Skip to content

Instantly share code, notes, and snippets.

@firmai

firmai/reinforcement-learning-example-finrl-package-semester-2.ipynb

Last active December 3, 2023 02:02
Show Gist options
  • Save firmai/ffc48e736be1caa9c0690d9a95108c39 to your computer and use it in GitHub Desktop.
Save firmai/ffc48e736be1caa9c0690d9a95108c39 to your computer and use it in GitHub Desktop.
Download ZIP
reinforcement-learning-example-finrl-package-semester-2.ipynb
Display the source blob
Display the rendered blob
Raw
reinforcement-learning-example-finrl-package-semester-2.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/firmai/ffc48e736be1caa9c0690d9a95108c39/reinforcement-learning-example-finrl-package-semester-2.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "gXaoZs2lh1hi"
},
"source": [
"# Automated stock trading using FinRL with financial data\n",
"\n",
"(Package has been updated see [FinRL Github for new installation](https://github.com/AI4Finance-Foundation/FinRL-Tutorials/blob/master/1-Introduction/Stock_Fundamental.ipynb))\n",
"\n",
"* Here we will train a deep reinforcement learning model using market data and fundamental data for the 30 publicly traded stocks on the Dow Jones.\n",
"* The goal is to maximize the value of the portfolio at the end of the training period, and we will investigate if we can outperform the benchmark.\n",
"* In this problem, the agent of the model is a robot trader, and the environment is what the agent observes in the market; stock prices, volumes, and financial ratios.\n",
"* The agent observes a current state the environment shows and chooses a trading action from the action space.\n",
"* During the training period, the agent updates its policy (like an instruction manual for trading) to achieve a better performance in the future.\n",
"* The agent's actions are defined by the combination of what stocks the agent will trade, types of trading action(buy, sell and hold), and how many shares the agent will trade.\n",
"* Then, the agent receives a reward from the environment in correspondence with the action it took.\n",
"* Here, the reward is defined by the portfolio values after taking action.\n",
"The agent acts to maximize the total rewards it will receive in the future.\n",
"\n",
"\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "lGunVt8oLCVS"
},
"source": [
"# Content"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HOzAKQ-SLGX6"
},
"source": [
"* [1. Task Discription](#0)\n",
"* [2. Install Python packages](#1)\n",
" * [2.1. Install Packages](#1.1) \n",
" * [2.2. A List of Python Packages](#1.2)\n",
" * [2.3. Import Packages](#1.3)\n",
" * [2.4. Create Folders](#1.4)\n",
"* [3. Download Data](#2)\n",
"* [4. Preprocess fundamental Data](#3) \n",
" * [4.1 Import financial data](#3.1)\n",
" * [4.2 Specify items needed to calculate financial ratios](#3.2)\n",
" * [4.3 Calculate financial ratios](#3.3)\n",
" * [4.4 Deal with NAs and infinite values](#3.4)\n",
" * [4.5 Merge stock price data and ratios into one dataframe](#3.5)\n",
" * [4.6 Calculate market valuation ratios using daily stock price data](#3.6)\n",
"* [5. Build Environment](#4) \n",
" * [5.1. Training & Trade Data Split](#4.1)\n",
" * [5.2. User-defined Environment](#4.2) \n",
" * [5.3. Initialize Environment](#4.3) \n",
"* [6. Train DRL Agents](#5) \n",
"* [7. Backtesting Performance](#6) \n",
" * [7.1. BackTestStats](#6.1)\n",
" * [7.2. BackTestPlot](#6.2) \n",
" * [7.3. Baseline Stats](#6.3) \n",
" * [7.3. Compare to Stock Market Index](#6.4) "
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "sApkDlD9LIZv"
},
"source": [
"<a id='0'></a>\n",
"# Part 1. Task Description"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HjLD2TZSLKZ-"
},
"source": [
"We train a DRL agent for stock trading. The task is modeled as a Markov Decision Process (MDP), and the objective function is maximizing (expected) cumulative return.\n",
"\n",
"We specify the state-action-reward as follows:\n",
"\n",
"* **State s**: The state space represents an agent's perception of the market environment. Like a human trader analyzes various information, here our agent passively observes many features and learn by interacting with the market environment (usually by replaying historical data).\n",
"\n",
"* **Action a**: The action space includes allowed actions that an agent can take at each state. For example, a ∈ {−1, 0, 1}, where −1, 0, 1 represent\n",
"selling, holding, and buying. When an action operates multiple shares, a ∈{−k, ..., −1, 0, 1, ..., k}, e.g.. \"Buy\n",
"10 shares of AAPL\" or \"Sell 10 shares of AAPL\" are 10 or −10, respectively\n",
"\n",
"* **Reward function r(s, a, s′)**: Reward is an incentive for an agent to learn a better policy. For example, it can be the change of the portfolio value when taking a at state s and arriving at new state s', i.e., r(s, a, s′) = v′ − v, where v′ and v represent the portfolio values at state s′ and s, respectively\n",
"\n",
"\n",
"**Market environment**: 30 consituent stocks of Dow Jones Industrial Average (DJIA) index. Accessed at the starting date of the testing period.\n",
"\n",
"\n",
"The data of the single stock that we will use for this case study is obtained from Yahoo Finance API. The data contains Open-High-Low-Close prices and volume.\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Ffsre789LY08"
},
"source": [
"<a id='1'></a>\n",
"# Part 2. Load Python Packages"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Uy5_PTmOh1hj"
},
"source": [
"<a id='1.1'></a>\n",
"## 2.1. Install all the packages through FinRL library\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "mPT0ipYE28wL",
"outputId": "0c9526e4-1cea-4b2a-bc4d-45a7046aa6c8"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting git+https://github.com/AI4Finance-Foundation/FinRL.git\n",
" Cloning https://github.com/AI4Finance-Foundation/FinRL.git to /tmp/pip-req-build-_y87ltgq\n",
" Running command git clone --filter=blob:none --quiet https://github.com/AI4Finance-Foundation/FinRL.git /tmp/pip-req-build-_y87ltgq\n",
" Resolved https://github.com/AI4Finance-Foundation/FinRL.git to commit 8a75a4bbb28f86f88ee2d4bd9a8c19cce444badb\n",
" Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
" Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
" Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting pyfolio@ git+https://github.com/quantopian/pyfolio.git#egg=pyfolio-0.9.2\n",
" Cloning https://github.com/quantopian/pyfolio.git to /tmp/pip-install-obc9ggag/pyfolio_35febe35b9a44a049a762d5fa3171d15\n",
" Running command git clone --filter=blob:none --quiet https://github.com/quantopian/pyfolio.git /tmp/pip-install-obc9ggag/pyfolio_35febe35b9a44a049a762d5fa3171d15\n",
" Resolved https://github.com/quantopian/pyfolio.git to commit 4b901f6d73aa02ceb6d04b7d83502e5c6f2e81aa\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting elegantrl@ git+https://github.com/AI4Finance-Foundation/ElegantRL.git#egg=elegantrl\n",
" Cloning https://github.com/AI4Finance-Foundation/ElegantRL.git to /tmp/pip-install-obc9ggag/elegantrl_78e7d9d6adb84c7096cd98666c97848a\n",
" Running command git clone --filter=blob:none --quiet https://github.com/AI4Finance-Foundation/ElegantRL.git /tmp/pip-install-obc9ggag/elegantrl_78e7d9d6adb84c7096cd98666c97848a\n",
" Resolved https://github.com/AI4Finance-Foundation/ElegantRL.git to commit b974a806e6235f59055c954418e54640fa549331\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: yfinance in /usr/local/lib/python3.9/dist-packages (from finrl==0.3.5) (0.2.18)\n",
"Collecting stable-baselines3<2.0.0,>=1.6.2\n",
" Downloading stable_baselines3-1.8.0-py3-none-any.whl (174 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m174.5/174.5 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: gym>=0.17 in /usr/local/lib/python3.9/dist-packages (from finrl==0.3.5) (0.25.2)\n",
"Collecting wrds>=3.1.6\n",
" Downloading wrds-3.1.6-py3-none-any.whl (12 kB)\n",
"Collecting gputil\n",
" Downloading GPUtil-1.4.0.tar.gz (5.5 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting stockstats>=0.4.0\n",
" Downloading stockstats-0.5.2-py2.py3-none-any.whl (20 kB)\n",
"Requirement already satisfied: scikit-learn>=0.21.0 in /usr/local/lib/python3.9/dist-packages (from finrl==0.3.5) (1.2.2)\n",
"Requirement already satisfied: matplotlib in /usr/local/lib/python3.9/dist-packages (from finrl==0.3.5) (3.7.1)\n",
"Collecting exchange_calendars==3.6.3\n",
" Downloading exchange_calendars-3.6.3.tar.gz (152 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m152.8/152.8 kB\u001b[0m \u001b[31m14.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: pandas>=1.1.5 in /usr/local/lib/python3.9/dist-packages (from finrl==0.3.5) (1.5.3)\n",
"Collecting ccxt>=1.66.32\n",
" Downloading ccxt-3.0.75-py2.py3-none-any.whl (3.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m48.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting lz4\n",
" Downloading lz4-4.3.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m22.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting alpaca_trade_api>=2.1.0\n",
" Downloading alpaca_trade_api-3.0.0-py3-none-any.whl (33 kB)\n",
"Collecting tensorboardX\n",
" Downloading tensorboardX-2.6-py2.py3-none-any.whl (114 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m114.5/114.5 kB\u001b[0m \u001b[31m10.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting jqdatasdk\n",
" Downloading jqdatasdk-1.8.11-py3-none-any.whl (158 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m158.2/158.2 kB\u001b[0m \u001b[31m12.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting importlib-metadata==4.13.0\n",
" Downloading importlib_metadata-4.13.0-py3-none-any.whl (23 kB)\n",
"Collecting ray[default,tune]>=2.0.0\n",
" Downloading ray-2.3.1-cp39-cp39-manylinux2014_x86_64.whl (58.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.6/58.6 MB\u001b[0m \u001b[31m10.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: numpy>=1.17.3 in /usr/local/lib/python3.9/dist-packages (from finrl==0.3.5) (1.22.4)\n",
"Collecting pyluach\n",
" Downloading pyluach-2.2.0-py3-none-any.whl (25 kB)\n",
"Requirement already satisfied: python-dateutil in /usr/local/lib/python3.9/dist-packages (from exchange_calendars==3.6.3->finrl==0.3.5) (2.8.2)\n",
"Requirement already satisfied: pytz in /usr/local/lib/python3.9/dist-packages (from exchange_calendars==3.6.3->finrl==0.3.5) (2022.7.1)\n",
"Requirement already satisfied: toolz in /usr/local/lib/python3.9/dist-packages (from exchange_calendars==3.6.3->finrl==0.3.5) (0.12.0)\n",
"Requirement already satisfied: korean_lunar_calendar in /usr/local/lib/python3.9/dist-packages (from exchange_calendars==3.6.3->finrl==0.3.5) (0.3.1)\n",
"Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.9/dist-packages (from importlib-metadata==4.13.0->finrl==0.3.5) (3.15.0)\n",
"Collecting websockets<11,>=9.0\n",
" Downloading websockets-10.4-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (106 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m106.5/106.5 kB\u001b[0m \u001b[31m9.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: requests<3,>2 in /usr/local/lib/python3.9/dist-packages (from alpaca_trade_api>=2.1.0->finrl==0.3.5) (2.27.1)\n",
"Requirement already satisfied: PyYAML==6.0 in /usr/local/lib/python3.9/dist-packages (from alpaca_trade_api>=2.1.0->finrl==0.3.5) (6.0)\n",
"Collecting msgpack==1.0.3\n",
" Downloading msgpack-1.0.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (322 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m322.2/322.2 kB\u001b[0m \u001b[31m26.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting aiohttp==3.8.1\n",
" Downloading aiohttp-3.8.1-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl (1.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m58.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting deprecation==2.1.0\n",
" Downloading deprecation-2.1.0-py2.py3-none-any.whl (11 kB)\n",
"Requirement already satisfied: urllib3<2,>1.24 in /usr/local/lib/python3.9/dist-packages (from alpaca_trade_api>=2.1.0->finrl==0.3.5) (1.26.15)\n",
"Requirement already satisfied: websocket-client<2,>=0.56.0 in /usr/local/lib/python3.9/dist-packages (from alpaca_trade_api>=2.1.0->finrl==0.3.5) (1.5.1)\n",
"Collecting multidict<7.0,>=4.5\n",
" Downloading multidict-6.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (114 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m114.2/114.2 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting aiosignal>=1.1.2\n",
" Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n",
"Collecting async-timeout<5.0,>=4.0.0a3\n",
" Downloading async_timeout-4.0.2-py3-none-any.whl (5.8 kB)\n",
"Requirement already satisfied: charset-normalizer<3.0,>=2.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp==3.8.1->alpaca_trade_api>=2.1.0->finrl==0.3.5) (2.0.12)\n",
"Collecting frozenlist>=1.1.1\n",
" Downloading frozenlist-1.3.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (158 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m158.8/158.8 kB\u001b[0m \u001b[31m10.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting yarl<2.0,>=1.0\n",
" Downloading yarl-1.9.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (269 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m269.3/269.3 kB\u001b[0m \u001b[31m19.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp==3.8.1->alpaca_trade_api>=2.1.0->finrl==0.3.5) (23.1.0)\n",
"Requirement already satisfied: packaging in /usr/local/lib/python3.9/dist-packages (from deprecation==2.1.0->alpaca_trade_api>=2.1.0->finrl==0.3.5) (23.1)\n",
"Requirement already satisfied: certifi>=2018.1.18 in /usr/local/lib/python3.9/dist-packages (from ccxt>=1.66.32->finrl==0.3.5) (2022.12.7)\n",
"Requirement already satisfied: cryptography>=2.6.1 in /usr/local/lib/python3.9/dist-packages (from ccxt>=1.66.32->finrl==0.3.5) (40.0.2)\n",
"Collecting aiodns>=1.1.1\n",
" Downloading aiodns-3.0.0-py3-none-any.whl (5.0 kB)\n",
"Requirement already satisfied: setuptools>=60.9.0 in /usr/local/lib/python3.9/dist-packages (from ccxt>=1.66.32->finrl==0.3.5) (67.7.1)\n",
"Requirement already satisfied: cloudpickle>=1.2.0 in /usr/local/lib/python3.9/dist-packages (from gym>=0.17->finrl==0.3.5) (2.2.1)\n",
"Requirement already satisfied: gym-notices>=0.0.4 in /usr/local/lib/python3.9/dist-packages (from gym>=0.17->finrl==0.3.5) (0.0.8)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from ray[default,tune]>=2.0.0->finrl==0.3.5) (3.11.0)\n",
"Requirement already satisfied: jsonschema in /usr/local/lib/python3.9/dist-packages (from ray[default,tune]>=2.0.0->finrl==0.3.5) (4.3.3)\n",
"Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.9/dist-packages (from ray[default,tune]>=2.0.0->finrl==0.3.5) (8.1.3)\n",
"Collecting virtualenv>=20.0.24\n",
" Downloading virtualenv-20.22.0-py3-none-any.whl (3.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.2/3.2 MB\u001b[0m \u001b[31m51.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: protobuf!=3.19.5,>=3.15.3 in /usr/local/lib/python3.9/dist-packages (from ray[default,tune]>=2.0.0->finrl==0.3.5) (3.20.3)\n",
"Requirement already satisfied: grpcio>=1.32.0 in /usr/local/lib/python3.9/dist-packages (from ray[default,tune]>=2.0.0->finrl==0.3.5) (1.53.0)\n",
"Requirement already satisfied: tabulate in /usr/local/lib/python3.9/dist-packages (from ray[default,tune]>=2.0.0->finrl==0.3.5) (0.8.10)\n",
"Collecting aiohttp-cors\n",
" Downloading aiohttp_cors-0.7.0-py3-none-any.whl (27 kB)\n",
