.

Author: smilesun

causalspyne/implicit_gen_Sigma.py

@@ -4,6 +4,7 @@
 from causalspyne.implicit_omega_condition_on_w import gen_joint_w_omega, get_max_degree
 from causalspyne.implicit_omega import get_extreme_eigenvalue
 
+
 def cov_to_corr(covariance_matrix):
     # Calculate the standard deviations
     std_devs = np.sqrt(np.diag(covariance_matrix))
@@ -45,15 +46,18 @@ def gen_sigma_y(max_w=0.5):
     return mat_sigma, dmax, max_omega
 
 
-if __name__ == "__main__":
+def gen_spectrum():
     mat_sigma, dmax, max_omega = gen_sigma_y()
     print(f"sigma: {mat_sigma}")
     inv_sigma = np.linalg.inv(mat_sigma)
     eigv_max, _ = get_extreme_eigenvalue(inv_sigma)
     print(f"max eigen value: {eigv_max}")
     print(f"max degree: {dmax}, max_omega: {max_omega}")
-
     mat_precision = cov_to_corr(inv_sigma)
     eigv_max, _ = get_extreme_eigenvalue(mat_precision)
     print(f"max eigen value: {eigv_max}")
+    return eigv_max
 
+
+if __name__ == "__main__":
+    gen_spectrum()

causalspyne/implicit_spectrum_histogram.py

@@ -0,0 +1,32 @@
+import numpy as np
+import matplotlib.pyplot as plt
+from scipy import stats
+from causalspyne.implicit_gen_Sigma import gen_spectrum
+
+
+# Generate sample data
+
+# samples = np.random.normal(size=10000)
+samples = [gen_spectrum() for _ in range(10000)]
+# Create histogram
+fig, ax = plt.subplots(figsize=(8, 6))
+
+hist, bins, _ = ax.hist(samples, bins=30, density=True, alpha=0.7,
+                        label="Histogram")
+
+# Calculate bin centers for PDF plotting
+bin_centers = 0.5 * (bins[1:] + bins[:-1])
+
+# Compute PDF
+pdf = stats.norm.pdf(bin_centers)
+
+# Plot PDF
+ax.plot(bin_centers, pdf, 'r-', label="PDF")
+
+# Customize plot
+ax.set_xlabel('eigenvalue')
+ax.set_ylabel('Density')
+ax.set_title('Histogram of maximum eigenvalue distribution')
+ax.legend()
+
+plt.show()