def test_sample_1():
# Test that the code actually runs and gives something non-crazy
# Make an ergodic dataset with two gaussian centers offset by 25 units.
chunk = np.random.normal(size=(20000, 3))
data = [np.vstack((chunk, chunk + 25)), np.vstack((chunk + 25, chunk))]
clusterer = cluster.KMeans(n_clusters=2)
msm = MarkovStateModel()
pipeline = sklearn.pipeline.Pipeline([("clusterer", clusterer),
("msm", msm)])
pipeline.fit(data)
trimmed_assignments = pipeline.transform(data)
# Now let's make make the output assignments start with
# zero at the first position.
i0 = trimmed_assignments[0][0]
if i0 == 1:
for m in trimmed_assignments:
m *= -1
m += 1
pairs = msm.draw_samples(trimmed_assignments, 2000)
samples = map_drawn_samples(pairs, data)
mu = np.mean(samples, axis=1)
eq(mu, np.array([[0., 0., 0.0], [25., 25., 25.]]), decimal=1)
# We should make sure we can sample from Trajectory objects too...
# Create a fake topology with 1 atom to match our input dataset
top = md.Topology.from_dataframe(pd.DataFrame({
"serial": [0],
"name": ["HN"],
"element": ["H"],
"resSeq": [1],
"resName": "RES",
"chainID": [0]
}),
bonds=np.zeros(shape=(0, 2), dtype='int'))
# np.newaxis reshapes the data to have a 40000 frames, 1 atom, 3 xyz
trajectories = [md.Trajectory(x[:, np.newaxis], top) for x in data]
trj_samples = map_drawn_samples(pairs, trajectories)
mu = np.array([t.xyz.mean(0)[0] for t in trj_samples])
eq(mu, np.array([[0., 0., 0.0], [25., 25., 25.]]), decimal=1)
def test_sample_1():
# Test that the code actually runs and gives something non-crazy
# Make an ergodic dataset with two gaussian centers offset by 25 units.
chunk = np.random.normal(size=(20000, 3))
data = [np.vstack((chunk, chunk + 25)), np.vstack((chunk + 25, chunk))]
clusterer = cluster.KMeans(n_clusters=2)
msm = MarkovStateModel()
pipeline = sklearn.pipeline.Pipeline(
[("clusterer", clusterer), ("msm", msm)]
)
pipeline.fit(data)
trimmed_assignments = pipeline.transform(data)
# Now let's make make the output assignments start with
# zero at the first position.
i0 = trimmed_assignments[0][0]
if i0 == 1:
for m in trimmed_assignments:
m *= -1
m += 1
pairs = msm.draw_samples(trimmed_assignments, 2000)
samples = map_drawn_samples(pairs, data)
mu = np.mean(samples, axis=1)
eq(mu, np.array([[0., 0., 0.0], [25., 25., 25.]]), decimal=1)
# We should make sure we can sample from Trajectory objects too...
# Create a fake topology with 1 atom to match our input dataset
top = md.Topology.from_dataframe(
pd.DataFrame({
"serial": [0], "name": ["HN"], "element": ["H"], "resSeq": [1],
"resName": "RES", "chainID": [0]
}), bonds=np.zeros(shape=(0, 2), dtype='int')
)
# np.newaxis reshapes the data to have a 40000 frames, 1 atom, 3 xyz
trajectories = [md.Trajectory(x[:, np.newaxis], top)
for x in data]
trj_samples = map_drawn_samples(pairs, trajectories)
mu = np.array([t.xyz.mean(0)[0] for t in trj_samples])
eq(mu, np.array([[0., 0., 0.0], [25., 25., 25.]]), decimal=1)
import mixtape.utils
n_iter = 1000
n_choose = 50
stride = 1
lag_time = 1
n_components = 2
filenames = glob.glob("./Trajectories/*.h5")
trajectories = [md.load(filename) for filename in filenames]
if len(trajectories) > 1:
train = trajectories[0::2]
test = trajectories[1::2]
else:
train = [trajectories[0][0:trajectories[0].n_frames/2]]
test = [trajectories[0][trajectories[0].n_frames/2:]]
featurizer = sklearn.externals.joblib.load("./featurizer-%d-%d.job" % (n_components, n_choose))
tica = mixtape.tica.tICA(lag_time=lag_time, n_components=n_components)
pipeline = sklearn.pipeline.Pipeline([("features", featurizer), ('tica', tica)])
pipeline.fit(train)
print(pipeline.score(train), pipeline.score(test))
pipeline.fit(trajectories)
X = pipeline.transform(trajectories)
q = np.concatenate(X)
hexbin(q[:, 0], q[:, 1], bins='log')
def main(args):
if args.predict is None:
# We are training a model.
np.random.seed(args.seed)
# Create a random generator with a given seed
generator = np.random.RandomState(args.seed)
train = Dataset()
data = train.data
target = train.target
# making features
bool_train = np.all(data.astype(int) == data, axis=0)
int_train = [i for i, b in enumerate(bool_train) if b]
real_train = [i for i, b in enumerate(bool_train) if not b]
i = "tr"
transformers = []
for arr, encoder in zip([int_train, real_train], [
sklearn.preprocessing.OneHotEncoder(sparse=False,
handle_unknown="ignore"),
sklearn.preprocessing.StandardScaler()
]):
if len(arr) > 0:
transformers.append((i, encoder, arr))
i += 'a'
ct = sklearn.compose.ColumnTransformer(transformers=transformers)
poly = sklearn.preprocessing.PolynomialFeatures(2, include_bias=False)
pipeline = sklearn.pipeline.Pipeline([('ct', ct), ('pl', poly)])
data = pipeline.fit_transform(data)
# TODO: Train a model on the given dataset and store it in `model`.
# adding ones
data = np.c_[data, np.ones(data.shape[0])]
# Generate initial linear regression weights
weights = generator.uniform(size=data.shape[1])
for epoch in range(args.epochs):
permutation = generator.permutation(data.shape[0])
i = 0
n_batches = data.shape[0] // args.batch_size
for batch in range(n_batches):
gradient_sum = np.zeros(shape=weights.shape)
for sample in range(args.batch_size):
index = permutation[i + sample]
predictions = np.transpose(data[index]) @ weights
gradient_sum += (predictions - target[index]) * data[index]
average_gradient = gradient_sum / args.batch_size
# SGD update
weights = weights - args.learning_rate * average_gradient
i = i + args.batch_size
model = weights
# Serialize features
with lzma.open(args.feature_path, "wb") as feature_file:
pickle.dump(pipeline, feature_file)
# Serialize the model.
with lzma.open(args.model_path, "wb") as model_file:
pickle.dump(model, model_file)
else:
# Use the model and return test set predictions, as either a Python list or a NumPy array.
test = Dataset(args.predict)
with lzma.open(args.model_path, "rb") as model_file:
model = pickle.load(model_file)
with lzma.open(args.feature_path, "rb") as feature_file:
pipeline = pickle.load(feature_file)
test_d = pipeline.transform(test.data)
test_d = np.c_[test_d, np.ones(test_d.shape[0])]
# TODO: Generate `predictions` with the test set predictions.
predictions = test_d @ model
return predictions
