Connect UI with SUR GeoDaCenter#4

fix an issue when load PLM style data: it seems the order of the rows (X matrix) DOES impact the regression results.
lixun910 · Oct 24, 2018 · 3af5ff0 · 3af5ff0
1 parent 2ae0e10
commit 3af5ff0
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 8 deletions.
diff --git a/econometrics/sur_utils.py b/econometrics/sur_utils.py
@@ -91,7 +91,9 @@ def sur_dictxy(db,y_vars,x_vars,space_id=None,time_id=None):
         longxc = np.hstack((np.ones((bign, 1)), longx))
         xvars = x_vars[0][:]
         xvars.insert(0,c)
-
+
+        skeys = []
+        sdict = {}
         tmpy = { t : {} for t in tt1 }
         tmpX = { t : {} for t in tt1 }
         for i in range(bign):
@@ -101,15 +103,18 @@ def sur_dictxy(db,y_vars,x_vars,space_id=None,time_id=None):
                 tmpy[tval][sval] = y[i]
             if tmpX.has_key(tval):
                 tmpX[tval][sval] = longxc[i]
+            if not sdict.has_key(sval):
+                skeys.append(sval)
+                sdict[sval] = True
 
         bigy = {}
         bigX = {}
         bigy_vars = {}
         bigX_vars = {}
         for r in range(n_eq):
             tval = tt2[r]
-            bigy[r] = np.array(tmpy[tval].values())
-            bigX[r] = np.array(tmpX[tval].values())
+            bigy[r] = np.array([tmpy[tval][v] for v in skeys])
+            bigX[r] = np.array([tmpX[tval][v] for v in skeys])
             bigy_vars[r] = y_vars[0] + "_" + tt3[r]
             bigX_vars[r] = [i + "_" + tt3[r] for i in xvars]
         return (bigy,bigX,bigy_vars,bigX_vars)

diff --git a/geodaspace/regression/M_regression.py b/geodaspace/regression/M_regression.py
@@ -423,11 +423,13 @@ def run(self, path=None, predy_resid=None):
         elif name_s and name_t and len(name_s)>0 and len(name_t) > 0:
             y, x, name_y, x_names = sur_dictxy(db, [name_y], [x_names], space_id=[name_s], time_id=[name_t])
 
-            yend_var1 = [ name.split(',') for name in ye_names]
-            ye, ye_names = sur_dictZ(db,yend_var1, form="plm", space_id=[name_s], time_id=[name_t])
-
-            q_var1 = [ name.split(',') for name in h_names]
-            h, h_names = sur_dictZ(db,q_var1, form="plm", space_id=[name_s], time_id=[name_t])              
+            if len(ye_names) > 0:
+                yend_var1 = [ name.split(',') for name in ye_names]
+                ye, ye_names = sur_dictZ(db,yend_var1, form="plm", space_id=[name_s], time_id=[name_t])
+
+            if len(h_names) > 0:         
+                q_var1 = [ name.split(',') for name in h_names]
+                h, h_names = sur_dictZ(db,q_var1, form="plm", space_id=[name_s], time_id=[name_t])              
 
         config = data['config']