def test_pipeline():
pipeline = dl.Pipeline([("scale", StandardScaler()), ("fdr", SelectFdr()),
("svm", LinearSVC())])
pipeline = pipeline.fit(X, y)
y2 = pipeline.predict(X)
score = pipeline.score(X, y)
assert isinstance(y2, di.Value)
assert isinstance(score, di.Value)
assert isinstance(score.compute(), float)
assert pipeline.score(X, y).key == pipeline.score(X, y).key
assert score.compute() == score.compute()
y22 = y2.compute()
assert y22.shape == y.shape
assert y22.dtype == y.dtype
skpipeline = sklearn.pipeline.Pipeline([("scale", StandardScaler()),
("fdr", SelectFdr()),
("svm", LinearSVC())])
skpipeline.fit(X, y)
sk_y2 = skpipeline.predict(X)
sk_score = skpipeline.score(X, y)
assert sk_score == score.compute()
def test_pipeline():
pipeline = dl.Pipeline([("scale", StandardScaler()),
("fdr", SelectFdr()),
("svm", LinearSVC())])
pipeline = pipeline.fit(X, y)
y2 = pipeline.predict(X)
score = pipeline.score(X, y)
assert isinstance(y2, di.Value)
assert isinstance(score, di.Value)
assert isinstance(score.compute(), float)
assert pipeline.score(X, y).key == pipeline.score(X, y).key
assert score.compute() == score.compute()
y22 = y2.compute()
assert y22.shape == y.shape
assert y22.dtype == y.dtype
skpipeline = sklearn.pipeline.Pipeline([("scale", StandardScaler()),
("fdr", SelectFdr()),
("svm", LinearSVC())])
skpipeline.fit(X, y)
sk_y2 = skpipeline.predict(X)
sk_score = skpipeline.score(X, y)
assert sk_score == score.compute()
def main(args):
# Use the MNIST dataset.
dataset = MNIST(data_size=5000)
# Split the dataset into a train set and a test set.
train_data, test_data, train_target, test_target = sklearn.model_selection.train_test_split(
dataset.data, dataset.target, test_size=args.test_size, random_state=args.seed)
pca = [("PCA", PCATransformer(args.pca, args.seed))] if args.pca else []
if args.with_reference:
pca = [("PCA", sklearn.decomposition.PCA(n_components=args.pca, random_state=args.seed))]
pipeline = sklearn.pipeline.Pipeline(
[("scaling", sklearn.preprocessing.MinMaxScaler())] +
pca +
[("classifier", sklearn.linear_model.LogisticRegression(solver="saga", max_iter=args.max_iter, random_state=args.seed))]
)
pipeline.fit(train_data, train_target)
test_accuracy = pipeline.score(test_data, test_target)
return test_accuracy
n_states = 3
tica = mixtape.tica.tICA(n_components=n_components, lag_time=lag_time)
subsampler = mixtape.utils.Subsampler(lag_time=lag_time)
msm = mixtape.markovstatemodel.MarkovStateModel(n_timescales=n_components)
cluster = mixtape.cluster.GMM(n_components=n_states, covariance_type='full')
feature_pipeline = sklearn.pipeline.Pipeline([("features", featurizer),
('tica', tica)])
cluster_pipeline = sklearn.pipeline.Pipeline([("features", featurizer),
('tica', tica),
("cluster", cluster)])
pipeline = sklearn.pipeline.Pipeline([("features", featurizer), ('tica', tica),
("subsampler", subsampler),
("cluster", cluster), ("msm", msm)])
pipeline.fit(train)
pipeline.score(train), pipeline.score(test)
X_all = feature_pipeline.transform(trajectories)
q = np.concatenate(X_all)
covars_ = cluster.covars_
covars_ = cluster.covars_.diagonal(axis1=1, axis2=2)
for i, j in [(0, 1)]:
fig = plt.figure()
plt.hexbin(q[:, i], q[:, j], bins='log')
plt.errorbar(cluster.means_[:, i],
cluster.means_[:, j],
xerr=covars_[:, i]**0.5,
yerr=covars_[:, j]**0.5,
fmt='kx',
import mixtape.featurizer, mixtape.tica, mixtape.cluster, mixtape.markovstatemodel, mixtape.ghmm
import numpy as np
import mdtraj as md
from parameters import load_trajectories, build_full_featurizer
import sklearn.pipeline, sklearn.externals.joblib
import mixtape.utils
n_choose = 50
stride = 1
lag_time = 1
n_components = 2
