├── .ipynb_checkpoints
    └── auto_coin_list-checkpoint.ipynb
├── README.md
├── auto_coin_list.ipynb
├── correlation script.ipynb
└── requirements.txt


/.ipynb_checkpoints/auto_coin_list-checkpoint.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 2,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import os\n",
 10 |     "from binance.client import Client\n",
 11 |     "from datetime import datetime, timedelta\n",
 12 |     "import matplotlib.pyplot as plt\n",
 13 |     "import numpy as np\n",
 14 |     "import pandas as pd\n",
 15 |     "import seaborn as sn"
 16 |    ]
 17 |   },
 18 |   {
 19 |    "cell_type": "markdown",
 20 |    "metadata": {},
 21 |    "source": [
 22 |     "## The Automatic Correlated Coin List (TACCL)"
 23 |    ]
 24 |   },
 25 |   {
 26 |    "cell_type": "markdown",
 27 |    "metadata": {},
 28 |    "source": [
 29 |     "This script will allow you to build a list of correlated coins around a coin of your choice. You will need: \n",
 30 |     "\n",
 31 |     "1. A binance API Key\n",
 32 |     "2. A chosen Bridge coin (Default USDT)\n",
 33 |     "3. A chosen start coin (Default QUMT)\n",
 34 |     "\n",
 35 |     "The script will do the rest. This is not a trading recommendation. Trading is risky, do not trade with money you cannot afford to lose. \n",
 36 |     "\n",
 37 |     "#### Basic strategy: \n",
 38 |     "\n",
 39 |     "This script will gather the data for all coin pairs available for your bridge coin. It will sequentially choose coins that maximise the sum of the correlations. This heuristic should pick a good list of co-related coins. "
 40 |    ]
 41 |   },
 42 |   {
 43 |    "cell_type": "markdown",
 44 |    "metadata": {},
 45 |    "source": [
 46 |     "## Usage Instructions"
 47 |    ]
 48 |   },
 49 |   {
 50 |    "cell_type": "markdown",
 51 |    "metadata": {},
 52 |    "source": [
 53 |     "Run every line of the script. The final two boxes will display the recommended coin list and the heatmap of the rolling average for the last 24 hours."
 54 |    ]
 55 |   },
 56 |   {
 57 |    "cell_type": "code",
 58 |    "execution_count": 10,
 59 |    "metadata": {},
 60 |    "outputs": [],
 61 |    "source": [
 62 |     "api_key = PUT YOUR OWN KEY HERE\n",
 63 |     "api_secret = PUT YOUR OWN KEY HERE\n",
 64 |     "client = Client(api_key, api_secret)"
 65 |    ]
 66 |   },
 67 |   {
 68 |    "cell_type": "code",
 69 |    "execution_count": 11,
 70 |    "metadata": {},
 71 |    "outputs": [],
 72 |    "source": [
 73 |     "def get_ticker_price(ticker_symbol: str, days:int ):\n",
 74 |     "    \"\"\"\n",
 75 |     "    Gets ticker price of a specific coin\n",
 76 |     "    \"\"\"\n",
 77 |     "\n",
 78 |     "    target_date = (datetime.now() -timedelta(days = days)).strftime(\"%d %b %Y %H:%M:%S\")\n",
 79 |     "    key = f\"{ticker_symbol}\"\n",
 80 |     "    end_date = datetime.now() \n",
 81 |     "    end_date = end_date.strftime(\"%d %b %Y %H:%M:%S\")\n",
 82 |     "    \n",
 83 |     "    coindata = pd.DataFrame(columns = [key])\n",
 84 |     "    \n",
 85 |     "    prices = []\n",
 86 |     "    dates = []\n",
 87 |     "    for result in client.get_historical_klines(\n",
 88 |     "        ticker_symbol, \"1m\", target_date, end_date, limit=1000\n",
 89 |     "        ):\n",
 90 |     "        date = datetime.utcfromtimestamp(result[0] / 1000).strftime(\"%d %b %Y %H:%M:%S\")\n",