"Collecting gpustat>=1.0.0\n",
" Downloading gpustat-1.1.tar.gz (97 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m97.9/97.9 kB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
" Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
" Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: pydantic in /usr/local/lib/python3.9/dist-packages (from ray[default,tune]>=2.0.0->finrl==0.3.5) (1.10.7)\n",
"Collecting opencensus\n",
" Downloading opencensus-0.11.2-py2.py3-none-any.whl (128 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m128.2/128.2 kB\u001b[0m \u001b[31m10.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting py-spy>=0.2.0\n",
" Downloading py_spy-0.3.14-py2.py3-none-manylinux_2_5_x86_64.manylinux1_x86_64.whl (3.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m44.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting colorful\n",
" Downloading colorful-0.5.5-py2.py3-none-any.whl (201 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m201.4/201.4 kB\u001b[0m \u001b[31m17.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: prometheus-client>=0.7.1 in /usr/local/lib/python3.9/dist-packages (from ray[default,tune]>=2.0.0->finrl==0.3.5) (0.16.0)\n",
"Requirement already satisfied: smart-open in /usr/local/lib/python3.9/dist-packages (from ray[default,tune]>=2.0.0->finrl==0.3.5) (6.3.0)\n",
"Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.9/dist-packages (from scikit-learn>=0.21.0->finrl==0.3.5) (1.2.0)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.9/dist-packages (from scikit-learn>=0.21.0->finrl==0.3.5) (3.1.0)\n",
"Requirement already satisfied: scipy>=1.3.2 in /usr/local/lib/python3.9/dist-packages (from scikit-learn>=0.21.0->finrl==0.3.5) (1.10.1)\n",
"Requirement already satisfied: torch>=1.11 in /usr/local/lib/python3.9/dist-packages (from stable-baselines3<2.0.0,>=1.6.2->finrl==0.3.5) (2.0.0+cu118)\n",
"Collecting gym>=0.17\n",
"\u001b[33m WARNING: Retrying (Retry(total=4, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ProtocolError('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))': /packages/4b/48/920cea66177b865663fde5a9390a59de0ef3b642ad98106ac1d8717d7005/gym-0.21.0.tar.gz\u001b[0m\u001b[33m\n",
"\u001b[0m Downloading gym-0.21.0.tar.gz (1.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.5/1.5 MB\u001b[0m \u001b[31m18.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h \u001b[1;31merror\u001b[0m: \u001b[1msubprocess-exited-with-error\u001b[0m\n",
" \n",
" \u001b[31m×\u001b[0m \u001b[32mpython setup.py egg_info\u001b[0m did not run successfully.\n",
" \u001b[31m│\u001b[0m exit code: \u001b[1;36m1\u001b[0m\n",
" \u001b[31m╰─>\u001b[0m See above for output.\n",
" \n",
" \u001b[1;35mnote\u001b[0m: This error originates from a subprocess, and is likely not a problem with pip.\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25herror\n",
"\u001b[1;31merror\u001b[0m: \u001b[1mmetadata-generation-failed\u001b[0m\n",
"\n",
"\u001b[31m×\u001b[0m Encountered error while generating package metadata.\n",
"\u001b[31m╰─>\u001b[0m See above for output.\n",
"\n",
"\u001b[1;35mnote\u001b[0m: This is an issue with the package mentioned above, not pip.\n",
"\u001b[1;36mhint\u001b[0m: See above for details.\n"
]
}
],
"source": [
"## install finrl library\n",
"!pip install git+https://github.com/AI4Finance-Foundation/FinRL.git"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "osBHhVysOEzi"
},
"source": [
"\n",
"<a id='1.2'></a>\n",
"## 2.2. A List of Python Packages\n",
"* Yahoo Finance API\n",
"* pandas\n",
"* numpy\n",
"* matplotlib\n",
"* stockstats\n",
"* OpenAI gym\n",
"* stable-baselines\n",
"* pyfolio"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "nGv01K8Sh1hn"
},
"source": [
"<a id='1.3'></a>\n",
"## 2.3. Import Packages"
]
},
{
"cell_type": "code",
"source": [
"!pip install wrds"
],
"metadata": {
"id": "lAXVcRIqwzay",
"outputId": "5657f514-f57f-4212-a140-007d5245eb13",
"colab": {
"base_uri": "https://localhost:8080/"
}
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Requirement already satisfied: wrds in /usr/local/lib/python3.9/dist-packages (3.1.6)\n",
"Requirement already satisfied: sqlalchemy<2 in /usr/local/lib/python3.9/dist-packages (from wrds) (1.4.47)\n",
"Requirement already satisfied: scipy in /usr/local/lib/python3.9/dist-packages (from wrds) (1.10.1)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.9/dist-packages (from wrds) (1.5.3)\n",
"Requirement already satisfied: psycopg2-binary in /usr/local/lib/python3.9/dist-packages (from wrds) (2.9.6)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.9/dist-packages (from wrds) (1.22.4)\n",
"Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.9/dist-packages (from sqlalchemy<2->wrds) (2.0.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.9/dist-packages (from pandas->wrds) (2022.7.1)\n",
"Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.9/dist-packages (from pandas->wrds) (2.8.2)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.9/dist-packages (from python-dateutil>=2.8.1->pandas->wrds) (1.16.0)\n"
]
}
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "lPqeTTwoh1hn"
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib\n",
"import matplotlib.pyplot as plt\n",
"# matplotlib.use('Agg')\n",
"import datetime\n",
"\n",
"%matplotlib inline\n",
"from finrl import config\n",
"from finrl import config_tickers\n",
"from finrl.meta.preprocessor.yahoodownloader import YahooDownloader\n",
"from finrl.meta.preprocessor.preprocessors import FeatureEngineer, data_split\n",
"from finrl.meta.env_stock_trading.env_stocktrading import StockTradingEnv\n",
"from finrl.agents.stablebaselines3.models import DRLAgent\n",
"from finrl.plot import backtest_stats, backtest_plot, get_daily_return, get_baseline\n",
"from finrl.main import check_and_make_directories\n",
"from pprint import pprint\n",
"from stable_baselines3.common.logger import configure\n",
"import sys\n",
"sys.path.append(\"../FinRL\")\n",
"\n",
"import itertools\n",
"\n",
"from finrl.config import (\n",
" DATA_SAVE_DIR,\n",
" TRAINED_MODEL_DIR,\n",
" TENSORBOARD_LOG_DIR,\n",
" RESULTS_DIR,\n",
" INDICATORS,\n",
" TRAIN_START_DATE,\n",
" TRAIN_END_DATE,\n",
" TEST_START_DATE,\n",
" TEST_END_DATE,\n",
" TRADE_START_DATE,\n",
" TRADE_END_DATE,\n",
")\n",
"\n",
"from finrl.config_tickers import DOW_30_TICKER"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "T2owTj985RW4"
},
"source": [
"<a id='1.4'></a>\n",
"## 2.4. Create Folders"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "w9A8CN5R5PuZ"
},
"outputs": [],
"source": [
"check_and_make_directories([DATA_SAVE_DIR, TRAINED_MODEL_DIR, TENSORBOARD_LOG_DIR, RESULTS_DIR])"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "A289rQWMh1hq"
},
"source": [
"<a id='2'></a>\n",
"# Part 3. Download Stock Data from Yahoo Finance\n",
"Yahoo Finance provides stock data, financial news, financial reports, etc. Yahoo Finance is free.\n",
"* FinRL uses a class **YahooDownloader** in FinRL-Meta to fetch data via Yahoo Finance API\n",
"* Call Limit: Using the Public API (without authentication), you are limited to 2,000 requests per hour per IP (or up to a total of 48,000 requests a day).\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "NPeQ7iS-LoMm"
},
"source": [
"\n",
"\n",
"-----\n",
"class YahooDownloader:\n",
" Retrieving daily stock data from Yahoo Finance API\n",
"\n",
" Attributes\n",
" ----------\n",
" start_date : str\n",
" start date of the data (modified from config.py)\n",
" end_date : str\n",
" end date of the data (modified from config.py)\n",
" ticker_list : list\n",
" a list of stock tickers (modified from config.py)\n",
"\n",
" Methods\n",
" -------\n",
" fetch_data()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "JzqRRTOX6aFu",
"outputId": "b88b31ef-ec6e-408b-c32f-7c2ced8ed9b1"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"['AXP', 'AMGN', 'AAPL', 'BA', 'CAT', 'CSCO', 'CVX', 'GS', 'HD', 'HON', 'IBM', 'INTC', 'JNJ', 'KO', 'JPM', 'MCD', 'MMM', 'MRK', 'MSFT', 'NKE', 'PG', 'TRV', 'UNH', 'CRM', 'VZ', 'V', 'WBA', 'WMT', 'DIS', 'DOW']\n"
]
}
],
"source": [
"print(DOW_30_TICKER)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "yCKm4om-s9kE",
"outputId": "2502be3f-3a04-4c1e-e04a-ad19501c2179"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"[*********************100%***********************] 1 of 1 completed\n",
"Shape of DataFrame: (88061, 8)\n"
]
}
],
"source": [
"TRAIN_START_DATE = '2009-01-01'\n",
"TRAIN_END_DATE = '2019-01-01'\n",
"TEST_START_DATE = '2019-01-01'\n",
"TEST_END_DATE = '2021-01-01'\n",
"\n",
"df = YahooDownloader(start_date = TRAIN_START_DATE,\n",
" end_date = TEST_END_DATE,\n",
" ticker_list = DOW_30_TICKER).fetch_data()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "CV3HrZHLh1hy",
"outputId": "f490cbf0-47fa-4499-9966-019452089018"
},
"outputs": [
{
"data": {
"text/plain": [
"(88090, 8)"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"id": "aBKF7sfV-Pi4",
"outputId": "c0914a2f-469f-4d7f-f93c-48d1d1cf4e51"
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>date</th>\n",
" <th>open</th>\n",
" <th>high</th>\n",
" <th>low</th>\n",
" <th>close</th>\n",
" <th>volume</th>\n",
" <th>tic</th>\n",
" <th>day</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2008-12-31</td>\n",
" <td>3.070357</td>\n",
" <td>3.133571</td>\n",
" <td>3.047857</td>\n",
" <td>2.602662</td>\n",
" <td>607541200</td>\n",
" <td>AAPL</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2008-12-31</td>\n",
" <td>57.110001</td>\n",
" <td>58.220001</td>\n",
" <td>57.060001</td>\n",
" <td>43.587833</td>\n",
" <td>6287200</td>\n",
" <td>AMGN</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2008-12-31</td>\n",
" <td>17.969999</td>\n",
" <td>18.750000</td>\n",
" <td>17.910000</td>\n",
" <td>14.852877</td>\n",
" <td>9625600</td>\n",
" <td>AXP</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2008-12-31</td>\n",
" <td>41.590000</td>\n",
" <td>43.049999</td>\n",
" <td>41.500000</td>\n",
" <td>32.005882</td>\n",
" <td>5443100</td>\n",
" <td>BA</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2008-12-31</td>\n",
" <td>43.700001</td>\n",
" <td>45.099998</td>\n",
" <td>43.700001</td>\n",
" <td>30.416981</td>\n",
" <td>6277400</td>\n",
" <td>CAT</td>\n",
" <td>2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" date open high low close volume tic \\\n",
"0 2008-12-31 3.070357 3.133571 3.047857 2.602662 607541200 AAPL \n",
"1 2008-12-31 57.110001 58.220001 57.060001 43.587833 6287200 AMGN \n",
"2 2008-12-31 17.969999 18.750000 17.910000 14.852877 9625600 AXP \n",
"3 2008-12-31 41.590000 43.049999 41.500000 32.005882 5443100 BA \n",
"4 2008-12-31 43.700001 45.099998 43.700001 30.416981 6277400 CAT \n",
"\n",
" day \n",
"0 2 \n",
"1 2 \n",
"2 2 \n",
"3 2 \n",
"4 2 "
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "QRWscKiPXXnj"
},
"outputs": [],
"source": [
"df['date'] = pd.to_datetime(df['date'],format='%Y-%m-%d')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"id": "4hYkeaPiICHS",
"outputId": "2c0a8f66-4b04-4f5e-b1a1-3641e2317052"
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>date</th>\n",
" <th>open</th>\n",
" <th>high</th>\n",
" <th>low</th>\n",
" <th>close</th>\n",
" <th>volume</th>\n",
" <th>tic</th>\n",
" <th>day</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2008-12-31</td>\n",
" <td>3.070357</td>\n",
" <td>3.133571</td>\n",
" <td>3.047857</td>\n",
" <td>2.602662</td>\n",
" <td>607541200</td>\n",
" <td>AAPL</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2008-12-31</td>\n",
" <td>57.110001</td>\n",
" <td>58.220001</td>\n",
" <td>57.060001</td>\n",
" <td>43.587833</td>\n",
" <td>6287200</td>\n",
" <td>AMGN</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2008-12-31</td>\n",
" <td>17.969999</td>\n",
" <td>18.750000</td>\n",
" <td>17.910000</td>\n",
" <td>14.852877</td>\n",
" <td>9625600</td>\n",
" <td>AXP</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2008-12-31</td>\n",
" <td>41.590000</td>\n",
" <td>43.049999</td>\n",
" <td>41.500000</td>\n",
" <td>32.005882</td>\n",
" <td>5443100</td>\n",
" <td>BA</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2008-12-31</td>\n",
" <td>43.700001</td>\n",
" <td>45.099998</td>\n",
" <td>43.700001</td>\n",
" <td>30.416981</td>\n",
" <td>6277400</td>\n",
" <td>CAT</td>\n",
" <td>2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" date open high low close volume tic day\n",
"0 2008-12-31 3.070357 3.133571 3.047857 2.602662 607541200 AAPL 2\n",
"1 2008-12-31 57.110001 58.220001 57.060001 43.587833 6287200 AMGN 2\n",
"2 2008-12-31 17.969999 18.750000 17.910000 14.852877 9625600 AXP 2\n",
"3 2008-12-31 41.590000 43.049999 41.500000 32.005882 5443100 BA 2\n",
"4 2008-12-31 43.700001 45.099998 43.700001 30.416981 6277400 CAT 2"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.sort_values(['date','tic'],ignore_index=True).head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "uqC6c40Zh1iH"
},
"source": [
"# Part 4: Preprocess fundamental data\n",
"- Import finanical data downloaded from Compustat via WRDS(Wharton Research Data Service)\n",
"- Preprocess the dataset and calculate financial ratios\n",
"- Add those ratios to the price data preprocessed in Part 3\n",
"- Calculate price-related ratios such as P/E and P/B"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "VbXEllD2oROq"
},
"source": [
"## 4.1 Import the financial data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "PmKP-1ii3RLS",
"outputId": "006dd708-469c-43e9-f65d-f0737561a7f5"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\Administrador\\AppData\\Local\\Programs\\Python\\Python38\\lib\\site-packages\\IPython\\core\\interactiveshell.py:3417: DtypeWarning: Columns (16,25) have mixed types.Specify dtype option on import or set low_memory=False.\n",
" exec(code_obj, self.user_global_ns, self.user_ns)\n"
]
}
],
"source": [
"# Import fundamental data from my GitHub repository\n",
"url = 'https://raw.githubusercontent.com/mariko-sawada/FinRL_with_fundamental_data/main/dow_30_fundamental_wrds.csv'\n",
"\n",
"fund = pd.read_csv(url)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 236
},
"id": "Tslhs_O5pOTL",
"outputId": "eeb8d443-1a0e-4967-97c1-9c05cd3ae02f"
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>gvkey</th>\n",
" <th>datadate</th>\n",
" <th>fyearq</th>\n",
" <th>fqtr</th>\n",
" <th>fyr</th>\n",
" <th>indfmt</th>\n",
" <th>consol</th>\n",
" <th>popsrc</th>\n",
" <th>datafmt</th>\n",
" <th>tic</th>\n",
" <th>...</th>\n",
" <th>dvpsxq</th>\n",
" <th>mkvaltq</th>\n",
" <th>prccq</th>\n",
" <th>prchq</th>\n",
" <th>prclq</th>\n",
" <th>adjex</th>\n",
" <th>ggroup</th>\n",
" <th>gind</th>\n",
" <th>gsector</th>\n",
" <th>gsubind</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1447</td>\n",
" <td>19990630</td>\n",
" <td>1999</td>\n",
" <td>2</td>\n",
" <td>12</td>\n",
" <td>INDL</td>\n",
" <td>C</td>\n",
" <td>D</td>\n",
" <td>STD</td>\n",
" <td>AXP</td>\n",
" <td>...</td>\n",
" <td>0.225</td>\n",
" <td>NaN</td>\n",
" <td>130.1250</td>\n",
" <td>142.6250</td>\n",
" <td>114.5000</td>\n",
" <td>3.0</td>\n",
" <td>4020</td>\n",
" <td>402020</td>\n",
" <td>40</td>\n",
" <td>40202010</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1447</td>\n",
" <td>19990930</td>\n",
" <td>1999</td>\n",
" <td>3</td>\n",
" <td>12</td>\n",
" <td>INDL</td>\n",
" <td>C</td>\n",
" <td>D</td>\n",
" <td>STD</td>\n",
" <td>AXP</td>\n",
" <td>...</td>\n",
" <td>0.000</td>\n",
" <td>NaN</td>\n",
" <td>135.0000</td>\n",
" <td>150.6250</td>\n",
