├── envs
├── __init__.py
├── stocks_env.py
├── forex_env.py
└── trading_env.py
├── .gitignore
├── README.md
├── Data
├── doge.csv
└── apple.csv
└── Doge_Predict_A2C.ipynb
/envs/__init__.py:
--------------------------------------------------------------------------------
1 | from .trading_env import TradingEnv, Actions, Positions
2 | from .forex_env import ForexEnv
3 | from .stocks_env import StocksEnv
4 |
--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | # Byte-compiled / optimized / DLL files
2 | __pycache__/
3 | *.py[cod]
4 | *$py.class
5 |
6 | # C extensions
7 | *.so
8 |
9 | # Distribution / packaging
10 | .DS_Store
11 | .Python
12 | build/
13 | develop-eggs/
14 | dist/
15 | downloads/
16 | eggs/
17 | .eggs/
18 | lib/
19 | lib64/
20 | parts/
21 | sdist/
22 | var/
23 | wheels/
24 | pip-wheel-metadata/
25 | share/python-wheels/
26 | *.egg-info/
27 | .installed.cfg
28 | *.egg
29 | MANIFEST
30 |
31 | # PyInstaller
32 | # Usually these files are written by a python script from a template
33 | # before PyInstaller builds the exe, so as to inject date/other infos into it.
34 | *.manifest
35 | *.spec
36 |
37 | # Installer logs
38 | pip-log.txt
39 | pip-delete-this-directory.txt
40 |
41 | # Unit test / coverage reports
42 | htmlcov/
43 | .tox/
44 | .nox/
45 | .coverage
46 | .coverage.*
47 | .cache
48 | nosetests.xml
49 | coverage.xml
50 | *.cover
51 | *.py,cover
52 | .hypothesis/
53 | .pytest_cache/
54 |
55 | # Translations
56 | *.mo
57 | *.pot
58 |
59 | # Django stuff:
60 | *.log
61 | local_settings.py
62 | db.sqlite3
63 | db.sqlite3-journal
64 |
65 | # Flask stuff:
66 | instance/
67 | .webassets-cache
68 |
69 | # Scrapy stuff:
70 | .scrapy
71 |
72 | # Sphinx documentation
73 | docs/_build/
74 |
75 | # PyBuilder
76 | target/
77 |
78 | # Jupyter Notebook
79 | .ipynb_checkpoints
80 |
81 | # IPython
82 | profile_default/
83 | ipython_config.py
84 |
85 | # pyenv
86 | .python-version
87 |
88 | # pipenv
89 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
90 | # However, in case of collaboration, if having platform-specific dependencies or dependencies
91 | # having no cross-platform support, pipenv may install dependencies that don't work, or not
92 | # install all needed dependencies.
93 | #Pipfile.lock
94 |
95 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow
96 | __pypackages__/
97 |
98 | # Celery stuff
99 | celerybeat-schedule
100 | celerybeat.pid
101 |
102 | # SageMath parsed files
103 | *.sage.py
104 |
105 | # Environments
106 | .env
107 | .venv
108 | env/
109 | venv/
110 | ENV/
111 | env.bak/
112 | venv.bak/
113 |
114 | # Spyder project settings
115 | .spyderproject
116 | .spyproject
117 |
118 | # Rope project settings
119 | .ropeproject
120 |
121 | # mkdocs documentation
122 | /site
123 |
124 | # mypy
125 | .mypy_cache/
126 | .dmypy.json
127 | dmypy.json
128 |
129 | # Pyre type checker
130 | .pyre/
131 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # Deep-RL-for-Automated-Stock-Trading
2 | Deep Reinforcement Learning methods for facilitating Automated Stock Trading.
3 |
4 | This project implements a Stock Trading Bot, trained using Deep Reinforcement Learning. Implementation is kept simple, Stable baselines has been used for implementation of RL algorithms.
5 |
6 | ## Reinforcement Learning
7 |
8 | 
9 |
10 | Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward.Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning.
11 |
12 |
13 | ## Stable-Baselines
14 |
15 | Stable Baselines is a set of improved implementations of Reinforcement Learning (RL) algorithms based on OpenAI Baselines.
16 |
17 | 
18 |
19 | 
20 |
21 | 
22 |
23 |
24 | ## Implementing A2C ALgorithm
25 | **A2C** is a policy gradient algorithm and it is part of the on-policy family. That means that we are learning the value function for one policy while following it, or in other words, we can’t learn the value function by following another policy. We will be using another policy if were using experience replay for example, because by learning from too old data, we use information generated by a policy (ie. the network) slightly different to the current state.
26 |
27 | 
28 |
29 | On each learning step, we update both the Actor parameter (with policy gradients and advantage value), and the Critic parameter (with minimizing the mean squared error with the Bellman update equation)
30 |
31 | ## Data
32 | You can download Historical Financial data from www.Marketwatch.com for training. We have used data of Apple and DogeCoin for Training.
33 |
34 | ## Training
35 | 
36 |
37 | We used data of Apple Stocks for a period of one year.
38 |
39 | Here,
40 | Red indicates Short SELL,
41 | Green indicates Short BUY.
42 |
43 |
44 | ## Evaluation
45 | 
46 |
47 | The Model predicted the **Stock Prices** for next 50 days.
48 |
--------------------------------------------------------------------------------
/envs/stocks_env.py:
--------------------------------------------------------------------------------
1 | import numpy as np
2 |
3 | from .trading_env import TradingEnv, Actions, Positions
4 |
5 |
6 | class StocksEnv(TradingEnv):
7 |
8 | def __init__(self, df, window_size, frame_bound):
9 | assert len(frame_bound) == 2
10 |
11 | self.frame_bound = frame_bound
12 | super().__init__(df, window_size)
13 |
14 | self.trade_fee_bid_percent = 0.01 # unit
15 | self.trade_fee_ask_percent = 0.005 # unit
16 |
17 |
18 | def _process_data(self):
19 | prices = self.df.loc[:, 'Close'].to_numpy()
20 |
21 | prices[self.frame_bound[0] - self.window_size] # validate index (TODO: Improve validation)
22 | prices = prices[self.frame_bound[0]-self.window_size:self.frame_bound[1]]
23 |
24 | diff = np.insert(np.diff(prices), 0, 0)
25 | signal_features = np.column_stack((prices, diff))
26 |
27 | return prices, signal_features
28 |
29 |
30 | def _calculate_reward(self, action):
31 | step_reward = 0
32 |
33 | trade = False
34 | if ((action == Actions.Buy.value and self._position == Positions.Short) or
35 | (action == Actions.Sell.value and self._position == Positions.Long)):
36 | trade = True
37 |
38 | if trade:
39 | current_price = self.prices[self._current_tick]
40 | last_trade_price = self.prices[self._last_trade_tick]
41 | price_diff = current_price - last_trade_price
42 |
43 | if self._position == Positions.Long:
44 | step_reward += price_diff
45 |
46 | return step_reward
47 |
48 |
49 | def _update_profit(self, action):
50 | trade = False
51 | if ((action == Actions.Buy.value and self._position == Positions.Short) or
52 | (action == Actions.Sell.value and self._position == Positions.Long)):
53 | trade = True
54 |
55 | if trade or self._done:
56 | current_price = self.prices[self._current_tick]
57 | last_trade_price = self.prices[self._last_trade_tick]
58 |
59 | if self._position == Positions.Long:
60 | shares = (self._total_profit * (1 - self.trade_fee_ask_percent)) / last_trade_price
61 | self._total_profit = (shares * (1 - self.trade_fee_bid_percent)) * current_price
62 |
63 |
64 | def max_possible_profit(self):
65 | current_tick = self._start_tick
66 | last_trade_tick = current_tick - 1
67 | profit = 1.
