# create the label vector and the corresponding semantic vector
y = np.array([0, 1, 2, 3, 4, 5, 6, 7])
labels = [
'LB_BC', 'RB_BC', 'LF_BC', 'RF_BC', 'LB_BP', 'RB_BP', 'LF_BP', 'RF_BP'
]
# segment the data and labels
segmenter = SegmentX(100, 0.5)
X_new, y_new, _ = segmenter.fit_transform(X, y)
###################################################################################################
# create a pipeline for LDA transformation of the feature representation
est = Pipeline([('features', FeatureRep()),
('lda', LinearDiscriminantAnalysis(n_components=2))])
pipe = SegPipe(est)
# plot embedding
X2, y2 = pipe.fit_transform(X_new, y_new)
plot_embedding(X2, y2.astype(int), labels)
plt.show()
###################################################################################################
# create a pipeline for feature representation
est = Pipeline([('features', FeatureRep()), ('scaler', StandardScaler()),
('rf', RandomForestClassifier())])
pipe = SegPipe(est)
# split the data
X_train, X_test, y_train, y_test = train_test_split(X_new,
model.compile(loss='categorical_crossentropy', optimizer='adam',
metrics=['accuracy'])
return model
# load the data
data = load_watch()
X = data['X']
y = data['y']
# create a segment learning pipeline
width = 100
est = KerasClassifier(build_fn=crnn_model, epochs = 10, batch_size = 256, verbose = 0)
pipe = SegPipe(est)
# split the data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, 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('segments.jpg')
plt.tight_layout()
##############################################
# SETUP
##############################################
# load the data
data = load_watch()
X = data['X']
y = data['y']
# create a feature representation pipeline
est = Pipeline([('features', FeatureRep()), ('scaler', StandardScaler()),
('rf', RandomForestClassifier())])
pipe = SegPipe(est)
# split the data
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.25,
random_state=42)
##############################################
# OPTION 1: Use the score SegPipe score method
##############################################
pipe.fit(X_train, y_train)
score = pipe.score(X_test, y_test)
print("Accuracy score: ", score)
# split the data along the time axis (our only option since we have only 1 time series)
X_train, X_test, y_train, y_test = temporal_split(X, y, test_size=0.25)
# create a feature representation pipeline
est = Pipeline([('features', FeatureRep()), ('lin', LinearRegression())])
# 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
segmenter = SegmentXYForecast(width=200,
overlap=0.5,
y_func=last,
forecast=200)
pipe = SegPipe(est, segmenter)
# fit and score
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("Score: ", score)
# generate some predictions
y, y_p = pipe.predict(X, y) # all predictions
ytr, ytr_p = pipe.predict(X_train, y_train) # training predictions
yte, yte_p = pipe.predict(X_test, y_test) # test predictions
############################################## # Setup ############################################## # load the data data = load_watch() X = data['X'] y = data['y'] # split the data X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42) # create a segment learning pipeline width = 100 est = KerasClassifier(build_fn=crnn_model, epochs = 10, batch_size = 256, verbose = 0, validation_split = 0.2) pipe = SegPipe(est) ############################################## # Accessing training history ############################################## # this is a bit of a hack, because history object is returned by the # keras wrapper when fit is called # this approach won't work with a more complex estimator pipeline, in which case # a callable class with the desired properties should be made passed to build_fn pipe.fit(X_train,y_train) print(DataFrame(pipe.history.history)) ac_train = pipe.history.history['acc'] ac_val = pipe.history.history['val_acc'] epoch = np.arange(len(ac_train))+1
def test_pipe_regression():
# no context data, single time series
X = [np.random.rand(1000, 10)]
y = [np.random.rand(1000)]
est = Pipeline([('ftr', FeatureRep()), ('ridge', Ridge())])
pipe = SegPipe(est, segmenter=SegmentXY())
pipe.fit(X, y)
pipe.predict(X, y)
pipe.score(X, y)
# context data, single time seres
Xt = [np.random.rand(1000, 10)]
Xc = [np.random.rand(3)]
X = make_ts_data(Xt, Xc)
y = [np.random.rand(1000)]
pipe.fit(X, y)
pipe.predict(X, y)
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 = make_ts_data(Xt, Xc)
y = [np.random.rand(1000), np.random.rand(100), np.random.rand(500)]
pipe.fit(X, y)
pipe.predict(X, y)
pipe.score(X, y)
# cross val
Xt = np.array([np.random.rand(1000, 10) for i in range(5)])
Xc = np.random.rand(5, 3)
X = make_ts_data(Xt, Xc)
y = np.array([np.random.rand(1000) for i in range(5)])
cross_validate(pipe, X, y)
# transform pipe
est = Pipeline([('ftr', FeatureRep()), ('scaler', StandardScaler())])
pipe = SegPipe(est, segmenter=SegmentXY())
Xt = [
np.random.rand(1000, 10),
np.random.rand(100, 10),
np.random.rand(500, 10)
]
Xc = np.random.rand(3, 3)
X = make_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)
def test_pipe_classification():
# no context data, single time series
X = [np.random.rand(1000, 10)]
y = [5]
est = Pipeline([('ftr', FeatureRep()),
('ridge', RandomForestClassifier())])
pipe = SegPipe(est, segmenter=SegmentX())
pipe.fit(X, y)
pipe.predict(X, y)
pipe.score(X, y)
# context data, single time seres
Xt = [np.random.rand(1000, 10)]
Xc = [np.random.rand(3)]
X = make_ts_data(Xt, Xc)
y = [5]
pipe.fit(X, y)
pipe.predict(X, y)
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 = make_ts_data(Xt, Xc)
y = [1, 2, 3]
pipe.fit(X, y)
pipe.predict(X, y)
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 = make_ts_data(Xt, Xc)
y = [1, 2, 3]
pipe.fit(X, y)
pipe.predict(X, y)
pipe.score(X, y)
# transform pipe
est = Pipeline([('ftr', FeatureRep()), ('scaler', StandardScaler())])
pipe = SegPipe(est, segmenter=SegmentX())
Xt = [
np.random.rand(1000, 10),
np.random.rand(100, 10),
np.random.rand(500, 10)
]
Xc = np.random.rand(3, 3)
X = make_ts_data(Xt, Xc)
y = [1, 2, 3]
pipe.fit(X, y)
pipe.transform(X, y)
pipe.fit_transform(X, y)
return model
# load the data
data = load_watch()
X = data['X']
y = data['y']
# temporal splitting of data
splitter = TemporalKFold(n_splits=3)
Xs, ys, cv = splitter.split(X,y)
# create a segment learning pipeline
width = 100
est = KerasClassifier(build_fn=crnn_model, epochs = 5, batch_size = 256, verbose = 0)
pipe = SegPipe(est)
# create a parameter dictionary using the SegPipe API - which is similar to the sklearn API
#
# parameters passed to an estimator in the ``feed`` pipeline are keyed ``f$estimator__parameter``
# parameters passed to an estimator in the ``est`` pipeline are keyed ``e$estimator__parameter``
#
# when the ``feed`` or ``est`` pipeline is not a pipeline, but just a single estimator
# the parameter would be keyed f$parameter or e$parameter respectively
#
# you can also set a parameter to be always equal to another parameter, by setting its value to
# parameter name to track
#
# note that if you want to set a parameter to a single value, it will still need to be as a list
par_grid = {'s$width' : [50,100,200],