" <td>121.8750</td>\n",
" <td>3.0</td>\n",
" <td>4020</td>\n",
" <td>402020</td>\n",
" <td>40</td>\n",
" <td>40202010</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1447</td>\n",
" <td>19991231</td>\n",
" <td>1999</td>\n",
" <td>4</td>\n",
" <td>12</td>\n",
" <td>INDL</td>\n",
" <td>C</td>\n",
" <td>D</td>\n",
" <td>STD</td>\n",
" <td>AXP</td>\n",
" <td>...</td>\n",
" <td>0.225</td>\n",
" <td>NaN</td>\n",
" <td>166.2500</td>\n",
" <td>168.8750</td>\n",
" <td>130.2500</td>\n",
" <td>3.0</td>\n",
" <td>4020</td>\n",
" <td>402020</td>\n",
" <td>40</td>\n",
" <td>40202010</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1447</td>\n",
" <td>20000331</td>\n",
" <td>2000</td>\n",
" <td>1</td>\n",
" <td>12</td>\n",
" <td>INDL</td>\n",
" <td>C</td>\n",
" <td>D</td>\n",
" <td>STD</td>\n",
" <td>AXP</td>\n",
" <td>...</td>\n",
" <td>0.225</td>\n",
" <td>NaN</td>\n",
" <td>148.9375</td>\n",
" <td>169.5000</td>\n",
" <td>119.5000</td>\n",
" <td>3.0</td>\n",
" <td>4020</td>\n",
" <td>402020</td>\n",
" <td>40</td>\n",
" <td>40202010</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1447</td>\n",
" <td>20000630</td>\n",
" <td>2000</td>\n",
" <td>2</td>\n",
" <td>12</td>\n",
" <td>INDL</td>\n",
" <td>C</td>\n",
" <td>D</td>\n",
" <td>STD</td>\n",
" <td>AXP</td>\n",
" <td>...</td>\n",
" <td>0.080</td>\n",
" <td>NaN</td>\n",
" <td>52.1250</td>\n",
" <td>57.1875</td>\n",
" <td>43.9375</td>\n",
" <td>1.0</td>\n",
" <td>4020</td>\n",
" <td>402020</td>\n",
" <td>40</td>\n",
" <td>40202010</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 647 columns</p>\n",
"</div>"
],
"text/plain": [
" gvkey datadate fyearq fqtr fyr indfmt consol popsrc datafmt tic ... \\\n",
"0 1447 19990630 1999 2 12 INDL C D STD AXP ... \n",
"1 1447 19990930 1999 3 12 INDL C D STD AXP ... \n",
"2 1447 19991231 1999 4 12 INDL C D STD AXP ... \n",
"3 1447 20000331 2000 1 12 INDL C D STD AXP ... \n",
"4 1447 20000630 2000 2 12 INDL C D STD AXP ... \n",
"\n",
" dvpsxq mkvaltq prccq prchq prclq adjex ggroup gind gsector \\\n",
"0 0.225 NaN 130.1250 142.6250 114.5000 3.0 4020 402020 40 \n",
"1 0.000 NaN 135.0000 150.6250 121.8750 3.0 4020 402020 40 \n",
"2 0.225 NaN 166.2500 168.8750 130.2500 3.0 4020 402020 40 \n",
"3 0.225 NaN 148.9375 169.5000 119.5000 3.0 4020 402020 40 \n",
"4 0.080 NaN 52.1250 57.1875 43.9375 1.0 4020 402020 40 \n",
"\n",
" gsubind \n",
"0 40202010 \n",
"1 40202010 \n",
"2 40202010 \n",
"3 40202010 \n",
"4 40202010 \n",
"\n",
"[5 rows x 647 columns]"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Check the imported dataset\n",
"fund.head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "9yk1dHTYogEP"
},
"source": [
"## 4.2 Specify items needed to calculate financial ratios\n",
"- To learn more about the data description of the dataset, please check WRDS's website(https://wrds-www.wharton.upenn.edu/). Login will be required."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "CD0kFC7Ap02K"
},
"outputs": [],
"source": [
"# List items that are used to calculate financial ratios\n",
"\n",
"items = [\n",
" 'datadate', # Date\n",
" 'tic', # Ticker\n",
" 'oiadpq', # Quarterly operating income\n",
" 'revtq', # Quartely revenue\n",
" 'niq', # Quartely net income\n",
" 'atq', # Total asset\n",
" 'teqq', # Shareholder's equity\n",
" 'epspiy', # EPS(Basic) incl. Extraordinary items\n",
" 'ceqq', # Common Equity\n",
" 'cshoq', # Common Shares Outstanding\n",
" 'dvpspq', # Dividends per share\n",
" 'actq', # Current assets\n",
" 'lctq', # Current liabilities\n",
" 'cheq', # Cash & Equivalent\n",
" 'rectq', # Recievalbles\n",
" 'cogsq', # Cost of Goods Sold\n",
" 'invtq', # Inventories\n",
" 'apq',# Account payable\n",
" 'dlttq', # Long term debt\n",
" 'dlcq', # Debt in current liabilites\n",
" 'ltq' # Liabilities\n",
"]\n",
"\n",
"# Omit items that will not be used\n",
"fund_data = fund[items]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "jE7UNYtIqFkv"
},
"outputs": [],
"source": [
"# Rename column names for the sake of readability\n",
"fund_data = fund_data.rename(columns={\n",
" 'datadate':'date', # Date\n",
" 'oiadpq':'op_inc_q', # Quarterly operating income\n",
" 'revtq':'rev_q', # Quartely revenue\n",
" 'niq':'net_inc_q', # Quartely net income\n",
" 'atq':'tot_assets', # Assets\n",
" 'teqq':'sh_equity', # Shareholder's equity\n",
" 'epspiy':'eps_incl_ex', # EPS(Basic) incl. Extraordinary items\n",
" 'ceqq':'com_eq', # Common Equity\n",
" 'cshoq':'sh_outstanding', # Common Shares Outstanding\n",
" 'dvpspq':'div_per_sh', # Dividends per share\n",
" 'actq':'cur_assets', # Current assets\n",
" 'lctq':'cur_liabilities', # Current liabilities\n",
" 'cheq':'cash_eq', # Cash & Equivalent\n",
" 'rectq':'receivables', # Receivalbles\n",
" 'cogsq':'cogs_q', # Cost of Goods Sold\n",
" 'invtq':'inventories', # Inventories\n",
" 'apq': 'payables',# Account payable\n",
" 'dlttq':'long_debt', # Long term debt\n",
" 'dlcq':'short_debt', # Debt in current liabilites\n",
" 'ltq':'tot_liabilities' # Liabilities\n",
"})"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 300
},
"id": "A0sszApfqO6D",
"outputId": "98f02355-81d6-4606-e0ba-06a0abf8ddb6"
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>date</th>\n",
" <th>tic</th>\n",
" <th>op_inc_q</th>\n",
" <th>rev_q</th>\n",
" <th>net_inc_q</th>\n",
" <th>tot_assets</th>\n",
" <th>sh_equity</th>\n",
" <th>eps_incl_ex</th>\n",
" <th>com_eq</th>\n",
" <th>sh_outstanding</th>\n",
" <th>...</th>\n",
" <th>cur_assets</th>\n",
" <th>cur_liabilities</th>\n",
" <th>cash_eq</th>\n",
" <th>receivables</th>\n",
" <th>cogs_q</th>\n",
" <th>inventories</th>\n",
" <th>payables</th>\n",
" <th>long_debt</th>\n",
" <th>short_debt</th>\n",
" <th>tot_liabilities</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>19990630</td>\n",
" <td>AXP</td>\n",
" <td>896.0</td>\n",
" <td>5564.0</td>\n",
" <td>646.0</td>\n",
" <td>132452.0</td>\n",
" <td>9762.0</td>\n",
" <td>2.73</td>\n",
" <td>9762.0</td>\n",
" <td>449.0</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6096.0</td>\n",
" <td>46774.0</td>\n",
" <td>4668.0</td>\n",
" <td>448.0</td>\n",
" <td>22282.0</td>\n",
" <td>7005.0</td>\n",
" <td>24785.0</td>\n",
" <td>122690.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>19990930</td>\n",
" <td>AXP</td>\n",
" <td>906.0</td>\n",
" <td>5584.0</td>\n",
" <td>648.0</td>\n",
" <td>132616.0</td>\n",
" <td>9744.0</td>\n",
" <td>4.18</td>\n",
" <td>9744.0</td>\n",
" <td>447.6</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>5102.0</td>\n",
" <td>48827.0</td>\n",
" <td>4678.0</td>\n",
" <td>284.0</td>\n",
" <td>23587.0</td>\n",
" <td>6720.0</td>\n",
" <td>24683.0</td>\n",
" <td>122872.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>19991231</td>\n",
" <td>AXP</td>\n",
" <td>845.0</td>\n",
" <td>6009.0</td>\n",
" <td>606.0</td>\n",
" <td>148517.0</td>\n",
" <td>10095.0</td>\n",
" <td>5.54</td>\n",
" <td>10095.0</td>\n",
" <td>446.9</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>10391.0</td>\n",
" <td>54033.0</td>\n",
" <td>5164.0</td>\n",
" <td>277.0</td>\n",
" <td>25719.0</td>\n",
" <td>4685.0</td>\n",
" <td>32437.0</td>\n",
" <td>138422.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>20000331</td>\n",
" <td>AXP</td>\n",
" <td>920.0</td>\n",
" <td>6021.0</td>\n",
" <td>656.0</td>\n",
" <td>150662.0</td>\n",
" <td>10253.0</td>\n",
" <td>1.48</td>\n",
" <td>10253.0</td>\n",
" <td>444.7</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>7425.0</td>\n",
" <td>53663.0</td>\n",
" <td>5101.0</td>\n",
" <td>315.0</td>\n",
" <td>26379.0</td>\n",
" <td>5670.0</td>\n",
" <td>29342.0</td>\n",
" <td>140409.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>20000630</td>\n",
" <td>AXP</td>\n",
" <td>1046.0</td>\n",
" <td>6370.0</td>\n",
" <td>740.0</td>\n",
" <td>148553.0</td>\n",
" <td>10509.0</td>\n",
" <td>1.05</td>\n",
" <td>10509.0</td>\n",
" <td>1333.0</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6841.0</td>\n",
" <td>54286.0</td>\n",
" <td>5324.0</td>\n",
" <td>261.0</td>\n",
" <td>29536.0</td>\n",
" <td>5336.0</td>\n",
" <td>26170.0</td>\n",
" <td>138044.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 21 columns</p>\n",
"</div>"
],
"text/plain": [
" date tic op_inc_q rev_q net_inc_q tot_assets sh_equity \\\n",
"0 19990630 AXP 896.0 5564.0 646.0 132452.0 9762.0 \n",
"1 19990930 AXP 906.0 5584.0 648.0 132616.0 9744.0 \n",
"2 19991231 AXP 845.0 6009.0 606.0 148517.0 10095.0 \n",
"3 20000331 AXP 920.0 6021.0 656.0 150662.0 10253.0 \n",
"4 20000630 AXP 1046.0 6370.0 740.0 148553.0 10509.0 \n",
"\n",
" eps_incl_ex com_eq sh_outstanding ... cur_assets cur_liabilities \\\n",
"0 2.73 9762.0 449.0 ... NaN NaN \n",
"1 4.18 9744.0 447.6 ... NaN NaN \n",
"2 5.54 10095.0 446.9 ... NaN NaN \n",
"3 1.48 10253.0 444.7 ... NaN NaN \n",
"4 1.05 10509.0 1333.0 ... NaN NaN \n",
"\n",
" cash_eq receivables cogs_q inventories payables long_debt short_debt \\\n",
"0 6096.0 46774.0 4668.0 448.0 22282.0 7005.0 24785.0 \n",
"1 5102.0 48827.0 4678.0 284.0 23587.0 6720.0 24683.0 \n",
"2 10391.0 54033.0 5164.0 277.0 25719.0 4685.0 32437.0 \n",
"3 7425.0 53663.0 5101.0 315.0 26379.0 5670.0 29342.0 \n",
"4 6841.0 54286.0 5324.0 261.0 29536.0 5336.0 26170.0 \n",
"\n",
" tot_liabilities \n",
"0 122690.0 \n",
"1 122872.0 \n",
"2 138422.0 \n",
"3 140409.0 \n",
"4 138044.0 \n",
"\n",
"[5 rows x 21 columns]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Check the data\n",
"fund_data.head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "xPvwtMQUqZdP"
},
"source": [
"## 4.3 Calculate financial ratios\n",
"- For items from Profit/Loss statements, we calculate LTM (Last Twelve Months) and use them to derive profitability related ratios such as Operating Maring and ROE. For items from balance sheets, we use the numbers on the day.\n",
"- To check the definitions of the financial ratios calculated here, please refer to CFI's website: https://corporatefinanceinstitute.com/resources/knowledge/finance/financial-ratios/"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "cfWtEophqS33",
"outputId": "1b830d42-0878-45e5-d4f1-68f905d78774"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"<ipython-input-15-217f6a06b836>:15: RuntimeWarning: divide by zero encountered in double_scalars\n",
" OPM.iloc[i] = np.sum(fund_data['op_inc_q'].iloc[i-3:i])/np.sum(fund_data['rev_q'].iloc[i-3:i])\n",
"<ipython-input-15-217f6a06b836>:15: RuntimeWarning: invalid value encountered in double_scalars\n",
" OPM.iloc[i] = np.sum(fund_data['op_inc_q'].iloc[i-3:i])/np.sum(fund_data['rev_q'].iloc[i-3:i])\n",
"<ipython-input-15-217f6a06b836>:25: RuntimeWarning: divide by zero encountered in double_scalars\n",
" NPM.iloc[i] = np.sum(fund_data['net_inc_q'].iloc[i-3:i])/np.sum(fund_data['rev_q'].iloc[i-3:i])\n",
"<ipython-input-15-217f6a06b836>:25: RuntimeWarning: invalid value encountered in double_scalars\n",
" NPM.iloc[i] = np.sum(fund_data['net_inc_q'].iloc[i-3:i])/np.sum(fund_data['rev_q'].iloc[i-3:i])\n",
"<ipython-input-15-217f6a06b836>:77: RuntimeWarning: divide by zero encountered in double_scalars\n",
" inv_turnover.iloc[i] = np.sum(fund_data['cogs_q'].iloc[i-3:i])/fund_data['inventories'].iloc[i]\n",
"<ipython-input-15-217f6a06b836>:77: RuntimeWarning: invalid value encountered in double_scalars\n",
" inv_turnover.iloc[i] = np.sum(fund_data['cogs_q'].iloc[i-3:i])/fund_data['inventories'].iloc[i]\n"
]
}
],
"source": [
"# Calculate financial ratios\n",
"date = pd.to_datetime(fund_data['date'],format='%Y%m%d')\n",
"\n",
"tic = fund_data['tic'].to_frame('tic')\n",
"\n",
"# Profitability ratios\n",
"# Operating Margin\n",
"OPM = pd.Series(np.empty(fund_data.shape[0],dtype=object),name='OPM')\n",
"for i in range(0, fund_data.shape[0]):\n",
" if i-3 < 0:\n",
" OPM[i] = np.nan\n",
" elif fund_data.iloc[i,1] != fund_data.iloc[i-3,1]:\n",
" OPM.iloc[i] = np.nan\n",
" else:\n",
" OPM.iloc[i] = np.sum(fund_data['op_inc_q'].iloc[i-3:i])/np.sum(fund_data['rev_q'].iloc[i-3:i])\n",
"\n",
"# Net Profit Margin\n",
"NPM = pd.Series(np.empty(fund_data.shape[0],dtype=object),name='NPM')\n",
"for i in range(0, fund_data.shape[0]):\n",
" if i-3 < 0:\n",
" NPM[i] = np.nan\n",
" elif fund_data.iloc[i,1] != fund_data.iloc[i-3,1]:\n",
" NPM.iloc[i] = np.nan\n",
" else:\n",
" NPM.iloc[i] = np.sum(fund_data['net_inc_q'].iloc[i-3:i])/np.sum(fund_data['rev_q'].iloc[i-3:i])\n",
"\n",
"# Return On Assets\n",
"ROA = pd.Series(np.empty(fund_data.shape[0],dtype=object),name='ROA')\n",
"for i in range(0, fund_data.shape[0]):\n",
" if i-3 < 0:\n",
" ROA[i] = np.nan\n",
" elif fund_data.iloc[i,1] != fund_data.iloc[i-3,1]:\n",
" ROA.iloc[i] = np.nan\n",
" else:\n",
" ROA.iloc[i] = np.sum(fund_data['net_inc_q'].iloc[i-3:i])/fund_data['tot_assets'].iloc[i]\n",
"\n",
"# Return on Equity\n",
"ROE = pd.Series(np.empty(fund_data.shape[0],dtype=object),name='ROE')\n",
"for i in range(0, fund_data.shape[0]):\n",
" if i-3 < 0:\n",
" ROE[i] = np.nan\n",
" elif fund_data.iloc[i,1] != fund_data.iloc[i-3,1]:\n",
" ROE.iloc[i] = np.nan\n",
" else:\n",
" ROE.iloc[i] = np.sum(fund_data['net_inc_q'].iloc[i-3:i])/fund_data['sh_equity'].iloc[i]\n",
"\n",
"# For calculating valuation ratios in the next subpart, calculate per share items in advance\n",
"# Earnings Per Share\n",
"EPS = fund_data['eps_incl_ex'].to_frame('EPS')\n",
"\n",
"# Book Per Share\n",
"BPS = (fund_data['com_eq']/fund_data['sh_outstanding']).to_frame('BPS') # Need to check units\n",
"\n",
"#Dividend Per Share\n",
"DPS = fund_data['div_per_sh'].to_frame('DPS')\n",
"\n",
"# Liquidity ratios\n",
"# Current ratio\n",
"cur_ratio = (fund_data['cur_assets']/fund_data['cur_liabilities']).to_frame('cur_ratio')\n",
"\n",
"# Quick ratio\n",
"quick_ratio = ((fund_data['cash_eq'] + fund_data['receivables'] )/fund_data['cur_liabilities']).to_frame('quick_ratio')\n",
"\n",
"# Cash ratio\n",
"cash_ratio = (fund_data['cash_eq']/fund_data['cur_liabilities']).to_frame('cash_ratio')\n",
"\n",
"\n",
"# Efficiency ratios\n",
"# Inventory turnover ratio\n",
"inv_turnover = pd.Series(np.empty(fund_data.shape[0],dtype=object),name='inv_turnover')\n",
"for i in range(0, fund_data.shape[0]):\n",
" if i-3 < 0:\n",
" inv_turnover[i] = np.nan\n",
" elif fund_data.iloc[i,1] != fund_data.iloc[i-3,1]:\n",
" inv_turnover.iloc[i] = np.nan\n",
" else:\n",
" inv_turnover.iloc[i] = np.sum(fund_data['cogs_q'].iloc[i-3:i])/fund_data['inventories'].iloc[i]\n",
"\n",
"# Receivables turnover ratio\n",
"acc_rec_turnover = pd.Series(np.empty(fund_data.shape[0],dtype=object),name='acc_rec_turnover')\n",
"for i in range(0, fund_data.shape[0]):\n",
" if i-3 < 0:\n",
" acc_rec_turnover[i] = np.nan\n",
" elif fund_data.iloc[i,1] != fund_data.iloc[i-3,1]:\n",
" acc_rec_turnover.iloc[i] = np.nan\n",
" else:\n",
" acc_rec_turnover.iloc[i] = np.sum(fund_data['rev_q'].iloc[i-3:i])/fund_data['receivables'].iloc[i]\n",
"\n",
"# Payable turnover ratio\n",
"acc_pay_turnover = pd.Series(np.empty(fund_data.shape[0],dtype=object),name='acc_pay_turnover')\n",
"for i in range(0, fund_data.shape[0]):\n",
" if i-3 < 0:\n",
" acc_pay_turnover[i] = np.nan\n",
" elif fund_data.iloc[i,1] != fund_data.iloc[i-3,1]:\n",
" acc_pay_turnover.iloc[i] = np.nan\n",
" else:\n",
" acc_pay_turnover.iloc[i] = np.sum(fund_data['cogs_q'].iloc[i-3:i])/fund_data['payables'].iloc[i]\n",
"\n",
"## Leverage financial ratios\n",
"# Debt ratio\n",
"debt_ratio = (fund_data['tot_liabilities']/fund_data['tot_assets']).to_frame('debt_ratio')\n",
"\n",
"# Debt to Equity ratio\n",
"debt_to_equity = (fund_data['tot_liabilities']/fund_data['sh_equity']).to_frame('debt_to_equity')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "wwFVopRDqcby"
