{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Useful links\n",
"\n",
"- https://blog.floydhub.com/a-beginners-guide-on-recurrent-neural-networks-with-pytorch/\n",
"- http://karpathy.github.io/2015/05/21/rnn-effectiveness/\n",
"- https://stackabuse.com/time-series-prediction-using-lstm-with-pytorch-in-python/\n",
"- https://towardsdatascience.com/pytorch-basics-how-to-train-your-neural-net-intro-to-rnn-cb6ebc594677\n",
"- https://towardsdatascience.com/time-series-forecasting-with-rnns-ff22683bbbb0\n",
"- https://towardsdatascience.com/time-series-forecasting-with-recurrent-neural-networks-74674e289816\n",
"- https://towardsdatascience.com/analyzing-time-series-data-in-pandas-be3887fdd621\n",
"- http://www.wildml.com/2015/10/recurrent-neural-networks-tutorial-part-3-backpropagation-through-time-and-vanishing-gradients/\n",
"- https://colah.github.io/posts/2015-09-NN-Types-FP/\n",
"- https://pytorch.org/docs/stable/nn.html#rnn"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import requests as rq\n",
"import datetime as dt\n",
"import traceback as tb\n",
"import torch\n",
"\n",
"tnn = torch.nn\n",
"top = torch.optim\n",
"from torch.utils import data as tdt"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Download India's data"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" date | \n",
" confirmed | \n",
" deceased | \n",
" recovered | \n",
"
\n",
" \n",
" \n",
" \n",
" | 45 | \n",
" 2020-03-15 | \n",
" 10 | \n",
" 0 | \n",
" 3 | \n",
"
\n",
" \n",
"
\n",
"