68 |
69 | while current_tick <= self._end_tick:
70 | position = None
71 | if self.prices[current_tick] < self.prices[current_tick - 1]:
72 | while (current_tick <= self._end_tick and
73 | self.prices[current_tick] < self.prices[current_tick - 1]):
74 | current_tick += 1
75 | position = Positions.Short
76 | else:
77 | while (current_tick <= self._end_tick and
78 | self.prices[current_tick] >= self.prices[current_tick - 1]):
79 | current_tick += 1
80 | position = Positions.Long
81 |
82 | if position == Positions.Long:
83 | current_price = self.prices[current_tick - 1]
84 | last_trade_price = self.prices[last_trade_tick]
85 | shares = profit / last_trade_price
86 | profit = shares * current_price
87 | last_trade_tick = current_tick - 1
88 |
89 | return profit
90 |
--------------------------------------------------------------------------------
/envs/forex_env.py:
--------------------------------------------------------------------------------
1 | import numpy as np
2 |
3 | from .trading_env import TradingEnv, Actions, Positions
4 |
5 |
6 | class ForexEnv(TradingEnv):
7 |
8 | def __init__(self, df, window_size, frame_bound, unit_side='left'):
9 | assert len(frame_bound) == 2
10 | assert unit_side.lower() in ['left', 'right']
11 |
12 | self.frame_bound = frame_bound
13 | self.unit_side = unit_side.lower()
14 | super().__init__(df, window_size)
15 |
16 | self.trade_fee = 0.0003 # unit
17 |
18 |
19 | def _process_data(self):
20 | prices = self.df.loc[:, 'Close'].to_numpy()
21 |
22 | prices[self.frame_bound[0] - self.window_size] # validate index (TODO: Improve validation)
23 | prices = prices[self.frame_bound[0]-self.window_size:self.frame_bound[1]]
24 |
25 | diff = np.insert(np.diff(prices), 0, 0)
26 | signal_features = np.column_stack((prices, diff))
27 |
28 | return prices, signal_features
29 |
30 |
31 | def _calculate_reward(self, action):
32 | step_reward = 0 # pip
33 |
34 | trade = False
35 | if ((action == Actions.Buy.value and self._position == Positions.Short) or
36 | (action == Actions.Sell.value and self._position == Positions.Long)):
37 | trade = True
38 |
39 | if trade:
40 | current_price = self.prices[self._current_tick]
41 | last_trade_price = self.prices[self._last_trade_tick]
42 | price_diff = current_price - last_trade_price
43 |
44 | if self._position == Positions.Short:
45 | step_reward += -price_diff * 10000
46 | elif self._position == Positions.Long:
47 | step_reward += price_diff * 10000
48 |
49 | return step_reward
50 |
51 |
52 | def _update_profit(self, action):
53 | trade = False
54 | if ((action == Actions.Buy.value and self._position == Positions.Short) or
55 | (action == Actions.Sell.value and self._position == Positions.Long)):
56 | trade = True
57 |
58 | if trade or self._done:
59 | current_price = self.prices[self._current_tick]
60 | last_trade_price = self.prices[self._last_trade_tick]
61 |
62 | if self.unit_side == 'left':
63 | if self._position == Positions.Short:
64 | quantity = self._total_profit * (last_trade_price - self.trade_fee)
65 | self._total_profit = quantity / current_price
66 |
67 | elif self.unit_side == 'right':
68 | if self._position == Positions.Long:
69 | quantity = self._total_profit / last_trade_price
70 | self._total_profit = quantity * (current_price - self.trade_fee)
71 |
72 |
73 | def max_possible_profit(self):
74 | current_tick = self._start_tick
75 | last_trade_tick = current_tick - 1
76 | profit = 1.
77 |
78 | while current_tick <= self._end_tick:
79 | position = None
80 | if self.prices[current_tick] < self.prices[current_tick - 1]:
81 | while (current_tick <= self._end_tick and
82 | self.prices[current_tick] < self.prices[current_tick - 1]):
83 | current_tick += 1
84 | position = Positions.Short
85 | else:
86 | while (current_tick <= self._end_tick and
87 | self.prices[current_tick] >= self.prices[current_tick - 1]):
88 | current_tick += 1
89 | position = Positions.Long
90 |
91 | current_price = self.prices[current_tick - 1]
92 | last_trade_price = self.prices[last_trade_tick]
93 |
94 | if self.unit_side == 'left':
95 | if position == Positions.Short:
96 | quantity = profit * (last_trade_price - self.trade_fee)
97 | profit = quantity / current_price
98 |
99 | elif self.unit_side == 'right':
100 | if position == Positions.Long:
101 | quantity = profit / last_trade_price
102 | profit = quantity * (current_price - self.trade_fee)
103 |
104 | last_trade_tick = current_tick - 1
105 |
106 | return profit
107 |
--------------------------------------------------------------------------------
/envs/trading_env.py:
--------------------------------------------------------------------------------
1 | import gym
2 | from gym import spaces
3 | from gym.utils import seeding
4 | import numpy as np
5 | from enum import Enum
6 | import matplotlib.pyplot as plt
7 |
8 |
9 | class Actions(Enum):
10 | Sell = 0
11 | Buy = 1
12 |
13 |
14 | class Positions(Enum):
15 | Short = 0
16 | Long = 1
17 |
18 | def opposite(self):
19 | return Positions.Short if self == Positions.Long else Positions.Long
20 |
21 |
22 | class TradingEnv(gym.Env):
23 |
24 | metadata = {'render.modes': ['human']}
25 |
26 | def __init__(self, df, window_size):
27 | assert df.ndim == 2
28 |
29 | self.seed()
30 | self.df = df
31 | self.window_size = window_size
32 | self.prices, self.signal_features = self._process_data()
33 | self.shape = (window_size, self.signal_features.shape[1])
34 |
35 | # spaces
36 | self.action_space = spaces.Discrete(len(Actions))
37 | self.observation_space = spaces.Box(low=-np.inf, high=np.inf, shape=self.shape, dtype=np.float32)
38 |
39 | # episode
40 | self._start_tick = self.window_size
41 | self._end_tick = len(self.prices) - 1
42 | self._done = None
43 | self._current_tick = None
44 | self._last_trade_tick = None
45 | self._position = None
46 | self._position_history = None
47 | self._total_reward = None
48 | self._total_profit = None
49 | self._first_rendering = None
50 | self.history = None
51 |
52 |
53 | def seed(self, seed=None):
54 | self.np_random, seed = seeding.np_random(seed)
55 | return [seed]
56 |
57 |
58 | def reset(self):
59 | self._done = False
60 | self._current_tick = self._start_tick
61 | self._last_trade_tick = self._current_tick - 1
62 | self._position = Positions.Short
63 | self._position_history = (self.window_size * [None]) + [self._position]
64 | self._total_reward = 0.
65 | self._total_profit = 1. # unit
66 | self._first_rendering = True
67 | self.history = {}
68 | return self._get_observation()
69 |
70 |
71 | def step(self, action):
72 | self._done = False
73 | self._current_tick += 1
74 |
75 | if self._current_tick == self._end_tick:
76 | self._done = True
77 |
78 | step_reward = self._calculate_reward(action)
79 | self._total_reward += step_reward
80 |
81 | self._update_profit(action)