},
"outputs": [],
"source": [
"# Create a dataframe that merges all the ratios\n",
"ratios = pd.concat([date,tic,OPM,NPM,ROA,ROE,EPS,BPS,DPS,\n",
" cur_ratio,quick_ratio,cash_ratio,inv_turnover,acc_rec_turnover,acc_pay_turnover,\n",
" debt_ratio,debt_to_equity], axis=1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"id": "Mvnw7izFsJcT",
"outputId": "e6bd5adc-ccb0-44b3-a5b5-2bd65637a3c0"
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>date</th>\n",
" <th>tic</th>\n",
" <th>OPM</th>\n",
" <th>NPM</th>\n",
" <th>ROA</th>\n",
" <th>ROE</th>\n",
" <th>EPS</th>\n",
" <th>BPS</th>\n",
" <th>DPS</th>\n",
" <th>cur_ratio</th>\n",
" <th>quick_ratio</th>\n",
" <th>cash_ratio</th>\n",
" <th>inv_turnover</th>\n",
" <th>acc_rec_turnover</th>\n",
" <th>acc_pay_turnover</th>\n",
" <th>debt_ratio</th>\n",
" <th>debt_to_equity</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1999-06-30</td>\n",
" <td>AXP</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2.73</td>\n",
" <td>21.741648</td>\n",
" <td>0.225</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.926298</td>\n",
" <td>12.568121</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1999-09-30</td>\n",
" <td>AXP</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.18</td>\n",
" <td>21.769437</td>\n",
" <td>0.225</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.926525</td>\n",
" <td>12.610016</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1999-12-31</td>\n",
" <td>AXP</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>5.54</td>\n",
" <td>22.588946</td>\n",
" <td>0.225</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.932028</td>\n",
" <td>13.711937</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2000-03-31</td>\n",
" <td>AXP</td>\n",
" <td>0.154281</td>\n",
" <td>0.110742</td>\n",
" <td>0.012611</td>\n",
" <td>0.185312</td>\n",
" <td>1.48</td>\n",
" <td>23.055993</td>\n",
" <td>0.225</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>46.063492</td>\n",
" <td>0.319717</td>\n",
" <td>0.550059</td>\n",
" <td>0.931947</td>\n",
" <td>13.694431</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2000-06-30</td>\n",
" <td>AXP</td>\n",
" <td>0.151641</td>\n",
" <td>0.108436</td>\n",
" <td>0.012857</td>\n",
" <td>0.181749</td>\n",
" <td>1.05</td>\n",
" <td>7.883721</td>\n",
" <td>0.080</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>57.252874</td>\n",
" <td>0.324467</td>\n",
" <td>0.505925</td>\n",
" <td>0.929258</td>\n",
" <td>13.135788</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" date tic OPM NPM ROA ROE EPS BPS \\\n",
"0 1999-06-30 AXP NaN NaN NaN NaN 2.73 21.741648 \n",
"1 1999-09-30 AXP NaN NaN NaN NaN 4.18 21.769437 \n",
"2 1999-12-31 AXP NaN NaN NaN NaN 5.54 22.588946 \n",
"3 2000-03-31 AXP 0.154281 0.110742 0.012611 0.185312 1.48 23.055993 \n",
"4 2000-06-30 AXP 0.151641 0.108436 0.012857 0.181749 1.05 7.883721 \n",
"\n",
" DPS cur_ratio quick_ratio cash_ratio inv_turnover acc_rec_turnover \\\n",
"0 0.225 NaN NaN NaN NaN NaN \n",
"1 0.225 NaN NaN NaN NaN NaN \n",
"2 0.225 NaN NaN NaN NaN NaN \n",
"3 0.225 NaN NaN NaN 46.063492 0.319717 \n",
"4 0.080 NaN NaN NaN 57.252874 0.324467 \n",
"\n",
" acc_pay_turnover debt_ratio debt_to_equity \n",
"0 NaN 0.926298 12.568121 \n",
"1 NaN 0.926525 12.610016 \n",
"2 NaN 0.932028 13.711937 \n",
"3 0.550059 0.931947 13.694431 \n",
"4 0.505925 0.929258 13.135788 "
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Check the ratio data\n",
"ratios.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"id": "AvG67ouguUKF",
"outputId": "7a0caeb6-fa49-4541-b264-f910ab15fb6c"
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>date</th>\n",
" <th>tic</th>\n",
" <th>OPM</th>\n",
" <th>NPM</th>\n",
" <th>ROA</th>\n",
" <th>ROE</th>\n",
" <th>EPS</th>\n",
" <th>BPS</th>\n",
" <th>DPS</th>\n",
" <th>cur_ratio</th>\n",
" <th>quick_ratio</th>\n",
" <th>cash_ratio</th>\n",
" <th>inv_turnover</th>\n",
" <th>acc_rec_turnover</th>\n",
" <th>acc_pay_turnover</th>\n",
" <th>debt_ratio</th>\n",
" <th>debt_to_equity</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2451</th>\n",
" <td>2020-03-31</td>\n",
" <td>V</td>\n",
" <td>0.667517</td>\n",
" <td>0.521213</td>\n",
" <td>0.129058</td>\n",
" <td>0.271736</td>\n",
" <td>2.85</td>\n",
" <td>13.647142</td>\n",
" <td>0.30</td>\n",
" <td>1.248714</td>\n",
" <td>1.140070</td>\n",
" <td>0.955150</td>\n",
" <td>inf</td>\n",
" <td>6.11635</td>\n",
" <td>2.697537</td>\n",
" <td>0.525062</td>\n",
" <td>1.105537</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2452</th>\n",
" <td>2020-06-30</td>\n",
" <td>V</td>\n",
" <td>0.668385</td>\n",
" <td>0.519867</td>\n",
" <td>0.120448</td>\n",
" <td>0.264075</td>\n",
" <td>3.92</td>\n",
" <td>14.203947</td>\n",
" <td>0.30</td>\n",
" <td>1.553478</td>\n",
" <td>1.443292</td>\n",
" <td>1.221925</td>\n",
" <td>inf</td>\n",
" <td>5.063131</td>\n",
" <td>1.889507</td>\n",
" <td>0.543886</td>\n",
" <td>1.192433</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2453</th>\n",
" <td>2020-09-30</td>\n",
" <td>V</td>\n",
" <td>0.654464</td>\n",
" <td>0.52129</td>\n",
" <td>0.107873</td>\n",
" <td>0.241066</td>\n",
" <td>4.90</td>\n",
" <td>14.653484</td>\n",
" <td>0.30</td>\n",
" <td>1.905238</td>\n",
" <td>1.784838</td>\n",
" <td>1.579807</td>\n",
" <td>inf</td>\n",
" <td>5.628571</td>\n",
" <td>2.730366</td>\n",
" <td>0.552515</td>\n",
" <td>1.234714</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2454</th>\n",
" <td>2020-12-31</td>\n",
" <td>V</td>\n",
" <td>0.638994</td>\n",
" <td>0.480876</td>\n",
" <td>0.094422</td>\n",
" <td>0.201545</td>\n",
" <td>1.42</td>\n",
" <td>15.908283</td>\n",
" <td>0.32</td>\n",
" <td>2.121065</td>\n",
" <td>1.969814</td>\n",
" <td>1.700081</td>\n",
" <td>inf</td>\n",
" <td>4.725314</td>\n",
" <td>2.347866</td>\n",
" <td>0.531507</td>\n",
" <td>1.134505</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2455</th>\n",
" <td>2021-03-31</td>\n",
" <td>V</td>\n",
" <td>0.640128</td>\n",
" <td>0.488704</td>\n",
" <td>0.095218</td>\n",
" <td>0.202568</td>\n",
" <td>2.80</td>\n",
" <td>16.088525</td>\n",
" <td>0.32</td>\n",
" <td>2.116356</td>\n",
" <td>1.954292</td>\n",
" <td>1.700574</td>\n",
" <td>inf</td>\n",
" <td>4.844961</td>\n",
" <td>2.367357</td>\n",
" <td>0.529946</td>\n",
" <td>1.127414</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" date tic OPM NPM ROA ROE EPS BPS \\\n",
"2451 2020-03-31 V 0.667517 0.521213 0.129058 0.271736 2.85 13.647142 \n",
"2452 2020-06-30 V 0.668385 0.519867 0.120448 0.264075 3.92 14.203947 \n",
"2453 2020-09-30 V 0.654464 0.52129 0.107873 0.241066 4.90 14.653484 \n",
"2454 2020-12-31 V 0.638994 0.480876 0.094422 0.201545 1.42 15.908283 \n",
"2455 2021-03-31 V 0.640128 0.488704 0.095218 0.202568 2.80 16.088525 \n",
"\n",
" DPS cur_ratio quick_ratio cash_ratio inv_turnover acc_rec_turnover \\\n",
"2451 0.30 1.248714 1.140070 0.955150 inf 6.11635 \n",
"2452 0.30 1.553478 1.443292 1.221925 inf 5.063131 \n",
"2453 0.30 1.905238 1.784838 1.579807 inf 5.628571 \n",
"2454 0.32 2.121065 1.969814 1.700081 inf 4.725314 \n",
"2455 0.32 2.116356 1.954292 1.700574 inf 4.844961 \n",
"\n",
" acc_pay_turnover debt_ratio debt_to_equity \n",
"2451 2.697537 0.525062 1.105537 \n",
"2452 1.889507 0.543886 1.192433 \n",
"2453 2.730366 0.552515 1.234714 \n",
"2454 2.347866 0.531507 1.134505 \n",
"2455 2.367357 0.529946 1.127414 "
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ratios.tail()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "JULhnNv8uaOB"
},
"source": [
"## 4.4 Deal with NAs and infinite values\n",
"- We replace N/A and infinite values with zero."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "nuKPlGe4sNzQ"
},
"outputs": [],
"source": [
"# Replace NAs infinite values with zero\n",
"final_ratios = ratios.copy()\n",
"final_ratios = final_ratios.fillna(0)\n",
"final_ratios = final_ratios.replace(np.inf,0)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"id": "wc_rvvm1sRDd",
"outputId": "f8028670-404f-4a50-b157-55ef87fe1756"
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>date</th>\n",
" <th>tic</th>\n",
" <th>OPM</th>\n",
" <th>NPM</th>\n",
" <th>ROA</th>\n",
" <th>ROE</th>\n",
" <th>EPS</th>\n",
" <th>BPS</th>\n",
" <th>DPS</th>\n",
" <th>cur_ratio</th>\n",
" <th>quick_ratio</th>\n",
" <th>cash_ratio</th>\n",
" <th>inv_turnover</th>\n",
" <th>acc_rec_turnover</th>\n",
" <th>acc_pay_turnover</th>\n",
" <th>debt_ratio</th>\n",
" <th>debt_to_equity</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1999-06-30</td>\n",
" <td>AXP</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>2.73</td>\n",
" <td>21.741648</td>\n",
" <td>0.225</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.926298</td>\n",
" <td>12.568121</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1999-09-30</td>\n",
" <td>AXP</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>4.18</td>\n",
" <td>21.769437</td>\n",
" <td>0.225</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.926525</td>\n",
" <td>12.610016</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1999-12-31</td>\n",
" <td>AXP</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>5.54</td>\n",
" <td>22.588946</td>\n",
" <td>0.225</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.932028</td>\n",
" <td>13.711937</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2000-03-31</td>\n",
" <td>AXP</td>\n",
" <td>0.154281</td>\n",
" <td>0.110742</td>\n",
" <td>0.012611</td>\n",
" <td>0.185312</td>\n",
" <td>1.48</td>\n",
" <td>23.055993</td>\n",
" <td>0.225</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>46.063492</td>\n",
" <td>0.319717</td>\n",
" <td>0.550059</td>\n",
" <td>0.931947</td>\n",
" <td>13.694431</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2000-06-30</td>\n",
" <td>AXP</td>\n",
" <td>0.151641</td>\n",
" <td>0.108436</td>\n",
" <td>0.012857</td>\n",
" <td>0.181749</td>\n",
" <td>1.05</td>\n",
" <td>7.883721</td>\n",
" <td>0.080</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>57.252874</td>\n",
" <td>0.324467</td>\n",
" <td>0.505925</td>\n",
" <td>0.929258</td>\n",
" <td>13.135788</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" date tic OPM NPM ROA ROE EPS BPS \\\n",
"0 1999-06-30 AXP 0.000000 0.000000 0.000000 0.000000 2.73 21.741648 \n",
"1 1999-09-30 AXP 0.000000 0.000000 0.000000 0.000000 4.18 21.769437 \n",
"2 1999-12-31 AXP 0.000000 0.000000 0.000000 0.000000 5.54 22.588946 \n",
"3 2000-03-31 AXP 0.154281 0.110742 0.012611 0.185312 1.48 23.055993 \n",
"4 2000-06-30 AXP 0.151641 0.108436 0.012857 0.181749 1.05 7.883721 \n",
"\n",
" DPS cur_ratio quick_ratio cash_ratio inv_turnover acc_rec_turnover \\\n",
"0 0.225 0.0 0.0 0.0 0.000000 0.000000 \n",
"1 0.225 0.0 0.0 0.0 0.000000 0.000000 \n",
"2 0.225 0.0 0.0 0.0 0.000000 0.000000 \n",
"3 0.225 0.0 0.0 0.0 46.063492 0.319717 \n",
"4 0.080 0.0 0.0 0.0 57.252874 0.324467 \n",
"\n",
" acc_pay_turnover debt_ratio debt_to_equity \n",
"0 0.000000 0.926298 12.568121 \n",
"1 0.000000 0.926525 12.610016 \n",
"2 0.000000 0.932028 13.711937 \n",
"3 0.550059 0.931947 13.694431 \n",
"4 0.505925 0.929258 13.135788 "
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"final_ratios.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 206
},
"id": "RKwmRfs5sfra",
"outputId": "3307342a-1b39-496f-cee3-1b5bf09e53fc"
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>date</th>\n",
" <th>tic</th>\n",
" <th>OPM</th>\n",
" <th>NPM</th>\n",
" <th>ROA</th>\n",
" <th>ROE</th>\n",
" <th>EPS</th>\n",
" <th>BPS</th>\n",
" <th>DPS</th>\n",
" <th>cur_ratio</th>\n",
" <th>quick_ratio</th>\n",
" <th>cash_ratio</th>\n",
" <th>inv_turnover</th>\n",
" <th>acc_rec_turnover</th>\n",
" <th>acc_pay_turnover</th>\n",
" <th>debt_ratio</th>\n",
" <th>debt_to_equity</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2451</th>\n",
" <td>2020-03-31</td>\n",
" <td>V</td>\n",
" <td>0.667517</td>\n",
" <td>0.521213</td>\n",
" <td>0.129058</td>\n",
" <td>0.271736</td>\n",
" <td>2.85</td>\n",
" <td>13.647142</td>\n",
" <td>0.30</td>\n",
" <td>1.248714</td>\n",
" <td>1.140070</td>\n",
" <td>0.955150</td>\n",
" <td>0.0</td>\n",
" <td>6.116350</td>\n",
" <td>2.697537</td>\n",
" <td>0.525062</td>\n",
" <td>1.105537</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2452</th>\n",
" <td>2020-06-30</td>\n",
" <td>V</td>\n",
" <td>0.668385</td>\n",
" <td>0.519867</td>\n",
" <td>0.120448</td>\n",
" <td>0.264075</td>\n",
" <td>3.92</td>\n",
" <td>14.203947</td>\n",
" <td>0.30</td>\n",
" <td>1.553478</td>\n",
" <td>1.443292</td>\n",
" <td>1.221925</td>\n",
" <td>0.0</td>\n",
" <td>5.063131</td>\n",
" <td>1.889507</td>\n",
" <td>0.543886</td>\n",
" <td>1.192433</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2453</th>\n",
" <td>2020-09-30</td>\n",
" <td>V</td>\n",
" <td>0.654464</td>\n",
" <td>0.521290</td>\n",
" <td>0.107873</td>\n",
" <td>0.241066</td>\n",
" <td>4.90</td>\n",
" <td>14.653484</td>\n",
" <td>0.30</td>\n",
" <td>1.905238</td>\n",
" <td>1.784838</td>\n",
" <td>1.579807</td>\n",
" <td>0.0</td>\n",
" <td>5.628571</td>\n",
" <td>2.730366</td>\n",
" <td>0.552515</td>\n",
" <td>1.234714</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2454</th>\n",
" <td>2020-12-31</td>\n",
" <td>V</td>\n",
" <td>0.638994</td>\n",
" <td>0.480876</td>\n",
" <td>0.094422</td>\n",
" <td>0.201545</td>\n",
" <td>1.42</td>\n",
" <td>15.908283</td>\n",
" <td>0.32</td>\n",
" <td>2.121065</td>\n",
" <td>1.969814</td>\n",
" <td>1.700081</td>\n",
" <td>0.0</td>\n",
" <td>4.725314</td>\n",
" <td>2.347866</td>\n",
" <td>0.531507</td>\n",
" <td>1.134505</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2455</th>\n",
" <td>2021-03-31</td>\n",
" <td>V</td>\n",
" <td>0.640128</td>\n",
" <td>0.488704</td>\n",
" <td>0.095218</td>\n",
" <td>0.202568</td>\n",
" <td>2.80</td>\n",
" <td>16.088525</td>\n",
" <td>0.32</td>\n",
" <td>2.116356</td>\n",
" <td>1.954292</td>\n",
" <td>1.700574</td>\n",
" <td>0.0</td>\n",
" <td>4.844961</td>\n",
" <td>2.367357</td>\n",
" <td>0.529946</td>\n",
" <td>1.127414</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" date tic OPM NPM ROA ROE EPS BPS \\\n",
"2451 2020-03-31 V 0.667517 0.521213 0.129058 0.271736 2.85 13.647142 \n",
"2452 2020-06-30 V 0.668385 0.519867 0.120448 0.264075 3.92 14.203947 \n",
"2453 2020-09-30 V 0.654464 0.521290 0.107873 0.241066 4.90 14.653484 \n",
"2454 2020-12-31 V 0.638994 0.480876 0.094422 0.201545 1.42 15.908283 \n",
"2455 2021-03-31 V 0.640128 0.488704 0.095218 0.202568 2.80 16.088525 \n",
"\n",
" DPS cur_ratio quick_ratio cash_ratio inv_turnover \\\n",
"2451 0.30 1.248714 1.140070 0.955150 0.0 \n",
"2452 0.30 1.553478 1.443292 1.221925 0.0 \n",
"2453 0.30 1.905238 1.784838 1.579807 0.0 \n",
"2454 0.32 2.121065 1.969814 1.700081 0.0 \n",
"2455 0.32 2.116356 1.954292 1.700574 0.0 \n",
"\n",
" acc_rec_turnover acc_pay_turnover debt_ratio debt_to_equity \n",
"2451 6.116350 2.697537 0.525062 1.105537 \n",
"2452 5.063131 1.889507 0.543886 1.192433 \n",
"2453 5.628571 2.730366 0.552515 1.234714 \n",
"2454 4.725314 2.347866 0.531507 1.134505 \n",
"2455 4.844961 2.367357 0.529946 1.127414 "
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"final_ratios.tail()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "66kjM0lhu91F"
},
"source": [
"## 4.5 Merge stock price data and ratios into one dataframe\n",
"- Merge the price dataframe preprocessed in Part 3 and the ratio dataframe created in this part\n",
