WIP notebooks cleanup

.gitignore

@@ -18,3 +18,6 @@ _build
 
 # Merge tool
 *.orig
+
+# Test artifacts
+mcmc.sqlite

docs/source/notebooks/BEST.ipynb

@@ -470,15 +470,6 @@
     "2.\tJohnson D. The insignificance of statistical significance testing. Journal of Wildlife Management. 1999;63(3):763-772.\n",
     "3.\tKruschke JK. Bayesian estimation supersedes the t test. J Exp Psychol Gen. 2013;142(2):573-603. doi:10.1037/a0029146."
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -499,6 +490,13 @@
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
    "version": "3.5.2"
+  },
+  "latex_envs": {
+   "bibliofile": "biblio.bib",
+   "cite_by": "apalike",
+   "current_citInitial": 1,
+   "eqLabelWithNumbers": true,
+   "eqNumInitial": 0
   }
  },
  "nbformat": 4,

docs/source/notebooks/discrete_find_MAP.ipynb

@@ -22,7 +22,7 @@
    },
    "outputs": [],
    "source": [
-    "import pymc3 as mc"
+    "import pymc3 as pm"
    ]
   },
   {
@@ -53,10 +53,10 @@
     "n = 20\n",
     "yes = 15\n",
     "\n",
-    "with mc.Model() as model:\n",
-    "    p = mc.Beta('p', alpha, beta)\n",
-    "    surv_sim = mc.Binomial('surv_sim', n=n, p=p)\n",
-    "    surv = mc.Binomial('surv', n=n, p=p, observed=yes)"
+    "with pm.Model() as model:\n",
+    "    p = pm.Beta('p', alpha, beta)\n",
+    "    surv_sim = pm.Binomial('surv_sim', n=n, p=p)\n",
+    "    surv = pm.Binomial('surv', n=n, p=p, observed=yes)"
    ]
   },
   {
@@ -72,18 +72,10 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'surv_sim': array(10), 'p_logodds_': array(0.42285684671251805)}\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "with model:\n",
-    "    print(mc.find_MAP())"
+    "    pm.find_MAP()"
    ]
   },
   {
@@ -99,18 +91,10 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'surv_sim': array(14), 'p_logodds_': array(0.7884573537909452)}\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "with model:\n",
-    "    print(mc.find_MAP(vars=model.vars, disp=True))"
+    "    pm.find_MAP(vars=model.vars, disp=True)"
    ]
   },
   {
@@ -134,9 +118,9 @@
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-5-299cdf766633>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      2\u001b[0m     \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m         \u001b[0ms\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0;34m'p'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;36m0.5\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'surv_sim'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m         \u001b[0mmap_est\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfind_MAP\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstart\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0ms\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvars\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvars\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfmin\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstarting\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moptimize\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfmin_bfgs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      5\u001b[0m         print('surv_sim: %i->%i, p: %f->%f, LogP:%f'%(s['surv_sim'],\n\u001b[1;32m      6\u001b[0m                                                       \u001b[0mmap_est\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'surv_sim'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m/home/wiecki/working/projects/pymc/pymc3/tuning/starting.py\u001b[0m in \u001b[0;36mfind_MAP\u001b[0;34m(start, vars, fmin, return_raw, model, *args, **kwargs)\u001b[0m\n\u001b[1;32m     82\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0;34m'fprime'\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mgetargspec\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfmin\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     83\u001b[0m         r = fmin(logp_o, bij.map(\n\u001b[0;32m---> 84\u001b[0;31m             start), fprime=grad_logp_o, *args, **kwargs)\n\u001b[0m\u001b[1;32m     85\u001b[0m     \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     86\u001b[0m         \u001b[0mr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfmin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlogp_o\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbij\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstart\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m/home/wiecki/working/projects/pymc/pymc3/blocking.py\u001b[0m in \u001b[0;36mmap\u001b[0;34m(self, dpt)\u001b[0m\n\u001b[1;32m     50\u001b[0m         \u001b[0mapt\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mempty\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mordering\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdimensions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     51\u001b[0m         \u001b[0;32mfor\u001b[0m \u001b[0mvar\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mslc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mordering\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvmap\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 52\u001b[0;31m             \u001b[0mapt\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mslc\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdpt\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mvar\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mravel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     53\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mapt\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     54\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m<ipython-input-5-1a981a0bba6e>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      2\u001b[0m     \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m         \u001b[0ms\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0;34m'p'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;36m0.5\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'surv_sim'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m         \u001b[0mmap_est\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpm\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfind_MAP\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstart\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0ms\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvars\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvars\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      5\u001b[0m         print('surv_sim: %i->%i, p: %f->%f, LogP:%f'%(s['surv_sim'],\n\u001b[1;32m      6\u001b[0m                                                       \u001b[0mmap_est\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'surv_sim'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Users/fonnescj/Repositories/pymc3/pymc3/tuning/starting.py\u001b[0m in \u001b[0;36mfind_MAP\u001b[0;34m(start, vars, fmin, return_raw, model, *args, **kwargs)\u001b[0m\n\u001b[1;32m     86\u001b[0m         \u001b[0;31m# Check to see if minimization function uses a starting value\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     87\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0;34m'x0'\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mgetargspec\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfmin\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 88\u001b[0;31m             \u001b[0mr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfmin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlogp_o\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbij\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstart\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     89\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     90\u001b[0m             \u001b[0mr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfmin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlogp_o\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Users/fonnescj/Repositories/pymc3/pymc3/blocking.py\u001b[0m in \u001b[0;36mmap\u001b[0;34m(self, dpt)\u001b[0m\n\u001b[1;32m     50\u001b[0m         \u001b[0mapt\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mempty\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mordering\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdimensions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     51\u001b[0m         \u001b[0;32mfor\u001b[0m \u001b[0mvar\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mslc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mordering\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvmap\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 52\u001b[0;31m             \u001b[0mapt\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mslc\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdpt\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mvar\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mravel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     53\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mapt\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     54\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;31mKeyError\u001b[0m: 'p_logodds_'"
      ]
     }
@@ -145,7 +129,7 @@
     "with model:\n",
     "    for i in range(n+1):\n",
     "        s = {'p':0.5, 'surv_sim':i}\n",
-    "        map_est = mc.find_MAP(start=s, vars=model.vars, fmin=mc.starting.optimize.fmin_bfgs)\n",
+    "        map_est = pm.find_MAP(start=s, vars=model.vars)\n",
     "        print('surv_sim: %i->%i, p: %f->%f, LogP:%f'%(s['surv_sim'],\n",
     "                                                      map_est['surv_sim'],\n",
     "                                                      s['p'],\n",
@@ -171,7 +155,7 @@
     "with model:\n",
     "    for i in range(n+1):\n",
     "        s = {'p':0.5, 'surv_sim':i}\n",
-    "        map_est = mc.find_MAP(start=s, vars=model.vars)\n",
+    "        map_est = pm.find_MAP(start=s, vars=model.vars)\n",
     "        print('surv_sim: %i->%i, p: %f->%f, LogP:%f'%(s['surv_sim'],\n",
     "                                                      map_est['surv_sim'],\n",
     "                                                      s['p'],\n",
@@ -195,14 +179,14 @@
    "outputs": [],
    "source": [
     "def bh(*args,**kwargs):\n",
-    "    result = mc.starting.optimize.basinhopping(*args, **kwargs)\n",
+    "    result = pm.starting.optimize.basinhopping(*args, **kwargs)\n",
     "    # A `Result` object is returned, the argmin value can be in `x`\n",
     "    return result['x']\n",
     "\n",
     "with model:\n",
     "    for i in range(n+1):\n",
     "        s = {'p':0.5, 'surv_sim':i}\n",
-    "        map_est = mc.find_MAP(start=s, vars=model.vars, fmin=bh)\n",
+    "        map_est = pm.find_MAP(start=s, vars=model.vars, fmin=bh)\n",
     "        print('surv_sim: %i->%i, p: %f->%f, LogP:%f'%(s['surv_sim'],\n",
     "                                                      floor(map_est['surv_sim']),\n",
     "                                                      s['p'],\n",
@@ -228,7 +212,7 @@
     "with model:\n",
     "    for i in range(n+1):\n",
     "        s = {'p':0.5, 'surv_sim':i}\n",
-    "        map_est = mc.find_MAP(start=s, vars=model.vars, fmin=bh, minimizer_kwargs={\"method\": /\"Powell\"})\n",
+    "        map_est = pm.find_MAP(start=s, vars=model.vars, fmin=bh, minimizer_kwargs={\"method\": /\"Powell\"})\n",
     "        print('surv_sim: %i->%i, p: %f->%f, LogP:%f'%(s['surv_sim'],\n",
     "                                                      map_est['surv_sim'],\n",
     "                                                      s['p'],\n",
@@ -252,8 +236,8 @@
    "outputs": [],
    "source": [
     "with model:\n",
-    "    step1 = mc.step_methods.HamiltonianMC(vars=[p])\n",
-    "    step2 = mc.step_methods.Metropolis(vars=[surv_sim])"
+    "    step1 = pm.step_methods.HamiltonianMC(vars=[p])\n",
+    "    step2 = pm.step_methods.Metropolis(vars=[surv_sim])"
    ]
   },
   {
@@ -276,17 +260,8 @@
    },
    "outputs": [],
    "source": [
-    "mc.traceplot(trace);"
+    "pm.traceplot(trace);"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -307,6 +282,13 @@
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
    "version": "3.5.2"
+  },
+  "latex_envs": {
+   "bibliofile": "biblio.bib",
+   "cite_by": "apalike",
+   "current_citInitial": 1,
+   "eqLabelWithNumbers": true,
+   "eqNumInitial": 0
   }
  },
  "nbformat": 4,