{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import numpy as np\n",
    "import torch\n",
    "torch.set_printoptions(edgeitems=2, linewidth=75)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "t_c = torch.tensor([0.5, 14.0, 15.0, 28.0, 11.0,\n",
    "                    8.0, 3.0, -4.0, 6.0, 13.0, 21.0])\n",
    "t_u = torch.tensor([35.7, 55.9, 58.2, 81.9, 56.3, 48.9,\n",
    "                    33.9, 21.8, 48.4, 60.4, 68.4])\n",
    "t_un = 0.1 * t_u"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def model(t_u, w, b):\n",
    "    return w * t_u + b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def loss_fn(t_p, t_c):\n",
    "    squared_diffs = (t_p - t_c)**2\n",
    "    return squared_diffs.mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['ASGD',\n",
       " 'Adadelta',\n",
       " 'Adagrad',\n",
       " 'Adam',\n",
       " 'AdamW',\n",
       " 'Adamax',\n",
       " 'LBFGS',\n",
       " 'Optimizer',\n",
       " 'RMSprop',\n",
       " 'Rprop',\n",
       " 'SGD',\n",
       " 'SparseAdam',\n",
       " '__builtins__',\n",
       " '__cached__',\n",
       " '__doc__',\n",
       " '__file__',\n",
       " '__loader__',\n",
       " '__name__',\n",
       " '__package__',\n",
       " '__path__',\n",
       " '__spec__',\n",
       " 'lr_scheduler']"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import torch.optim as optim\n",
    "\n",
    "dir(optim)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "params = torch.tensor([1.0, 0.0], requires_grad=True)\n",
    "learning_rate = 1e-5\n",
    "optimizer = optim.SGD([params], lr=learning_rate)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([ 9.5483e-01, -8.2600e-04], requires_grad=True)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "t_p = model(t_u, *params)\n",
    "loss = loss_fn(t_p, t_c)\n",
    "loss.backward()\n",
    "\n",
    "optimizer.step()\n",
    "\n",
    "params"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([1.7761, 0.1064], requires_grad=True)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "params = torch.tensor([1.0, 0.0], requires_grad=True)\n",
    "learning_rate = 1e-2\n",
    "optimizer = optim.SGD([params], lr=learning_rate)\n",
    "\n",
    "t_p = model(t_un, *params)\n",
    "loss = loss_fn(t_p, t_c)\n",
    "\n",
    "optimizer.zero_grad() # <1>\n",
    "loss.backward()\n",
    "optimizer.step()\n",
    "\n",
    "params"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "def training_loop(n_epochs, optimizer, params, t_u, t_c):\n",
    "    for epoch in range(1, n_epochs + 1):\n",
    "        t_p = model(t_u, *params) \n",
    "        loss = loss_fn(t_p, t_c)\n",
    "        \n",
    "        optimizer.zero_grad()\n",
    "        loss.backward()\n",
    "        optimizer.step()\n",
    "\n",
    "        if epoch % 500 == 0:\n",
    "            print('Epoch %d, Loss %f' % (epoch, float(loss)))\n",
    "            \n",
    "    return params"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 500, Loss 7.860118\n",
      "Epoch 1000, Loss 3.828538\n",
      "Epoch 1500, Loss 3.092191\n",
      "Epoch 2000, Loss 2.957697\n",
      "Epoch 2500, Loss 2.933134\n",
      "Epoch 3000, Loss 2.928648\n",
      "Epoch 3500, Loss 2.927830\n",
      "Epoch 4000, Loss 2.927680\n",
      "Epoch 4500, Loss 2.927651\n",
      "Epoch 5000, Loss 2.927648\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "tensor([  5.3671, -17.3012], requires_grad=True)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "params = torch.tensor([1.0, 0.0], requires_grad=True)\n",
    "learning_rate = 1e-2\n",
    "optimizer = optim.SGD([params], lr=learning_rate) # <1>\n",
    "\n",
    "training_loop(\n",
    "    n_epochs = 5000, \n",
    "    optimizer = optimizer,\n",
    "    params = params, # <1> \n",
    "    t_u = t_un,\n",
    "    t_c = t_c)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 500, Loss 7.612903\n",
      "Epoch 1000, Loss 3.086700\n",
      "Epoch 1500, Loss 2.928578\n",
      "Epoch 2000, Loss 2.927646\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "tensor([  0.5367, -17.3021], requires_grad=True)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "params = torch.tensor([1.0, 0.0], requires_grad=True)\n",
