Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add Features: absolute_maximum; mean_n_absolut_max | Add install_requirements.sh script #833

Merged
merged 21 commits into from
Apr 1, 2021
Merged

Add Features: absolute_maximum; mean_n_absolut_max | Add install_requirements.sh script #833

Show file tree
Hide file tree
Changes from 13 commits
Commits
Show all changes
21 commits
Select commit Hold shift + click to select a range
adb4577
root_mean_square feature and unit tests
OliEfr Feb 24, 2021
e394333
removed .coverage.* files
OliEfr Feb 24, 2021
c5a8191
fix codestyle
OliEfr Feb 24, 2021
0a96e36
fixed test errors
OliEfr Feb 26, 2021
c53e6f4
Merge branch 'main' of https://github.com/blue-yonder/tsfresh into main
OliEfr Feb 27, 2021
a941393
Merge branch 'main' of https://github.com/blue-yonder/tsfresh into main
OliEfr Mar 3, 2021
eeb6eec
Merge https://github.com/blue-yonder/tsfresh into main
OliEfr Mar 28, 2021
6eaf90d
added features; added tests; added install script
OliEfr Mar 28, 2021
59e8000
fix typo
OliEfr Mar 28, 2021
53bf052
fix codestyle
OliEfr Mar 28, 2021
cab46a4
Update tsfresh/feature_extraction/feature_calculators.py
OliEfr Mar 29, 2021
984e4b0
Update .gitignore
OliEfr Mar 29, 2021
f24dd2f
update tests
OliEfr Mar 29, 2021
9ca9a41
Update tsfresh/feature_extraction/feature_calculators.py
OliEfr Apr 1, 2021
51df235
Update tsfresh/feature_extraction/feature_calculators.py
OliEfr Apr 1, 2021
705ff93
updates
OliEfr Apr 1, 2021
64e2c47
update
OliEfr Apr 1, 2021
704f7bb
updates
OliEfr Apr 1, 2021
58c78fa
finally remove dask-worker-space
OliEfr Apr 1, 2021
08724e9
remove dask-worker-space
OliEfr Apr 1, 2021
9e675bb
fix code style
OliEfr Apr 1, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Empty file added dask-worker-space/dask-worker-space/global.lock
View file
Open in desktop
Empty file.
Empty file added dask-worker-space/dask-worker-space/purge.lock
View file
Open in desktop
Empty file.
5 changes: 5 additions & 0 deletions install_requirements.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
#!/bin/bash
OliEfr marked this conversation as resolved.
Show resolved Hide resolved
pip install -r requirements.txt
pip install -r rdocs-requirements.txt
pip install -r test-requirements.txt
pip install -e .
32 changes: 16 additions & 16 deletions tests/integrations/test_feature_extraction.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,28 +29,28 @@ def test_pandas(self):
self.assertIn("1__mean", X.columns)
self.assertAlmostEqual(X.loc["5", "1__mean"], 5.516e-05, 4)
self.assertIn("11", X.index)
self.assertEqual(X.shape, (100, 18))
self.assertEqual(X.shape, (100, 20))

X = extract_features(df, column_id="my_id", column_sort="time", column_kind="dimension",
default_fc_parameters=MinimalFCParameters())
self.assertIn("1__mean", X.columns)
self.assertAlmostEqual(X.loc["5", "1__mean"], 5.516e-05, 4)
self.assertIn("11", X.index)
self.assertEqual(X.shape, (100, 18))
self.assertEqual(X.shape, (100, 20))

X = extract_features(df.drop(columns=["dimension"]), column_id="my_id", column_sort="time",
default_fc_parameters=MinimalFCParameters())
self.assertIn("value__mean", X.columns)
self.assertAlmostEqual(X.loc["5", "value__mean"], 5.516e-05, 4)
self.assertIn("11", X.index)
self.assertEqual(X.shape, (100, 9))
self.assertEqual(X.shape, (100, 10))

X = extract_features(df.drop(columns=["dimension", "time"]), column_id="my_id",
default_fc_parameters=MinimalFCParameters())
self.assertIn("value__mean", X.columns)
self.assertAlmostEqual(X.loc["5", "value__mean"], 5.516e-05, 4)
self.assertIn("11", X.index)
self.assertEqual(X.shape, (100, 9))
self.assertEqual(X.shape, (100, 10))

def test_pandas_no_pivot(self):
df = self.df
Expand All @@ -62,7 +62,7 @@ def test_pandas_no_pivot(self):
X = pd.DataFrame(X, columns=["my_id", "variable", "value"])
self.assertIn("1__mean", X["variable"].values)
self.assertAlmostEqual(X[(X["my_id"] == "5") & (X["variable"] == "1__mean")]["value"].iloc[0], 5.516e-05, 4)
self.assertEqual(X.shape, (100*18, 3))
self.assertEqual(X.shape, (100*20, 3))