 91 |     "        price = float(result[1])\n",
 92 |     "        dates.append(date)\n",
 93 |     "        prices.append(price)\n",
 94 |     "\n",
 95 |     "    coindata[key] = prices\n",
 96 |     "    coindata['date'] = dates\n",
 97 |     "\n",
 98 |     "\n",
 99 |     "\n",
100 |     "\n",
101 |     "    return(coindata.reindex(columns =['date',key]))"
102 |    ]
103 |   },
104 |   {
105 |    "cell_type": "code",
106 |    "execution_count": 18,
107 |    "metadata": {},
108 |    "outputs": [],
109 |    "source": [
110 |     "def get_price_data(tickers, window = 1, granularity = \"1m\"):\n",
111 |     "    '''\n",
112 |     "    Collects price data from the binance server.\n",
113 |     "    '''\n",
114 |     "    failures = []\n",
115 |     "    coindata = get_ticker_price(tickers[0],1)\n",
116 |     "    for tick in tickers[1:]:\n",
117 |     "        newdata = get_ticker_price(tick,1)\n",
118 |     "        if not newdata.empty:\n",
119 |     "            coindata = pd.merge(coindata, newdata)\n",
120 |     "        else:\n",
121 |     "            failures.append(tick)\n",
122 |     "    print('The following coins do not have historical data')\n",
123 |     "    print(failures)\n",
124 |     "    return(coindata)"
125 |    ]
126 |   },
127 |   {
128 |    "cell_type": "code",
129 |    "execution_count": 13,
130 |    "metadata": {},
131 |    "outputs": [],
132 |    "source": [
133 |     "def take_rolling_average(coindata):\n",
134 |     "\n",
135 |     "    RA = pd.DataFrame()\n",
136 |     "\n",
137 |     "    for column in coindata:\n",
138 |     "        if column != 'date':\n",
139 |     "            RA[column] = coindata[column].rolling(window=3).mean()\n",
140 |     "    return(RA)"
141 |    ]
142 |   },
143 |   {
144 |    "cell_type": "code",
145 |    "execution_count": 14,
146 |    "metadata": {},
147 |    "outputs": [],
148 |    "source": [
149 |     "def pick_coins(start_ticker , day_corr , week_corr, two_week_corr, n):\n",
150 |     "    '''\n",
151 |     "    Takes your starting coin, then sequentially picks the coin that jointly maximises\n",
152 |     "    the correlation for the whole coin list.\n",
153 |     "    \n",
154 |     "    INPUT:\n",
155 |     "    start_ticker : STR : The ticker for a coin you wish to include in your list\n",
156 |     "    day_corr     : PD.CORR : daily correlation data\n",
157 |     "    week_corr    : PD.CORR : Weekly correlation data\n",
158 |     "    two_week_corr: PD.CORR : bi-weekly correlation data\n",
159 |     "    n            : INTEGER : number of coins to include in your list.\n",
160 |     "    '''\n",
161 |     "    \n",
162 |     "    coinlist = [start_ticker]\n",
163 |     "    for i in range(n-1):    \n",
164 |     "        new_day_corr = day_corr[~day_corr.index.isin(coinlist)]\n",
165 |     "        new_week_corr = week_corr[~week_corr.index.isin(coinlist)]\n",
166 |     "        new_two_week_corr = two_week_corr[~two_week_corr.index.isin(coinlist)]\n",
167 |     "        corrsum = pd.DataFrame()\n",
168 |     "        for coin in coinlist:\n",
169 |     "            if corrsum.empty:\n",
170 |     "                corrsum = new_day_corr[coin] + new_week_corr[coin] + new_two_week_corr[coin]\n",
171 |     "            else:\n",
172 |     "                corrsum += new_day_corr[coin] + new_week_corr[coin] + new_two_week_corr[coin]\n",