82 |
83 | trade = False
84 | if ((action == Actions.Buy.value and self._position == Positions.Short) or
85 | (action == Actions.Sell.value and self._position == Positions.Long)):
86 | trade = True
87 |
88 | if trade:
89 | self._position = self._position.opposite()
90 | self._last_trade_tick = self._current_tick
91 |
92 | self._position_history.append(self._position)
93 | observation = self._get_observation()
94 | info = dict(
95 | total_reward = self._total_reward,
96 | total_profit = self._total_profit,
97 | position = self._position.value
98 | )
99 | self._update_history(info)
100 |
101 | return observation, step_reward, self._done, info
102 |
103 |
104 | def _get_observation(self):
105 | return self.signal_features[(self._current_tick-self.window_size):self._current_tick]
106 |
107 |
108 | def _update_history(self, info):
109 | if not self.history:
110 | self.history = {key: [] for key in info.keys()}
111 |
112 | for key, value in info.items():
113 | self.history[key].append(value)
114 |
115 |
116 | def render(self, mode='human'):
117 |
118 | def _plot_position(position, tick):
119 | color = None
120 | if position == Positions.Short:
121 | color = 'red'
122 | elif position == Positions.Long:
123 | color = 'green'
124 | if color:
125 | plt.scatter(tick, self.prices[tick], color=color)
126 |
127 | if self._first_rendering:
128 | self._first_rendering = False
129 | plt.cla()
130 | plt.plot(self.prices)
131 | start_position = self._position_history[self._start_tick]
132 | _plot_position(start_position, self._start_tick)
133 |
134 | _plot_position(self._position, self._current_tick)
135 |
136 | plt.suptitle(
137 | "Total Reward: %.6f" % self._total_reward + ' ~ ' +
138 | "Total Profit: %.6f" % self._total_profit
139 | )
140 |
141 | plt.pause(0.01)
142 |
143 |
144 | def render_all(self, mode='human'):
145 | window_ticks = np.arange(len(self._position_history))
146 | plt.plot(self.prices)
147 |
148 | short_ticks = []
149 | long_ticks = []
150 | for i, tick in enumerate(window_ticks):
151 | if self._position_history[i] == Positions.Short:
152 | short_ticks.append(tick)
153 | elif self._position_history[i] == Positions.Long:
154 | long_ticks.append(tick)
155 |
156 | plt.plot(short_ticks, self.prices[short_ticks], 'ro')
157 | plt.plot(long_ticks, self.prices[long_ticks], 'go')
158 |
159 | plt.suptitle(
160 | "Total Reward: %.6f" % self._total_reward + ' ~ ' +
161 | "Total Profit: %.6f" % self._total_profit
162 | )
163 |
164 |
165 | def close(self):
166 | plt.close()
167 |
168 |
169 | def save_rendering(self, filepath):
170 | plt.savefig(filepath)
171 |
172 |
173 | def pause_rendering(self):
174 | plt.show()
175 |
176 |
177 | def _process_data(self):
178 | raise NotImplementedError
179 |
180 |
181 | def _calculate_reward(self, action):
182 | raise NotImplementedError
183 |
184 |
185 | def _update_profit(self, action):
186 | raise NotImplementedError
187 |
188 |
189 | def max_possible_profit(self): # trade fees are ignored
190 | raise NotImplementedError
191 |
--------------------------------------------------------------------------------
/Data/doge.csv:
--------------------------------------------------------------------------------
1 | Date,Open,High,Low,Close,Volume
2 | 03/12/21,0.330407,0.432618,0.297074,0.397741,13850000000
3 | 03/11/21,0.474719,0.477866,0.217528,0.330353,19280000000
4 | 03/10/21,0.486444,0.512529,0.468941,0.474714,4750000000
5 | 03/09/21,0.513062,0.514821,0.457331,0.486366,6840000000
6 | 03/08/21,0.507796,0.547205,0.449635,0.513023,8260000000
7 | 03/05/21,0.559594,0.563262,0.493248,0.507448,7920000000
8 | 03/04/21,0.486983,0.589075,0.464572,0.559581,16220000000
9 | 03/03/21,0.389257,0.514831,0.353838,0.48691,16690000000
10 | 03/02/21,0.493226,0.519039,0.385839,0.389159,8600000000
11 | 03/01/21,0.449956,0.544636,0.44294,0.493231,12460000000
12 | 02/26/2021,0.568689,0.568689,0.422392,0.449977,15360000000
13 | 02/25/2021,0.63533,0.697487,0.423602,0.568682,37250000000
14 | 02/24/2021,0.686914,0.738255,0.605162,0.634394,16920000000
15 | 02/23/2021,0.579819,0.729865,0.519357,0.68688,18810000000
16 | 02/22/2021,0.653501,0.663006,0.541526,0.579839,12970000000
17 | 02/19/2021,0.559521,0.693839,0.536232,0.655355,28030000000
18 | 02/18/2021,0.438349,0.594039,0.398416,0.559005,31900000000
19 | 02/17/2021,0.372467,0.443181,0.372467,0.438244,9970000000
20 | 02/16/2021,0.390686,0.399246,0.363912,0.372404,8200000000
21 | 02/12/21,0.336657,0.396647,0.327317,0.390642,11340000000
22 | 02/11/21,0.303226,0.338327,0.300761,0.336635,6480000000
23 | 02/10/21,0.323591,0.323797,0.295612,0.30324,6740000000
24 | 02/09/21,0.270696,0.343505,0.255591,0.323582,21220000000
25 | 02/08/21,0.270118,0.278347,0.264018,0.270668,5380000000
26 | 02/05/21,0.251192,0.279737,0.24739,0.269805,7900000000
27 | 02/04/21,0.269932,0.288841,0.224455,0.251103,10020000000
28 | 02/03/21,0.24879,0.289165,0.229214,0.270017,17250000000
29 | 02/02/21,0.2608,0.269065,0.166312,0.248731,27910000000
30 | 02/01/21,0.305718,0.308332,0.256061,0.26081,17340000000
31 | 01/29/2021,0.317922,0.346599,0.297108,0.305633,15480000000
32 | 01/28/2021,0.407451,0.422212,0.271758,0.317696,33270000000
33 | 01/27/2021,0.322197,0.433969,0.309128,0.407335,31680000000
34 | 01/26/2021,0.282723,0.349748,0.239707,0.322037,29110000000
35 | 01/25/2021,0.365389,0.378924,0.23201,0.281909,39280000000
36 | 01/22/2021,0.182628,0.449889,0.180132,0.365551,83390000000
37 | 01/21/2021,0.121275,0.189446,0.120291,0.182784,37960000000
38 | 01/20/2021,0.09425,0.144229,0.092535,0.121349,57290000000
39 | 01/19/2021,0.070709,0.095671,0.070705,0.093763,23190000000
40 | 01/15/2021,0.074205,0.075337,0.068792,0.070719,8900000000
41 | 01/14/2021,0.06368,0.079712,0.063402,0.07415,24470000000
42 | 01/13/2021,0.061605,0.065016,0.060969,0.063688,5300000000
43 | 01/12/21,0.061754,0.063832,0.060536,0.061582,4130000000
44 | 01/11/21,0.05873,0.062168,0.058705,0.061757,3860000000
45 | 01/08/21,0.064281,0.067151,0.057211,0.058728,9590000000
46 | 01/07/21,0.059921,0.064989,0.058068,0.064283,9450000000
47 | 01/06/21,0.057393,0.060593,0.056318,0.059948,5220000000
48 | 01/05/21,0.055542,0.058122,0.055121,0.057401,3280000000
49 | 01/04/21,0.057567,0.05944,0.055553,0.055554,4080000000
50 | 12/31/2020,0.062093,0.062794,0.057285,0.05757,8100000000
51 | 12/30/2020,0.053742,0.070722,0.053723,0.062113,26140000000
52 | 12/29/2020,0.054026,0.054484,0.051896,0.053744,2260000000
53 | 12/28/2020,0.054122,0.055567,0.053738,0.054027,2810000000
54 | 12/24/2020,0.053641,0.054673,0.05323,0.054102,1920000000
55 | 12/23/2020,0.054436,0.054859,0.053046,0.053637,1420000000
56 | 12/22/2020,0.053976,0.055388,0.053456,0.054426,2390000000
57 | 12/21/2020,0.051249,0.053988,0.051241,0.053973,2110000000
58 | 12/18/2020,0.051501,0.05241,0.04965,0.051263,3470000000
