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)
from seglearn.split import temporal_split X_train, X_else, y_train, y_else = train_test_split(df1_new, df1_new["sales_item_price_created"], test_size=0.2, shuffle=False) X_valid, X_test, y_valid, y_test = train_test_split(X_else, y_else, test_size=0.5, shuffle=False) #X_train, X_valid, y_train, y_valid = temporal_split(df1_new, df1_new["sales_item_price_created"], test_size=0.25) #normalizers = minmax_scale(X_train, y_train) #%% TIME_WINDOW=100 FORECAST_DISTANCE=24 from seglearn.transform import FeatureRep, SegmentXYForecast, last segmenter = SegmentXYForecast(width=TIME_WINDOW, step=1, y_func=last, forecast=FORECAST_DISTANCE) X_train_rolled, y_train_rolled,_=segmenter.fit_transform([X_train.values],[y_train]) X_train_rolled #%% X_train_rolled.shape shape = X_train_rolled.shape X_train_flattened = X_train_rolled.reshape(shape[0],shape[1]*shape[2]) X_train_flattened.shape X_valid_rolled, y_valid_rolled,_=segmenter.fit_transform([X_valid.values],[y_valid])
# remember for a single time series, we need to make a list
X = [X]
y = [y]
# 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
# 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
# remember for a single time series, we need to make a list
X = [X]
y = [y]
# 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
def test_pipe_forecast():
# 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=SegmentXYForecast())
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=SegmentXYForecast())
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_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())])
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', 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)]
pipe.fit(X, y)
pipe.transform(X, y)
pipe.fit_transform(X, y)
# with forecasting, X can include the target
X = np.stack([t, y], axis=1)
# remember for a single time series, we need to make a list
X = [X]
y = [y]
# 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
# 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