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_simulated(self):
exp_dataframe = pd.read_pickle(
os.path.join(CAMD_TEST_FILES, "mn-ni-o-sb.pickle"))
experiment = ATFSampler(exp_dataframe)
candidate_data = exp_dataframe.iloc[:, :-11]
# Set up agents and loop parameters
agent = AgentStabilityAdaBoost(
model=MLPRegressor(hidden_layer_sizes=(84, 50)),
n_query=2,
hull_distance=0.2,
exploit_fraction=1.0,
uncertainty=True,
alpha=0.5,
diversify=True,
n_estimators=20)
analyzer = StabilityAnalyzer(hull_distance=0.2)
# Reduce seed_data
icsd_data = load_dataframe("oqmd1.2_exp_based_entries_featurized_v2")
seed_data = filter_dataframe_by_composition(icsd_data, "MnNiOSb")
leftover = ~icsd_data.index.isin(seed_data.index)
# Add some random other data to test compositional flexibility
seed_data = seed_data.append(icsd_data.loc[leftover].sample(30))
del icsd_data
with ScratchDir('.'):
campaign = ProtoDFTCampaign(candidate_data=candidate_data,
agent=agent,
experiment=experiment,
analyzer=analyzer,
seed_data=seed_data,
heuristic_stopper=5)
campaign.autorun()
self.assertTrue(os.path.isfile('hull_finalized.png'))
def setUp(self):
test_dataframe = pd.DataFrame({
"index": np.arange(5),
"squared": np.arange(5)**2
})
params = {"dataframe": test_dataframe, "index_values": [0, 2, 3]}
self.simple_exp = ATFSampler(params)
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_submit_get_results(self):
test_dataframe = pd.DataFrame({
"index": np.arange(5),
"squared": np.arange(5)**2
})
simple_exp = ATFSampler(test_dataframe)
simple_exp.submit(test_dataframe.loc[[0, 2, 3]])
self.assertEqual(simple_exp.job_status, "COMPLETED")
simple_exp.monitor()
self.assertTrue((simple_exp.get_results()['squared'] == [0, 4,
9]).all())
def test_construction(self):
test_dataframe = pd.DataFrame({
"index": np.arange(5),
"squared": np.arange(5)**2
})
params = {"dataframe": test_dataframe}
simple_exp = ATFSampler(params)
self.assertEqual(simple_exp.get_state(), "completed")
self.assertTrue(
(simple_exp.get_results([0, 2,
3])['squared'] == np.array([0, 4,
9])).all())
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 test_simulated(self):
exp_dataframe = pd.read_pickle(
os.path.join(CAMD_TEST_FILES, "mn-ni-o-sb.pickle"))
experiment = ATFSampler(exp_dataframe)
candidate_data = exp_dataframe.iloc[:, :-11]
agent = RandomAgent(n_query=2)
analyzer = StabilityAnalyzer(hull_distance=0.2)
# Reduce seed_data
seed_data = load_dataframe("oqmd1.2_exp_based_entries_featurized_v2")
seed_data = filter_dataframe_by_composition(seed_data, "MnNiOSb")
with ScratchDir('.'):
campaign = ProtoDFTCampaign(candidate_data=candidate_data,
agent=agent,
experiment=experiment,
analyzer=analyzer,
seed_data=seed_data,
heuristic_stopper=5)
campaign.autorun()
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 from_chemsys(cls, chemsys):
"""
Args:
chemsys:
Returns:
"""
s3_prefix = "oqmd-atf/runs/{}".format(chemsys)
df = pd.read_csv(os.path.join(CAMD_TEST_FILES, 'test_df.csv'))
n_seed = 200 # Starting sample size
n_query = 10 # This many new candidates are "calculated with DFT" (i.e. requested from Oracle -- DFT)
agent = RandomAgent(n_query=n_query)
analyzer = StabilityAnalyzer(hull_distance=0.05)
experiment = ATFSampler(dataframe=df)
candidate_data = df
return cls(candidate_data,
agent,
experiment,
analyzer,
create_seed=n_seed,
s3_prefix=s3_prefix)
def test_gp_bucb_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_seed = 5 # This many samples are randomly acquired in the beginning to form a seed.
agent = GPBatchUCB(n_query=2)
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)
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_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_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_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_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)
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)