"- Since the prices are daily and ratios are quartely, we have NAs in the ratio columns after merging the two dataframes. We deal with this by backfilling the ratios."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Kixon2tR3RLT"
},
"outputs": [],
"source": [
"list_ticker = df[\"tic\"].unique().tolist()\n",
"list_date = list(pd.date_range(df['date'].min(),df['date'].max()))\n",
"combination = list(itertools.product(list_date,list_ticker))\n",
"\n",
"# Merge stock price data and ratios into one dataframe\n",
"processed_full = pd.DataFrame(combination,columns=[\"date\",\"tic\"]).merge(df,on=[\"date\",\"tic\"],how=\"left\")\n",
"processed_full = processed_full.merge(final_ratios,how='left',on=['date','tic'])\n",
"processed_full = processed_full.sort_values(['tic','date'])\n",
"\n",
"# Backfill the ratio data to make them daily\n",
"processed_full = processed_full.bfill(axis='rows')\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "CGU69Ccfw_bR"
},
"source": [
"## 4.6 Calculate market valuation ratios using daily stock price data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "EhiYLZPBVZNW"
},
"outputs": [],
"source": [
"# Calculate P/E, P/B and dividend yield using daily closing price\n",
"processed_full['PE'] = processed_full['close']/processed_full['EPS']\n",
"processed_full['PB'] = processed_full['close']/processed_full['BPS']\n",
"processed_full['Div_yield'] = processed_full['DPS']/processed_full['close']\n",
"\n",
"# Drop per share items used for the above calculation\n",
"processed_full = processed_full.drop(columns=['day','EPS','BPS','DPS'])\n",
"# Replace NAs infinite values with zero\n",
"processed_full = processed_full.copy()\n",
"processed_full = processed_full.fillna(0)\n",
"processed_full = processed_full.replace(np.inf,0)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 630
},
"id": "grvhGJJII3Xn",
"outputId": "2a1c873f-38af-4f87-d858-a1466130f924"
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>date</th>\n",
" <th>tic</th>\n",
" <th>open</th>\n",
" <th>high</th>\n",
" <th>low</th>\n",
" <th>close</th>\n",
" <th>volume</th>\n",
" <th>OPM</th>\n",
" <th>NPM</th>\n",
" <th>ROA</th>\n",
" <th>...</th>\n",
" <th>quick_ratio</th>\n",
" <th>cash_ratio</th>\n",
" <th>inv_turnover</th>\n",
" <th>acc_rec_turnover</th>\n",
" <th>acc_pay_turnover</th>\n",
" <th>debt_ratio</th>\n",
" <th>debt_to_equity</th>\n",
" <th>PE</th>\n",
" <th>PB</th>\n",
" <th>Div_yield</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2008-12-31</td>\n",
" <td>AAPL</td>\n",
" <td>3.070357</td>\n",
" <td>3.133571</td>\n",
" <td>3.047857</td>\n",
" <td>2.602662</td>\n",
" <td>607541200.0</td>\n",
" <td>0.181409</td>\n",
" <td>0.142233</td>\n",
" <td>0.076028</td>\n",
" <td>...</td>\n",
" <td>1.969235</td>\n",
" <td>1.737955</td>\n",
" <td>37.098485</td>\n",
" <td>6.701143</td>\n",
" <td>3.115801</td>\n",
" <td>0.464580</td>\n",
" <td>0.867694</td>\n",
" <td>1.024670</td>\n",
" <td>0.101159</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2008-12-31</td>\n",
" <td>AMGN</td>\n",
" <td>57.110001</td>\n",
" <td>58.220001</td>\n",
" <td>57.060001</td>\n",
" <td>43.587833</td>\n",
" <td>6287200.0</td>\n",
" <td>0.125036</td>\n",
" <td>0.099890</td>\n",
" <td>0.019504</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.315453</td>\n",
" <td>0.692029</td>\n",
" <td>0.906079</td>\n",
" <td>9.647243</td>\n",
" <td>18.787859</td>\n",
" <td>4.270069</td>\n",
" <td>0.004130</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2008-12-31</td>\n",
" <td>AXP</td>\n",
" <td>17.969999</td>\n",
" <td>18.750000</td>\n",
" <td>17.910000</td>\n",
" <td>14.852877</td>\n",
" <td>9625600.0</td>\n",
" <td>0.125036</td>\n",
" <td>0.099890</td>\n",
" <td>0.019504</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.315453</td>\n",
" <td>0.692029</td>\n",
" <td>0.906079</td>\n",
" <td>9.647243</td>\n",
" <td>6.402102</td>\n",
" <td>1.455058</td>\n",
" <td>0.012119</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2008-12-31</td>\n",
" <td>BA</td>\n",
" <td>41.590000</td>\n",
" <td>43.049999</td>\n",
" <td>41.500000</td>\n",
" <td>32.005882</td>\n",
" <td>5443100.0</td>\n",
" <td>0.086413</td>\n",
" <td>0.057167</td>\n",
" <td>0.051284</td>\n",
" <td>...</td>\n",
" <td>0.300922</td>\n",
" <td>0.106031</td>\n",
" <td>2.423841</td>\n",
" <td>8.004812</td>\n",
" <td>6.445410</td>\n",
" <td>1.024061</td>\n",
" <td>-42.560278</td>\n",
" <td>8.650238</td>\n",
" <td>-17.267792</td>\n",
" <td>0.012498</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2008-12-31</td>\n",
" <td>CAT</td>\n",
" <td>43.700001</td>\n",
" <td>45.099998</td>\n",
" <td>43.700001</td>\n",
" <td>30.416981</td>\n",
" <td>6277400.0</td>\n",
" <td>0.149397</td>\n",
" <td>0.075415</td>\n",
" <td>0.042725</td>\n",
" <td>...</td>\n",
" <td>0.819095</td>\n",
" <td>0.106909</td>\n",
" <td>3.062977</td>\n",
" <td>2.068351</td>\n",
" <td>5.571991</td>\n",
" <td>0.902467</td>\n",
" <td>0.000000</td>\n",
" <td>5.217321</td>\n",
" <td>3.005854</td>\n",
" <td>0.013808</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>2008-12-31</td>\n",
" <td>CRM</td>\n",
" <td>7.712500</td>\n",
" <td>8.130000</td>\n",
" <td>7.707500</td>\n",
" <td>8.002500</td>\n",
" <td>5367600.0</td>\n",
" <td>0.234698</td>\n",
" <td>0.196418</td>\n",
" <td>0.097593</td>\n",
" <td>...</td>\n",
" <td>2.498162</td>\n",
" <td>2.170759</td>\n",
" <td>9.054201</td>\n",
" <td>6.844634</td>\n",
" <td>16.036800</td>\n",
" <td>0.400215</td>\n",
" <td>0.667591</td>\n",
" <td>12.702380</td>\n",
" <td>1.271419</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>2008-12-31</td>\n",
" <td>CSCO</td>\n",
" <td>16.180000</td>\n",
" <td>16.549999</td>\n",
" <td>16.120001</td>\n",
" <td>11.575116</td>\n",
" <td>37513700.0</td>\n",
" <td>0.234698</td>\n",
" <td>0.196418</td>\n",
" <td>0.097593</td>\n",
" <td>...</td>\n",
" <td>2.498162</td>\n",
" <td>2.170759</td>\n",
" <td>9.054201</td>\n",
" <td>6.844634</td>\n",
" <td>16.036800</td>\n",
" <td>0.400215</td>\n",
" <td>0.667591</td>\n",
" <td>18.373200</td>\n",
" <td>1.839028</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>2008-12-31</td>\n",
" <td>CVX</td>\n",
" <td>72.900002</td>\n",
" <td>74.629997</td>\n",
" <td>72.900002</td>\n",
" <td>42.924400</td>\n",
" <td>9964300.0</td>\n",
" <td>0.139325</td>\n",
" <td>0.088934</td>\n",
" <td>0.118115</td>\n",
" <td>...</td>\n",
" <td>0.793680</td>\n",
" <td>0.298535</td>\n",
" <td>25.122702</td>\n",
" <td>13.499432</td>\n",
" <td>10.385464</td>\n",
" <td>0.459455</td>\n",
" <td>0.854584</td>\n",
" <td>3.656252</td>\n",
" <td>0.992873</td>\n",
" <td>0.015143</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>2008-12-31</td>\n",
" <td>DIS</td>\n",
" <td>22.570000</td>\n",
" <td>22.950001</td>\n",
" <td>22.520000</td>\n",
" <td>19.538343</td>\n",
" <td>9012100.0</td>\n",
" <td>0.197510</td>\n",
" <td>0.115987</td>\n",
" <td>0.048951</td>\n",
" <td>...</td>\n",
" <td>0.785544</td>\n",
" <td>0.301095</td>\n",
" <td>11.043571</td>\n",
" <td>4.485915</td>\n",
" <td>3.131064</td>\n",
" <td>0.477435</td>\n",
" <td>0.913637</td>\n",
" <td>42.474660</td>\n",
" <td>1.088774</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>2008-12-31</td>\n",
" <td>DOW</td>\n",
" <td>52.750000</td>\n",
" <td>53.500000</td>\n",
" <td>49.500000</td>\n",
" <td>41.373940</td>\n",
" <td>2350800.0</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>179.886694</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>10 rows × 22 columns</p>\n",
"</div>"
],
"text/plain": [
" date tic open high low close volume \\\n",
"0 2008-12-31 AAPL 3.070357 3.133571 3.047857 2.602662 607541200.0 \n",
"1 2008-12-31 AMGN 57.110001 58.220001 57.060001 43.587833 6287200.0 \n",
"2 2008-12-31 AXP 17.969999 18.750000 17.910000 14.852877 9625600.0 \n",
"3 2008-12-31 BA 41.590000 43.049999 41.500000 32.005882 5443100.0 \n",
"4 2008-12-31 CAT 43.700001 45.099998 43.700001 30.416981 6277400.0 \n",
"5 2008-12-31 CRM 7.712500 8.130000 7.707500 8.002500 5367600.0 \n",
"6 2008-12-31 CSCO 16.180000 16.549999 16.120001 11.575116 37513700.0 \n",
"7 2008-12-31 CVX 72.900002 74.629997 72.900002 42.924400 9964300.0 \n",
"8 2008-12-31 DIS 22.570000 22.950001 22.520000 19.538343 9012100.0 \n",
"9 2008-12-31 DOW 52.750000 53.500000 49.500000 41.373940 2350800.0 \n",
"\n",
" OPM NPM ROA ... quick_ratio cash_ratio inv_turnover \\\n",
"0 0.181409 0.142233 0.076028 ... 1.969235 1.737955 37.098485 \n",
"1 0.125036 0.099890 0.019504 ... 0.000000 0.000000 0.000000 \n",
"2 0.125036 0.099890 0.019504 ... 0.000000 0.000000 0.000000 \n",
"3 0.086413 0.057167 0.051284 ... 0.300922 0.106031 2.423841 \n",
"4 0.149397 0.075415 0.042725 ... 0.819095 0.106909 3.062977 \n",
"5 0.234698 0.196418 0.097593 ... 2.498162 2.170759 9.054201 \n",
"6 0.234698 0.196418 0.097593 ... 2.498162 2.170759 9.054201 \n",
"7 0.139325 0.088934 0.118115 ... 0.793680 0.298535 25.122702 \n",
"8 0.197510 0.115987 0.048951 ... 0.785544 0.301095 11.043571 \n",
"9 0.000000 0.000000 0.000000 ... 0.000000 0.000000 0.000000 \n",
"\n",
" acc_rec_turnover acc_pay_turnover debt_ratio debt_to_equity PE \\\n",
"0 6.701143 3.115801 0.464580 0.867694 1.024670 \n",
"1 0.315453 0.692029 0.906079 9.647243 18.787859 \n",
"2 0.315453 0.692029 0.906079 9.647243 6.402102 \n",
"3 8.004812 6.445410 1.024061 -42.560278 8.650238 \n",
"4 2.068351 5.571991 0.902467 0.000000 5.217321 \n",
"5 6.844634 16.036800 0.400215 0.667591 12.702380 \n",
"6 6.844634 16.036800 0.400215 0.667591 18.373200 \n",
"7 13.499432 10.385464 0.459455 0.854584 3.656252 \n",
"8 4.485915 3.131064 0.477435 0.913637 42.474660 \n",
"9 0.000000 0.000000 0.000000 0.000000 179.886694 \n",
"\n",
" PB Div_yield \n",
"0 0.101159 0.000000 \n",
"1 4.270069 0.004130 \n",
"2 1.455058 0.012119 \n",
"3 -17.267792 0.012498 \n",
"4 3.005854 0.013808 \n",
"5 1.271419 0.000000 \n",
"6 1.839028 0.000000 \n",
"7 0.992873 0.015143 \n",
"8 1.088774 0.000000 \n",
"9 0.000000 0.000000 \n",
"\n",
"[10 rows x 22 columns]"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Check the final data\n",
"processed_full.sort_values(['date','tic'],ignore_index=True).head(10)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "-QsYaY0Dh1iw"
},
"source": [
"<a id='4'></a>\n",
"# Part 5. A Market Environment in OpenAI Gym-style\n",
"The training process involves observing stock price change, taking an action and reward's calculation. By interacting with the market environment, the agent will eventually derive a trading strategy that may maximize (expected) rewards.\n",
"\n",
"Our market environment, based on OpenAI Gym, simulates stock markets with historical market data."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "5TOhcryx44bb"
},
"source": [
"## 5.1 Data Split\n",
"- Training data period: 2009-01-01 to 2019-01-01\n",
"- Trade data period: 2019-01-01 to 2020-12-31"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "W0qaVGjLtgbI",
"outputId": "b1a3102a-5d4e-438e-faca-7d03a2e1f584"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"109560\n",
"21930\n"
]
}
],
"source": [
"train_data = data_split(processed_full, TRAIN_START_DATE, TRAIN_END_DATE)\n",
"trade_data = data_split(processed_full, TEST_START_DATE, TEST_END_DATE)\n",
"# Check the length of the two datasets\n",
"print(len(train_data))\n",
"print(len(trade_data))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 386
},
"id": "p52zNCOhTtLR",
"outputId": "0a43f44d-af70-420f-9a0c-6b17482849b6"
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>date</th>\n",
" <th>tic</th>\n",
" <th>open</th>\n",
" <th>high</th>\n",
" <th>low</th>\n",
" <th>close</th>\n",
" <th>volume</th>\n",
" <th>OPM</th>\n",
" <th>NPM</th>\n",
" <th>ROA</th>\n",
" <th>...</th>\n",
" <th>quick_ratio</th>\n",
" <th>cash_ratio</th>\n",
" <th>inv_turnover</th>\n",
" <th>acc_rec_turnover</th>\n",
" <th>acc_pay_turnover</th>\n",
" <th>debt_ratio</th>\n",
" <th>debt_to_equity</th>\n",
" <th>PE</th>\n",
" <th>PB</th>\n",
" <th>Div_yield</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2009-01-01</td>\n",
" <td>AAPL</td>\n",
" <td>3.067143</td>\n",
" <td>3.251429</td>\n",
" <td>3.041429</td>\n",
" <td>2.767331</td>\n",
" <td>746015200.0</td>\n",
" <td>0.217886</td>\n",
" <td>0.163846</td>\n",
" <td>0.103222</td>\n",
" <td>...</td>\n",
" <td>2.039779</td>\n",
" <td>1.818995</td>\n",
" <td>54.403846</td>\n",
" <td>8.972003</td>\n",
" <td>4.269115</td>\n",
" <td>0.437727</td>\n",
" <td>0.778495</td>\n",
" <td>0.636168</td>\n",
" <td>0.101527</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2009-01-01</td>\n",
" <td>AMGN</td>\n",
" <td>58.590000</td>\n",
" <td>59.080002</td>\n",
" <td>57.750000</td>\n",
" <td>44.523754</td>\n",
" <td>6547900.0</td>\n",
" <td>0.125036</td>\n",
" <td>0.099890</td>\n",
" <td>0.019504</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.315453</td>\n",
" <td>0.692029</td>\n",
" <td>0.906079</td>\n",
" <td>9.647243</td>\n",
" <td>19.191273</td>\n",
" <td>4.361756</td>\n",
" <td>0.004043</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2009-01-01</td>\n",
" <td>AXP</td>\n",
" <td>18.570000</td>\n",
" <td>19.520000</td>\n",
" <td>18.400000</td>\n",
" <td>15.477422</td>\n",
" <td>10955700.0</td>\n",
" <td>0.093973</td>\n",
" <td>0.072040</td>\n",
" <td>0.014094</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.351354</td>\n",
" <td>0.653355</td>\n",
" <td>0.869784</td>\n",
" <td>6.679531</td>\n",
" <td>49.927167</td>\n",
" <td>1.433367</td>\n",
" <td>0.011630</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2009-01-01</td>\n",
" <td>BA</td>\n",
" <td>42.799999</td>\n",
" <td>45.560001</td>\n",
" <td>42.779999</td>\n",
" <td>33.941090</td>\n",
" <td>7010200.0</td>\n",
" <td>0.047307</td>\n",
" <td>0.032525</td>\n",
" <td>0.026400</td>\n",
" <td>...</td>\n",
" <td>0.368463</td>\n",
" <td>0.148507</td>\n",
" <td>2.329670</td>\n",
" <td>6.815203</td>\n",
" <td>2.076967</td>\n",
" <td>1.009198</td>\n",
" <td>-109.722986</td>\n",
" <td>39.012747</td>\n",
" <td>-35.751042</td>\n",
" <td>0.012374</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2009-01-01</td>\n",
" <td>CAT</td>\n",
" <td>44.910000</td>\n",
" <td>46.980000</td>\n",
" <td>44.709999</td>\n",
" <td>31.942242</td>\n",
" <td>7117200.0</td>\n",
" <td>0.124545</td>\n",
" <td>0.066662</td>\n",
" <td>0.040891</td>\n",
" <td>...</td>\n",
" <td>0.890488</td>\n",
" <td>0.163158</td>\n",
" <td>3.540791</td>\n",
" <td>2.460351</td>\n",
" <td>8.472455</td>\n",
" <td>0.893715</td>\n",
" <td>9.089489</td>\n",
" <td>-168.117061</td>\n",
" <td>3.083087</td>\n",
" <td>0.013149</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 22 columns</p>\n",
"</div>"
],
"text/plain": [
" date tic open high low close volume \\\n",
"0 2009-01-01 AAPL 3.067143 3.251429 3.041429 2.767331 746015200.0 \n",
"0 2009-01-01 AMGN 58.590000 59.080002 57.750000 44.523754 6547900.0 \n",
"0 2009-01-01 AXP 18.570000 19.520000 18.400000 15.477422 10955700.0 \n",
"0 2009-01-01 BA 42.799999 45.560001 42.779999 33.941090 7010200.0 \n",
"0 2009-01-01 CAT 44.910000 46.980000 44.709999 31.942242 7117200.0 \n",
"\n",
" OPM NPM ROA ... quick_ratio cash_ratio inv_turnover \\\n",
"0 0.217886 0.163846 0.103222 ... 2.039779 1.818995 54.403846 \n",
"0 0.125036 0.099890 0.019504 ... 0.000000 0.000000 0.000000 \n",
"0 0.093973 0.072040 0.014094 ... 0.000000 0.000000 0.000000 \n",
"0 0.047307 0.032525 0.026400 ... 0.368463 0.148507 2.329670 \n",
"0 0.124545 0.066662 0.040891 ... 0.890488 0.163158 3.540791 \n",
"\n",
" acc_rec_turnover acc_pay_turnover debt_ratio debt_to_equity PE \\\n",
"0 8.972003 4.269115 0.437727 0.778495 0.636168 \n",
