# create a feature representation pipeline
# setting y_func = last, and forecast = 200 makes us predict the value of y
# 200 samples ahead of the segment
# other reasonable options for y_func are ``mean``, ``all`` (or create your own function)
# see the API documentation for further details
clf = Pype([('segment',
SegmentXYForecast(width=200,
overlap=0.5,
y_func=last,
forecast=200)), ('features', FeatureRep()),
('lin', LinearRegression())])
# fit and score
clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
print("N series in train: ", len(X_train))
print("N series in test: ", len(X_test))
print("N segments in train: ", clf.N_train)
print("N segments in test: ", clf.N_test)
print("Score: ", score)
# generate some predictions
y, y_p = clf.transform_predict(X, y) # all predictions
ytr, ytr_p = clf.transform_predict(X_train, y_train) # training predictions
yte, yte_p = clf.transform_predict(X_test, y_test) # test predictions
# note - the first few segments in the test set won't have predictions (gap)
# we plot the 'gap' for the visualization to hopefully make the situation clear
Ns = len(y)
def test_pipe_regression():
# no context data, single time series
X = [np.random.rand(1000, 10)]
y = [np.random.rand(1000)]
pipe = Pype([('seg', SegmentXY()), ('ftr', FeatureRep()),
('ridge', Ridge())])
pipe.fit(X, y)
pipe.transform_predict(X, y)
pipe.predict(X)
pipe.score(X, y)
# context data, single time seres
Xt = [np.random.rand(1000, 10)]
Xc = [np.random.rand(3)]
X = TS_Data(Xt, Xc)
y = [np.random.rand(1000)]
pipe.fit(X, y)
pipe.transform_predict(X, y)
pipe.predict(X)
pipe.score(X, y)
# multiple time seres
Xt = [
np.random.rand(1000, 10),
np.random.rand(100, 10),
np.random.rand(500, 10)
]
Xc = np.random.rand(3, 3)
X = TS_Data(Xt, Xc)
y = [np.random.rand(1000), np.random.rand(100), np.random.rand(500)]
pipe.fit(X, y)
pipe.transform_predict(X, y)
pipe.predict(X)
pipe.score(X, y)
# cross val
Xt = np.array([np.random.rand(1000, 10)] * 5)
Xc = np.random.rand(5, 3)
X = TS_Data(Xt, Xc)
y = np.array([np.random.rand(1000)] * 5)
cross_validate(pipe, X, y, cv=3)
# transform pipe
pipe = Pype([('seg', SegmentXY()), ('ftr', FeatureRep()),
('scaler', StandardScaler())])
Xt = [
np.random.rand(1000, 10),
np.random.rand(100, 10),
np.random.rand(500, 10)
]
Xc = np.random.rand(3, 3)
X = TS_Data(Xt, Xc)
y = [np.random.rand(1000), np.random.rand(100), np.random.rand(500)]
pipe.fit(X, y)
pipe.transform(X, y)
pipe.fit_transform(X, y)
# load the data
data = load_watch()
X = data['X']
y = data['y']
# create a feature representation pipeline with PadTrunc segmentation
# the time series are between 20-40 seconds
# this truncates them all to the first 5 seconds (sampling rate is 50 Hz)
pipe = Pype([('trunc', PadTrunc(width=250)), ('features', FeatureRep()),
('scaler', StandardScaler()), ('svc', LinearSVC())])
# split the data
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.25,
shuffle=True,
random_state=42)
pipe.fit(X_train, y_train)
score = pipe.score(X_test, y_test)
print("N series in train: ", len(X_train))
print("N series in test: ", len(X_test))
print("N segments in train: ", pipe.N_train)
print("N segments in test: ", pipe.N_test)
print("Accuracy score: ", score)
img = mpimg.imread('trunk.jpg')
plt.imshow(img)
def test_pipe_PadTrunc():
# no context data, single time series
X = [np.random.rand(1000, 10)]
y = [5]
pipe = Pype([('trunc', PadTrunc()), ('ftr', FeatureRep()),
('rf', RandomForestClassifier(n_estimators=10))])
pipe.fit(X, y)
pipe.transform_predict(X, y)
pipe.predict(X)
pipe.score(X, y)
# context data, single time seres
Xt = [np.random.rand(1000, 10)]
Xc = [np.random.rand(3)]
X = TS_Data(Xt, Xc)
y = [5]
pipe.fit(X, y)
pipe.transform_predict(X, y)
pipe.predict(X)
pipe.score(X, y)
# multiple time series
Xt = [
np.random.rand(1000, 10),
np.random.rand(100, 10),
np.random.rand(500, 10)
]
Xc = np.random.rand(3, 3)
X = TS_Data(Xt, Xc)
y = [1, 2, 3]
pipe.fit(X, y)
pipe.transform_predict(X, y)
pipe.predict(X)
pipe.score(X, y)
# univariate data
Xt = [np.random.rand(1000), np.random.rand(100), np.random.rand(500)]
Xc = np.random.rand(3)
X = TS_Data(Xt, Xc)
y = [1, 2, 3]
pipe.fit(X, y)
pipe.transform_predict(X, y)
pipe.predict(X)
pipe.score(X, y)
# transform pipe
pipe = Pype([('trunc', PadTrunc()), ('ftr', FeatureRep()),
('scaler', StandardScaler())])
Xt = [
np.random.rand(1000, 10),
np.random.rand(100, 10),
np.random.rand(500, 10)
]
Xc = np.random.rand(3, 3)
X = TS_Data(Xt, Xc)
y = [1, 2, 3]
pipe.fit(X, y)
pipe.transform(X, y)
pipe.fit_transform(X, y)