59 | 12/17/2020,0.053431,0.056659,0.050887,0.05151,3000000000
60 | 12/16/2020,0.054913,0.056043,0.052797,0.053437,2810000000
61 | 12/15/2020,0.057475,0.057923,0.054801,0.054929,2420000000
62 | 12/14/2020,0.058829,0.059509,0.056763,0.057471,2570000000
63 | 12/11/20,0.058263,0.060603,0.058042,0.058827,3430000000
64 | 12/10/20,0.05729,0.059825,0.056462,0.05827,3120000000
65 | 12/09/20,0.057878,0.05915,0.056997,0.057294,2560000000
66 | 12/08/20,0.058606,0.058881,0.056567,0.05788,2390000000
67 | 12/07/20,0.056968,0.05905,0.055365,0.058611,3910000000
68 | 12/04/20,0.058429,0.059736,0.055064,0.056965,4770000000
69 | 12/03/20,0.062676,0.06351,0.058431,0.058431,9160000000
70 | 12/02/20,0.055238,0.062739,0.054694,0.062694,6370000000
71 | 12/01/20,0.055896,0.056965,0.054298,0.055261,3660000000
72 | 11/30/2020,0.055877,0.056895,0.054398,0.055893,3390000000
73 | 11/27/2020,0.0579,0.058642,0.054554,0.0559,4710000000
74 | 11/25/2020,0.062851,0.062851,0.056009,0.057978,8670000000
75 | 11/24/2020,0.051888,0.062848,0.051622,0.062848,13640000000
76 | 11/23/2020,0.050924,0.052248,0.050548,0.051881,3030000000
77 | 11/20/2020,0.049523,0.052453,0.049256,0.050935,5280000000
78 | 11/19/2020,0.049925,0.050877,0.048026,0.049584,3760000000
79 | 11/18/2020,0.050469,0.051118,0.047762,0.049927,3650000000
80 | 11/17/2020,0.050343,0.052153,0.050011,0.050474,3640000000
81 | 11/16/2020,0.050582,0.052423,0.049198,0.050279,4670000000
82 | 11/13/2020,0.048134,0.05229,0.047929,0.050576,5220000000
83 | 11/12/20,0.050076,0.050176,0.044811,0.048129,4850000000
84 | 11/11/20,0.050466,0.051993,0.049173,0.050076,4450000000
85 | 11/10/20,0.049909,0.052537,0.048537,0.050463,6160000000
86 | 11/09/20,0.056663,0.05803,0.049862,0.050045,9270000000
87 | 11/06/20,0.047663,0.0604,0.046065,0.056653,19490000000
88 | 11/05/20,0.053537,0.053774,0.041782,0.047673,11250000000
89 | 11/04/20,0.056136,0.060737,0.046516,0.05353,15500000000
90 | 11/03/20,0.054196,0.059292,0.05335,0.055881,10290000000
91 | 11/02/20,0.055044,0.060455,0.051115,0.054135,14030000000
92 | 10/30/2020,0.059117,0.059628,0.054075,0.055036,11880000000
93 | 10/29/2020,0.049469,0.063482,0.04897,0.059134,21380000000
94 | 10/28/2020,0.053513,0.055054,0.04796,0.049467,10520000000
95 | 10/27/2020,0.056427,0.05981,0.050815,0.053513,11600000000
96 | 10/26/2020,0.062639,0.064003,0.047653,0.056442,19300000000
97 | 10/23/2020,0.066244,0.066392,0.055785,0.062639,13800000000
98 | 10/22/2020,0.069815,0.071703,0.065915,0.066249,7320000000
99 | 10/21/2020,0.06978,0.07272,0.061285,0.069791,13240000000
100 | 10/20/2020,0.07258,0.074843,0.068152,0.069611,11230000000
101 | 10/19/2020,0.070015,0.081396,0.067081,0.072584,22670000000
102 | 10/16/2020,0.078782,0.083567,0.064053,0.070012,22360000000
103 | 10/15/2020,0.077936,0.085037,0.063839,0.078793,38110000000
104 | 10/14/2020,0.057506,0.086356,0.053464,0.078508,54230000000
105 | 10/13/2020,0.046788,0.058646,0.044505,0.057465,26400000000
106 | 10/12/20,0.052933,0.054033,0.043289,0.046783,27110000000
107 | 10/09/20,0.03734,0.059081,0.035919,0.052944,72240000000
108 | 10/08/20,0.031297,0.039651,0.031031,0.037345,20280000000
109 | 10/07/20,0.034784,0.035142,0.029054,0.031296,19700000000
110 | 10/06/20,0.036826,0.0437,0.033096,0.034705,39340000000
111 | 10/05/20,0.028199,0.048998,0.026909,0.036841,65010000000
112 | 10/02/20,0.045859,0.050499,0.022269,0.028197,77240000000
113 | 10/01/20,0.036085,0.07797,0.03234,0.046597,146800000000
114 | 09/30/2020,0.007415,0.037902,0.007415,0.036265,12410000000
115 | 09/29/2020,0.008244,0.008245,0.007268,0.007441,2010000000
116 | 09/28/2020,0.008349,0.008454,0.008014,0.00824,1470000000
117 | 09/25/2020,0.008714,0.008899,0.008259,0.008353,2070000000
118 | 09/24/2020,0.008571,0.008955,0.008504,0.008714,1840000000
119 | 09/23/2020,0.008516,0.008801,0.008359,0.008571,1790000000
120 | 09/22/2020,0.008167,0.008751,0.007571,0.008516,2470000000
121 | 09/21/2020,0.009055,0.009099,0.008049,0.008172,2880000000
122 | 09/18/2020,0.00905,0.009141,0.008506,0.009055,2650000000
123 | 09/17/2020,0.009173,0.009655,0.009,0.009053,3510000000
124 | 09/16/2020,0.009094,0.009302,0.008949,0.009172,2480000000
125 | 09/15/2020,0.009235,0.009365,0.008806,0.009094,3070000000
126 | 09/14/2020,0.00937,0.009546,0.009095,0.009235,3590000000
127 | 09/11/20,0.009398,0.009827,0.008373,0.009373,6690000000
128 | 09/10/20,0.008672,0.010064,0.008329,0.0094,7540000000
129 | 09/09/20,0.008068,0.008669,0.007779,0.008669,3980000000
130 | 09/08/20,0.008824,0.009136,0.007848,0.008066,5990000000
131 | 09/04/20,0.009829,0.009846,0.006727,0.008828,11360000000
132 | 09/03/20,0.010159,0.01085,0.009056,0.009831,8010000000
133 | 09/02/20,0.009753,0.010687,0.009658,0.010158,6610000000
134 | 09/01/20,0.009728,0.010253,0.008834,0.009753,5480000000
135 | 08/31/2020,0.010443,0.010497,0.008972,0.009724,7150000000
136 | 08/28/2020,0.00996,0.010968,0.009652,0.010443,16840000000
137 | 08/27/2020,0.009784,0.010319,0.008866,0.009958,15370000000
138 | 08/26/2020,0.009845,0.011493,0.007623,0.00978,38720000000
139 | 08/25/2020,0.010493,0.013928,0.009381,0.00985,71680000000
140 | 08/24/2020,0.005667,0.014008,0.005553,0.010489,100850000000
141 | 08/21/2020,0.004666,0.005676,0.004606,0.005661,8410000000
142 | 08/20/2020,0.004626,0.004756,0.004522,0.004666,3050000000
143 | 08/19/2020,0.004488,0.004718,0.004439,0.004627,3430000000
144 | 08/18/2020,0.004594,0.004622,0.004255,0.004488,3420000000
145 | 08/17/2020,0.004549,0.004732,0.004509,0.004594,3590000000
146 | 08/14/2020,0.004511,0.004818,0.004399,0.004548,5620000000
147 | 08/13/2020,0.004558,0.004659,0.004412,0.004508,5180000000
148 | 08/12/20,0.004573,0.004638,0.004384,0.004563,5340000000
149 | 08/11/20,0.003764,0.004594,0.003673,0.004573,6350000000
150 | 08/10/20,0.004515,0.004766,0.003604,0.003767,8030000000
151 | 08/07/20,0.004777,0.004866,0.004339,0.004514,8850000000
152 | 08/06/20,0.004645,0.005463,0.004339,0.004773,32480000000
153 | 08/05/20,0.003919,0.004721,0.003815,0.004641,23480000000
154 | 08/04/20,0.003862,0.004025,0.003799,0.003925,4570000000
155 | 08/03/20,0.003723,0.003985,0.003606,0.003863,4750000000
156 | 07/31/2020,0.003419,0.004127,0.003397,0.003723,9510000000
157 | 07/30/2020,0.003203,0.003439,0.003174,0.003423,1810000000
158 | 07/29/2020,0.003226,0.003262,0.003169,0.003204,1110000000
159 | 07/28/2020,0.003259,0.003285,0.003192,0.003224,1160000000
160 | 07/27/2020,0.003164,0.003278,0.003149,0.003259,1150000000
161 | 07/24/2020,0.003076,0.00319,0.003072,0.003164,1100000000
162 | 07/23/2020,0.003109,0.003114,0.003001,0.003075,996000000
163 | 07/22/2020,0.003158,0.003171,0.003058,0.003109,780000000
164 | 07/21/2020,0.003176,0.003191,0.003006,0.003158,1280000000
165 | 07/20/2020,0.003333,0.003368,0.003115,0.003176,1430000000