"0 0.315453 0.692029 0.906079 9.647243 19.191273 \n",
"0 0.351354 0.653355 0.869784 6.679531 49.927167 \n",
"0 6.815203 2.076967 1.009198 -109.722986 39.012747 \n",
"0 2.460351 8.472455 0.893715 9.089489 -168.117061 \n",
"\n",
" PB Div_yield \n",
"0 0.101527 0.000000 \n",
"0 4.361756 0.004043 \n",
"0 1.433367 0.011630 \n",
"0 -35.751042 0.012374 \n",
"0 3.083087 0.013149 \n",
"\n",
"[5 rows x 22 columns]"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_data.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 386
},
"id": "k9zU9YaTTvFq",
"outputId": "3cdc86bc-e7b4-46d4-bfdf-d3b706da2351"
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>date</th>\n",
" <th>tic</th>\n",
" <th>open</th>\n",
" <th>high</th>\n",
" <th>low</th>\n",
" <th>close</th>\n",
" <th>volume</th>\n",
" <th>OPM</th>\n",
" <th>NPM</th>\n",
" <th>ROA</th>\n",
" <th>...</th>\n",
" <th>quick_ratio</th>\n",
" <th>cash_ratio</th>\n",
" <th>inv_turnover</th>\n",
" <th>acc_rec_turnover</th>\n",
" <th>acc_pay_turnover</th>\n",
" <th>debt_ratio</th>\n",
" <th>debt_to_equity</th>\n",
" <th>PE</th>\n",
" <th>PB</th>\n",
" <th>Div_yield</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2019-01-01</td>\n",
" <td>AAPL</td>\n",
" <td>38.722500</td>\n",
" <td>39.712502</td>\n",
" <td>38.557499</td>\n",
" <td>38.168350</td>\n",
" <td>148158800.0</td>\n",
" <td>0.258891</td>\n",
" <td>0.227773</td>\n",
" <td>0.133360</td>\n",
" <td>...</td>\n",
" <td>1.134347</td>\n",
" <td>0.854114</td>\n",
" <td>23.571867</td>\n",
" <td>7.620024</td>\n",
" <td>3.781658</td>\n",
" <td>0.690466</td>\n",
" <td>2.230663</td>\n",
" <td>5.696769</td>\n",
" <td>1.661179</td>\n",
" <td>0.019126</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2019-01-01</td>\n",
" <td>AMGN</td>\n",
" <td>192.520004</td>\n",
" <td>193.199997</td>\n",
" <td>188.949997</td>\n",
" <td>171.580231</td>\n",
" <td>3009100.0</td>\n",
" <td>0.125036</td>\n",
" <td>0.099890</td>\n",
" <td>0.019504</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.315453</td>\n",
" <td>0.692029</td>\n",
" <td>0.906079</td>\n",
" <td>9.647243</td>\n",
" <td>73.956996</td>\n",
" <td>16.808806</td>\n",
" <td>0.001049</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2019-01-01</td>\n",
" <td>AXP</td>\n",
" <td>93.910004</td>\n",
" <td>96.269997</td>\n",
" <td>93.769997</td>\n",
" <td>90.748329</td>\n",
" <td>4175400.0</td>\n",
" <td>0.203479</td>\n",
" <td>0.160494</td>\n",
" <td>0.026811</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.231669</td>\n",
" <td>0.279424</td>\n",
" <td>0.887329</td>\n",
" <td>7.875371</td>\n",
" <td>50.137198</td>\n",
" <td>3.418685</td>\n",
" <td>0.004298</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2019-01-01</td>\n",
" <td>BA</td>\n",
" <td>316.190002</td>\n",
" <td>323.950012</td>\n",
" <td>313.709991</td>\n",
" <td>314.645142</td>\n",
" <td>3292200.0</td>\n",
" <td>0.116496</td>\n",
" <td>0.102682</td>\n",
" <td>0.066409</td>\n",
" <td>...</td>\n",
" <td>0.262465</td>\n",
" <td>0.092436</td>\n",
" <td>0.933164</td>\n",
" <td>5.468453</td>\n",
" <td>4.151637</td>\n",
" <td>0.998070</td>\n",
" <td>517.142241</td>\n",
" <td>83.019826</td>\n",
" <td>1418.196271</td>\n",
" <td>0.006531</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2019-01-01</td>\n",
" <td>CAT</td>\n",
" <td>124.029999</td>\n",
" <td>127.879997</td>\n",
" <td>123.000000</td>\n",
" <td>114.941399</td>\n",
" <td>4783200.0</td>\n",
" <td>0.186871</td>\n",
" <td>0.107064</td>\n",
" <td>0.056932</td>\n",
" <td>...</td>\n",
" <td>0.919490</td>\n",
" <td>0.266175</td>\n",
" <td>2.135008</td>\n",
" <td>2.339630</td>\n",
" <td>3.660183</td>\n",
" <td>0.803394</td>\n",
" <td>4.086316</td>\n",
" <td>34.936595</td>\n",
" <td>4.256800</td>\n",
" <td>0.007482</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 22 columns</p>\n",
"</div>"
],
"text/plain": [
" date tic open high low close \\\n",
"0 2019-01-01 AAPL 38.722500 39.712502 38.557499 38.168350 \n",
"0 2019-01-01 AMGN 192.520004 193.199997 188.949997 171.580231 \n",
"0 2019-01-01 AXP 93.910004 96.269997 93.769997 90.748329 \n",
"0 2019-01-01 BA 316.190002 323.950012 313.709991 314.645142 \n",
"0 2019-01-01 CAT 124.029999 127.879997 123.000000 114.941399 \n",
"\n",
" volume OPM NPM ROA ... quick_ratio cash_ratio \\\n",
"0 148158800.0 0.258891 0.227773 0.133360 ... 1.134347 0.854114 \n",
"0 3009100.0 0.125036 0.099890 0.019504 ... 0.000000 0.000000 \n",
"0 4175400.0 0.203479 0.160494 0.026811 ... 0.000000 0.000000 \n",
"0 3292200.0 0.116496 0.102682 0.066409 ... 0.262465 0.092436 \n",
"0 4783200.0 0.186871 0.107064 0.056932 ... 0.919490 0.266175 \n",
"\n",
" inv_turnover acc_rec_turnover acc_pay_turnover debt_ratio \\\n",
"0 23.571867 7.620024 3.781658 0.690466 \n",
"0 0.000000 0.315453 0.692029 0.906079 \n",
"0 0.000000 0.231669 0.279424 0.887329 \n",
"0 0.933164 5.468453 4.151637 0.998070 \n",
"0 2.135008 2.339630 3.660183 0.803394 \n",
"\n",
" debt_to_equity PE PB Div_yield \n",
"0 2.230663 5.696769 1.661179 0.019126 \n",
"0 9.647243 73.956996 16.808806 0.001049 \n",
"0 7.875371 50.137198 3.418685 0.004298 \n",
"0 517.142241 83.019826 1418.196271 0.006531 \n",
"0 4.086316 34.936595 4.256800 0.007482 \n",
"\n",
"[5 rows x 22 columns]"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"trade_data.head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "qqGG78pLyCX7"
},
"source": [
"## 5.2 Set up the training environment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "LPD0wZLO-Pse"
},
"outputs": [],
"source": [
"import gym\n",
"import matplotlib\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"import pandas as pd\n",
"from gym import spaces\n",
"from gym.utils import seeding\n",
"from stable_baselines3.common.vec_env import DummyVecEnv\n",
"\n",
"matplotlib.use(\"Agg\")\n",
"\n",
"# from stable_baselines3.common import logger\n",
"\n",
"\n",
"class StockTradingEnv(gym.Env):\n",
" \"\"\"A stock trading environment for OpenAI gym\"\"\"\n",
"\n",
" metadata = {\"render.modes\": [\"human\"]}\n",
"\n",
" def __init__(\n",
" self,\n",
" df,\n",
" stock_dim,\n",
" hmax,\n",
" initial_amount,\n",
" buy_cost_pct,\n",
" sell_cost_pct,\n",
" reward_scaling,\n",
" state_space,\n",
" action_space,\n",
" tech_indicator_list,\n",
" turbulence_threshold=None,\n",
" risk_indicator_col=\"turbulence\",\n",
" make_plots=False,\n",
" print_verbosity=10,\n",
" day=0,\n",
" initial=True,\n",
" previous_state=[],\n",
" model_name=\"\",\n",
" mode=\"\",\n",
" iteration=\"\",\n",
" ):\n",
" self.day = day\n",
" self.df = df\n",
" self.stock_dim = stock_dim\n",
" self.hmax = hmax\n",
" self.initial_amount = initial_amount\n",
" self.buy_cost_pct = buy_cost_pct\n",
" self.sell_cost_pct = sell_cost_pct\n",
" self.reward_scaling = reward_scaling\n",
" self.state_space = state_space\n",
" self.action_space = action_space\n",
" self.tech_indicator_list = tech_indicator_list\n",
" self.action_space = spaces.Box(low=-1, high=1, shape=(self.action_space,))\n",
" self.observation_space = spaces.Box(\n",
" low=-np.inf, high=np.inf, shape=(self.state_space,)\n",
" )\n",
" self.data = self.df.loc[self.day, :]\n",
" self.terminal = False\n",
" self.make_plots = make_plots\n",
" self.print_verbosity = print_verbosity\n",
" self.turbulence_threshold = turbulence_threshold\n",
" self.risk_indicator_col = risk_indicator_col\n",
" self.initial = initial\n",
" self.previous_state = previous_state\n",
" self.model_name = model_name\n",
" self.mode = mode\n",
" self.iteration = iteration\n",
" # initalize state\n",
" self.state = self._initiate_state()\n",
"\n",
" # initialize reward\n",
" self.reward = 0\n",
" self.turbulence = 0\n",
" self.cost = 0\n",
" self.trades = 0\n",
" self.episode = 0\n",
" # memorize all the total balance change\n",
" self.asset_memory = [self.initial_amount]\n",
" self.rewards_memory = []\n",
" self.actions_memory = []\n",
" self.date_memory = [self._get_date()]\n",
" # self.reset()\n",
" self._seed()\n",
"\n",
" def _sell_stock(self, index, action):\n",
" def _do_sell_normal():\n",
" if self.state[index + 1] > 0:\n",
" # Sell only if the price is > 0 (no missing data in this particular date)\n",
" # perform sell action based on the sign of the action\n",
" if self.state[index + self.stock_dim + 1] > 0:\n",
" # Sell only if current asset is > 0\n",
" sell_num_shares = min(\n",
" abs(action), self.state[index + self.stock_dim + 1]\n",
" )\n",
" sell_amount = (\n",
" self.state[index + 1]\n",
" * sell_num_shares\n",
" * (1 - self.sell_cost_pct)\n",
" )\n",
" # update balance\n",
" self.state[0] += sell_amount\n",
"\n",
" self.state[index + self.stock_dim + 1] -= sell_num_shares\n",
" self.cost += (\n",
" self.state[index + 1] * sell_num_shares * self.sell_cost_pct\n",
" )\n",
" self.trades += 1\n",
" else:\n",
" sell_num_shares = 0\n",
" else:\n",
" sell_num_shares = 0\n",
"\n",
" return sell_num_shares\n",
"\n",
" # perform sell action based on the sign of the action\n",
" if self.turbulence_threshold is not None:\n",
" if self.turbulence >= self.turbulence_threshold:\n",
" if self.state[index + 1] > 0:\n",
" # Sell only if the price is > 0 (no missing data in this particular date)\n",
" # if turbulence goes over threshold, just clear out all positions\n",
" if self.state[index + self.stock_dim + 1] > 0:\n",
" # Sell only if current asset is > 0\n",
" sell_num_shares = self.state[index + self.stock_dim + 1]\n",
" sell_amount = (\n",
" self.state[index + 1]\n",
" * sell_num_shares\n",
" * (1 - self.sell_cost_pct)\n",
" )\n",
" # update balance\n",
" self.state[0] += sell_amount\n",
" self.state[index + self.stock_dim + 1] = 0\n",
" self.cost += (\n",
" self.state[index + 1] * sell_num_shares * self.sell_cost_pct\n",
" )\n",
" self.trades += 1\n",
" else:\n",
" sell_num_shares = 0\n",
" else:\n",
" sell_num_shares = 0\n",
" else:\n",
" sell_num_shares = _do_sell_normal()\n",
" else:\n",
" sell_num_shares = _do_sell_normal()\n",
"\n",
" return sell_num_shares\n",
"\n",
" def _buy_stock(self, index, action):\n",
" def _do_buy():\n",
" if self.state[index + 1] > 0:\n",
" # Buy only if the price is > 0 (no missing data in this particular date)\n",
" available_amount = self.state[0] // self.state[index + 1]\n",
" # print('available_amount:{}'.format(available_amount))\n",
"\n",
" # update balance\n",
" buy_num_shares = min(available_amount, action)\n",
" buy_amount = (\n",
" self.state[index + 1] * buy_num_shares * (1 + self.buy_cost_pct)\n",
" )\n",
" self.state[0] -= buy_amount\n",
"\n",
" self.state[index + self.stock_dim + 1] += buy_num_shares\n",
"\n",
" self.cost += self.state[index + 1] * buy_num_shares * self.buy_cost_pct\n",
" self.trades += 1\n",
" else:\n",
" buy_num_shares = 0\n",
"\n",
" return buy_num_shares\n",
"\n",
" # perform buy action based on the sign of the action\n",
" if self.turbulence_threshold is None:\n",
" buy_num_shares = _do_buy()\n",
" else:\n",
" if self.turbulence < self.turbulence_threshold:\n",
" buy_num_shares = _do_buy()\n",
" else:\n",
" buy_num_shares = 0\n",
" pass\n",
"\n",
" return buy_num_shares\n",
"\n",
" def _make_plot(self):\n",
" plt.plot(self.asset_memory, \"r\")\n",
" plt.savefig(\"results/account_value_trade_{}.png\".format(self.episode))\n",
" plt.close()\n",
"\n",
" def step(self, actions):\n",
" self.terminal = self.day >= len(self.df.index.unique()) - 1\n",
" if self.terminal:\n",
" # print(f\"Episode: {self.episode}\")\n",
" if self.make_plots:\n",
" self._make_plot()\n",
" end_total_asset = self.state[0] + sum(\n",
" np.array(self.state[1 : (self.stock_dim + 1)])\n",
" * np.array(self.state[(self.stock_dim + 1) : (self.stock_dim * 2 + 1)])\n",
" )\n",
" df_total_value = pd.DataFrame(self.asset_memory)\n",
" tot_reward = (\n",
" self.state[0]\n",
" + sum(\n",
" np.array(self.state[1 : (self.stock_dim + 1)])\n",
" * np.array(\n",
" self.state[(self.stock_dim + 1) : (self.stock_dim * 2 + 1)]\n",
" )\n",
" )\n",
" - self.initial_amount\n",
" )\n",
" df_total_value.columns = [\"account_value\"]\n",
" df_total_value[\"date\"] = self.date_memory\n",
" df_total_value[\"daily_return\"] = df_total_value[\"account_value\"].pct_change(\n",
" 1\n",
" )\n",
" if df_total_value[\"daily_return\"].std() != 0:\n",
" sharpe = (\n",
" (252 ** 0.5)\n",
" * df_total_value[\"daily_return\"].mean()\n",
" / df_total_value[\"daily_return\"].std()\n",
" )\n",
" df_rewards = pd.DataFrame(self.rewards_memory)\n",
" df_rewards.columns = [\"account_rewards\"]\n",
" df_rewards[\"date\"] = self.date_memory[:-1]\n",
" if self.episode % self.print_verbosity == 0:\n",
" print(f\"day: {self.day}, episode: {self.episode}\")\n",
" print(f\"begin_total_asset: {self.asset_memory[0]:0.2f}\")\n",
" print(f\"end_total_asset: {end_total_asset:0.2f}\")\n",
" print(f\"total_reward: {tot_reward:0.2f}\")\n",
" print(f\"total_cost: {self.cost:0.2f}\")\n",
" print(f\"total_trades: {self.trades}\")\n",
" if df_total_value[\"daily_return\"].std() != 0:\n",
" print(f\"Sharpe: {sharpe:0.3f}\")\n",
" print(\"=================================\")\n",
"\n",
" if (self.model_name != \"\") and (self.mode != \"\"):\n",
" df_actions = self.save_action_memory()\n",
" df_actions.to_csv(\n",
" \"results/actions_{}_{}_{}.csv\".format(\n",
" self.mode, self.model_name, self.iteration\n",
" )\n",
" )\n",
" df_total_value.to_csv(\n",
" \"results/account_value_{}_{}_{}.csv\".format(\n",
" self.mode, self.model_name, self.iteration\n",
" ),\n",
" index=False,\n",
" )\n",
" df_rewards.to_csv(\n",
" \"results/account_rewards_{}_{}_{}.csv\".format(\n",
" self.mode, self.model_name, self.iteration\n",
" ),\n",
" index=False,\n",
" )\n",
" plt.plot(self.asset_memory, \"r\")\n",
" plt.savefig(\n",
" \"results/account_value_{}_{}_{}.png\".format(\n",
" self.mode, self.model_name, self.iteration\n",
" ),\n",
" index=False,\n",
" )\n",
" plt.close()\n",
"\n",
" # Add outputs to logger interface\n",
" # logger.record(\"environment/portfolio_value\", end_total_asset)\n",
" # logger.record(\"environment/total_reward\", tot_reward)\n",
" # logger.record(\"environment/total_reward_pct\", (tot_reward / (end_total_asset - tot_reward)) * 100)\n",
" # logger.record(\"environment/total_cost\", self.cost)\n",
" # logger.record(\"environment/total_trades\", self.trades)\n",
"\n",
" return self.state, self.reward, self.terminal, {}\n",
"\n",
" else:\n",
"\n",
" actions = actions * self.hmax # actions initially is scaled between 0 to 1\n",
" actions = actions.astype(\n",
" int\n",
" ) # convert into integer because we can't by fraction of shares\n",
" if self.turbulence_threshold is not None:\n",
" if self.turbulence >= self.turbulence_threshold:\n",
" actions = np.array([-self.hmax] * self.stock_dim)\n",
" begin_total_asset = self.state[0] + sum(\n",
" np.array(self.state[1 : (self.stock_dim + 1)])\n",
" * np.array(self.state[(self.stock_dim + 1) : (self.stock_dim * 2 + 1)])\n",
" )\n",
" # print(\"begin_total_asset:{}\".format(begin_total_asset))\n",
"\n",
" argsort_actions = np.argsort(actions)\n",
"\n",
" sell_index = argsort_actions[: np.where(actions < 0)[0].shape[0]]\n",
" buy_index = argsort_actions[::-1][: np.where(actions > 0)[0].shape[0]]\n",
"\n",
" for index in sell_index:\n",
" # print(f\"Num shares before: {self.state[index+self.stock_dim+1]}\")\n",
" # print(f'take sell action before : {actions[index]}')\n",
" actions[index] = self._sell_stock(index, actions[index]) * (-1)\n",
" # print(f'take sell action after : {actions[index]}')\n",
" # print(f\"Num shares after: {self.state[index+self.stock_dim+1]}\")\n",
"\n",
