
new_campaign.auto_loop(n_iterations=3,
save_iterations=True,
initialize=True)
# Test iteration read
s3 = boto3.resource('s3')
obj = s3.Object(CAMD_S3_BUCKET, "test/iteration.json")
loaded = json.loads(obj.get()['Body'].read())
self.assertEqual(loaded, 2)
# Test save directories
for iteration in [-1, 0, 1, 2]:
obj = s3.Object(CAMD_S3_BUCKET, f"test/{iteration}/iteration.json")
loaded = json.loads(obj.get()['Body'].read())
self.assertEqual(loaded, iteration)
def test_svgp_loop(self):
df = pd.read_csv(os.path.join(CAMD_TEST_FILES, 'test_df.csv'))
df_sub = df[df['N_species'] <= 3]
n_seed = 200 # Starting sample size
agent = SVGProcessStabilityAgent(n_query=10, hull_distance=0.05, alpha=0.5, M=100)
analyzer = StabilityAnalyzer(hull_distance=0.05, parallel=False)
experiment = ATFSampler(df_sub)
candidate_data = df_sub
new_loop = Campaign(candidate_data, agent, experiment, analyzer,
create_seed=n_seed)
new_loop.initialize()
self.assertTrue(new_loop.initialized)
new_loop.auto_loop(3)
self.assertTrue(True)
def test_qbc_agent_loop(self):
df = pd.read_csv(os.path.join(CAMD_TEST_FILES, 'test_df.csv'))
df_sub = df[df['N_species'] <= 3]
n_seed = 200 # Starting sample size
agent = QBCStabilityAgent(model=MLPRegressor(hidden_layer_sizes=(84, 50)),
n_query=10, hull_distance=0.05, alpha=0.5)
analyzer = StabilityAnalyzer(hull_distance=0.05, parallel=False)
experiment = ATFSampler(dataframe=df_sub)
candidate_data = df_sub
new_loop = Campaign(candidate_data, agent, experiment, analyzer,
create_seed=n_seed)
new_loop.initialize()
self.assertTrue(new_loop.initialized)
new_loop.auto_loop(3)
self.assertTrue(True)
def test_simple_gp_loop(self):
df = pd.read_csv(os.path.join(CAMD_TEST_FILES, 'test_df.csv'))
df_sub = df[df['N_species'] <= 3]
n_seed = 200 # Starting sample size
n_query = 10 # This many new candidates are "calculated with DFT" (i.e. requested from Oracle -- DFT)
agent = GaussianProcessStabilityAgent(n_query=n_query, hull_distance=0.05, alpha=0.5, parallel=False)
analyzer = StabilityAnalyzer(hull_distance=0.05, parallel=False)
experiment = ATFSampler(dataframe=df_sub)
candidate_data = df_sub
new_loop = Campaign(candidate_data, agent, experiment, analyzer,
create_seed=n_seed)
new_loop.initialize()
self.assertTrue(new_loop.initialized)
new_loop.auto_loop(2)
self.assertTrue(True)
def test_agent(self, agent):
"""
Runs a simulation of a given agent according to the
class attributes
Args:
agent (HypothesisAgent):
Returns:
None
"""
campaign = Campaign(
candidate_data=self.atf_dataframe,
seed_data=self.seed_data,
agent=agent,
analyzer=self.analyzer,
experiment=ATFSampler(dataframe=self.atf_dataframe),
)
campaign.auto_loop(n_iterations=self.iterations, initialize=True)
return campaign
from sklearn.neural_network import MLPRegressor
from camd.agent.stability import AgentStabilityML5
from camd.analysis import StabilityAnalyzer
from camd.experiment.base import ATFSampler
from camd.utils.data import load_default_atf_data
##########################################################
# Load dataset and filter by N_species of 2 or less
##########################################################
df = load_default_atf_data()
## Epsilon-Greedy
n_seed = 5000 # Starting sample size - a seed of this size will be randomly chosen.
n_query = 200 # This many new candidates are "calculated with DFT" (i.e. requested from Oracle -- DFT)
agent = AgentStabilityML5(model=MLPRegressor(hidden_layer_sizes=(84, 50)),
n_query=n_query,
hull_distance=0.05,
exploit_fraction=0.5)
analyzer = StabilityAnalyzer(hull_distance=0.05)
experiment = ATFSampler(dataframe=df)
candidate_data = df
##########################################################
new_loop = Campaign(candidate_data,
agent,
experiment,
analyzer,
create_seed=n_seed)
new_loop.auto_loop(n_iterations=4, initialize=True)