whenxaun: update the version

Author: wwhenxuan

examples/sjmd.ipynb

@@ -54,7 +54,7 @@
     "from pysdkit import SJMD, SMJMD\n",
     "\n",
     "print(SJMD())\n",
-    "print(SMJMD is SJMD)\n"
+    "print(SMJMD is SJMD)"
    ]
   },
   {
@@ -105,7 +105,7 @@
     "osc = np.vstack([ch1, ch2, ch3])\n",
     "\n",
     "Sig = osc + jump_mc + 0.1 * rng.standard_normal((3, n))\n",
-    "print(\"Sig shape (C, N):\", Sig.shape)\n"
+    "print(\"Sig shape (C, N):\", Sig.shape)"
    ]
   },
   {
@@ -131,7 +131,7 @@
     "    tau=50,\n",
     "    beta=0.5,\n",
     "    b_bar=0.9,\n",
-    "    stopc=4,   # power of the last mode (recommended)\n",
+    "    stopc=4,  # power of the last mode (recommended)\n",
     "    tol=1e-5,\n",
     ")\n",
     "\n",

pysdkit/__init__.py

@@ -2,7 +2,7 @@
 A Python library for signal decomposition algorithms.
 """
 
-__version__ = "0.4.29"
+__version__ = "0.4.30"
 
 # Empirical Mode Decomposition
 from ._emd import EMD

pysdkit/_jmd/sjmd.py

@@ -166,7 +166,10 @@ def _check_stop(
                 err = np.linalg.norm(f_hat_temp - u_hat_i[:, :, 0].T) ** 2
             else:
                 err = np.linalg.norm(f_hat_temp - np.sum(u_hat_i, axis=2).T) ** 2
-            bic.append(2 * t_len * np.log(err + np.finfo(float).eps) + (3 * k) * np.log(2 * t_len))
+            bic.append(
+                2 * t_len * np.log(err + np.finfo(float).eps)
+                + (3 * k) * np.log(2 * t_len)
+            )
             if k > 1 and bic[-1] > bic[-2]:
                 stop = True
         elif stopc == 3:
@@ -288,9 +291,9 @@ def fit_transform(
                                 - u_hat_l[:, c, n + 1]
                             )
                         )
-                        den_g = 1.0 + 2.0 * (alpha_val**2) * (
-                            omega_freqs - omega_l[n]
-                        ) ** 4
+                        den_g = (
+                            1.0 + 2.0 * (alpha_val**2) * (omega_freqs - omega_l[n]) ** 4
+                        )
                         g_hat_plus[:, c, n + 1] = num_g / den_g
 
                     # shared / single center frequency
@@ -311,9 +314,7 @@ def fit_transform(
                     u_td = np.zeros((n_ch, t_len), dtype=float)
                     fr_td = np.zeros((n_ch, t_len), dtype=float)
                     for c in range(n_ch):
-                        u_td[c, :] = np.real(
-                            np.fft.ifft(np.fft.ifftshift(u_hat[:, c]))
-                        )
+                        u_td[c, :] = np.real(np.fft.ifft(np.fft.ifftshift(u_hat[:, c])))
                         fr_td[c, :] = np.real(
                             np.fft.ifft(np.fft.ifftshift(g_hat[:, c]))
                         )