attempt at fix

assignment-2/assignment_2/Gaussian Maximum Likelihood.ipynb

@@ -1548,28 +1548,50 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 18,
    "id": "7c8b167d-c397-4155-93f3-d826c279fbb2",
    "metadata": {
     "tags": []
    },
    "outputs": [
     {
-     "ename": "SyntaxError",
-     "evalue": "invalid syntax (3400372070.py, line 66)",
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "SGD Problem 4\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_615396/2481416868.py:22: RuntimeWarning: divide by zero encountered in log\n",
+      "  [ki * np.log(l) for ki in k]\n"
+     ]
+    },
+    {
+     "ename": "ValueError",
+     "evalue": "operands could not be broadcast together with shapes (3,) (214,) ",
      "output_type": "error",
      "traceback": [
-      "\u001b[0;36m  Cell \u001b[0;32mIn[7], line 66\u001b[0;36m\u001b[0m\n\u001b[0;31m    p_dw = lambda w, xi: np.array([primitive(xi, wi) for xi, wi in ])\u001b[0m\n\u001b[0m                                                                   ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n"
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[18], line 44\u001b[0m\n\u001b[1;32m     40\u001b[0m     dflog \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mDataFrame(log4)\n\u001b[1;32m     41\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m dflog\n\u001b[0;32m---> 44\u001b[0m _ \u001b[38;5;241m=\u001b[39m \u001b[43mdebug_SGD_3\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m     45\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdf\u001b[49m\u001b[43m[\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mHIGH_T\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mLOW_T\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mPRECIP\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto_numpy\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     46\u001b[0m \u001b[43m    \u001b[49m\u001b[43mw\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43marray\u001b[49m\u001b[43m(\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m1.0\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1.0\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1.0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     47\u001b[0m \u001b[43m)\u001b[49m\n",
+      "Cell \u001b[0;32mIn[18], line 39\u001b[0m, in \u001b[0;36mdebug_SGD_3\u001b[0;34m(data, w)\u001b[0m\n\u001b[1;32m     37\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdebug_SGD_3\u001b[39m(data, w\u001b[38;5;241m=\u001b[39mnp\u001b[38;5;241m.\u001b[39marray([\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m1\u001b[39m])):\n\u001b[1;32m     38\u001b[0m     \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mSGD Problem 4\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m---> 39\u001b[0m     \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mw: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[43mSGD_problem4\u001b[49m\u001b[43m(\u001b[49m\u001b[43mw\u001b[49m\u001b[43m,\u001b[49m\u001b[38;5;250;43m \u001b[39;49m\u001b[43mdata\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m     40\u001b[0m     dflog \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mDataFrame(log4)\n\u001b[1;32m     41\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m dflog\n",
+      "Cell \u001b[0;32mIn[18], line 24\u001b[0m, in \u001b[0;36mSGD_problem4\u001b[0;34m(w, x, learning_rate, n_epochs)\u001b[0m\n\u001b[1;32m     19\u001b[0m \u001b[38;5;66;03m# custom\u001b[39;00m\n\u001b[1;32m     20\u001b[0m \u001b[38;5;66;03m# loss = x.shape[0] * np.exp(np.dot(x, w))\u001b[39;00m\n\u001b[1;32m     21\u001b[0m loss_fn \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mlambda\u001b[39;00m k, l: \u001b[38;5;28mlen\u001b[39m(k) \u001b[38;5;241m*\u001b[39m l \u001b[38;5;241m-\u001b[39m np\u001b[38;5;241m.\u001b[39msum(\n\u001b[1;32m     22\u001b[0m     [ki \u001b[38;5;241m*\u001b[39m np\u001b[38;5;241m.\u001b[39mlog(l) \u001b[38;5;28;01mfor\u001b[39;00m ki \u001b[38;5;129;01min\u001b[39;00m k]\n\u001b[1;32m     23\u001b[0m )  \u001b[38;5;66;03m# + np.sum([np.log(np.math.factorial(ki)) for ki in k])\u001b[39;00m\n\u001b[0;32m---> 24\u001b[0m loss \u001b[38;5;241m=\u001b[39m \u001b[43mloss_fn\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexp\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdot\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mw\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     25\u001b[0m log4\u001b[38;5;241m.\u001b[39mappend(\n\u001b[1;32m     26\u001b[0m     {\n\u001b[1;32m     27\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mEpoch\u001b[39m\u001b[38;5;124m\"\u001b[39m: epoch,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     31\u001b[0m     }\n\u001b[1;32m     32\u001b[0m )\n\u001b[1;32m     33\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mEpoch \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mepoch\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mLoss: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mloss\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
