{
 "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)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "t_c = torch.tensor([0.5, 14.0, 15.0, 28.0, 11.0, 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, 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",
       " '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 7.860116\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 2.927679\n",
      "Epoch 4500, Loss 2.927652\n",
      "Epoch 5000, Loss 2.927647\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 7.612901\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([ 8,  0,  3,  6,  4,  1,  2,  5, 10]), tensor([9, 7]))"
      ]
     },
     "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": [
    "t_u_train = t_u[train_indices]\n",
    "t_c_train = t_c[train_indices]\n",
    "\n",
    "t_u_val = t_u[val_indices]\n",
    "t_c_val = t_c[val_indices]\n",
    "\n",
    "t_un_train = 0.1 * t_u_train\n",
    "t_un_val = 0.1 * t_u_val"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "def training_loop(n_epochs, optimizer, params, t_u_train, t_u_val, t_c_train, t_c_val):\n",
    "    for epoch in range(1, n_epochs + 1):\n",
    "        t_p_train = model(t_un_train, *params) # <1>\n",
    "        loss_train = loss_fn(t_p_train, t_c_train)\n",
    "\n",
    "        t_p_val = model(t_un_val, *params) # <1>\n",
    "        loss_val = loss_fn(t_p_val, t_c_val)\n",
    "        \n",
    "        optimizer.zero_grad()\n",
    "        loss_train.backward() # <2>\n",
    "        optimizer.step()\n",
    "\n",
    "        if epoch <= 3 or epoch % 500 == 0:\n",
    "            print('Epoch {}, Training loss {}, Validation loss {}'.format(\n",
    "                epoch, float(loss_train), float(loss_val)))\n",
    "            \n",
    "    return params"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1, Training loss 88.59708404541016, Validation loss 43.31699752807617\n",
      "Epoch 2, Training loss 34.42190933227539, Validation loss 35.03486633300781\n",
      "Epoch 3, Training loss 27.57990264892578, Validation loss 40.214229583740234\n",
      "Epoch 500, Training loss 9.516923904418945, Validation loss 9.02982234954834\n",
      "Epoch 1000, Training loss 4.543173789978027, Validation loss 2.596876621246338\n",
      "Epoch 1500, Training loss 3.1108808517456055, Validation loss 2.9066450595855713\n",
      "Epoch 2000, Training loss 2.6984243392944336, Validation loss 4.1561737060546875\n",
      "Epoch 2500, Training loss 2.579646348953247, Validation loss 5.138668537139893\n",
      "Epoch 3000, Training loss 2.5454416275024414, Validation loss 5.755766868591309\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "tensor([  5.6473, -18.7334], 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",
    "    t_u_train = t_un_train, # <1> \n",
    "    t_u_val = t_un_val, # <1> \n",
    "    t_c_train = t_c_train,\n",
    "    t_c_val = t_c_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "def training_loop(n_epochs, optimizer, params, t_u_train, t_u_val, t_c_train, t_c_val):\n",
    "    for epoch in range(1, n_epochs + 1):\n",
    "        t_p_train = model(t_un_train, *params)\n",
    "        loss_train = loss_fn(t_p_train, t_c_train)\n",
    "\n",
    "        with torch.no_grad(): # <1>\n",
    "            t_p_val = model(t_un_val, *params)\n",
    "            loss_val = loss_fn(t_p_val, t_c_val)\n",
    "            assert loss_val.requires_grad == False # <2>\n",
    "            \n",
    "        optimizer.zero_grad()\n",
    "        loss_train.backward()\n",
    "        optimizer.step()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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": "3.6.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}