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_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_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_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_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)