166 | 07/17/2020,0.003388,0.003407,0.003309,0.003335,1040000000
167 | 07/16/2020,0.003391,0.003447,0.003348,0.003388,1050000000
168 | 07/15/2020,0.003285,0.003411,0.003255,0.003391,1120000000
169 | 07/14/2020,0.003433,0.003449,0.003272,0.003282,1650000000
170 | 07/13/2020,0.003369,0.003522,0.003343,0.003433,1730000000
171 | 07/10/20,0.003327,0.003457,0.003274,0.003369,1800000000
172 | 07/09/20,0.003559,0.003585,0.003261,0.00332,2970000000
173 | 07/08/20,0.00344,0.003592,0.003408,0.003551,2450000000
174 | 07/07/20,0.003393,0.003532,0.003345,0.00344,1610000000
175 | 07/06/20,0.00327,0.003482,0.003236,0.003392,2140000000
176 | 07/02/20,0.003251,0.003359,0.003089,0.00327,2940000000
177 | 07/01/20,0.003716,0.003793,0.002945,0.003245,7720000000
178 | 06/30/2020,0.004232,0.004287,0.003598,0.003716,7730000000
179 | 06/29/2020,0.003682,0.004263,0.003551,0.00424,13300000000
180 | 06/26/2020,0.00334,0.003686,0.003231,0.003684,5150000000
181 | 06/25/2020,0.00351,0.003673,0.003159,0.00334,5990000000
182 | 06/24/2020,0.002987,0.003587,0.002983,0.00351,9100000000
183 | 06/23/2020,0.002906,0.003023,0.002904,0.002986,2780000000
184 | 06/22/2020,0.002908,0.002963,0.002856,0.002905,1900000000
185 | 06/19/2020,0.002935,0.003017,0.002817,0.002904,2870000000
186 | 06/18/2020,0.002879,0.002991,0.002874,0.002935,3210000000
187 | 06/17/2020,0.002773,0.003024,0.002745,0.002879,3970000000
188 | 06/16/2020,0.002766,0.00282,0.002732,0.002773,1320000000
189 | 06/15/2020,0.002811,0.002819,0.002708,0.002769,1880000000
190 | 06/12/20,0.002774,0.002855,0.002761,0.002811,1580000000
191 | 06/11/20,0.002757,0.002797,0.002725,0.002773,1150000000
192 | 06/10/20,0.00276,0.002863,0.00274,0.002757,1990000000
193 | 06/09/20,0.002671,0.002881,0.002632,0.00276,2520000000
194 | 06/08/20,0.002707,0.002786,0.002651,0.002673,1480000000
195 | 06/05/20,0.00267,0.002745,0.002645,0.002707,923000000
196 | 06/04/20,0.002757,0.002828,0.0026,0.00267,2240000000
197 | 06/03/20,0.002639,0.002815,0.002625,0.002757,2800000000
198 | 06/02/20,0.002546,0.002666,0.002546,0.002639,1290000000
199 | 06/01/20,0.002517,0.00256,0.002484,0.002546,1260000000
200 | 05/29/2020,0.002513,0.002529,0.002453,0.002517,1330000000
201 | 05/28/2020,0.002576,0.002588,0.00251,0.002514,1170000000
202 | 05/27/2020,0.002569,0.002586,0.002557,0.002576,657000000
203 | 05/26/2020,0.002583,0.002599,0.002548,0.002568,1050000000
204 | 05/22/2020,0.002576,0.002598,0.002512,0.002583,1640000000
205 | 05/21/2020,0.002583,0.00261,0.002512,0.002576,1220000000
206 | 05/20/2020,0.002674,0.002696,0.002566,0.002583,1810000000
207 | 05/19/2020,0.002666,0.002704,0.00262,0.002674,2380000000
208 | 05/18/2020,0.002651,0.002905,0.002634,0.002665,5750000000
209 | 05/15/2020,0.002634,0.002673,0.002618,0.002652,1130000000
210 | 05/14/2020,0.002644,0.00265,0.00261,0.002634,969000000
211 | 05/13/2020,0.002647,0.00269,0.002627,0.002644,959000000
212 | 05/12/20,0.002624,0.002689,0.002618,0.002647,1330000000
213 | 05/11/20,0.002595,0.002662,0.002593,0.002624,1700000000
214 | 05/08/20,0.002592,0.002624,0.002581,0.002595,1360000000
215 | 05/07/20,0.002592,0.002619,0.002573,0.002592,1410000000
216 | 05/06/20,0.002585,0.002605,0.002579,0.002593,653000000
217 | 05/05/20,0.002604,0.002607,0.002575,0.002585,597000000
218 | 05/04/20,0.002601,0.00262,0.002554,0.002604,1420000000
219 | 05/01/20,0.002638,0.002639,0.002572,0.0026,1270000000
220 | 04/30/2020,0.002637,0.002661,0.002621,0.002638,735000000
221 | 04/29/2020,0.002669,0.002679,0.002629,0.002637,926000000
222 | 04/28/2020,0.002681,0.002711,0.002628,0.002667,1260000000
223 | 04/27/2020,0.002666,0.002704,0.002652,0.002681,815000000
224 | 04/24/2020,0.002657,0.002719,0.002652,0.002666,1710000000
225 | 04/23/2020,0.002605,0.00268,0.002594,0.002657,2470000000
226 | 04/22/2020,0.002594,0.002628,0.002555,0.002609,2260000000
227 | 04/21/2020,0.002599,0.002614,0.002559,0.002595,2160000000
228 | 04/20/2020,0.002622,0.00263,0.002573,0.002602,2020000000
229 | 04/17/2020,0.002638,0.002654,0.0026,0.002621,1820000000
230 | 04/16/2020,0.002599,0.002676,0.002592,0.002638,1880000000
231 | 04/15/2020,0.00259,0.002634,0.002575,0.002597,1830000000
232 | 04/14/2020,0.002625,0.002633,0.002541,0.00259,4000000000
233 | 04/13/2020,0.002634,0.002684,0.002569,0.002625,2360000000
234 | 04/09/20,0.002673,0.002682,0.002619,0.002634,1460000000
235 | 04/08/20,0.002648,0.002709,0.002635,0.002673,2200000000
236 | 04/07/20,0.002697,0.002737,0.002624,0.002649,1600000000
237 | 04/06/20,0.002697,0.002733,0.002663,0.002697,1060000000
238 | 04/03/20,0.002713,0.002753,0.002675,0.002697,1660000000
239 | 04/02/20,0.002631,0.002723,0.002616,0.002713,2110000000
240 | 04/01/20,0.00255,0.002655,0.002533,0.00263,1400000000
241 | 03/31/2020,0.002643,0.002648,0.002539,0.002549,1500000000
242 | 03/30/2020,0.0026,0.002655,0.002583,0.002643,1360000000
243 | 03/27/2020,0.002774,0.002799,0.002583,0.002606,2400000000
244 | 03/26/2020,0.002792,0.0028,0.002725,0.002774,1690000000
245 | 03/25/2020,0.002788,0.002808,0.002766,0.002792,1540000000
246 | 03/24/2020,0.002807,0.002815,0.002751,0.002787,1150000000
247 | 03/23/2020,0.002793,0.002839,0.002771,0.002807,1410000000
248 | 03/20/2020,0.002829,0.002857,0.002783,0.002793,2020000000
249 | 03/19/2020,0.00279,0.002868,0.002778,0.002829,2210000000
250 | 03/18/2020,0.002783,0.002811,0.00274,0.00279,1840000000
251 | 03/17/2020,0.002815,0.002817,0.002743,0.002783,2020000000
252 | 03/16/2020,0.002796,0.002835,0.002762,0.002815,2280000000
--------------------------------------------------------------------------------
/Data/apple.csv:
--------------------------------------------------------------------------------
1 | Date,Open,High,Low,Close,Volume
2 | 03/12/2021,"120.40","121.17","119.16","121.03","88,105,047"
3 | 03/11/2021,"122.54","123.21","121.26","121.96","103,026,492"
4 | 03/10/2021,"121.69","122.17","119.45","119.98","111,943,297"
5 | 03/09/2021,"119.03","122.06","118.79","121.09","129,525,797"
6 | 03/08/2021,"120.93","121.00","116.21","116.36","154,376,609"
7 | 03/05/2021,"120.98","121.94","117.57","121.42","153,766,594"
8 | 03/04/2021,"121.75","123.60","118.62","120.13","178,155,016"
9 | 03/03/2021,"124.81","125.71","121.84","122.06","112,966,305"
10 | 03/02/2021,"128.41","128.72","125.01","125.12","102,260,898"
11 | 03/01/2021,"123.75","127.93","122.79","127.79","116,307,906"
12 | 02/26/2021,"122.59","124.85","121.20","121.26","164,560,406"
13 | 02/25/2021,"124.68","126.46","120.54","120.99","148,199,500"
14 | 02/24/2021,"124.94","125.56","122.23","125.35","111,039,906"
15 | 02/23/2021,"123.76","126.71","118.39","125.86","158,272,984"
16 | 02/22/2021,"128.01","129.72","125.60","126.00","103,916,398"
17 | 02/19/2021,"130.24","130.71","128.80","129.87","87,668,828"
18 | 02/18/2021,"129.20","130.00","127.41","129.71","96,856,750"
