ium_478855/notebooks/05_BibliotekiML.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "from tqdm import tqdm\n",
    "import matplotlib\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\PROGRAMY\\Anaconda3\\envs\\ium\\lib\\site-packages\\ipykernel_launcher.py:2: MatplotlibDeprecationWarning: Support for setting an rcParam that expects a str value to a non-str value is deprecated since 3.5 and support will be removed two minor releases later.\n",
      "  \n"
     ]
    }
   ],
   "source": [
    "matplotlib.rc('text', usetex=True)\n",
    "matplotlib.rcParams['text.latex.preamble']=[r\"\\usepackage{amsmath}\"]\n",
    "sns.set_style(\"darkgrid\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_dataset = pd.read_csv('../train_dataset.csv')\n",
    "test_dataset = pd.read_csv('../test_dataset.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train = train_dataset.drop(columns=['No-show']).to_numpy()\n",
    "X_test = test_dataset.drop(columns=['No-show']).to_numpy()\n",
    "y_train = train_dataset['No-show'].to_numpy()\n",
    "y_test = test_dataset['No-show'].to_numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "class LogisticRegression(torch.nn.Module):\n",
    "    def __init__(self, input_dim, output_dim):\n",
    "        super(LogisticRegression, self).__init__()\n",
    "        self.linear = torch.nn.Linear(input_dim, output_dim)     \n",
    "    def forward(self, x):\n",
    "        outputs = torch.sigmoid(self.linear(x))\n",
    "        return outputs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "epochs = 50_000\n",
    "input_dim = 9\n",
    "output_dim = 1\n",
    "learning_rate = 0.01"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = LogisticRegression(input_dim, output_dim)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "criterion = torch.nn.BCELoss()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test = torch.Tensor(X_train),torch.Tensor(X_test)\n",
    "y_train, y_test = torch.Tensor(y_train),torch.Tensor(y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Training Epochs: 100%|██████████| 50000/50000 [02:01<00:00, 411.29it/s]\n"
     ]
    }
   ],
   "source": [
    "losses = []\n",
    "losses_test = []\n",
    "Iterations = []\n",
    "iter = 0\n",
    "for epoch in tqdm(range(int(epochs)), desc='Training Epochs'):\n",
    "    x = X_train\n",
    "    labels = y_train\n",
    "    optimizer.zero_grad() # Setting our stored gradients equal to zero\n",
    "    outputs = model(X_train)\n",
    "    loss = criterion(torch.squeeze(outputs), labels) \n",
    "    \n",
    "    loss.backward() # Computes the gradient of the given tensor w.r.t. the weights/bias\n",
    "    \n",
    "    optimizer.step() # Updates weights and biases with the optimizer (SGD)\n",
    "    \n",
    "    iter+=1\n",
    "    if iter%10000==0:\n",
    "        with torch.no_grad():\n",
    "            # Calculating the loss and accuracy for the test dataset\n",
    "            correct_test = 0\n",
    "            total_test = 0\n",
    "            outputs_test = torch.squeeze(model(X_test))\n",
    "            loss_test = criterion(outputs_test, y_test)\n",
    "            \n",
    "            predicted_test = outputs_test.round().detach().numpy()\n",
    "            total_test += y_test.size(0)\n",
    "            correct_test += np.sum(predicted_test == y_test.detach().numpy())\n",
    "            accuracy_test = 100 * correct_test/total_test\n",
    "            losses_test.append(loss_test.item())\n",
    "            \n",
    "            # Calculating the loss and accuracy for the train dataset\n",
    "            total = 0\n",
    "            correct = 0\n",
    "            total += y_train.size(0)\n",
    "            correct += np.sum(torch.squeeze(outputs).round().detach().numpy() == y_train.detach().numpy())\n",
    "            accuracy = 100 * correct/total\n",
    "            losses.append(loss.item())\n",
    "            Iterations.append(iter)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Iteration: 50000. \n",
      "Test - Loss: 0.480914831161499. Accuracy: 79.76567447751742\n",
      "Train -  Loss: 0.48352959752082825. Accuracy: 79.37570685365301\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(f\"Iteration: {iter}. \\nTest - Loss: {loss_test.item()}. Accuracy: {accuracy_test}\")\n",
    "print(f\"Train -  Loss: {loss.item()}. Accuracy: {accuracy}\\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"logs.txt\", \"a\") as myfile:\n",
    "    myfile.write(f\"loss={loss.item()}, accuracy={accuracy}\\n\")"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "3c12dc341c1078754dffca0e61bfc548ab04f96cfe0a82a85a936b702c4881ab"
  },
  "kernelspec": {
   "display_name": "Python 3.7.11 ('ium')",
   "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": "3.7.11"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}