{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "52680b11",
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import torch.nn as nn\n",
    "import torch.optim as optim\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "c42f60f1",
   "metadata": {},
   "outputs": [],
   "source": [
    "class PINN(nn.Module):\n",
    "    def __init__(self):\n",
    "        super(PINN,self).__init__()\n",
    "        self.net = nn.Sequential(\n",
    "            nn.Linear(3,64),\n",
    "            nn.Tanh(),\n",
    "            nn.Linear(64,64),\n",
    "            nn.Tanh(),\n",
    "            nn.Linear(64,1)\n",
    "        )\n",
    "    def forward(self,x):\n",
    "        return self.net(x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "0d3d62a8",
   "metadata": {},
   "outputs": [],
   "source": [
    "def intial_condition(x,y):\n",
    "    return torch.sin(torch.pi * x) * torch.sin(torch.pi * y)\n",
    "\n",
    "def boundary_condition(x,y,t, custom_value):\n",
    "    return torch.full_like(x, custom_value)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6cf104d1",
   "metadata": {},
   "outputs": [],
   "source": [
    "def generate_training_data(num_points):\n",
    "    x = torch.rand(num_points, 1, requires_grad = True)\n",
    "    y = torch.rand(num_points, 1, requires_grad = True)\n",
    "    t = torch.rand(num_points, 1, requires_grad = True)\n",
    "    \n",
    "    return x,y,t"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a42303a2",
   "metadata": {},
   "outputs": [],
   "source": [
    "def generate_boundary_points(num_points):\n",
    "    x_boundary = torch.tensor([0.0,1.0]).repeat(num_points//2)\n",
    "    y_boundary = torch.rand(num_points)\n",
    "    \n",
    "    if torch.rand(1) > 0.5:\n",
    "        x_boundary, y_boundary = y_boundary,x_boundary\n",
    "        \n",
    "    return x_boundary.view(-1,1), y_boundary.view(-1,1)\n",
    "\n",
    "\n",
    "def generate_boundary_training_data(num_points):\n",
    "    x_boundary, y_boundary = generate_boundary_points(num_points)\n",
    "    t = torch.rand(num_points, 1, requires_grad= True)\n",
    "    \n",
    "    return x_boundary, y_boundary, t"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9f9e7a39",
   "metadata": {},
   "outputs": [],
   "source": [
    "def pde(x,y,t,model):\n",
    "    input_data = torch.cat([x,y,t],dim=1)\n",
    "    u = model(input_data)\n",
    "    u_x,u_y = torch.autograd.grad(u,[x,y],grad_outputs= torch.ones_like(u), create_graph= True, retain_graph=True) \n",
    "    u_xx = torch.autograd.grad(u_x,x,grad_outputs= torch.ones_like(u_x), create_graph= True, retain_graph=True)[0]\n",
    "    u_yy = torch.autograd.grad(u_y,y,grad_outputs= torch.ones_like(u_y), create_graph= True, retain_graph=True)[0]\n",
    "    u_t = torch.autograd.grad(u,t,grad_outputs= torch.ones_like(u), create_graph= True, retain_graph=True)[0]\n",
    "    heat_eq_residual = 1 * u_xx + 1 * u_yy - u_t\n",
    "    return heat_eq_residual"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "00395c93",
   "metadata": {},
   "outputs": [],
   "source": [
    "def train_PINN(model, num_iterations, num_points):\n",
    "    optimizer = optim.Adam(model.parameters(), lr=1e-3)\n",
    "    \n",
    "    for  iteration in range(num_iterations):\n",