19 | 02/17/2021,"131.25","132.22","129.47","130.84","98,085,250"
20 | 02/16/2021,"135.49","136.01","132.79","133.19","80,576,320"
21 | 02/12/2021,"134.35","135.53","133.69","135.37","60,145,129"
22 | 02/11/2021,"135.90","136.39","133.77","135.13","64,280,031"
23 | 02/10/2021,"136.48","136.99","134.40","135.39","73,046,562"
24 | 02/09/2021,"136.62","137.88","135.85","136.01","76,774,211"
25 | 02/08/2021,"136.03","136.96","134.92","136.91","71,297,211"
26 | 02/05/2021,"137.35","137.42","135.86","136.76","75,693,828"
27 | 02/04/2021,"136.30","137.40","134.59","137.39","84,183,055"
28 | 02/03/2021,"135.76","135.77","133.61","133.94","89,880,945"
29 | 02/02/2021,"135.73","136.31","134.61","134.99","83,305,367"
30 | 02/01/2021,"133.75","135.38","130.93","134.14","106,239,797"
31 | 01/29/2021,"135.83","136.74","130.21","131.96","177,523,812"
32 | 01/28/2021,"139.52","141.99","136.70","137.09","142,621,109"
33 | 01/27/2021,"143.43","144.30","140.41","142.06","140,843,812"
34 | 01/26/2021,"143.60","144.30","141.37","143.16","98,390,562"
35 | 01/25/2021,"143.07","145.09","136.54","142.92","157,611,703"
36 | 01/22/2021,"136.28","139.85","135.02","139.07","114,459,398"
37 | 01/21/2021,"133.80","139.67","133.59","136.87","120,529,508"
38 | 01/20/2021,"128.66","132.49","128.55","132.03","104,319,508"
39 | 01/19/2021,"127.78","128.71","126.94","127.83","90,757,328"
40 | 01/15/2021,"128.78","130.22","127.00","127.14","111,598,492"
41 | 01/14/2021,"130.80","131.00","128.76","128.91","90,221,758"
42 | 01/13/2021,"128.76","131.45","128.49","130.89","88,636,828"
43 | 01/12/2021,"128.50","129.69","126.86","128.80","91,951,148"
44 | 01/11/2021,"129.19","130.17","128.50","128.98","100,620,898"
45 | 01/08/2021,"132.43","132.63","130.23","132.05","105,158,203"
46 | 01/07/2021,"128.36","131.63","127.86","130.92","109,578,203"
47 | 01/06/2021,"127.72","131.05","126.38","126.60","155,088,000"
48 | 01/05/2021,"128.89","131.74","128.43","131.01","97,664,898"
49 | 01/04/2021,"133.52","133.61","126.76","129.41","143,301,906"
50 | 12/31/2020,"134.08","134.74","131.72","132.69","99,116,594"
51 | 12/30/2020,"135.58","135.99","133.40","133.72","96,452,117"
52 | 12/29/2020,"138.05","138.79","134.34","134.87","121,047,297"
53 | 12/28/2020,"133.99","137.34","133.51","136.69","124,486,203"
54 | 12/24/2020,"131.32","133.46","131.10","131.97","54,930,059"
55 | 12/23/2020,"132.16","132.43","130.78","130.96","88,223,688"
56 | 12/22/2020,"131.61","134.41","129.65","131.88","169,351,812"
57 | 12/21/2020,"125.02","128.31","123.45","128.23","121,251,602"
58 | 12/18/2020,"128.96","129.10","126.12","126.66","192,541,500"
59 | 12/17/2020,"128.90","129.58","128.05","128.70","94,359,805"
60 | 12/16/2020,"127.41","128.37","126.56","127.81","98,208,594"
61 | 12/15/2020,"124.34","127.90","124.13","127.88","157,572,297"
62 | 12/14/2020,"122.60","123.35","121.54","121.78","79,075,992"
63 | 12/11/2020,"122.43","122.76","120.55","122.41","86,939,789"
64 | 12/10/2020,"120.50","123.87","120.15","123.24","81,312,172"
65 | 12/09/2020,"124.53","125.95","121.00","121.78","115,089,203"
66 | 12/08/2020,"124.37","124.98","123.09","124.38","82,225,516"
67 | 12/07/2020,"122.31","124.57","122.25","123.75","86,711,992"
68 | 12/04/2020,"122.60","122.86","121.52","122.25","78,260,414"
69 | 12/03/2020,"123.52","123.78","122.21","122.94","78,967,633"
70 | 12/02/2020,"122.02","123.37","120.89","123.08","89,004,203"
71 | 12/01/2020,"121.01","123.47","120.01","122.72","128,166,797"
72 | 11/30/2020,"116.97","120.97","116.81","119.05","169,410,203"
73 | 11/27/2020,"116.57","117.49","116.22","116.59","46,691,328"
74 | 11/25/2020,"115.55","116.75","115.17","116.03","76,499,234"
75 | 11/24/2020,"113.91","115.85","112.59","115.17","113,874,203"
76 | 11/23/2020,"117.18","117.62","113.75","113.85","127,959,297"
77 | 11/20/2020,"118.64","118.77","117.29","117.34","73,604,289"
78 | 11/19/2020,"117.59","119.06","116.81","118.64","74,112,969"
79 | 11/18/2020,"118.61","119.82","118.00","118.03","76,322,109"
80 | 11/17/2020,"119.55","120.67","118.96","119.39","74,270,969"
81 | 11/16/2020,"118.92","120.99","118.15","120.30","91,183,023"
82 | 11/13/2020,"119.44","119.67","117.87","119.26","81,688,594"
83 | 11/12/2020,"119.62","120.53","118.57","119.21","103,350,703"
84 | 11/11/2020,"117.19","119.63","116.44","119.49","112,295,000"
85 | 11/10/2020,"115.55","117.59","114.13","115.97","138,023,391"
86 | 11/09/2020,"120.50","121.99","116.05","116.32","154,515,297"
87 | 11/06/2020,"118.32","119.20","116.13","118.69","114,457,906"
88 | 11/05/2020,"117.95","119.62","116.87","119.03","126,387,102"
89 | 11/04/2020,"114.14","115.59","112.35","114.95","138,235,500"
90 | 11/03/2020,"109.66","111.49","108.73","110.44","107,624,398"
91 | 11/02/2020,"109.11","110.68","107.32","108.77","122,866,898"
92 | 10/30/2020,"111.06","111.99","107.72","108.86","190,573,500"
93 | 10/29/2020,"112.37","116.93","112.20","115.32","146,129,203"
94 | 10/28/2020,"115.05","115.43","111.10","111.20","143,937,797"
95 | 10/27/2020,"115.49","117.28","114.54","116.60","92,276,766"
96 | 10/26/2020,"114.01","116.55","112.88","115.05","111,850,703"
97 | 10/23/2020,"116.39","116.55","114.28","115.04","82,572,648"
98 | 10/22/2020,"117.45","118.04","114.59","115.75","101,988,000"
99 | 10/21/2020,"116.67","118.71","116.45","116.87","89,945,984"
100 | 10/20/2020,"116.20","118.98","115.63","117.51","124,423,695"
101 | 10/19/2020,"119.96","120.42","115.66","115.98","120,639,297"
102 | 10/16/2020,"121.28","121.55","118.81","119.02","115,393,797"
103 | 10/15/2020,"118.72","121.20","118.15","120.71","112,559,203"
104 | 10/14/2020,"121.00","123.03","119.62","121.19","151,062,297"
105 | 10/13/2020,"125.27","125.39","119.65","121.10","262,330,500"
106 | 10/12/2020,"120.06","125.18","119.28","124.40","240,226,797"
107 | 10/09/2020,"115.28","117.00","114.92","116.97","100,506,898"
108 | 10/08/2020,"116.25","116.40","114.59","114.97","83,477,148"
109 | 10/07/2020,"114.62","115.55","114.13","115.08","96,848,992"
110 | 10/06/2020,"115.70","116.12","112.25","113.16","161,498,203"
111 | 10/05/2020,"113.91","116.65","113.55","116.50","106,243,797"
112 | 10/02/2020,"112.89","115.37","112.22","113.02","144,712,000"
113 | 10/01/2020,"117.64","117.72","115.83","116.79","116,120,398"
114 | 09/30/2020,"113.79","117.26","113.62","115.81","142,675,203"
115 | 09/29/2020,"114.55","115.31","113.57","114.09","100,060,492"
116 | 09/28/2020,"115.01","115.32","112.78","114.96","137,672,406"
117 | 09/25/2020,"108.43","112.44","107.67","112.28","149,981,406"
118 | 09/24/2020,"105.17","110.25","105.00","108.22","167,743,297"
119 | 09/23/2020,"111.62","112.11","106.77","107.12","150,718,703"
120 | 09/22/2020,"112.68","112.86","109.16","111.81","183,055,391"
121 | 09/21/2020,"104.54","110.19","103.10","110.08","195,713,797"