X = extract_features(df, column_id="my_id", column_sort="time",
column_kind="dimension",
Expand All @@ -71,7 +71,7 @@ def test_pandas_no_pivot(self):
X = pd.DataFrame(X, columns=["my_id", "variable", "value"])
self.assertIn("1__mean", X["variable"].values)
self.assertAlmostEqual(X[(X["my_id"] == "5") & (X["variable"] == "1__mean")]["value"].iloc[0], 5.516e-05, 4)
self.assertEqual(X.shape, (100*18, 3))
self.assertEqual(X.shape, (100*20, 3))

X = extract_features(df.drop(columns=["dimension"]), column_id="my_id",
column_sort="time",
Expand All @@ -80,15 +80,15 @@ def test_pandas_no_pivot(self):
X = pd.DataFrame(X, columns=["my_id", "variable", "value"])
self.assertIn("value__mean", X["variable"].values)
self.assertAlmostEqual(X[(X["my_id"] == "5") & (X["variable"] == "value__mean")]["value"].iloc[0], 5.516e-05, 4)
self.assertEqual(X.shape, (100*9, 3))
self.assertEqual(X.shape, (100*10, 3))

X = extract_features(df.drop(columns=["dimension", "time"]), column_id="my_id",
pivot=False,
default_fc_parameters=MinimalFCParameters())
X = pd.DataFrame(X, columns=["my_id", "variable", "value"])
self.assertIn("value__mean", X["variable"].values)
self.assertAlmostEqual(X[(X["my_id"] == "5") & (X["variable"] == "value__mean")]["value"].iloc[0], 5.516e-05, 4)
self.assertEqual(X.shape, (100*9, 3))
self.assertEqual(X.shape, (100*10, 3))

def test_dask(self):
df = dd.from_pandas(self.df, npartitions=1)
Expand All @@ -99,30 +99,30 @@ def test_dask(self):
self.assertIn("1__mean", X.columns)
self.assertAlmostEqual(X.loc["5", "1__mean"], 5.516e-05, 4)
self.assertIn("11", X.index)
self.assertEqual(X.shape, (100, 18))
self.assertEqual(X.shape, (100, 20))

X = extract_features(df, column_id="my_id", column_sort="time",
column_kind="dimension",
default_fc_parameters=MinimalFCParameters()).compute()
self.assertIn("1__mean", X.columns)
self.assertAlmostEqual(X.loc["5", "1__mean"], 5.516e-05, 4)
self.assertIn("11", X.index)
self.assertEqual(X.shape, (100, 18))
self.assertEqual(X.shape, (100, 20))

X = extract_features(df.drop(columns=["dimension"]), column_id="my_id",
column_sort="time",
default_fc_parameters=MinimalFCParameters()).compute()
self.assertIn("value__mean", X.columns)
self.assertAlmostEqual(X.loc["5", "value__mean"], 5.516e-05, 4)
self.assertIn("11", X.index)
self.assertEqual(X.shape, (100, 9))
self.assertEqual(X.shape, (100, 10))

X = extract_features(df.drop(columns=["dimension", "time"]), column_id="my_id",
default_fc_parameters=MinimalFCParameters()).compute()
self.assertIn("value__mean", X.columns)
self.assertAlmostEqual(X.loc["5", "value__mean"], 5.516e-05, 4)
self.assertIn("11", X.index)
self.assertEqual(X.shape, (100, 9))
self.assertEqual(X.shape, (100, 10))

def test_dask_no_pivot(self):
df = dd.from_pandas(self.df, npartitions=1)
Expand All @@ -133,27 +133,27 @@ def test_dask_no_pivot(self):
default_fc_parameters=MinimalFCParameters()).compute()
self.assertIn("1__mean", X["variable"].values)
self.assertAlmostEqual(X[(X["my_id"] == "5") & (X["variable"] == "1__mean")]["value"].iloc[0], 5.516e-05, 4)
self.assertEqual(X.shape, (100*18, 3))
self.assertEqual(X.shape, (100*20, 3))

X = extract_features(df, column_id="my_id", column_sort="time",
column_kind="dimension",
pivot=False,
default_fc_parameters=MinimalFCParameters()).compute()
self.assertIn("1__mean", X["variable"].values)
self.assertAlmostEqual(X[(X["my_id"] == "5") & (X["variable"] == "1__mean")]["value"].iloc[0], 5.516e-05, 4)
self.assertEqual(X.shape, (100*18, 3))
self.assertEqual(X.shape, (100*20, 3))