173 |     "                \n",
174 |     "        ind = corrsum.argmax()\n",
175 |     "        coinlist.append(new_day_corr.index[ind])\n",
176 |     "    return(coinlist)"
177 |    ]
178 |   },
179 |   {
180 |    "cell_type": "markdown",
181 |    "metadata": {},
182 |    "source": [
183 |     "# Choose your Bridge coin and Starting coin here"
184 |    ]
185 |   },
186 |   {
187 |    "cell_type": "code",
188 |    "execution_count": 15,
189 |    "metadata": {},
190 |    "outputs": [],
191 |    "source": [
192 |     "bridge = 'USDT'\n",
193 |     "startcoin = 'QTUM'\n",
194 |     "size_of_list = 10"
195 |    ]
196 |   },
197 |   {
198 |    "cell_type": "code",
199 |    "execution_count": 16,
200 |    "metadata": {},
201 |    "outputs": [],
202 |    "source": [
203 |     "client = Client(api_key, api_secret)\n",
204 |     "\n",
205 |     "# Download ALL the coinpairs from binance\n",
206 |     "exchange_info = client.get_exchange_info()\n",
207 |     "\n",
208 |     "full_coin_list = [] \n",
209 |     "\n",
210 |     "# Only keep the pairs to our bridge coin\n",
211 |     "for s in exchange_info['symbols']:\n",
212 |     "    if s['symbol'].endswith(bridge):\n",
213 |     "        full_coin_list.append(s['symbol'][:-4])\n",
214 |     "\n",
215 |     "# List of words to eliminate futures markets coins\n",
216 |     "forbidden_words = ['DOWN','UP','BULL','BEAR']\n",
217 |     "for forbidden in forbidden_words:\n",
218 |     "    full_coin_list = [word for word in full_coin_list if forbidden not in word]\n",
219 |     "\n",
220 |     "#Alphabetical order because pretty :)\n",
221 |     "full_coin_list.sort()"
222 |    ]
223 |   },
224 |   {
225 |    "cell_type": "code",
226 |    "execution_count": 19,
227 |    "metadata": {},
228 |    "outputs": [
229 |     {
230 |      "name": "stdout",
231 |      "output_type": "stream",
232 |      "text": [
233 |       "The following coins do not have historical data\n",
234 |       "['BCCUSDT', 'BCHABCUSDT', 'BCHSVUSDT', 'BKRWUSDT', 'DAIUSDT', 'ERDUSDT', 'HCUSDT', 'LENDUSDT', 'MCOUSDT', 'NPXSUSDT', 'STORMUSDT', 'STRATUSDT', 'USDSUSDT', 'USDSBUSDT', 'VENUSDT', 'XZCUSDT']\n",
235 |       "The following coins do not have historical data\n",
236 |       "['BCCUSDT', 'BCHABCUSDT', 'BCHSVUSDT', 'BKRWUSDT', 'DAIUSDT', 'ERDUSDT', 'HCUSDT', 'LENDUSDT', 'MCOUSDT', 'NPXSUSDT', 'STORMUSDT', 'STRATUSDT', 'USDSUSDT', 'USDSBUSDT', 'VENUSDT', 'XZCUSDT']\n",
237 |       "The following coins do not have historical data\n",
238 |       "['BCCUSDT', 'BCHABCUSDT', 'BCHSVUSDT', 'BKRWUSDT', 'DAIUSDT', 'ERDUSDT', 'HCUSDT', 'LENDUSDT', 'MCOUSDT', 'NPXSUSDT', 'STORMUSDT', 'STRATUSDT', 'USDSUSDT', 'USDSBUSDT', 'VENUSDT', 'XZCUSDT']\n"
239 |      ]
240 |     }
241 |    ],
242 |    "source": [
243 |     "# Collect the data for 3 different windows (1 day, 1 week, 2 weeks)\n",
244 |     "# with granularity (1 minute, 1 hour ,2 hours)\n",
245 |     "\n",
246 |     "cointickers = [coin+ bridge for coin in full_coin_list]\n",
247 |     "day_data = get_price_data(cointickers, 1, \"1m\")\n",
248 |     "week_data = get_price_data(cointickers, 7, \"1h\")\n",
249 |     "two_week_data = get_price_data(cointickers, 14, \"2h\")"
250 |    ]
251 |   },
252 |   {
253 |    "cell_type": "code",
254 |    "execution_count": 21,
255 |    "metadata": {},
256 |    "outputs": [],