+      "Cell \u001b[0;32mIn[18], line 22\u001b[0m, in \u001b[0;36mSGD_problem4.<locals>.<lambda>\u001b[0;34m(k, l)\u001b[0m\n\u001b[1;32m     18\u001b[0m w \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m=\u001b[39m learning_rate \u001b[38;5;241m*\u001b[39m dw(w, x)\n\u001b[1;32m     19\u001b[0m \u001b[38;5;66;03m# custom\u001b[39;00m\n\u001b[1;32m     20\u001b[0m \u001b[38;5;66;03m# loss = x.shape[0] * np.exp(np.dot(x, w))\u001b[39;00m\n\u001b[1;32m     21\u001b[0m loss_fn \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mlambda\u001b[39;00m k, l: \u001b[38;5;28mlen\u001b[39m(k) \u001b[38;5;241m*\u001b[39m l \u001b[38;5;241m-\u001b[39m np\u001b[38;5;241m.\u001b[39msum(\n\u001b[0;32m---> 22\u001b[0m     [ki \u001b[38;5;241m*\u001b[39m np\u001b[38;5;241m.\u001b[39mlog(l) \u001b[38;5;28;01mfor\u001b[39;00m ki \u001b[38;5;129;01min\u001b[39;00m k]\n\u001b[1;32m     23\u001b[0m )  \u001b[38;5;66;03m# + np.sum([np.log(np.math.factorial(ki)) for ki in k])\u001b[39;00m\n\u001b[1;32m     24\u001b[0m loss \u001b[38;5;241m=\u001b[39m loss_fn(x, np\u001b[38;5;241m.\u001b[39mexp(np\u001b[38;5;241m.\u001b[39mdot(x, w)))\n\u001b[1;32m     25\u001b[0m log4\u001b[38;5;241m.\u001b[39mappend(\n\u001b[1;32m     26\u001b[0m     {\n\u001b[1;32m     27\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mEpoch\u001b[39m\u001b[38;5;124m\"\u001b[39m: epoch,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     31\u001b[0m     }\n\u001b[1;32m     32\u001b[0m )\n",
+      "Cell \u001b[0;32mIn[18], line 22\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m     18\u001b[0m w \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m=\u001b[39m learning_rate \u001b[38;5;241m*\u001b[39m dw(w, x)\n\u001b[1;32m     19\u001b[0m \u001b[38;5;66;03m# custom\u001b[39;00m\n\u001b[1;32m     20\u001b[0m \u001b[38;5;66;03m# loss = x.shape[0] * np.exp(np.dot(x, w))\u001b[39;00m\n\u001b[1;32m     21\u001b[0m loss_fn \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mlambda\u001b[39;00m k, l: \u001b[38;5;28mlen\u001b[39m(k) \u001b[38;5;241m*\u001b[39m l \u001b[38;5;241m-\u001b[39m np\u001b[38;5;241m.\u001b[39msum(\n\u001b[0;32m---> 22\u001b[0m     [\u001b[43mki\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlog\u001b[49m\u001b[43m(\u001b[49m\u001b[43ml\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m ki \u001b[38;5;129;01min\u001b[39;00m k]\n\u001b[1;32m     23\u001b[0m )  \u001b[38;5;66;03m# + np.sum([np.log(np.math.factorial(ki)) for ki in k])\u001b[39;00m\n\u001b[1;32m     24\u001b[0m loss \u001b[38;5;241m=\u001b[39m loss_fn(x, np\u001b[38;5;241m.\u001b[39mexp(np\u001b[38;5;241m.\u001b[39mdot(x, w)))\n\u001b[1;32m     25\u001b[0m log4\u001b[38;5;241m.\u001b[39mappend(\n\u001b[1;32m     26\u001b[0m     {\n\u001b[1;32m     27\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mEpoch\u001b[39m\u001b[38;5;124m\"\u001b[39m: epoch,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     31\u001b[0m     }\n\u001b[1;32m     32\u001b[0m )\n",
+      "\u001b[0;31mValueError\u001b[0m: operands could not be broadcast together with shapes (3,) (214,) "
      ]
     }
    ],
    "source": [
     "## pset 4\n",
     "\n",
-    "# dw = lambda w, x: len(x) * np.exp(np.dot(x, w)) * x - np.sum()\n",
+    "dw = lambda w, x: np.sum([len(x) * np.exp(np.dot(xi, w)) * x - np.sum(np.dot(x.T,x)) for xi in x])\n",
     "\n",
-    "primitive = lambda xi, wi: (x.shape[0] * np.exp(wi * xi) * xi) - (xi**2)\n",
-    "p_dw = lambda w, xi: np.array([primitive(xi, wi) for xi, wi in ])\n",
+    "#primitive = lambda xi, wi: (x.shape[0] * np.exp(wi * xi) * xi) - (xi**2)\n",
+    "#p_dw = lambda w, xi: np.array([primitive(xi, wi) for xi, wi in ])\n",
     "\n",
     "\n",
     "def SGD_problem4(\n",
@@ -1581,7 +1603,7 @@
     "    global log4\n",
     "    log4 = []\n",
     "    for epoch in range(n_epochs):\n",
-    "        w -= learning_rate * p_dw(w, x)\n",
+    "        w -= learning_rate * dw(w, x)\n",
     "        # custom\n",
     "        # loss = x.shape[0] * np.exp(np.dot(x, w))\n",
     "        loss_fn = lambda k, l: len(k) * l - np.sum(\n",
@@ -1613,42 +1635,6 @@
     ")"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "69e9148b-70fb-46e3-bc29-a08f471cccab",
-   "metadata": {},
-   "source": [
-    "Seek to maximize likelihood, which is equivalent to minimizing log likelihood, which is equivalent to maximizing MSE.\n",
-    "\n",
-    "-> Find MSE"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "fb9d2e20-8a02-4f78-a3d3-6fc171f17af6",
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "SyntaxError",
-     "evalue": "incomplete input (3680490224.py, line 3)",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;36m  Cell \u001b[0;32mIn[2], line 3\u001b[0;36m\u001b[0m\n\u001b[0;31m    def MSE(x: List):\u001b[0m\n\u001b[0m                     ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m incomplete input\n"
-     ]
-    }
-   ],
-   "source": [
-    "from typing import List\n",
-    "from numpy import \n",
-    "\n",
-    "w = np.array(2)\n",
-    "\n",
-    "def partial_of_Loss(w, x, y):\n",
-    "    \n",
-    "    "
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,