    "        optimizer.zero_grad()\n",
    "        \n",
    "        x,y,t = generate_training_data(num_points)\n",
    "        \n",
    "        x_b,y_b,t_b = generate_boundary_training_data(num_points)\n",
    "        \n",
    "        t_intial = torch.zeros_like(t)\n",
    "        u_intial = intial_condition(x,y)\n",
    "        \n",
    "        custom_value = 0\n",
    "        u_boundary_x = boundary_condition(x_b,y_b,t_b,custom_value)\n",
    "        u_boundary_y = boundary_condition(y_b,x_b,t_b,custom_value)\n",
    "        \n",
    "        residual = pde(x,y,t,model)\n",
    "        \n",
    "        loss =  nn.MSELoss()(u_intial, model(torch.cat([x,y,t_intial], dim=1))) + \\\n",
    "                nn.MSELoss()(u_boundary_x, model(torch.cat([x_b,y_b,t_b], dim=1))) + \\\n",
    "                nn.MSELoss()(u_boundary_y, model(torch.cat([y_b,x_b,t_b], dim=1))) + \\\n",
    "                nn.MSELoss()(residual, torch.zeros_like(residual))\n",
    "                \n",
    "        loss.backward()\n",
    "        optimizer.step()\n",
    "        \n",
    "        if iteration % 100 ==0:\n",
    "            print(\"itration\",iteration, \"loss\",loss )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "3565e7b3",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "itration 0 loss tensor(0.2301, grad_fn=<AddBackward0>)\n",
      "itration 100 loss tensor(0.1240, grad_fn=<AddBackward0>)\n",
      "itration 200 loss tensor(0.1258, grad_fn=<AddBackward0>)\n",
      "itration 300 loss tensor(0.0957, grad_fn=<AddBackward0>)\n",
      "itration 400 loss tensor(0.0781, grad_fn=<AddBackward0>)\n",
      "itration 500 loss tensor(0.0680, grad_fn=<AddBackward0>)\n",
      "itration 600 loss tensor(0.0603, grad_fn=<AddBackward0>)\n",
      "itration 700 loss tensor(0.0532, grad_fn=<AddBackward0>)\n",
      "itration 800 loss tensor(0.0522, grad_fn=<AddBackward0>)\n",
      "itration 900 loss tensor(0.0465, grad_fn=<AddBackward0>)\n",
      "itration 1000 loss tensor(0.0399, grad_fn=<AddBackward0>)\n",
      "itration 1100 loss tensor(0.0364, grad_fn=<AddBackward0>)\n",
      "itration 1200 loss tensor(0.0355, grad_fn=<AddBackward0>)\n",
      "itration 1300 loss tensor(0.0329, grad_fn=<AddBackward0>)\n",
      "itration 1400 loss tensor(0.0267, grad_fn=<AddBackward0>)\n",
      "itration 1500 loss tensor(0.0272, grad_fn=<AddBackward0>)\n",
      "itration 1600 loss tensor(0.0237, grad_fn=<AddBackward0>)\n",
      "itration 1700 loss tensor(0.0217, grad_fn=<AddBackward0>)\n",
      "itration 1800 loss tensor(0.0205, grad_fn=<AddBackward0>)\n",
      "itration 1900 loss tensor(0.0200, grad_fn=<AddBackward0>)\n",
      "itration 2000 loss tensor(0.0179, grad_fn=<AddBackward0>)\n",
      "itration 2100 loss tensor(0.0167, grad_fn=<AddBackward0>)\n",
      "itration 2200 loss tensor(0.0167, grad_fn=<AddBackward0>)\n",
      "itration 2300 loss tensor(0.0151, grad_fn=<AddBackward0>)\n",
      "itration 2400 loss tensor(0.0161, grad_fn=<AddBackward0>)\n",
      "itration 2500 loss tensor(0.0143, grad_fn=<AddBackward0>)\n",
      "itration 2600 loss tensor(0.0120, grad_fn=<AddBackward0>)\n",
      "itration 2700 loss tensor(0.0143, grad_fn=<AddBackward0>)\n",
      "itration 2800 loss tensor(0.0129, grad_fn=<AddBackward0>)\n",