" for index in buy_index:\n",
" # print('take buy action: {}'.format(actions[index]))\n",
" actions[index] = self._buy_stock(index, actions[index])\n",
"\n",
" self.actions_memory.append(actions)\n",
"\n",
" # state: s -> s+1\n",
" self.day += 1\n",
" self.data = self.df.loc[self.day, :]\n",
" if self.turbulence_threshold is not None:\n",
" if len(self.df.tic.unique()) == 1:\n",
" self.turbulence = self.data[self.risk_indicator_col]\n",
" elif len(self.df.tic.unique()) > 1:\n",
" self.turbulence = self.data[self.risk_indicator_col].values[0]\n",
" self.state = self._update_state()\n",
"\n",
" end_total_asset = self.state[0] + sum(\n",
" np.array(self.state[1 : (self.stock_dim + 1)])\n",
" * np.array(self.state[(self.stock_dim + 1) : (self.stock_dim * 2 + 1)])\n",
" )\n",
" self.asset_memory.append(end_total_asset)\n",
" self.date_memory.append(self._get_date())\n",
" self.reward = end_total_asset - begin_total_asset\n",
" self.rewards_memory.append(self.reward)\n",
" self.reward = self.reward * self.reward_scaling\n",
"\n",
" return self.state, self.reward, self.terminal, {}\n",
"\n",
" def reset(self):\n",
" # initiate state\n",
" self.state = self._initiate_state()\n",
"\n",
" if self.initial:\n",
" self.asset_memory = [self.initial_amount]\n",
" else:\n",
" previous_total_asset = self.previous_state[0] + sum(\n",
" np.array(self.state[1 : (self.stock_dim + 1)])\n",
" * np.array(\n",
" self.previous_state[(self.stock_dim + 1) : (self.stock_dim * 2 + 1)]\n",
" )\n",
" )\n",
" self.asset_memory = [previous_total_asset]\n",
"\n",
" self.day = 0\n",
" self.data = self.df.loc[self.day, :]\n",
" self.turbulence = 0\n",
" self.cost = 0\n",
" self.trades = 0\n",
" self.terminal = False\n",
" # self.iteration=self.iteration\n",
" self.rewards_memory = []\n",
" self.actions_memory = []\n",
" self.date_memory = [self._get_date()]\n",
"\n",
" self.episode += 1\n",
"\n",
" return self.state\n",
"\n",
" def render(self, mode=\"human\", close=False):\n",
" return self.state\n",
"\n",
" def _initiate_state(self):\n",
" if self.initial:\n",
" # For Initial State\n",
" if len(self.df.tic.unique()) > 1:\n",
" # for multiple stock\n",
" state = (\n",
" [self.initial_amount]\n",
" + self.data.close.values.tolist()\n",
" + [0] * self.stock_dim\n",
" + sum(\n",
" [\n",
" self.data[tech].values.tolist()\n",
" for tech in self.tech_indicator_list\n",
" ],\n",
" [],\n",
" )\n",
" )\n",
" else:\n",
" # for single stock\n",
" state = (\n",
" [self.initial_amount]\n",
" + [self.data.close]\n",
" + [0] * self.stock_dim\n",
" + sum([[self.data[tech]] for tech in self.tech_indicator_list], [])\n",
" )\n",
" else:\n",
" # Using Previous State\n",
" if len(self.df.tic.unique()) > 1:\n",
" # for multiple stock\n",
" state = (\n",
" [self.previous_state[0]]\n",
" + self.data.close.values.tolist()\n",
" + self.previous_state[\n",
" (self.stock_dim + 1) : (self.stock_dim * 2 + 1)\n",
" ]\n",
" + sum(\n",
" [\n",
" self.data[tech].values.tolist()\n",
" for tech in self.tech_indicator_list\n",
" ],\n",
" [],\n",
" )\n",
" )\n",
" else:\n",
" # for single stock\n",
" state = (\n",
" [self.previous_state[0]]\n",
" + [self.data.close]\n",
" + self.previous_state[\n",
" (self.stock_dim + 1) : (self.stock_dim * 2 + 1)\n",
" ]\n",
" + sum([[self.data[tech]] for tech in self.tech_indicator_list], [])\n",
" )\n",
" return state\n",
"\n",
" def _update_state(self):\n",
" if len(self.df.tic.unique()) > 1:\n",
" # for multiple stock\n",
" state = (\n",
" [self.state[0]]\n",
" + self.data.close.values.tolist()\n",
" + list(self.state[(self.stock_dim + 1) : (self.stock_dim * 2 + 1)])\n",
" + sum(\n",
" [\n",
" self.data[tech].values.tolist()\n",
" for tech in self.tech_indicator_list\n",
" ],\n",
" [],\n",
" )\n",
" )\n",
"\n",
" else:\n",
" # for single stock\n",
" state = (\n",
" [self.state[0]]\n",
" + [self.data.close]\n",
" + list(self.state[(self.stock_dim + 1) : (self.stock_dim * 2 + 1)])\n",
" + sum([[self.data[tech]] for tech in self.tech_indicator_list], [])\n",
" )\n",
" return state\n",
"\n",
" def _get_date(self):\n",
" if len(self.df.tic.unique()) > 1:\n",
" date = self.data.date.unique()[0]\n",
" else:\n",
" date = self.data.date\n",
" return date\n",
"\n",
" def save_asset_memory(self):\n",
" date_list = self.date_memory\n",
" asset_list = self.asset_memory\n",
" # print(len(date_list))\n",
" # print(len(asset_list))\n",
" df_account_value = pd.DataFrame(\n",
" {\"date\": date_list, \"account_value\": asset_list}\n",
" )\n",
" return df_account_value\n",
"\n",
" def save_action_memory(self):\n",
" if len(self.df.tic.unique()) > 1:\n",
" # date and close price length must match actions length\n",
" date_list = self.date_memory[:-1]\n",
" df_date = pd.DataFrame(date_list)\n",
" df_date.columns = [\"date\"]\n",
"\n",
" action_list = self.actions_memory\n",
" df_actions = pd.DataFrame(action_list)\n",
" df_actions.columns = self.data.tic.values\n",
" df_actions.index = df_date.date\n",
" # df_actions = pd.DataFrame({'date':date_list,'actions':action_list})\n",
" else:\n",
" date_list = self.date_memory[:-1]\n",
" action_list = self.actions_memory\n",
" df_actions = pd.DataFrame({\"date\": date_list, \"actions\": action_list})\n",
" return df_actions\n",
"\n",
" def _seed(self, seed=None):\n",
" self.np_random, seed = seeding.np_random(seed)\n",
" return [seed]\n",
"\n",
" def get_sb_env(self):\n",
" e = DummyVecEnv([lambda: self])\n",
" obs = e.reset()\n",
" return e, obs"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Q2zqII8rMIqn",
"outputId": "b7deda63-17d4-421d-cf1c-102f08bcc151"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Stock Dimension: 30, State Space: 511\n"
]
}
],
"source": [
"ratio_list = ['OPM', 'NPM','ROA', 'ROE', 'cur_ratio', 'quick_ratio', 'cash_ratio', 'inv_turnover','acc_rec_turnover', 'acc_pay_turnover', 'debt_ratio', 'debt_to_equity',\n",
" 'PE', 'PB', 'Div_yield']\n",
"\n",
"stock_dimension = len(train_data.tic.unique())\n",
"state_space = 1 + 2*stock_dimension + len(ratio_list)*stock_dimension\n",
"print(f\"Stock Dimension: {stock_dimension}, State Space: {state_space}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "AWyp84Ltto19"
},
"outputs": [],
"source": [
"# Parameters for the environment\n",
"env_kwargs = {\n",
" \"hmax\": 100,\n",
" \"initial_amount\": 1000000,\n",
" \"buy_cost_pct\": 0.001,\n",
" \"sell_cost_pct\": 0.001,\n",
" \"state_space\": state_space,\n",
" \"stock_dim\": stock_dimension,\n",
" \"tech_indicator_list\": ratio_list,\n",
" \"action_space\": stock_dimension,\n",
" \"reward_scaling\": 1e-4\n",
"\n",
"}\n",
"\n",
"#Establish the training environment using StockTradingEnv() class\n",
"e_train_gym = StockTradingEnv(df = train_data, **env_kwargs)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "64EoqOrQjiVf"
},
"source": [
"## Environment for Training\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "xwSvvPjutpqS",
"outputId": "199470fd-2620-47ca-c3de-307b851dcaff"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'stable_baselines3.common.vec_env.dummy_vec_env.DummyVecEnv'>\n"
]
}
],
"source": [
"env_train, _ = e_train_gym.get_sb_env()\n",
"print(type(env_train))"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HMNR5nHjh1iz"
},
"source": [
"<a id='5'></a>\n",
"# Part 6: Train DRL Agents\n",
"* The DRL algorithms are from **Stable Baselines 3**. Users are also encouraged to try **ElegantRL** and **Ray RLlib**.\n",
"* FinRL library includes fine-tuned standard DRL algorithms, such as DQN, DDPG,\n",
"Multi-Agent DDPG, PPO, SAC, A2C and TD3. We also allow users to\n",
"design their own DRL algorithms by adapting these DRL algorithms."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "364PsqckttcQ"
},
"outputs": [],
"source": [
"# Set up the agent using DRLAgent() class using the environment created in the previous part\n",
"agent = DRLAgent(env = env_train)\n",
"\n",
"if_using_a2c = False\n",
"if_using_ddpg = False\n",
"if_using_ppo = False\n",
"if_using_td3 = False\n",
"if_using_sac = True"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "YDmqOyF9h1iz"
},
"source": [
"### Agent Training: 5 algorithms (A2C, DDPG, PPO, TD3, SAC)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "_gDkU-j-fCmZ"
},
"source": [
"### Model 1: PPO"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "y5D5PFUhMzSV",
"outputId": "002fa6dd-6f39-4ef4-e077-1a0774d4feb9"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'n_steps': 2048, 'ent_coef': 0.01, 'learning_rate': 0.00025, 'batch_size': 128}\n",
"Using cpu device\n"
]
}
],
"source": [
"agent = DRLAgent(env = env_train)\n",
"PPO_PARAMS = {\n",
" \"n_steps\": 2048,\n",
" \"ent_coef\": 0.01,\n",
" \"learning_rate\": 0.00025,\n",
" \"batch_size\": 128,\n",
"}\n",
"model_ppo = agent.get_model(\"ppo\",model_kwargs = PPO_PARAMS)\n",
"\n",
"if if_using_ppo:\n",
" # set up logger\n",
" tmp_path = RESULTS_DIR + '/ppo'\n",
" new_logger_ppo = configure(tmp_path, [\"stdout\", \"csv\", \"tensorboard\"])\n",
" # Set new logger\n",
" model_ppo.set_logger(new_logger_ppo)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Gt8eIQKYM4G3"
},
"outputs": [],
"source": [
"trained_ppo = agent.train_model(model=model_ppo,\n",
" tb_log_name='ppo',\n",
" total_timesteps=50000) if if_using_ppo else None"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "MRiOtrywfAo1"
},
"source": [
"### Model 2: DDPG"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "M2YadjfnLwgt",
"outputId": "53b3e7a9-5a5f-4c0a-db24-66667962436c"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'batch_size': 128, 'buffer_size': 50000, 'learning_rate': 0.001}\n",
"Using cpu device\n"
]
}
],
"source": [
"agent = DRLAgent(env = env_train)\n",
"model_ddpg = agent.get_model(\"ddpg\")\n",
"\n",
"if if_using_ddpg:\n",
" # set up logger\n",
" tmp_path = RESULTS_DIR + '/ddpg'\n",
" new_logger_ddpg = configure(tmp_path, [\"stdout\", \"csv\", \"tensorboard\"])\n",
" # Set new logger\n",
" model_ddpg.set_logger(new_logger_ddpg)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true,
"id": "tCDa78rqfO_a"
},
"outputs": [],
"source": [
"trained_ddpg = agent.train_model(model=model_ddpg,\n",
" tb_log_name='ddpg',\n",
" total_timesteps=50000) if if_using_ddpg else None"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "uijiWgkuh1jB"
},
"source": [
"### Model 3: A2C\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "GUCnkn-HIbmj",
"outputId": "a8d5a6e9-2ea1-49f4-ade3-40fd640a2ba4"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'n_steps': 5, 'ent_coef': 0.01, 'learning_rate': 0.0007}\n",
"Using cpu device\n"
]
}
],
"source": [
"agent = DRLAgent(env = env_train)\n",
"model_a2c = agent.get_model(\"a2c\")\n",
"\n",
"if if_using_a2c:\n",
" # set up logger\n",
" tmp_path = RESULTS_DIR + '/a2c'\n",
" new_logger_a2c = configure(tmp_path, [\"stdout\", \"csv\", \"tensorboard\"])\n",
" # Set new logger\n",
" model_a2c.set_logger(new_logger_a2c)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "0GVpkWGqH4-D"
},
"outputs": [],
"source": [
"trained_a2c = agent.train_model(model=model_a2c,\n",
" tb_log_name='a2c',\n",
" total_timesteps=50000) if if_using_a2c else None"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "3Zpv4S0-fDBv"
},
"source": [
"### Model 4: TD3"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "JSAHhV4Xc-bh",
"outputId": "ee6723fd-a659-4764-8905-61e8c8f85124"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'batch_size': 100, 'buffer_size': 1000000, 'learning_rate': 0.001}\n",
"Using cpu device\n"
]
}
],
"source": [
"agent = DRLAgent(env = env_train)\n",
"TD3_PARAMS = {\"batch_size\": 100,\n",
" \"buffer_size\": 1000000,\n",
" \"learning_rate\": 0.001}\n",
"\n",
"model_td3 = agent.get_model(\"td3\",model_kwargs = TD3_PARAMS)\n",
"\n",
"if if_using_td3:\n",
" # set up logger\n",
" tmp_path = RESULTS_DIR + '/td3'\n",
" new_logger_td3 = configure(tmp_path, [\"stdout\", \"csv\", \"tensorboard\"])\n",
" # Set new logger\n",
" model_td3.set_logger(new_logger_td3)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "OSRxNYAxdKpU"
},
"outputs": [],
"source": [
"trained_td3 = agent.train_model(model=model_td3,\n",
" tb_log_name='td3',\n",
" total_timesteps=30000) if if_using_td3 else None"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Dr49PotrfG01"
},
"source": [
"### Model 5: SAC"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "xwOhVjqRkCdM",
"outputId": "a7947b0e-e8fe-4f42-8cba-a57b0fe69f58"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'batch_size': 128, 'buffer_size': 1000000, 'learning_rate': 0.0001, 'learning_starts': 100, 'ent_coef': 'auto_0.1'}\n",
"Using cpu device\n",
"Logging to results/sac\n"
]
}
],
"source": [
"agent = DRLAgent(env = env_train)\n",
"SAC_PARAMS = {\n",
" \"batch_size\": 128,\n",
" \"buffer_size\": 1000000,\n",
" \"learning_rate\": 0.0001,\n",
" \"learning_starts\": 100,\n",
" \"ent_coef\": \"auto_0.1\",\n",
"}\n",
"\n",
"model_sac = agent.get_model(\"sac\",model_kwargs = SAC_PARAMS)\n",
"\n",
"if if_using_sac:\n",
" # set up logger\n",
" tmp_path = RESULTS_DIR + '/sac'\n",
" new_logger_sac = configure(tmp_path, [\"stdout\", \"csv\", \"tensorboard\"])\n",
" # Set new logger\n",
" model_sac.set_logger(new_logger_sac)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 750
},
"id": "K8RSdKCckJyH",
"outputId": "a293320f-54e9-431b-8f17-2f8e0b47a6b8"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------\n",
"| time/ | |\n",
"| episodes | 4 |\n",
"| fps | 27 |\n",
"| time_elapsed | 536 |\n",
"| total_timesteps | 14608 |\n",
"| train/ | |\n",
"| actor_loss | 134 |\n",
"| critic_loss | 558 |\n",
"| ent_coef | 0.0473 |\n",
"| ent_coef_loss | -141 |\n",
"| learning_rate | 0.0001 |\n",
"| n_updates | 14507 |\n",
"| reward | -0.0059304885 |\n",
"--------------------------------------\n",
"---------------------------------\n",
"| time/ | |\n",
"| episodes | 8 |\n",
"| fps | 24 |\n",
"| time_elapsed | 1198 |\n",
"| total_timesteps | 29216 |\n",
"| train/ | |\n",
"| actor_loss | 34.4 |\n",
"| critic_loss | 6.09 |\n",
"| ent_coef | 0.0112 |\n",
"| ent_coef_loss | -168 |\n",
"| learning_rate | 0.0001 |\n",
"| n_updates | 29115 |\n",
"| reward | 0.0 |\n",
"---------------------------------\n"
]
}
],
"source": [
"trained_sac = agent.train_model(model=model_sac,\n",
" tb_log_name='sac',\n",
" total_timesteps=30000) if if_using_sac else None"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "f2wZgkQXh1jE"
},
"source": [
"## Trading\n",
"Assume that we have $1,000,000 initial capital at TEST_START_DATE. We use the DDPG model to trade Dow jones 30 stocks."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "U5mmgQF_h1jQ"
},
"source": [
"### Trade\n",
"\n",
"DRL model needs to update periodically in order to take full advantage of the data, ideally we need to retrain our model yearly, quarterly, or monthly. We also need to tune the parameters along the way, in this notebook I only use the in-sample data from 2009-01 to 2018-12 to tune the parameters once, so there is some alpha decay here as the length of trade date extends.\n",
"\n",
"Numerous hyperparameters – e.g. the learning rate, the total number of samples to train on – influence the learning process and are usually determined by testing some variations."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "cIqoV0GSI52v"
},
"outputs": [],
"source": [
"trade_data = data_split(processed_full, TEST_START_DATE, TEST_END_DATE)\n",
"e_trade_gym = StockTradingEnv(df = trade_data, **env_kwargs)\n",
"# env_trade, obs_trade = e_trade_gym.get_sb_env()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "W_XNgGsBMeVw",
