A Very Fast (Almost) Deterministic Transform for Time Series Classification.
create_scripts

<function tsai.imports.create_scripts(max_elapsed=60)>

class MiniRocketClassifier[source]

MiniRocketClassifier() :: Pipeline

Time series classification using MINIROCKET features and a linear classifier

MiniRocketClassifier.__doc__

'Time series classification using MINIROCKET features and a linear classifier'

load_minirocket[source]

load_minirocket(fname, path='./models')

class MiniRocketRegressor[source]

MiniRocketRegressor() :: Pipeline

Time series regression using MINIROCKET features and a linear regressor

load_minirocket[source]

load_minirocket(fname, path='./models')

class MiniRocketVotingClassifier[source]

MiniRocketVotingClassifier() :: VotingClassifier

Time series classification ensemble using MINIROCKET features, a linear classifier and majority voting

get_minirocket_preds[source]

get_minirocket_preds(X, fname, path='./models', model=None)

class MiniRocketVotingRegressor[source]

MiniRocketVotingRegressor() :: VotingRegressor

Time series regression ensemble using MINIROCKET features, a linear regressor and a voting regressor

dsid = 'OliveOil'
fname = 'MiniRocketClassifier'
X_train, y_train, X_test, y_test = get_UCR_data(dsid)
cls = MiniRocketClassifier()
cls.fit(X_train, y_train)
cls.save(fname)
pred = cls.score(X_test, y_test)
del cls
cls = load_minirocket(fname)
test_eq(cls.score(X_test, y_test), pred)

dsid = 'NATOPS'
X_train, y_train, X_test, y_test = get_UCR_data(dsid)
cls = MiniRocketClassifier()
cls.fit(X_train, y_train)
cls.score(X_test, y_test)

0.9222222222222223
dsid = 'NATOPS'
X_train, y_train, X_test, y_test = get_UCR_data(dsid)
cls = MiniRocketVotingClassifier(5)
cls.fit(X_train, y_train)
cls.score(X_test, y_test)

0.9333333333333333
from sklearn.metrics import mean_squared_error
dsid = 'Covid3Month'
fname = 'MiniRocketRegressor'
X_train, y_train, X_test, y_test = get_Monash_data(dsid)
rmse_scorer = make_scorer(mean_squared_error, greater_is_better=False)
reg = MiniRocketRegressor(scoring=rmse_scorer)
reg.fit(X_train, y_train)
reg.save(fname)
del reg
reg = load_minirocket(fname)
y_pred = reg.predict(X_test)
rmse = mean_squared_error(y_test, y_pred, squared=False)
rmse

0.04159226078258895
from sklearn.metrics import mean_squared_error
dsid = 'AppliancesEnergy'
X_train, y_train, X_test, y_test = get_Monash_data(dsid)
rmse_scorer = make_scorer(mean_squared_error, greater_is_better=False)
reg = MiniRocketRegressor(scoring=rmse_scorer)
reg.fit(X_train, y_train)
reg.save(fname)
del reg
reg = load_minirocket(fname)
y_pred = reg.predict(X_test)
rmse = mean_squared_error(y_test, y_pred, squared=False)
rmse

2.11075459259585
reg = MiniRocketVotingRegressor(5, scoring=rmse_scorer)
reg.fit(X_train, y_train)
y_pred = reg.predict(X_test)
rmse = mean_squared_error(y_test, y_pred, squared=False)
rmse

2.2958481292101465