257 |    "source": [
258 |     "# Calculate the rolling average (RA3) for all the coins \n",
259 |     "\n",
260 |     "RA_day_data = take_rolling_average(day_data)\n",
261 |     "RA_week_data = take_rolling_average(week_data)\n",
262 |     "RA_2week_data = take_rolling_average(two_week_data)"
263 |    ]
264 |   },
265 |   {
266 |    "cell_type": "code",
267 |    "execution_count": 22,
268 |    "metadata": {},
269 |    "outputs": [],
270 |    "source": [
271 |     "# take the correlations of the rolling averages.\n",
272 |     "\n",
273 |     "day_corr = RA_day_data.corr()\n",
274 |     "week_corr = RA_week_data.corr()\n",
275 |     "two_week_corr = RA_2week_data.corr()\n",
276 |     "\n",
277 |     "coinlist = pick_coins(startcoin + bridge, day_corr , week_corr , two_week_corr , size_of_list )"
278 |    ]
279 |   },
280 |   {
281 |    "cell_type": "markdown",
282 |    "metadata": {},
283 |    "source": [
284 |     "# TACCL result: "
285 |    ]
286 |   },
287 |   {
288 |    "cell_type": "markdown",
289 |    "metadata": {},
290 |    "source": [
291 |     "This list is not a recommended trading list. Do not risk money if you are not sure what you are doing. "
292 |    ]
293 |   },
294 |   {
295 |    "cell_type": "code",
296 |    "execution_count": 27,
297 |    "metadata": {},
298 |    "outputs": [
299 |     {
300 |      "name": "stdout",
301 |      "output_type": "stream",
302 |      "text": [
303 |       "['QTUM', 'VET', 'BTT', 'LSK', 'ZIL', 'ONT', 'ONG', 'NEO', 'ZRX', 'ARDR']\n"
304 |      ]
305 |     }
306 |    ],
307 |    "source": [
308 |     "coins = [coin.replace(bridge,'') for coin in coinlist]\n",
309 |     "print(coins)"
310 |    ]
311 |   },
312 |   {
313 |    "cell_type": "markdown",
314 |    "metadata": {},
315 |    "source": [
316 |     "The rest of the code will plot the correlation matric for the rolling average of the selected coins."
317 |    ]
318 |   },
319 |   {
320 |    "cell_type": "code",
321 |    "execution_count": 28,
322 |    "metadata": {},
323 |    "outputs": [],
324 |    "source": [
325 |     "# Grab coin prices from binance server \n",
326 |     "\n",
327 |     "### Set Period here ###\n",
328 |     "num_days = 1\n",
329 |     "###\n",
330 |     "\n",
331 |     "#Create initial df with first coin then fill with all from list\n",
332 |     "\n",
333 |     "coindata = get_ticker_price(coinlist[0],num_days)\n",
334 |     "for tick in coinlist[1:]:\n",
335 |     "    newdata = get_ticker_price(tick,num_days)\n",
336 |     "    coindata = pd.merge(coindata, newdata)"
337 |    ]
338 |   },
339 |   {
340 |    "cell_type": "code",
341 |    "execution_count": 29,
342 |    "metadata": {
343 |     "scrolled": true
344 |    },
345 |    "outputs": [
346 |     {
347 |      "data": {
348 |       "image/png": "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\n",
349 |       "text/plain": [
350 |        "<Figure size 1440x1440 with 2 Axes>"
351 |       ]
352 |      },
353 |      "metadata": {
354 |       "needs_background": "light"
355 |      },
356 |      "output_type": "display_data"
357 |     }
358 |    ],
359 |    "source": [
360 |     "### Examine the trend of the rolling average\n",
361 |     "\n",
362 |     "radf2 = pd.DataFrame()\n",
363 |     "\n",
364 |     "for column in coindata:\n",
365 |     "    if column != 'date':\n",
366 |     "        radf2[column] = coindata[column].rolling(window=3).mean()\n",
