Linear regression (and logistic regression) in PyTorch from scratch

PytorchLinearRegression.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import torch.nn as nn\n",
    "from sklearn.datasets import load_breast_cancer\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data Preparation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "# Load data\n",
    "data = load_breast_cancer()\n",
    "X, y = data.data, data.target\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)\n",
    "\n",
    "n_samples, n_features = X.shape\n",
    "\n",
    "# Scale\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "sc = StandardScaler()\n",
    "X_train = sc.fit_transform(X_train)\n",
    "X_test = sc.transform(X_test)\n",
    "\n",
    "X_train = torch.from_numpy(X_train.astype(np.float32))\n",
    "X_test = torch.from_numpy(X_test.astype(np.float32))\n",
    "y_train = torch.from_numpy(y_train.astype(np.float32))\n",
    "y_test = torch.from_numpy(y_test.astype(np.float32))\n",
    "\n",
    "y_train = y_train.view(y_train.shape[0], 1)\n",
    "y_test = y_test.view(y_test.shape[0], 1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "epoch: 50, loss = 0.1129\n",
      "epoch: 100, loss = 0.0599\n",
      "epoch: 150, loss = 0.0566\n",
      "epoch: 200, loss = 0.0552\n",
      "accuracy = 0.9561\n"
     ]
    }
   ],
   "source": [
    "class LinearRegression(nn.Module):\n",
    "    def __init__(self, n_input_features) -> None:\n",
    "        super(LinearRegression, self).__init__()\n",
    "        self.linear = nn.Linear(n_input_features, 1)\n",
    "    def forward(self, x):\n",
    "        return self.linear(x)\n",
    "\n",
    "class LogisticRegression(nn.Module):\n",
    "    def __init__(self, n_input_features) -> None:\n",
    "        super(LogisticRegression, self).__init__()\n",
    "        self.linear = nn.Linear(n_input_features, 1)\n",
    "    def forward(self, x):\n",
    "        return torch.sigmoid(self.linear(x))\n",
    "\n",
    "model = LinearRegression(n_features)\n",
    "if torch.cuda.is_available():\n",
    "    model.cuda()\n",
    "    \n",
    "# Loss\n",
    "criterion = nn.MSELoss()\n",
    "optimizer = torch.optim.Adam(model.parameters(), lr=0.01)\n",
    "\n",
    "for epoch in range(200):\n",
    "    # Forward pass and loss\n",
    "    y_pred = model(X_train)\n",
    "    loss = criterion(y_pred, y_train)\n",
    "\n",
    "    # Backward pass\n",
    "    loss.backward()\n",
    "\n",
    "    # Update weight\n",
    "    optimizer.step()\n",
    "\n",
    "    # Zero gradients\n",
    "    optimizer.zero_grad()\n",
    "\n",
    "    if (epoch + 1) % 50 == 0:\n",
    "        print(f'epoch: {epoch+1}, loss = {loss.item():.4f}')\n",
    "\n",
    "with torch.no_grad():\n",
    "    y_pred = model(X_test)\n",
    "    y_pred_cls = y_pred.round()\n",
    "    acc = y_pred_cls.eq(y_test).sum() / float(y_test.shape[0])\n",
    "    print(f'accuracy = {acc:.4f}')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.6 64-bit",
   "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": "3.9.6"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}