def test_pipe_transformation():
# SegmentX transform pipe
pipe = Pype([('seg', SegmentX()),
('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]
transformation_test(pipe, X, y)
X = pd.DataFrame(Xc)
X['ts_data'] = Xt
X = TS_Data.from_df(X)
transformation_test(pipe, X, y)
# SegmentXY 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)]
transformation_test(pipe, X, y)
X = pd.DataFrame(Xc)
X['ts_data'] = Xt
X = TS_Data.from_df(X)
transformation_test(pipe, X, y)
# Forecast transform pipe
pipe = Pype([('seg', SegmentXYForecast()),
('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)]
transformation_test(pipe, X, y)
X = pd.DataFrame(Xc)
X['ts_data'] = Xt
X = TS_Data.from_df(X)
transformation_test(pipe, X, y)
# Padtrunc 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]
transformation_test(pipe, X, y)
X = pd.DataFrame(Xc)
X['ts_data'] = Xt
X = TS_Data.from_df(X)
transformation_test(pipe, X, y)
def test_pipe_forecast():
# no context data, single time series
X = [np.random.rand(1000, 10)]
y = [np.random.rand(1000)]
pipe = Pype([('seg', SegmentXYForecast()), ('ftr', FeatureRep()),
('ridge', Ridge())])
forecast_test(pipe, 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)]
forecast_test(pipe, X, y)
X = pd.DataFrame(Xc)
X['ts_data'] = Xt
X = TS_Data.from_df(X)
forecast_test(pipe, 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)]
forecast_test(pipe, X, y)
X = pd.DataFrame(Xc)
X['ts_data'] = Xt
X = TS_Data.from_df(X)
forecast_test(pipe, 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)
X = pd.DataFrame(Xc)
Xt = [np.random.rand(1000, 10)] * 5
X['ts_data'] = Xt
X = TS_Data.from_df(X)
cross_validate(pipe, X, y, cv=3)
def test_pipe_classification():
# no context data, single time series
X = [np.random.rand(1000, 10)]
y = [5]
pipe = Pype([('seg', SegmentX()), ('ftr', FeatureRep()),
('rf', RandomForestClassifier(n_estimators=10))])
classifier_test(pipe, 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]
classifier_test(pipe, X, y)
X = pd.DataFrame(Xc)
X['ts_data'] = Xt
X = TS_Data.from_df(X)
classifier_test(pipe, 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]
classifier_test(pipe, X, y)
X = pd.DataFrame(Xc)
X['ts_data'] = Xt
X = TS_Data.from_df(X)
classifier_test(pipe, 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]
classifier_test(pipe, X, y)
X = pd.DataFrame(Xc)
X['ts_data'] = Xt
X = TS_Data.from_df(X)
classifier_test(pipe, X, y)
def test_pd():
ts = np.array([np.random.rand(100, 10), np.random.rand(200, 10), np.random.rand(20, 10)], dtype=object)
c = np.random.rand(3, 10)
df = pd.DataFrame(c)
df['ts_data'] = ts
data = TS_Data.from_df(df)
assert np.all([np.array_equal(data.ts_data[i], ts[i]) for i in range(len(ts))])
assert np.array_equal(data.context_data, c)
def test_trle():
# Multivariate data
Nt = 100
nvars = 5
X = [np.random.rand(Nt, nvars)]
y = [
np.concatenate(
[np.full(3, 1),
np.full(26, 2),
np.full(1, 3),
np.full(70, 4)])
]
rle = TargetRunLengthEncoder(min_length=5)
rle.fit(X)
Xt, yt, _ = rle.transform(X, y)
assert len(Xt) == len(yt) and len(yt) == 2
assert yt[0] == 2 and yt[1] == 4
assert len(Xt[0]) == 26 and len(Xt[1]) == 70
# Nothing excluded
Nt = 100
nvars = 5
X = [np.random.rand(Nt, nvars)]
y = [np.concatenate([np.full(50, 1), np.full(50, 2)])]
rle = TargetRunLengthEncoder(min_length=5)
rle.fit(X, y)
Xt, yt, _ = rle.transform(X, y)
assert len(Xt) == len(yt) and len(yt) == 2
assert np.all(np.concatenate(Xt) == X)
assert yt[0] == 1 and yt[1] == 2
assert len(Xt[0]) == 50 and len(Xt[1]) == 50
# Univariate data with sample weight and context
Nt = 100
Xts = [np.random.rand(Nt)]
Xc = [5]
X = TS_Data(Xts, Xc)
y = [
np.concatenate(
[np.full(3, 1),
np.full(26, 2),
np.full(1, 3),
np.full(70, 4)])
]
sw = [1]
rle = TargetRunLengthEncoder(min_length=5)
rle.fit(X)
Xt, yt, swt = rle.transform(X, y, sw)
Xtc = Xt.context_data
assert len(Xt) == len(yt) and len(swt) == len(yt) and len(yt) == 2
assert yt[0] == 2 and yt[1] == 4
assert len(Xt[0]) == 26 and len(Xt[1]) == 70
assert swt[0] == 1 and swt[1] == 1
assert Xtc[0] == 5 and Xtc[1] == 5
X = pd.DataFrame(Xc)
X['ts_data'] = Xts
X = TS_Data.from_df(X)
rle = TargetRunLengthEncoder(min_length=5)
rle.fit(X)
Xt, yt, swt = rle.transform(X, y, sw)
Xtc = Xt.context_data
assert len(Xt) == len(yt) and len(swt) == len(yt) and len(yt) == 2
assert yt[0] == 2 and yt[1] == 4
assert len(Xt[0]) == 26 and len(Xt[1]) == 70
assert swt[0] == 1 and swt[1] == 1
assert Xtc[0] == 5 and Xtc[1] == 5