      "itration 2900 loss tensor(0.0121, grad_fn=<AddBackward0>)\n",
      "itration 3000 loss tensor(0.0125, grad_fn=<AddBackward0>)\n",
      "itration 3100 loss tensor(0.0116, grad_fn=<AddBackward0>)\n",
      "itration 3200 loss tensor(0.0114, grad_fn=<AddBackward0>)\n",
      "itration 3300 loss tensor(0.0122, grad_fn=<AddBackward0>)\n",
      "itration 3400 loss tensor(0.0104, grad_fn=<AddBackward0>)\n",
      "itration 3500 loss tensor(0.0103, grad_fn=<AddBackward0>)\n",
      "itration 3600 loss tensor(0.0102, grad_fn=<AddBackward0>)\n",
      "itration 3700 loss tensor(0.0099, grad_fn=<AddBackward0>)\n",
      "itration 3800 loss tensor(0.0095, grad_fn=<AddBackward0>)\n",
      "itration 3900 loss tensor(0.0083, grad_fn=<AddBackward0>)\n",
      "itration 4000 loss tensor(0.0090, grad_fn=<AddBackward0>)\n",
      "itration 4100 loss tensor(0.0086, grad_fn=<AddBackward0>)\n",
      "itration 4200 loss tensor(0.0084, grad_fn=<AddBackward0>)\n",
      "itration 4300 loss tensor(0.0079, grad_fn=<AddBackward0>)\n",
      "itration 4400 loss tensor(0.0083, grad_fn=<AddBackward0>)\n",
      "itration 4500 loss tensor(0.0076, grad_fn=<AddBackward0>)\n",
      "itration 4600 loss tensor(0.0082, grad_fn=<AddBackward0>)\n",
      "itration 4700 loss tensor(0.0068, grad_fn=<AddBackward0>)\n",
      "itration 4800 loss tensor(0.0094, grad_fn=<AddBackward0>)\n",
      "itration 4900 loss tensor(0.0076, grad_fn=<AddBackward0>)\n",
      "itration 5000 loss tensor(0.0080, grad_fn=<AddBackward0>)\n",
      "itration 5100 loss tensor(0.0068, grad_fn=<AddBackward0>)\n",
      "itration 5200 loss tensor(0.0062, grad_fn=<AddBackward0>)\n",
      "itration 5300 loss tensor(0.0058, grad_fn=<AddBackward0>)\n",
      "itration 5400 loss tensor(0.0063, grad_fn=<AddBackward0>)\n",
      "itration 5500 loss tensor(0.0062, grad_fn=<AddBackward0>)\n",
      "itration 5600 loss tensor(0.0065, grad_fn=<AddBackward0>)\n",
      "itration 5700 loss tensor(0.0071, grad_fn=<AddBackward0>)\n",
      "itration 5800 loss tensor(0.0057, grad_fn=<AddBackward0>)\n",
      "itration 5900 loss tensor(0.0052, grad_fn=<AddBackward0>)\n",
      "itration 6000 loss tensor(0.0056, grad_fn=<AddBackward0>)\n",
      "itration 6100 loss tensor(0.0049, grad_fn=<AddBackward0>)\n",
      "itration 6200 loss tensor(0.0062, grad_fn=<AddBackward0>)\n",
      "itration 6300 loss tensor(0.0046, grad_fn=<AddBackward0>)\n",
      "itration 6400 loss tensor(0.0050, grad_fn=<AddBackward0>)\n",
      "itration 6500 loss tensor(0.0045, grad_fn=<AddBackward0>)\n",
      "itration 6600 loss tensor(0.0070, grad_fn=<AddBackward0>)\n",
      "itration 6700 loss tensor(0.0048, grad_fn=<AddBackward0>)\n",
      "itration 6800 loss tensor(0.0049, grad_fn=<AddBackward0>)\n",
      "itration 6900 loss tensor(0.0052, grad_fn=<AddBackward0>)\n",
      "itration 7000 loss tensor(0.0044, grad_fn=<AddBackward0>)\n",
      "itration 7100 loss tensor(0.0041, grad_fn=<AddBackward0>)\n",
      "itration 7200 loss tensor(0.0038, grad_fn=<AddBackward0>)\n",
      "itration 7300 loss tensor(0.0045, grad_fn=<AddBackward0>)\n",
      "itration 7400 loss tensor(0.0038, grad_fn=<AddBackward0>)\n",
      "itration 7500 loss tensor(0.0038, grad_fn=<AddBackward0>)\n",
      "itration 7600 loss tensor(0.0043, grad_fn=<AddBackward0>)\n",
