Relaxed the HAVOK tests

Author: sichinaga

pydmd/havok.py

@@ -278,16 +278,16 @@ def r(self):
 
     def hankel(self, X):
         """
-        Given a data matrix X as a 1D or 2D numpy.ndarray, uses the `delays`
-        and `lag` attributes to return the data as a 2D Hankel matrix.
+        Given a data matrix X as a 1-D or 2-D numpy.ndarray, uses the `delays`
+        and `lag` attributes to return the data as a 2-D Hankel matrix.
 
         :param X: (m,) or (n, m) array of data.
         :type X: numpy.ndarray
         :return: Hankel matrix of data.
         :rtype: numpy.ndarray
         """
         if not isinstance(X, np.ndarray) or X.ndim > 2:
-            raise ValueError("Data must be a 1D or 2D numpy array.")
+            raise ValueError("Data must be a 1-D or 2-D numpy array.")
         if X.ndim == 1:
             X = X[None]
         n, m = X.shape
@@ -310,16 +310,16 @@ def hankel(self, X):
 
     def dehankel(self, H):
         """
-        Given a Hankel matrix H as a 2D numpy.ndarray, uses the `delays`
+        Given a Hankel matrix H as a 2-D numpy.ndarray, uses the `delays`
         and `lag` attributes to unravel the data in the Hankel matrix.
 
-        :param H: Hankel matrix of data.
+        :param H: 2-D Hankel matrix of data.
         :type H: numpy.ndarray
         :return: de-Hankeled (m,) or (n, m) array of data.
         :rtype: numpy.ndarray
         """
         if not isinstance(H, np.ndarray) or H.ndim != 2:
-            raise ValueError("Data must be a 2D numpy array.")
+            raise ValueError("Data must be a 2-D numpy array.")
 
         Hn, Hm = H.shape
         n = int(Hn / self._delays)
@@ -364,7 +364,7 @@ def fit(self, X, t):
         else:
             time = np.squeeze(np.array(t))
 
-            # Throw error if the time vector is not 1D or the correct length.
+            # Throw error if the time vector is not 1-D or the correct length.
             if time.ndim != 1 or len(time) != n_samples:
                 raise ValueError(
                     f"Please provide a 1-D array of {n_samples} time values."

tests/test_havok.py

@@ -17,7 +17,7 @@ def generate_lorenz_data(t_eval):
     the snapshots of the Lorenz system as columns of the matrix X.
     """
 
-    def lorenz_system(t, state):
+    def lorenz_system(state_t, state):
         sigma, rho, beta = 10, 28, 8 / 3  # chaotic parameters
         x, y, z = state
         x_dot = sigma * (y - x)
@@ -281,7 +281,7 @@ def test_reconstruction_1():
     """
     havok = HAVOK(svd_rank=16, delays=100).fit(x, t)
     error = x - havok.reconstructed_data
-    assert np.linalg.norm(error) / np.linalg.norm(x) < 0.1
+    assert np.linalg.norm(error) / np.linalg.norm(x) < 0.2
 
 
 def test_reconstruction_2():
@@ -290,7 +290,7 @@ def test_reconstruction_2():
     """
     havok = HAVOK(svd_rank=4, delays=100, structured=True).fit(x, t)
     error = x[:-1] - havok.reconstructed_data
-    assert np.linalg.norm(error) / np.linalg.norm(x[:-1]) < 0.1
+    assert np.linalg.norm(error) / np.linalg.norm(x[:-1]) < 0.2
 
 
 def test_predict_1():
@@ -324,7 +324,7 @@ def test_predict_2():
 
     # Get the error of the full prediction.
     error = x_long - havok.predict(forcing_long, time_long)
-    assert np.linalg.norm(error) / np.linalg.norm(x_long) < 0.55
+    assert np.linalg.norm(error) / np.linalg.norm(x_long) < 0.6
 
 
 def test_predict_3():
@@ -394,7 +394,7 @@ def test_dmd_1():
     havok = HAVOK(svd_rank=16, delays=100, dmd=dmd).fit(x, t)
     havok.plot_summary()
     error = x - havok.reconstructed_data
-    assert np.linalg.norm(error) / np.linalg.norm(x) < 0.1
+    assert np.linalg.norm(error) / np.linalg.norm(x) < 0.2
 
 
 def test_dmd_2():
@@ -412,4 +412,4 @@ def test_dmd_2():
     havok = HAVOK(svd_rank=4, delays=100, dmd=pidmd).fit(x, t)
     havok.plot_summary()
     error = x - havok.reconstructed_data
-    assert np.linalg.norm(error) / np.linalg.norm(x) < 0.1
+    assert np.linalg.norm(error) / np.linalg.norm(x) < 0.2