trj0, trajectories, filenames = load_trajectories(stride=stride)
train = trajectories[0::2]
test = trajectories[1::2]
featurizer = sklearn.externals.joblib.load("./featurizer-%d-%d.job" % (n_components, n_choose))
for n_states in [10, 20, 30, 40, 50]:
n_components = n_components
tica = mixtape.tica.tICA(n_components=n_components, lag_time=lag_time)
msm = mixtape.markovstatemodel.MarkovStateModel(n_timescales=5)
cluster = mixtape.cluster.KMeans(n_clusters=n_states)
pipeline = sklearn.pipeline.Pipeline([("features", featurizer), ('tica', tica), ("cluster", cluster), ("msm", msm)])
pipeline.fit(train)
print(pipeline.score(train), pipeline.score(test))
pipeline.fit(trajectories)
print(msm.timescales_)
n_components_list = [8]
n_states_list = range(5, 60)
train_scores = np.zeros((len(n_components_list), len(n_states_list)))
test_scores = np.zeros((len(n_components_list), len(n_states_list)))
for i, n_components in enumerate(n_components_list):
for j, n_states in enumerate(n_states_list):
print(n_components, n_states)
tica = mixtape.tica.tICA(n_components=n_components, lag_time=lag_time)
subsampler = mixtape.utils.Subsampler(lag_time=lag_time)
msm = mixtape.markovstatemodel.MarkovStateModel(n_timescales=n_components)
cluster = mixtape.cluster.KMeans(n_states)
pipeline = sklearn.pipeline.Pipeline(
[("features", featurizer), ("tica", tica), ("subsampler", subsampler), ("cluster", cluster), ("msm", msm)]
)
pipeline.fit(train)
train_scores[i, j] = pipeline.score(train)
test_scores[i, j] = pipeline.score(test)
plot(n_states_list, train_scores.T, "o", label="train")
plot(n_states_list, test_scores.T, "o", label="test")
xlabel("n_states")
ylabel("Score")
title("tICA KMeans SETD2")
legend(loc=0)
ylim(4, 10)
savefig("/home/kyleb/src/kyleabeauchamp/MixtapeTalk/figures/SETD2_tICA_KMeans.png")
test = trajectories[1::2]
featurizer = sklearn.externals.joblib.load("./featurizer-%d.job" % n_choose)
n_components = 3
n_states = 100
tica = mixtape.tica.tICA(n_components=n_components, lag_time=lag_time)
subsampler = mixtape.utils.Subsampler(lag_time=lag_time)
msm = mixtape.markovstatemodel.MarkovStateModel(n_timescales=n_components)
cluster = mixtape.cluster.KMeans(n_states)
feature_pipeline = sklearn.pipeline.Pipeline([("features", featurizer), ('tica', tica)])
cluster_pipeline = sklearn.pipeline.Pipeline([("features", featurizer), ('tica', tica), ("cluster", cluster)])
pipeline = sklearn.pipeline.Pipeline([("features", featurizer), ('tica', tica), ("subsampler", subsampler), ("cluster", cluster), ("msm", msm)])
pipeline.fit(train)
pipeline.score(train), pipeline.score(test)
X_all = feature_pipeline.transform(trajectories)
q = np.concatenate(X_all)
covars_ = cluster.covars_
covars_ = cluster.covars_.diagonal(axis1=1, axis2=2)
for i, j in [(0, 1)]:
figure()
hexbin(q[:,i], q[:, j], bins='log')
errorbar(cluster.means_[:, i], cluster.means_[:, j], xerr=covars_[:,i] ** 0.5, yerr=covars_[:, j] ** 0.5, fmt='kx', linewidth=4)
states = cluster_pipeline.transform(trajectories)
ind = msm.draw_samples(states, 3)
#in[152]
log_reg.score(X_test, y_test)
#in[153]
from sklearn.pipeline import Pipeline
#in[154]
pipeline = Pipeline([
("kmeans", KMeans(n_clusters=50, random_state=42)),
("log_reg", LogisticRegression(multi_class="ovr", solver="liblinear", random_state=42))
])
pipeline.fit(X_train, y_train)
#ini[155]
pipeline.score(X_test, y_test)
#in[156]
1 - (1 - 0.9822222)/(1 - 0.9666666)
#in[157]
from sklearn.model_selection import GridSearchCV
#in[158]
param_grid = dict(kmeans__n_clusters=range(2, 100)) # Create a dictionary
grid_clf = GridSearchCV(pipeline, param_grid, cv=3, verbose=2)
grid_clf.fit(X_train, y_train)
#in[159]
grid_clf.best_params_
