From: Debian Science Maintainers <debian-science-maintainers@lists.alioth.debian.org>
Date: Sat, 2 Mar 2019 14:59:35 +0000 (+0000)
Subject: Create a normal array, not an array of 1x1 arrays
X-Git-Tag: archive/raspbian/0.11.1-2+rpi1~2^2^2~5
X-Git-Url: https://dgit.raspbian.org/%22http://www.example.com/cgi/success//%22http:/www.example.com/cgi/success/?a=commitdiff_plain;h=8a9caef404938233131c1516748e85972b218fed;p=statsmodels.git

Create a normal array, not an array of 1x1 arrays

Fixes "object arrays are not supported".

Author: Kevin "bashtage" Sheppard
Origin: upstream https://github.com/statsmodels/statsmodels/pull/4911/commits/18dcceefbfed61b0d11ae5884a9f4cea82c2edb5
Forwarded: not-needed


Gbp-Pq: Name unconstrain_stationary_multivariate.patch
---

diff --git a/statsmodels/tsa/statespace/tools.py b/statsmodels/tsa/statespace/tools.py
index 6c485e9..a97efce 100644
--- a/statsmodels/tsa/statespace/tools.py
+++ b/statsmodels/tsa/statespace/tools.py
@@ -965,7 +965,7 @@ def _compute_multivariate_acovf_from_coefficients(
     # Then stack the VAR(p) into a VAR(1) in companion matrix form:
     # z_{t+1} = F z_t + v_t
     companion = companion_matrix(
-        [1] + [-coefficients[i] for i in range(order)]
+        [1] + [-np.squeeze(coefficients[i]) for i in range(order)]
     ).T
 
     # Compute the error variance matrix for the stacked form: E v_t v_t'