122 | 09/18/2020,"110.40","110.88","106.09","106.84","287,104,906"
123 | 09/17/2020,"109.72","112.20","108.71","110.34","178,011,016"
124 | 09/16/2020,"115.23","116.00","112.04","112.13","155,026,703"
125 | 09/15/2020,"118.33","118.83","113.61","115.54","184,642,000"
126 | 09/14/2020,"114.72","115.93","112.80","115.36","140,150,094"
127 | 09/11/2020,"114.57","115.23","110.00","112.00","180,860,297"
128 | 09/10/2020,"120.36","120.50","112.50","113.49","182,274,406"
129 | 09/09/2020,"117.26","119.14","115.26","117.32","176,940,500"
130 | 09/08/2020,"113.95","118.99","112.68","112.82","231,366,594"
131 | 09/04/2020,"120.07","123.70","110.89","120.96","332,607,188"
132 | 09/03/2020,"126.91","128.84","120.50","120.88","257,599,594"
133 | 09/02/2020,"137.59","137.98","127.00","131.40","200,119,016"
134 | 09/01/2020,"132.76","134.80","130.53","134.18","152,470,094"
135 | 08/31/2020,"127.58","131.00","126.00","129.04","225,702,703"
136 | 08/28/2020,"126.01","126.44","124.58","124.81","187,629,920"
137 | 08/27/2020,"127.14","127.49","123.83","125.01","155,552,408"
138 | 08/26/2020,"126.18","126.99","125.08","126.52","163,022,264"
139 | 08/25/2020,"124.70","125.18","123.05","124.83","211,495,812"
140 | 08/24/2020,"128.70","128.79","123.94","125.86","345,937,752"
141 | 08/21/2020,"119.26","124.87","119.25","124.37","338,054,656"
142 | 08/20/2020,"115.75","118.39","115.73","118.28","126,907,204"
143 | 08/19/2020,"115.98","117.16","115.61","115.71","145,538,000"
144 | 08/18/2020,"114.35","116.00","114.01","115.56","105,633,564"
145 | 08/17/2020,"116.06","116.09","113.96","114.61","119,561,436"
146 | 08/14/2020,"114.83","115.00","113.05","114.91","165,565,204"
147 | 08/13/2020,"114.43","116.04","113.93","115.01","210,082,080"
148 | 08/12/2020,"110.50","113.28","110.30","113.01","165,944,828"
149 | 08/11/2020,"111.97","112.48","109.11","109.38","187,902,376"
150 | 08/10/2020,"112.60","113.78","110.00","112.73","212,403,436"
151 | 08/07/2020,"113.21","113.68","110.29","111.11","198,045,592"
152 | 08/06/2020,"110.41","114.41","109.80","113.90","202,428,920"
153 | 08/05/2020,"109.38","110.39","108.90","110.06","121,991,960"
154 | 08/04/2020,"109.13","110.79","108.39","109.67","172,792,360"
155 | 08/03/2020,"108.20","111.64","107.89","108.94","308,151,408"
156 | 07/31/2020,"102.88","106.42","100.83","106.26","374,295,500"
157 | 07/30/2020,"94.19","96.30","93.77","96.19","158,130,048"
158 | 07/29/2020,"93.75","95.23","93.71","95.04","90,329,244"
159 | 07/28/2020,"94.37","94.55","93.25","93.25","103,625,524"
160 | 07/27/2020,"93.71","94.91","93.48","94.81","121,214,204"
161 | 07/24/2020,"90.99","92.97","89.15","92.62","185,438,876"
162 | 07/23/2020,"97.00","97.08","92.01","92.85","197,004,452"
163 | 07/22/2020,"96.69","97.98","96.60","97.27","89,001,640"
164 | 07/21/2020,"99.17","99.25","96.74","97.00","103,645,844"
165 | 07/20/2020,"96.42","98.50","96.06","98.36","90,317,920"
166 | 07/17/2020,"96.99","97.15","95.84","96.33","92,186,920"
167 | 07/16/2020,"96.56","97.41","95.91","96.52","110,577,680"
168 | 07/15/2020,"98.99","99.25","96.49","97.73","153,197,920"
169 | 07/14/2020,"94.84","97.26","93.88","97.06","170,989,360"
170 | 07/13/2020,"97.27","99.96","95.26","95.48","191,649,156"
171 | 07/10/2020,"95.34","95.98","94.71","95.92","90,257,320"
172 | 07/09/2020,"96.26","96.32","94.67","95.68","125,642,600"
173 | 07/08/2020,"94.18","95.38","94.09","95.34","117,091,884"
174 | 07/07/2020,"93.85","94.66","93.06","93.17","112,424,436"
175 | 07/06/2020,"92.50","93.95","92.47","93.46","118,655,640"
176 | 07/02/2020,"91.96","92.62","90.91","91.03","114,041,476"
177 | 07/01/2020,"91.28","91.84","90.98","91.03","110,737,244"
178 | 06/30/2020,"90.02","91.50","90.00","91.20","140,223,280"
179 | 06/29/2020,"88.31","90.54","87.82","90.45","130,646,080"
180 | 06/26/2020,"91.10","91.33","88.26","88.41","205,256,828"
181 | 06/25/2020,"90.18","91.25","89.39","91.21","137,522,532"
182 | 06/24/2020,"91.25","92.20","89.63","90.02","192,623,392"
183 | 06/23/2020,"91.00","93.10","90.57","91.63","212,155,484"
184 | 06/22/2020,"87.84","89.87","87.79","89.72","135,445,280"
185 | 06/19/2020,"88.66","89.14","86.29","87.43","264,475,812"
186 | 06/18/2020,"87.85","88.36","87.31","87.93","96,820,400"
187 | 06/17/2020,"88.79","88.85","87.77","87.90","114,406,524"
188 | 06/16/2020,"87.87","88.30","86.18","88.02","165,428,720"
189 | 06/15/2020,"83.31","86.42","83.15","85.75","138,808,920"
190 | 06/12/2020,"86.18","86.95","83.56","84.70","200,146,048"
191 | 06/11/2020,"87.33","87.77","83.87","83.98","201,662,436"
192 | 06/10/2020,"86.98","88.69","86.52","88.21","166,651,764"
193 | 06/09/2020,"83.04","86.40","83.00","86.00","147,712,360"
194 | 06/08/2020,"82.56","83.40","81.83","83.37","95,654,524"
195 | 06/05/2020,"80.84","82.94","80.81","82.88","137,250,204"
196 | 06/04/2020,"81.10","81.41","80.20","80.58","87,560,360"
197 | 06/03/2020,"81.17","81.55","80.58","81.28","104,491,204"
198 | 06/02/2020,"80.19","80.86","79.73","80.84","87,642,796"
199 | 06/01/2020,"79.44","80.59","79.30","80.46","81,018,600"
200 | 05/29/2020,"79.81","80.29","79.12","79.49","153,598,108"
201 | 05/28/2020,"79.19","80.86","78.91","79.56","133,796,408"
202 | 05/27/2020,"79.04","79.68","78.27","79.53","112,945,080"
203 | 05/26/2020,"80.88","81.06","79.13","79.18","125,521,796"
204 | 05/22/2020,"78.94","79.81","78.84","79.72","81,803,000"
205 | 05/21/2020,"79.67","80.22","78.97","79.21","102,688,844"
206 | 05/20/2020,"79.17","79.88","79.05","79.81","111,504,884"
207 | 05/19/2020,"78.76","79.63","78.25","78.29","101,729,564"
208 | 05/18/2020,"78.29","79.13","77.58","78.74","135,372,516"
209 | 05/15/2020,"75.09","76.98","75.05","76.93","166,348,360"
210 | 05/14/2020,"76.13","77.45","75.38","77.39","158,929,092"
211 | 05/13/2020,"78.04","78.99","75.80","76.91","200,622,564"
212 | 05/12/2020,"79.46","79.92","77.73","77.85","162,301,048"
213 | 05/11/2020,"77.03","79.26","76.81","78.75","145,946,236"
214 | 05/08/2020,"76.41","77.59","76.07","77.53","134,047,952"
215 | 05/07/2020,"75.81","76.29","75.49","75.94","115,215,040"
216 | 05/06/2020,"75.12","75.81","74.72","75.16","142,333,764"
217 | 05/05/2020,"73.77","75.25","73.62","74.39","147,751,204"
218 | 05/04/2020,"72.29","73.42","71.58","73.29","133,567,952"
219 | 05/01/2020,"71.56","74.75","71.46","72.27","240,616,720"
220 | 04/30/2020,"72.49","73.63","72.09","73.45","183,063,876"
221 | 04/29/2020,"71.18","72.42","70.97","71.93","137,280,796"
222 | 04/28/2020,"71.27","71.46","69.55","69.65","112,004,756"
223 | 04/27/2020,"70.45","71.14","69.99","70.79","117,087,564"
224 | 04/24/2020,"69.30","70.75","69.25","70.74","126,508,720"
225 | 04/23/2020,"68.97","70.44","68.72","68.76","124,814,320"
226 | 04/22/2020,"68.40","69.48","68.05","69.03","117,057,360"