X = extract_features(df.drop(columns=["dimension"]), column_id="my_id",
column_sort="time",
pivot=False,
default_fc_parameters=MinimalFCParameters()).compute()
self.assertIn("value__mean", X["variable"].values)
self.assertAlmostEqual(X[(X["my_id"] == "5") & (X["variable"] == "value__mean")]["value"].iloc[0], 5.516e-05, 4)
self.assertEqual(X.shape, (100*9, 3))
self.assertEqual(X.shape, (100*10, 3))

X = extract_features(df.drop(columns=["dimension", "time"]), column_id="my_id",
pivot=False,
default_fc_parameters=MinimalFCParameters()).compute()
self.assertIn("value__mean", X["variable"].values)
self.assertAlmostEqual(X[(X["my_id"] == "5") & (X["variable"] == "value__mean")]["value"].iloc[0], 5.516e-05, 4)
self.assertEqual(X.shape, (100*9, 3))
self.assertEqual(X.shape, (100*10, 3))
9 changes: 9 additions & 0 deletions tests/units/feature_extraction/test_feature_calculations.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -476,6 +476,15 @@ def test_root_mean_square(self):
self.assertAlmostEqualOnAllArrayTypes(root_mean_square, [1], 1)
self.assertAlmostEqualOnAllArrayTypes(root_mean_square, [-1], 1)

def test_mean_n_absolute_max(self):
self.assertIsNanOnAllArrayTypes(mean_n_absolute_max, [], number_of_maxima=1)
self.assertIsNanOnAllArrayTypes(mean_n_absolute_max, [12,3], number_of_maxima=10)
self.assertRaises(AssertionError, mean_n_absolute_max, [12,3], number_of_maxima=0)
self.assertRaises(AssertionError, mean_n_absolute_max, [12,3], number_of_maxima=-1)
self.assertAlmostEqualOnAllArrayTypes(mean_n_absolute_max, [-1, -5, 4, 10], 6.33333333333, number_of_maxima=3)
self.assertAlmostEqualOnAllArrayTypes(mean_n_absolute_max, [0, -5, -9], 7.000000, number_of_maxima=2)
self.assertAlmostEqualOnAllArrayTypes(mean_n_absolute_max, [0,0,0], 0, number_of_maxima=1)

def test_absolute_sum_of_changes(self):
self.assertEqualOnAllArrayTypes(absolute_sum_of_changes, [1, 1, 1, 1, 2, 1], 2)
self.assertEqualOnAllArrayTypes(absolute_sum_of_changes, [1, -1, 1, -1], 6)
Expand Down
2 changes: 1 addition & 1 deletion tests/units/feature_extraction/test_settings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,5 +202,5 @@ def test_extraction_runs_through(self):

self.assertCountEqual(extracted_features.columns, ["0__median", "0__standard_deviation", "0__sum_values",
"0__maximum", "0__variance", "0__minimum", "0__mean",
"0__length", "0__root_mean_square"])
"0__length", "0__root_mean_square", "0__absolut_maximum"])
self.assertCountEqual(extracted_features.index, [0, 1])
34 changes: 34 additions & 0 deletions tsfresh/feature_extraction/feature_calculators.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1547,6 +1547,26 @@ def c3(x, lag):
return np.mean((_roll(x, 2 * -lag) * _roll(x, -lag) * x)[0:(n - 2 * lag)])


@set_property("fctype", "simple")
@set_property("minimal", True)
def mean_n_absolute_max(x, number_of_maxima):
"""
Calculates the arithmetic mean of the n absolut maximum values of the time series.
OliEfr marked this conversation as resolved.
Show resolved Hide resolved

:param x: the time series to calculate the feature of
:type x: numpy.ndarray
:param number_of_maxima: the number of maxima, which should be considered
:type number_of_maxima: int

:return: the value of this feature
:return type: float
"""

assert number_of_maxima > 0, f" number_of_maxima={number_of_maxima} which is not greater than 1"

return np.mean(np.sort(np.absolute(x))[-number_of_maxima:]) if len(x) > number_of_maxima else np.NaN
OliEfr marked this conversation as resolved.
Show resolved Hide resolved
OliEfr marked this conversation as resolved.
Show resolved Hide resolved


@set_property("fctype", "simple")
def binned_entropy(x, max_bins):
"""
Expand Down Expand Up @@ -1889,6 +1909,20 @@ def maximum(x):
return np.max(x)


@set_property("fctype", "simple")
@set_property("minimal", True)
def absolut_maximum(x):
"""
Calculates the highest absolut value of the time series x.
OliEfr marked this conversation as resolved.
Show resolved Hide resolved

:param x: the time series to calculate the feature of
:type x: numpy.ndarray
:return: the value of this feature
:return type: float
"""
return np.max(np.absolute(x))
OliEfr marked this conversation as resolved.
Show resolved Hide resolved


@set_property("fctype", "simple")
@set_property("minimal", True)
def minimum(x):
Expand Down