    "learning_rate = 1e-1\n",
    "optimizer = optim.Adam([params], lr=learning_rate) # <1>\n",
    "\n",
    "training_loop(\n",
    "    n_epochs = 2000, \n",
    "    optimizer = optimizer,\n",
    "    params = params,\n",
    "    t_u = t_u, # <2> \n",
    "    t_c = t_c)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(tensor([9, 6, 5, 8, 4, 7, 0, 1, 3]), tensor([ 2, 10]))"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "n_samples = t_u.shape[0]\n",
    "n_val = int(0.2 * n_samples)\n",
    "\n",
    "shuffled_indices = torch.randperm(n_samples)\n",
    "\n",
    "train_indices = shuffled_indices[:-n_val]\n",
    "val_indices = shuffled_indices[-n_val:]\n",
    "\n",
    "train_indices, val_indices  # <1>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_t_u = t_u[train_indices]\n",
    "train_t_c = t_c[train_indices]\n",
    "\n",
    "val_t_u = t_u[val_indices]\n",
    "val_t_c = t_c[val_indices]\n",
    "\n",
    "train_t_un = 0.1 * train_t_u\n",
    "val_t_un = 0.1 * val_t_u"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "def training_loop(n_epochs, optimizer, params, train_t_u, val_t_u,\n",
    "                  train_t_c, val_t_c):\n",
    "    for epoch in range(1, n_epochs + 1):\n",
    "        train_t_p = model(train_t_u, *params) # <1>\n",
    "        train_loss = loss_fn(train_t_p, train_t_c)\n",
    "                             \n",
    "        val_t_p = model(val_t_u, *params) # <1>\n",
    "        val_loss = loss_fn(val_t_p, val_t_c)\n",
    "        \n",
    "        optimizer.zero_grad()\n",
    "        train_loss.backward() # <2>\n",
    "        optimizer.step()\n",
    "\n",
    "        if epoch <= 3 or epoch % 500 == 0:\n",
    "            print(f\"Epoch {epoch}, Training loss {train_loss.item():.4f},\"\n",
    "                  f\" Validation loss {val_loss.item():.4f}\")\n",
    "            \n",
    "    return params"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1, Training loss 66.5811, Validation loss 142.3890\n",
      "Epoch 2, Training loss 38.8626, Validation loss 64.0434\n",
      "Epoch 3, Training loss 33.3475, Validation loss 39.4590\n",
      "Epoch 500, Training loss 7.1454, Validation loss 9.1252\n",
      "Epoch 1000, Training loss 3.5940, Validation loss 5.3110\n",
      "Epoch 1500, Training loss 3.0942, Validation loss 4.1611\n",
      "Epoch 2000, Training loss 3.0238, Validation loss 3.7693\n",
      "Epoch 2500, Training loss 3.0139, Validation loss 3.6279\n",
      "Epoch 3000, Training loss 3.0125, Validation loss 3.5756\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "tensor([  5.1964, -16.7512], requires_grad=True)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "params = torch.tensor([1.0, 0.0], requires_grad=True)\n",
    "learning_rate = 1e-2\n",
    "optimizer = optim.SGD([params], lr=learning_rate)\n",
    "\n",
    "training_loop(\n",
    "    n_epochs = 3000, \n",
    "    optimizer = optimizer,\n",
    "    params = params,\n",
    "    train_t_u = train_t_un, # <1> \n",
    "    val_t_u = val_t_un, # <1> \n",
    "    train_t_c = train_t_c,\n",
    "    val_t_c = val_t_c)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "def training_loop(n_epochs, optimizer, params, train_t_u, val_t_u,\n",
    "                  train_t_c, val_t_c):\n",
    "    for epoch in range(1, n_epochs + 1):\n",
    "        train_t_p = model(train_t_u, *params)\n",
    "        train_loss = loss_fn(train_t_p, train_t_c)\n",
    "\n",
    "        with torch.no_grad(): # <1>\n",
    "            val_t_p = model(val_t_u, *params)\n",
    "            val_loss = loss_fn(val_t_p, val_t_c)\n",
    "            assert val_loss.requires_grad == False # <2>\n",
    "            \n",
    "        optimizer.zero_grad()\n",
    "        train_loss.backward()\n",
    "        optimizer.step()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "def calc_forward(t_u, t_c, is_train):\n",
    "    with torch.set_grad_enabled(is_train):\n",
    "        t_p = model(t_u, *params)\n",
    "        loss = loss_fn(t_p, t_c)\n",
    "    return loss"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}