added cid_ce feature calculator (blue-yonder#332)

* added cid_ce feature calculator

* polish cid_ce docstring

Author: MaxBenChrist

tests/units/feature_extraction/test_feature_calculations.py

@@ -274,6 +274,15 @@ def test_abs_energy(self):
         self.assertAlmostEqualOnAllArrayTypes(abs_energy, [-1, 1.3], 2.69)
         self.assertEqualOnAllArrayTypes(abs_energy, [1], 1)
 
+    def test_cid_ce(self):
+        self.assertEqualOnAllArrayTypes(cid_ce, [1, 1, 1], 0, normalize=True)
+        self.assertEqualOnAllArrayTypes(cid_ce, [0, 4], 2, normalize=True)
+        self.assertEqualOnAllArrayTypes(cid_ce, [100, 104], 2, normalize=True)
+
+        self.assertEqualOnAllArrayTypes(cid_ce, [1, 1, 1], 0, normalize=False)
+        self.assertEqualOnAllArrayTypes(cid_ce, [0.5, 3.5, 7.5], 5, normalize=False)
+        self.assertEqualOnAllArrayTypes(cid_ce, [-4.33, -1.33, 2.67], 5, normalize=False)
+
     def test_ratio_beyond_r_sigma(self):
 
         x = [0, 1]*10 + [10, 20, -30] # std of x is 7.21, mean 3.04

tsfresh/feature_extraction/feature_calculators.py

@@ -391,6 +391,44 @@ def abs_energy(x):
     return sum(x * x)
 
 
+@set_property("fctype", "simple")
+def cid_ce(x, normalize):
+    """
+    This function calculator is an estimate for a time series complexity [1] (A more complex time series has more peaks,
+    valleys etc.). It calculates the value of
+
+    .. math::
+
+        \\sqrt{ \\sum_{i=0}^{n-2lag} ( x_{i} - x_{i+1})^2 }
+
+    .. rubric:: References
+
+    |  [1] Batista, Gustavo EAPA, et al (2014).
+    |  CID: an efficient complexity-invariant distance for time series.
+    |  Data Mining and Knowledge Difscovery 28.3 (2014): 634-669.
+
+    :param x: the time series to calculate the feature of
+    :type x: pandas.Series
+    :param normalize: should the time series be z-transformed?
+    :type normalize: bool
+
+    :return: the value of this feature
+    :return type: float
+    """
+
+    x = np.asarray(x)
+
+    if normalize:
+        s = np.std(x)
+        if s!=0:
+            x = (x - np.mean(x))/s
+        else:
+            return 0.0
+
+    x = np.diff(x)
+    return np.sqrt(np.sum((x * x)))
+
+
 @set_property("fctype", "simple")
 def mean_abs_change(x):
     """

tsfresh/feature_extraction/settings.py

@@ -105,6 +105,7 @@ def __init__(self):
         name_to_param.update({
             "time_reversal_asymmetry_statistic": [{"lag": lag} for lag in range(1, 4)],
             "c3": [{"lag": lag} for lag in range(1, 4)],
+            "cid_ce": [{"normalize": True}, {"normalize": False}],
             "symmetry_looking": [{"r": r * 0.05} for r in range(20)],
             "large_standard_deviation": [{"r": r * 0.05} for r in range(1, 20)],
             "quantile": [{"q": q} for q in [.1, .2, .3, .4, .6, .7, .8, .9]],