"outputId": "79b4ba94-ef3d-493a-c890-5ddea53cca6a"
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>date</th>\n",
" <th>tic</th>\n",
" <th>open</th>\n",
" <th>high</th>\n",
" <th>low</th>\n",
" <th>close</th>\n",
" <th>volume</th>\n",
" <th>OPM</th>\n",
" <th>NPM</th>\n",
" <th>ROA</th>\n",
" <th>...</th>\n",
" <th>quick_ratio</th>\n",
" <th>cash_ratio</th>\n",
" <th>inv_turnover</th>\n",
" <th>acc_rec_turnover</th>\n",
" <th>acc_pay_turnover</th>\n",
" <th>debt_ratio</th>\n",
" <th>debt_to_equity</th>\n",
" <th>PE</th>\n",
" <th>PB</th>\n",
" <th>Div_yield</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2019-01-01</td>\n",
" <td>AAPL</td>\n",
" <td>38.722500</td>\n",
" <td>39.712502</td>\n",
" <td>38.557499</td>\n",
" <td>38.168350</td>\n",
" <td>148158800.0</td>\n",
" <td>0.258891</td>\n",
" <td>0.227773</td>\n",
" <td>0.133360</td>\n",
" <td>...</td>\n",
" <td>1.134347</td>\n",
" <td>0.854114</td>\n",
" <td>23.571867</td>\n",
" <td>7.620024</td>\n",
" <td>3.781658</td>\n",
" <td>0.690466</td>\n",
" <td>2.230663</td>\n",
" <td>5.696769</td>\n",
" <td>1.661179</td>\n",
" <td>0.019126</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2019-01-01</td>\n",
" <td>AMGN</td>\n",
" <td>192.520004</td>\n",
" <td>193.199997</td>\n",
" <td>188.949997</td>\n",
" <td>171.580231</td>\n",
" <td>3009100.0</td>\n",
" <td>0.125036</td>\n",
" <td>0.099890</td>\n",
" <td>0.019504</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.315453</td>\n",
" <td>0.692029</td>\n",
" <td>0.906079</td>\n",
" <td>9.647243</td>\n",
" <td>73.956996</td>\n",
" <td>16.808806</td>\n",
" <td>0.001049</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2019-01-01</td>\n",
" <td>AXP</td>\n",
" <td>93.910004</td>\n",
" <td>96.269997</td>\n",
" <td>93.769997</td>\n",
" <td>90.748329</td>\n",
" <td>4175400.0</td>\n",
" <td>0.203479</td>\n",
" <td>0.160494</td>\n",
" <td>0.026811</td>\n",
" <td>...</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.231669</td>\n",
" <td>0.279424</td>\n",
" <td>0.887329</td>\n",
" <td>7.875371</td>\n",
" <td>50.137198</td>\n",
" <td>3.418685</td>\n",
" <td>0.004298</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2019-01-01</td>\n",
" <td>BA</td>\n",
" <td>316.190002</td>\n",
" <td>323.950012</td>\n",
" <td>313.709991</td>\n",
" <td>314.645142</td>\n",
" <td>3292200.0</td>\n",
" <td>0.116496</td>\n",
" <td>0.102682</td>\n",
" <td>0.066409</td>\n",
" <td>...</td>\n",
" <td>0.262465</td>\n",
" <td>0.092436</td>\n",
" <td>0.933164</td>\n",
" <td>5.468453</td>\n",
" <td>4.151637</td>\n",
" <td>0.998070</td>\n",
" <td>517.142241</td>\n",
" <td>83.019826</td>\n",
" <td>1418.196271</td>\n",
" <td>0.006531</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2019-01-01</td>\n",
" <td>CAT</td>\n",
" <td>124.029999</td>\n",
" <td>127.879997</td>\n",
" <td>123.000000</td>\n",
" <td>114.941399</td>\n",
" <td>4783200.0</td>\n",
" <td>0.186871</td>\n",
" <td>0.107064</td>\n",
" <td>0.056932</td>\n",
" <td>...</td>\n",
" <td>0.919490</td>\n",
" <td>0.266175</td>\n",
" <td>2.135008</td>\n",
" <td>2.339630</td>\n",
" <td>3.660183</td>\n",
" <td>0.803394</td>\n",
" <td>4.086316</td>\n",
" <td>34.936595</td>\n",
" <td>4.256800</td>\n",
" <td>0.007482</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 22 columns</p>\n",
"</div>"
],
"text/plain": [
" date tic open high low close \\\n",
"0 2019-01-01 AAPL 38.722500 39.712502 38.557499 38.168350 \n",
"0 2019-01-01 AMGN 192.520004 193.199997 188.949997 171.580231 \n",
"0 2019-01-01 AXP 93.910004 96.269997 93.769997 90.748329 \n",
"0 2019-01-01 BA 316.190002 323.950012 313.709991 314.645142 \n",
"0 2019-01-01 CAT 124.029999 127.879997 123.000000 114.941399 \n",
"\n",
" volume OPM NPM ROA ... quick_ratio cash_ratio \\\n",
"0 148158800.0 0.258891 0.227773 0.133360 ... 1.134347 0.854114 \n",
"0 3009100.0 0.125036 0.099890 0.019504 ... 0.000000 0.000000 \n",
"0 4175400.0 0.203479 0.160494 0.026811 ... 0.000000 0.000000 \n",
"0 3292200.0 0.116496 0.102682 0.066409 ... 0.262465 0.092436 \n",
"0 4783200.0 0.186871 0.107064 0.056932 ... 0.919490 0.266175 \n",
"\n",
" inv_turnover acc_rec_turnover acc_pay_turnover debt_ratio \\\n",
"0 23.571867 7.620024 3.781658 0.690466 \n",
"0 0.000000 0.315453 0.692029 0.906079 \n",
"0 0.000000 0.231669 0.279424 0.887329 \n",
"0 0.933164 5.468453 4.151637 0.998070 \n",
"0 2.135008 2.339630 3.660183 0.803394 \n",
"\n",
" debt_to_equity PE PB Div_yield \n",
"0 2.230663 5.696769 1.661179 0.019126 \n",
"0 9.647243 73.956996 16.808806 0.001049 \n",
"0 7.875371 50.137198 3.418685 0.004298 \n",
"0 517.142241 83.019826 1418.196271 0.006531 \n",
"0 4.086316 34.936595 4.256800 0.007482 \n",
"\n",
"[5 rows x 22 columns]"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"trade_data.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "eLOnL5eYh1jR",
"outputId": "8ce8d96c-0d6e-4a38-fa68-354746d8f7ca"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"hit end!\n"
]
}
],
"source": [
"df_account_value_ppo, df_actions_ppo = DRLAgent.DRL_prediction(\n",
" model=trained_ppo,\n",
" environment = e_trade_gym) if if_using_ppo else [None, None]\n",
"\n",
"df_account_value_ddpg, df_actions_ddpg = DRLAgent.DRL_prediction(\n",
" model=trained_ddpg,\n",
" environment = e_trade_gym) if if_using_ddpg else [None, None]\n",
"\n",
"df_account_value_a2c, df_actions_a2c = DRLAgent.DRL_prediction(\n",
" model=trained_a2c,\n",
" environment = e_trade_gym) if if_using_a2c else [None, None]\n",
"\n",
"df_account_value_td3, df_actions_td3 = DRLAgent.DRL_prediction(\n",
" model=trained_td3,\n",
" environment = e_trade_gym) if if_using_td3 else [None, None]\n",
"\n",
"df_account_value_sac, df_actions_sac = DRLAgent.DRL_prediction(\n",
" model=trained_sac,\n",
" environment = e_trade_gym) if if_using_sac else [None, None]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ERxw3KqLkcP4"
},
"outputs": [],
"source": [
"# df_account_value_ppo.shape\n",
"# df_account_value_ddpg.shape\n",
"# df_account_value_a2c.shape\n",
"# df_account_value_td3.shape\n",
"# df_account_value_sac.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "2yRkNguY5yvp"
},
"outputs": [],
"source": [
"# df_account_value_ppo.tail()\n",
"# df_account_value_ddpg.tail()\n",
"# df_account_value_a2c.tail()\n",
"# df_account_value_td3.tail()\n",
"# df_account_value_sac.tail()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "nFlK5hNbWVFk"
},
"outputs": [],
"source": [
"# df_actions_ppo.head()\n",
"# df_actions_ddpg.head()\n",
"# df_actions_a2c.head()\n",
"# df_actions_td3.head()\n",
"# df_actions_sac.head()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "W6vvNSC6h1jZ"
},
"source": [
"<a id='6'></a>\n",
"# Part 7: Backtest Our Strategy\n",
"Backtesting plays a key role in evaluating the performance of a trading strategy. Automated backtesting tool is preferred because it reduces the human error. We usually use the Quantopian pyfolio package to backtest our trading strategies. It is easy to use and consists of various individual plots that provide a comprehensive image of the performance of a trading strategy."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Lr2zX7ZxNyFQ"
},
"source": [
"<a id='6.1'></a>\n",
"## 7.1 BackTestStats\n",
"pass in df_account_value, this information is stored in env class\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Nzkr9yv-AdV_",
"outputId": "c270bdbf-6b90-465f-c369-3d3e25581232"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"==============Get Backtest Results===========\n",
"\n",
" sac:\n",
"Annual return 0.090031\n",
"Cumulative returns 0.284112\n",
"Annual volatility 0.232226\n",
"Sharpe ratio 0.488980\n",
"Calmar ratio 0.239450\n",
"Stability 0.039437\n",
"Max drawdown -0.375992\n",
"Omega ratio 1.138393\n",
"Sortino ratio 0.668995\n",
"Skew NaN\n",
"Kurtosis NaN\n",
"Tail ratio 1.034548\n",
"Daily value at risk -0.028807\n",
"dtype: float64\n"
]
}
],
"source": [
"print(\"==============Get Backtest Results===========\")\n",
"now = datetime.datetime.now().strftime('%Y%m%d-%Hh%M')\n",
"\n",
"if if_using_ppo:\n",
" print(\"\\n ppo:\")\n",
" perf_stats_all_ppo = backtest_stats(account_value=df_account_value_ppo)\n",
" perf_stats_all_ppo = pd.DataFrame(perf_stats_all_ppo)\n",
" perf_stats_all_ppo.to_csv(\"./\"+config.RESULTS_DIR+\"/perf_stats_all_ppo_\"+now+'.csv')\n",
"\n",
"if if_using_ddpg:\n",
" print(\"\\n ddpg:\")\n",
" perf_stats_all_ddpg = backtest_stats(account_value=df_account_value_ddpg)\n",
" perf_stats_all_ddpg = pd.DataFrame(perf_stats_all_ddpg)\n",
" perf_stats_all_ddpg.to_csv(\"./\"+config.RESULTS_DIR+\"/perf_stats_all_ddpg_\"+now+'.csv')\n",
"\n",
"if if_using_a2c:\n",
" print(\"\\n a2c:\")\n",
" perf_stats_all_a2c = backtest_stats(account_value=df_account_value_a2c)\n",
" perf_stats_all_a2c = pd.DataFrame(perf_stats_all_a2c)\n",
" perf_stats_all_a2c.to_csv(\"./\"+config.RESULTS_DIR+\"/perf_stats_all_a2c_\"+now+'.csv')\n",
"\n",
"if if_using_td3:\n",
" print(\"\\n atd3:\")\n",
" perf_stats_all_td3 = backtest_stats(account_value=df_account_value_td3)\n",
" perf_stats_all_td3 = pd.DataFrame(perf_stats_all_td3)\n",
" perf_stats_all_td3.to_csv(\"./\"+config.RESULTS_DIR+\"/perf_stats_all_td3_\"+now+'.csv')\n",
"\n",
"if if_using_sac:\n",
" print(\"\\n sac:\")\n",
" perf_stats_all_sac = backtest_stats(account_value=df_account_value_sac)\n",
" perf_stats_all_sac = pd.DataFrame(perf_stats_all_sac)\n",
" perf_stats_all_sac.to_csv(\"./\"+config.RESULTS_DIR+\"/perf_stats_all_sac_\"+now+'.csv')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "QkV-LB66iwhD",
"outputId": "c8f0972d-786c-4340-ec72-d566d41b7347"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"==============Get Baseline Stats===========\n",
"[*********************100%***********************] 1 of 1 completed\n",
"Shape of DataFrame: (506, 8)\n",
"Annual return 0.144827\n",
"Cumulative returns 0.312037\n",
"Annual volatility 0.274346\n",
"Sharpe ratio 0.632258\n",
"Calmar ratio 0.390515\n",
"Stability 0.119309\n",
"Max drawdown -0.370862\n",
"Omega ratio 1.149712\n",
"Sortino ratio 0.871240\n",
"Skew NaN\n",
"Kurtosis NaN\n",
"Tail ratio 0.860739\n",
"Daily value at risk -0.033876\n",
"dtype: float64\n"
]
}
],
"source": [
"#baseline stats\n",
"print(\"==============Get Baseline Stats===========\")\n",
"baseline_df = get_baseline(\n",
" ticker=\"^DJI\",\n",
" start = TEST_START_DATE,\n",
" end = TEST_END_DATE)\n",
"\n",
"stats = backtest_stats(baseline_df, value_col_name = 'close')\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "9U6Suru3h1jc"
},
"source": [
"<a id='6.2'></a>\n",
"## 7.2 BackTestPlot"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "lKRGftSS7pNM",
"outputId": "283fc3a4-e3c1-42e4-a13a-d0a68f865907"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"==============Compare to DJIA===========\n",
"[*********************100%***********************] 1 of 1 completed\n",
"Shape of DataFrame: (506, 8)\n"
]
},
{
"data": {
"text/html": [
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\"><th>Start date</th><td colspan=2>2019-01-01</td></tr>\n",
" <tr style=\"text-align: right;\"><th>End date</th><td colspan=2>2020-12-31</td></tr>\n",
" <tr style=\"text-align: right;\"><th>Total months</th><td colspan=2>34</td></tr>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Backtest</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Annual return</th>\n",
" <td>9.003%</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Cumulative returns</th>\n",
" <td>28.411%</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Annual volatility</th>\n",
" <td>23.223%</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Sharpe ratio</th>\n",
" <td>0.49</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Calmar ratio</th>\n",
" <td>0.24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Stability</th>\n",
" <td>0.04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Max drawdown</th>\n",
" <td>-37.599%</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Omega ratio</th>\n",
" <td>1.14</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Sortino ratio</th>\n",
" <td>0.67</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Skew</th>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Kurtosis</th>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Tail ratio</th>\n",
" <td>1.03</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Daily value at risk</th>\n",
" <td>-2.881%</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Alpha</th>\n",
" <td>0.03</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Beta</th>\n",
" <td>0.68</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>Worst drawdown periods</th>\n",
" <th>Net drawdown in %</th>\n",
" <th>Peak date</th>\n",
" <th>Valley date</th>\n",
" <th>Recovery date</th>\n",
" <th>Duration</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>37.60</td>\n",
" <td>2020-02-12</td>\n",
" <td>2020-03-21</td>\n",
" <td>2020-11-14</td>\n",
" <td>198</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>6.97</td>\n",
" <td>2019-04-12</td>\n",
" <td>2019-05-31</td>\n",
" <td>2019-06-20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6.42</td>\n",
" <td>2019-07-23</td>\n",
" <td>2019-08-14</td>\n",
" <td>2019-09-05</td>\n",
" <td>33</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.69</td>\n",
" <td>2019-03-01</td>\n",
" <td>2019-03-22</td>\n",
" <td>2019-04-12</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>3.79</td>\n",
" <td>2019-09-13</td>\n",
" <td>2019-10-02</td>\n",
" <td>2019-11-07</td>\n",
" <td>40</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>Stress Events</th>\n",
" <th>mean</th>\n",
" <th>min</th>\n",
" <th>max</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>New Normal</th>\n",
" <td>0.05%</td>\n",
" <td>-13.24%</td>\n",
" <td>11.70%</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 1008x5184 with 13 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 1008x432 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"print(\"==============Compare to DJIA===========\")\n",
"%matplotlib inline\n",
"# S&P 500: ^GSPC\n",
"# Dow Jones Index: ^DJI\n",
"# NASDAQ 100: ^NDX\n",
"\n",
"if if_using_ppo:\n",
" backtest_plot(df_account_value_ppo,\n",
" baseline_ticker = '^DJI',\n",
" baseline_start = TEST_START_DATE,\n",
" baseline_end = TEST_END_DATE)\n",
"\n",
"if if_using_ddpg:\n",
" backtest_plot(df_account_value_ddpg,\n",
" baseline_ticker = '^DJI',\n",
" baseline_start = TEST_START_DATE,\n",
" baseline_end = TEST_END_DATE)\n",
"\n",
"if if_using_a2c:\n",
" backtest_plot(df_account_value_a2c,\n",
" baseline_ticker = '^DJI',\n",
" baseline_start = TEST_START_DATE,\n",
" baseline_end = TEST_END_DATE)\n",
"\n",
"if if_using_td3:\n",
" backtest_plot(df_account_value_td3,\n",
" baseline_ticker = '^DJI',\n",
" baseline_start = TEST_START_DATE,\n",
" baseline_end = TEST_END_DATE)\n",
"\n",
"if if_using_sac:\n",
" backtest_plot(df_account_value_sac,\n",
" baseline_ticker = '^DJI',\n",
" baseline_start = TEST_START_DATE,\n",
" baseline_end = TEST_END_DATE)"
]
}
],
"metadata": {
"colab": {
"collapsed_sections": [
"_gDkU-j-fCmZ",
"MRiOtrywfAo1",
"3Zpv4S0-fDBv",
"Dr49PotrfG01"
],
"provenance": [],
"include_colab_link": true
},
"gpuClass": "standard",
"kernelspec": {
"display_name": "Python 3.8.6 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": "3.8.6"
},
"vscode": {
"interpreter": {
"hash": "a1dc24e770f11933509167a1c29cdaaeb86ecb8b4614cc65da123615b71c0aa2"
}
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment