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_random_agent_loop(self):
df = load_default_atf_data()
n_seed = 200 # Starting sample size
agent = RandomAgent(n_query=10)
analyzer = StabilityAnalyzer(hull_distance=0.05, parallel=False)
experiment = ATFSampler(dataframe=df)
candidate_data = df
new_loop = Campaign(candidate_data,
agent,
experiment,
analyzer,
create_seed=n_seed)
new_loop.initialize()
self.assertFalse(new_loop.create_seed)
for _ in range(6):
new_loop.run()
self.assertTrue(True)
# Testing the continuation
new_loop = Campaign(candidate_data,
agent,
experiment,
analyzer,
create_seed=n_seed)
self.assertTrue(new_loop.initialized)
self.assertEqual(new_loop.iteration, 6)
self.assertEqual(new_loop.loop_state, None)
new_loop.run()
self.assertTrue(True)
self.assertEqual(new_loop.iteration, 7)
def test_mp_loop(self):
df = pd.read_csv(os.path.join(CAMD_TEST_FILES, 'test_df_analysis.csv'))
df['id'] = [int(mp_id.replace("mp-", "").replace('mvc-', ''))
for mp_id in df['id']]
df.set_index("id")
df['Composition'] = df['formula']
# Just use the Ti-O-N chemsys
seed = df.iloc[:38]
candidates = df.iloc[38:209]
agent = RandomAgent(n_query=20)
analyzer = StabilityAnalyzer(hull_distance=0.05, parallel=False)
experiment = ATFSampler(dataframe=df)
new_loop = Campaign(
candidates, agent, experiment, analyzer, seed_data=seed
)
new_loop.initialize()
for iteration in range(6):
new_loop.run()
self.assertTrue(os.path.isfile("hull.png"))
if iteration >= 1:
self.assertTrue(
os.path.isfile("history.pickle"))
# Testing the continuation
new_loop = Campaign(df, agent, experiment, analyzer)
self.assertTrue(new_loop.initialized)
self.assertEqual(new_loop.iteration, 6)
self.assertEqual(new_loop.loop_state, None)
new_loop.run()
self.assertTrue(True)
self.assertEqual(new_loop.iteration, 7)
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.initialize()
s3 = boto3.resource('s3')
obj = s3.Object(CAMD_S3_BUCKET, "test/iteration.json")
loaded = json.loads(obj.get()['Body'].read())
self.assertEqual(loaded, 0)
def update_run(folder):
"""
Updates existing runs in s3 to include plots
Returns:
List of modified chemsys
"""
required_files = ["seed_data.pickle", "report.log"]
with cd(folder):
if os.path.isfile("error.json"):
error = loadfn("error.json")
print("{} ERROR: {}".format(folder, error))
if not all([os.path.isfile(fn) for fn in required_files]):
print("{} ERROR: no seed data, no analysis to be done")
else:
analyzer = StabilityAnalyzer(hull_distance=0.2)
# Generate report plots
for iteration in range(0, 25):
print("{}: {}".format(folder, iteration))
if not os.path.isdir(str(iteration)) or not os.path.isdir(
str(iteration - 1)):
continue
with open(os.path.join(str(iteration), "seed_data.pickle"),
"rb") as f:
result_df = pickle.load(f)
all_result_ids = loadfn(
os.path.join(str(iteration - 1),
"consumed_candidates.json"))
new_result_ids = loadfn(
os.path.join(str(iteration - 1),
"submitted_experiment_requests.json"))
analyzer.plot_hull(df=result_df,
new_result_ids=new_result_ids,
all_result_ids=all_result_ids,
filename="hull_{}.png".format(iteration),
finalize=False)
Campaign.generate_report_plot()
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
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_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_random_agent_loop(self):
df = load_dataframe("oqmd1.2_exp_based_entries_featurized_v2")
n_seed = 5000
agent = RandomAgent(n_query=200)
analyzer = StabilityAnalyzer(hull_distance=0.05, parallel=False)
experiment = ATFSampler(dataframe=df)
candidate_data = df
new_loop = Campaign(candidate_data, agent, experiment, analyzer,
create_seed=n_seed)
new_loop.initialize()
self.assertFalse(new_loop.create_seed)
for _ in range(6):
new_loop.run()
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_gp_ucb_generic(self):
def f(x):
return np.sin(x) * np.sin(x) * (x ** 2)
x = np.linspace(0, 10, 500)
y = f(x)
df = pd.DataFrame({'x': x, 'target': y})
N_query = 2 # This many experiments are requested in each iteration
N_seed = 5 # This many samples are randomly acquired in the beginning to form a seed.
agent = GenericGPUCB(n_query=2,kernel=ConstantKernel(100.0) + RBF(10.0) * ConstantKernel(1.0))
analyzer = GenericMaxAnalyzer(threshold=58)
experiment = ATFSampler(dataframe=df)
candidate_data = df
new_loop = Campaign(candidate_data, agent, experiment, analyzer, create_seed=N_seed)
new_loop.initialize(random_state=20)
self.assertTrue(new_loop.initialized)
new_loop.run()
self.assertTrue(True)
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)
from camd.campaigns.base import Campaign
from camd.agent.stability import QBCStabilityAgent
from camd.analysis import StabilityAnalyzer
from camd.experiment.dft import OqmdDFTonMC1
from sklearn.neural_network import MLPRegressor
# Let's create our search domain as Ir-Fe-O ternary. We restrict our search to structures with max 10 atoms.
# We further restrict the possible stoichiometry coefficients to integers to [1,4).
domain = StructureDomain.from_bounds(["Ir", "Fe", "O"], charge_balanced=True, n_max_atoms = 10, **{"grid": range(1,4)})
candidate_data = domain.candidates()
structure_dict = domain.hypo_structures_dict
# Setup the loop for this campaign.
agent = QBCStabilityAgent(MLPRegressor(hidden_layer_sizes=(84, 50)),
n_query=3,
hull_distance=0.1,
training_fraction=0.5,
n_members=10)
analyzer = StabilityAnalyzer(hull_distance=0.05)
experiment = OqmdDFTonMC1 # This is the Experiment method to run OQMD compatible DFT on AWS-MC1
experiment_params = {'structure_dict': structure_dict, # Parameters of this experiment class include structures.
'candidate_data': candidate_data, 'timeout': 30000}
# Campaign class puts all the above pieces together.
new_loop = Campaign(candidate_data, agent, experiment, analyzer,
agent_params=agent_params, analyzer_params=analyzer_params, experiment_params=experiment_params)
# Let's start the campaign!
new_loop.auto_loop_in_directories(n_iterations=3, timeout=1, monitor=True, initialize=True, with_icsd=True)