227 | 04/21/2020,"69.07","69.31","66.36","67.09","180,991,548"
228 | 04/20/2020,"69.49","70.42","69.21","69.23","130,015,000"
229 | 04/17/2020,"71.17","71.74","69.22","70.70","215,249,920"
230 | 04/16/2020,"71.85","72.05","70.59","71.67","157,125,156"
231 | 04/15/2020,"70.60","71.58","70.16","71.11","131,154,564"
232 | 04/14/2020,"70.00","72.06","69.51","71.76","194,994,688"
233 | 04/13/2020,"67.08","68.43","66.46","68.31","131,022,920"
234 | 04/09/2020,"67.18","67.52","66.18","67.00","162,116,484"
235 | 04/08/2020,"65.69","66.84","65.31","66.52","168,895,280"
236 | 04/07/2020,"67.70","67.93","64.75","64.86","202,887,328"
237 | 04/06/2020,"62.73","65.78","62.35","65.62","200,337,200"
238 | 04/03/2020,"60.70","61.43","59.74","60.35","129,880,080"
239 | 04/02/2020,"60.09","61.29","59.23","61.23","165,933,952"
240 | 04/01/2020,"61.63","62.18","59.78","60.23","176,218,564"
241 | 03/31/2020,"63.90","65.62","63.00","63.57","197,002,000"
242 | 03/30/2020,"62.69","63.88","62.35","63.70","167,976,452"
243 | 03/27/2020,"63.19","63.97","61.76","61.94","204,216,608"
244 | 03/26/2020,"61.63","64.67","61.59","64.61","252,560,672"
245 | 03/25/2020,"62.69","64.56","61.08","61.38","303,602,064"
246 | 03/24/2020,"59.09","61.92","58.58","61.72","287,531,064"
247 | 03/23/2020,"57.02","57.12","53.15","56.09","336,752,844"
248 | 03/20/2020,"61.80","62.96","57.00","57.31","401,693,188"
249 | 03/19/2020,"61.85","63.21","60.65","61.20","271,857,032"
250 | 03/18/2020,"59.94","62.50","59.28","61.67","300,233,624"
251 | 03/17/2020,"61.88","64.40","59.60","63.22","324,055,876"
252 | 03/16/2020,"60.49","64.77","60.00","60.55","322,423,500"
253 |
--------------------------------------------------------------------------------
/Doge_Predict_A2C.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "kernelspec": {
6 | "display_name": "Python 3",
7 | "language": "python",
8 | "name": "python3"
9 | },
10 | "language_info": {
11 | "codemirror_mode": {
12 | "name": "ipython",
13 | "version": 3
14 | },
15 | "file_extension": ".py",
16 | "mimetype": "text/x-python",
17 | "name": "python",
18 | "nbconvert_exporter": "python",
19 | "pygments_lexer": "ipython3",
20 | "version": "3.7.3"
21 | },
22 | "colab": {
23 | "name": "Doge Predict A2C.ipynb",
24 | "provenance": [],
25 | "collapsed_sections": [],
26 | "include_colab_link": true
27 | }
28 | },
29 | "cells": [
30 | {
31 | "cell_type": "markdown",
32 | "metadata": {
33 | "id": "view-in-github",
34 | "colab_type": "text"
35 | },
36 | "source": [
37 | "![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\")
"
38 | ]
39 | },
40 | {
41 | "cell_type": "markdown",
42 | "metadata": {
43 | "id": "iHtx87S1IoIp"
44 | },
45 | "source": [
46 | "#Dependencies"
47 | ]
48 | },
49 | {
50 | "cell_type": "code",
51 | "metadata": {
52 | "collapsed": true,
53 | "id": "cEMIqiDfIoIq"
54 | },
55 | "source": [
56 | "!pip install tensorflow-gpu==1.15.0 tensorflow==1.15.0 stable-baselines gym-anytrading gym"
57 | ],
58 | "execution_count": null,
59 | "outputs": []
60 | },
61 | {
62 | "cell_type": "code",
63 | "metadata": {
64 | "id": "-Msb95l5IoIr"
65 | },
66 | "source": [
67 | "\n",
68 | "import gym\n",
69 | "import gym_anytrading\n",
70 | "\n",
71 | "\n",
72 | "from stable_baselines.common.vec_env import DummyVecEnv\n",
73 | "from stable_baselines import A2C\n",
74 | "\n",
75 | "\n",
76 | "import numpy as np\n",
77 | "import pandas as pd\n",
78 | "from matplotlib import pyplot as plt"
79 | ],
80 | "execution_count": null,
81 | "outputs": []
82 | },
83 | {
84 | "cell_type": "markdown",
85 | "metadata": {
86 | "id": "nz6WJkO2IoIs"
87 | },
88 | "source": [
89 | "#Importing Data"
90 | ]
91 | },
92 | {
93 | "cell_type": "code",
94 | "metadata": {
95 | "id": "apKdZZjHIoIs"
96 | },
97 | "source": [
98 | "df = pd.read_csv('doge.csv')"
99 | ],
100 | "execution_count": 13,
101 | "outputs": []
102 | },
103 | {
104 | "cell_type": "code",
105 | "metadata": {
106 | "colab": {
107 | "base_uri": "https://localhost:8080/",
108 | "height": 204
109 | },
110 | "id": "XLrDZ20xIoIs",
111 | "outputId": "23ae64ee-3907-469c-a411-18fb78486bfa"
112 | },
113 | "source": [
114 | "df.head()"
115 | ],
116 | "execution_count": 14,
117 | "outputs": [
118 | {
119 | "output_type": "execute_result",
120 | "data": {
121 | "text/html": [
122 | "\n",
123 | "\n",
136 | "
\n",
137 | " \n",
138 | " \n",
139 | " | \n",
140 | " Date | \n",
141 | " Open | \n",
142 | " High | \n",
143 | " Low | \n",
144 | " Close | \n",
145 | " Volume | \n",
146 | "
\n",
147 | " \n",
148 | " \n",
149 | " \n",
150 | " | 0 | \n",
151 | " 03/12/21 | \n",
152 | " 0.330407 | \n",
153 | " 0.432618 | \n",
154 | " 0.297074 | \n",
155 | " 0.397741 | \n",
156 | " 13850000000 | \n",
157 | "
\n",
158 | " \n",
159 | " | 1 | \n",
160 | " 03/11/21 | \n",
161 | " 0.474719 | \n",
162 | " 0.477866 | \n",
163 | " 0.217528 | \n",
164 | " 0.330353 | \n",
165 | " 19280000000 | \n",
166 | "
\n",
167 | " \n",
168 | " | 2 | \n",
169 | " 03/10/21 | \n",
170 | " 0.486444 | \n",
171 | " 0.512529 | \n",
172 | " 0.468941 | \n",
173 | " 0.474714 | \n",
174 | " 4750000000 | \n",
175 | "
\n",
176 | " \n",
177 | " | 3 | \n",
178 | " 03/09/21 | \n",
179 | " 0.513062 | \n",
180 | " 0.514821 | \n",
181 | " 0.457331 | \n",
182 | " 0.486366 | \n",
183 | " 6840000000 | \n",
184 | "
\n",
185 | " \n",
186 | " | 4 | \n",
187 | " 03/08/21 | \n",
188 | " 0.507796 | \n",
189 | " 0.547205 | \n",
190 | " 0.449635 | \n",
191 | " 0.513023 | \n",
192 | " 8260000000 | \n",
193 | "
\n",
194 | " \n",
195 | "
\n",
196 | "
\n",
270 | "\n",
283 | "
\n",
284 | " \n",
285 | " \n",
286 | " | \n",
287 | " Open | \n",
288 | " High | \n",
289 | " Low | \n",
290 | " Close | \n",
291 | " Volume | \n",
292 | "
\n",
293 | " \n",
294 | " | Date | \n",
295 | " | \n",
296 | " | \n",
297 | " | \n",
298 | " | \n",
299 | " | \n",
300 | "
\n",
301 | " \n",
302 | " \n",
303 | " \n",
304 | " | 2021-03-12 | \n",
305 | " 0.330407 | \n",
306 | " 0.432618 | \n",
307 | " 0.297074 | \n",
308 | " 0.397741 | \n",
309 | " 13850000000 | \n",
310 | "
\n",
311 | " \n",
312 | " | 2021-03-11 | \n",
313 | " 0.474719 | \n",
314 | " 0.477866 | \n",
315 | " 0.217528 | \n",
316 | " 0.330353 | \n",
317 | " 19280000000 | \n",
318 | "
\n",
319 | " \n",
320 | " | 2021-03-10 | \n",
321 | " 0.486444 | \n",
322 | " 0.512529 | \n",
323 | " 0.468941 | \n",
324 | " 0.474714 | \n",
325 | " 4750000000 | \n",
326 | "
\n",
327 | " \n",
328 | " | 2021-03-09 | \n",
329 | " 0.513062 | \n",
330 | " 0.514821 | \n",
331 | " 0.457331 | \n",
332 | " 0.486366 | \n",
333 | " 6840000000 | \n",
334 | "
\n",
335 | " \n",
336 | " | 2021-03-08 | \n",
337 | " 0.507796 | \n",
338 | " 0.547205 | \n",
339 | " 0.449635 | \n",
340 | " 0.513023 | \n",
341 | " 8260000000 | \n",
342 | "
\n",
343 | " \n",
344 | "
\n",
345 | "