{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_data = torch.tensor([[1],[2],[3],[4],[5],[6],[7],[8]], dtype = torch.float)\n",
    "y_data = torch.tensor([[0],[0],[0],[0],[1],[1],[1],[1]], dtype = torch.float)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch.nn.functional as F"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "class LogisticRegression(torch.nn.Module):\n",
    "    def __init__(self):\n",
    "        super(LogisticRegression,self).__init__()\n",
    "        self.linear = torch.nn.Linear(1,1)\n",
    "        #self.sigmoid = torch.nn.Sigmoid() #another way to use sigmoid\n",
    "    def forward(self,x):\n",
    "        l1 = self.linear(x)\n",
    "        #o1 = self.sigmoid(l1) #another way to use sigmoid\n",
    "        return F.sigmoid(l1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "optimizer = torch.optim.RMSprop(model.parameters(), lr = 0.01)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "criterion = torch.nn.BCELoss()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "epoch_list = []\n",
    "loss_list = []\n",
    "for epoch in range(1000):\n",
    "    y_pred = model(x_data)\n",
    "    loss = criterion(y_pred, y_data)\n",
    "    loss.backward()\n",
    "    epoch_list.append(epoch)\n",
    "    loss_list.append(loss.item())\n",
    "    optimizer.step()\n",
    "    optimizer.zero_grad()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x120408b38>]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x11d0eb860>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(epoch_list,loss_list)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 1]], dtype=torch.uint8)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model(torch.tensor([[5]], dtype = torch.float)) >0.5"
   ]
  }
 ],
 "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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}