      "itration 7700 loss tensor(0.0042, grad_fn=<AddBackward0>)\n",
      "itration 7800 loss tensor(0.0037, grad_fn=<AddBackward0>)\n",
      "itration 7900 loss tensor(0.0037, grad_fn=<AddBackward0>)\n",
      "itration 8000 loss tensor(0.0034, grad_fn=<AddBackward0>)\n",
      "itration 8100 loss tensor(0.0030, grad_fn=<AddBackward0>)\n",
      "itration 8200 loss tensor(0.0035, grad_fn=<AddBackward0>)\n",
      "itration 8300 loss tensor(0.0033, grad_fn=<AddBackward0>)\n",
      "itration 8400 loss tensor(0.0031, grad_fn=<AddBackward0>)\n",
      "itration 8500 loss tensor(0.0031, grad_fn=<AddBackward0>)\n",
      "itration 8600 loss tensor(0.0030, grad_fn=<AddBackward0>)\n",
      "itration 8700 loss tensor(0.0057, grad_fn=<AddBackward0>)\n",
      "itration 8800 loss tensor(0.0029, grad_fn=<AddBackward0>)\n",
      "itration 8900 loss tensor(0.0029, grad_fn=<AddBackward0>)\n",
      "itration 9000 loss tensor(0.0040, grad_fn=<AddBackward0>)\n",
      "itration 9100 loss tensor(0.0023, grad_fn=<AddBackward0>)\n",
      "itration 9200 loss tensor(0.0036, grad_fn=<AddBackward0>)\n",
      "itration 9300 loss tensor(0.0022, grad_fn=<AddBackward0>)\n",
      "itration 9400 loss tensor(0.0032, grad_fn=<AddBackward0>)\n",
      "itration 9500 loss tensor(0.0020, grad_fn=<AddBackward0>)\n",
      "itration 9600 loss tensor(0.0030, grad_fn=<AddBackward0>)\n",
      "itration 9700 loss tensor(0.0063, grad_fn=<AddBackward0>)\n",
      "itration 9800 loss tensor(0.0026, grad_fn=<AddBackward0>)\n",
      "itration 9900 loss tensor(0.0022, grad_fn=<AddBackward0>)\n"
     ]
    }
   ],
   "source": [
    "model = PINN()\n",
    "num_iterations = 10000\n",
    "num_points = 1000\n",
    "train_PINN(model,num_iterations,num_points)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "da8f8045",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "with torch.no_grad():\n",
    "    x_vals = torch.linspace(0,1,100)\n",
    "    y_vals = torch.linspace(0,1,100)\n",
    "    X, Y = torch.meshgrid(x_vals,y_vals)\n",
    "    t_val = torch.ones_like(X) * 0 # spacify the time\n",
    "    \n",
    "    input_data = torch.stack([X.flatten(),Y.flatten(),t_val.flatten()], dim=1)\n",
    "    solution = model(input_data).reshape(X.shape,Y.shape)\n",
    "    \n",
    "    plt.figure(figsize=(8,6))\n",
    "    sns.heatmap(solution, cmap=\"jet\")\n",
    "    plt.title(\"2D Heat Equation Solution\")\n",
    "    plt.xlabel(\"X\")\n",
    "    plt.ylabel(\"y\")\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "6c6239f6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "with torch.no_grad():\n",
    "    x_vals = torch.linspace(0,1,100)\n",
    "    y_vals = torch.linspace(0,1,100)\n",
    "    X, Y = torch.meshgrid(x_vals,y_vals)\n",
    "    t_val = torch.ones_like(X) * 1 # spacify the time\n",
    "    \n",
    "    input_data = torch.stack([X.flatten(),Y.flatten(),t_val.flatten()], dim=1)\n",
    "    solution = model(input_data).reshape(X.shape,Y.shape)\n",
    "    \n",
    "    plt.figure(figsize=(8,6))\n",
    "    sns.heatmap(solution, cmap=\"jet\")\n",
    "    plt.title(\"2D Heat Equation Solution\")\n",
    "    plt.xlabel(\"X\")\n",
    "    plt.ylabel(\"y\")\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "692ef83c",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}