{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"
\n",
" An introduction to Deep Learning with Pytorch
\n",
"
\n",
" Yifei Huang\n",
"
\n",
" MAFS6010U\n",
"
\n",
" HKUST\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prerequires "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"- Materials available on Piazza\n",
" \n",
"- Require a Python distribution with scientific packages (NumPy, SciPy, Scikit-Learn, Pandas, Pytorch)\n",
"\n",
"- One can refer to this Link to install Pytorch\n",
"\n",
"- One can refer to this Link to learn basic operation in Pytorch"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Outline\n",
"\n",
"* Preprocess data with Pytorch Dataloader\n",
"* RNN and CNN\n",
"* Generative Adversarial Network\n",
"* Reinforcement Learning"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Load some packages"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import torch\n",
"from torch import nn, optim\n",
"from torch.utils.data import DataLoader, Dataset\n",
"import torch.nn.functional as F\n",
"\n",
"import os\n",
"import argparse\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"os.environ[\"CUDA_VISIBLE_DEVICES\"] = '1' # indecate which gpu you want to use\n",
"\n",
"try:\n",
" from mpl_finance import candlestick_ohlc\n",
"except ImportError:\n",
" ! pip install mpl_finance\n",
" from mpl_finance import candlestick_ohlc\n",
" \n",
"import matplotlib.pyplot as plt\n",
"import matplotlib.dates as mdates\n",
"%matplotlib inline\n",
"plt.style.use('ggplot')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Loading external data with pandas"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"data = pd.read_csv('./okex_future_BTC_USD_this_week_1H.csv',\n",
" parse_dates=['candle_begin_time'])"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" candle_begin_time | \n",
" open | \n",
" high | \n",
" low | \n",
" close | \n",
" volume | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 2018-05-15 00:00:00 | \n",
" 8674.33 | \n",
" 8761.76 | \n",
" 8663.17 | \n",
" 8696.66 | \n",
" 172152.0 | \n",
"
\n",
" \n",
" | 1 | \n",
" 2018-05-15 01:00:00 | \n",
" 8694.66 | \n",
" 8728.17 | \n",
" 8662.17 | \n",
" 8701.85 | \n",
" 122668.0 | \n",
"
\n",
" \n",
" | 2 | \n",
" 2018-05-15 02:00:00 | \n",
" 8699.98 | \n",
" 8741.04 | \n",
" 8642.36 | \n",
" 8673.34 | \n",
" 181228.0 | \n",
"
\n",
" \n",
" | 3 | \n",
" 2018-05-15 03:00:00 | \n",
" 8673.19 | \n",
" 8717.70 | \n",
" 8638.95 | \n",
" 8707.10 | \n",
" 193166.0 | \n",
"
\n",
" \n",
" | 4 | \n",
" 2018-05-15 04:00:00 | \n",
" 8710.92 | \n",
" 8737.36 | \n",
" 8684.20 | \n",
" 8699.16 | \n",
" 155912.0 | \n",
"
\n",
" \n",
"
\n",
"