367 |     "\n",
368 |     "corrMatrix = radf2.corr()\n",
369 |     "fig = plt.figure(figsize=(20,20))\n",
370 |     "sn.heatmap(corrMatrix, annot=True)\n",
371 |     "plt.title('Correlation for Rolling mean')\n",
372 |     "plt.show()"
373 |    ]
374 |   },
375 |   {
376 |    "cell_type": "code",
377 |    "execution_count": null,
378 |    "metadata": {},
379 |    "outputs": [],
380 |    "source": [
381 |     "# Print average correlation. \n",
382 |     "\n",
383 |     "print(f\"Correlation avg: {corrMatrix.values[np.triu_indices_from(corrMatrix.values,1)].mean()}\")"
384 |    ]
385 |   }
386 |  ],
387 |  "metadata": {
388 |   "kernelspec": {
389 |    "display_name": "Python 3.7.7 64-bit ('SAIL': conda)",
390 |    "language": "python",
391 |    "name": "python377jvsc74a57bd0ab71b7b42b43c15f1c9e79e31db88a750ed80330c48386c0633a863b3dbc7252"
392 |   },
393 |   "language_info": {
394 |    "codemirror_mode": {
395 |     "name": "ipython",
396 |     "version": 3
397 |    },
398 |    "file_extension": ".py",
399 |    "mimetype": "text/x-python",
400 |    "name": "python",
401 |    "nbconvert_exporter": "python",
402 |    "pygments_lexer": "ipython3",
403 |    "version": "3.7.7"
404 |   }
405 |  },
406 |  "nbformat": 4,
407 |  "nbformat_minor": 2
408 | }
409 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | ## About these scripts
 2 | 
 3 | These scripts were created in order to support the selection of coin trading lists for use with automated trading strategies. Specifically, this one https://github.com/edeng23/binance-trade-bot
 4 | 
 5 | ## How to use
 6 | 
 7 | Install requirements with 
 8 | 
 9 | ```python
10 | python install -r requirements.txt
11 | ```
12 | 
13 | The scripts are python notebooks, whilst they use python 3, you will need jupyter notebook (or something that reads notebook docs) to access it.
14 | https://jupyter.org/
15 | 
16 | 
17 | ## Automatic Correlated Coin List - auto_coin_list.ipynb
18 | ##### WARNING - This can take some time to run as it downloads a lot of data from binance servers
19 | An automatic coin list generator that will scout binance for the most correlated trading pairs to a single starting coin. It will 
20 | 
21 | 1. Provide an automatic list for running a reverse greedy trading algorithm
22 | 2. Plot a volatility histogram
23 | 3. Plot correlation heat maps over different periods
24 | 4. calculate trade volume in USD and warn against coins at high risk of slippage
25 | 
26 | 
27 | 
28 | ## binance_correlation_script
29 | 
30 | A jupyter notebook that calculates correlation matrices for crypto coins in binance exchange
31 | 
32 | This script will require a binance API key to run and will do the following
33 | 
34 | 
35 | **1.** Download binance coin data from coinlist
36 | 
37 | **2.** Produce correlation matrix for
38 | 
39 | &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;**Raw Coin value** (1 minute intervals)
40 | 
41 | &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;**Detrended coin value** (first difference)
42 | 
43 | &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;**Detrended coin value** (rolling mean) 
44 |   
45 | &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;**rolling mean** itself
46 | 
47 | coded in Python 3.7
48 | 
49 | 
50 | 


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | python-binance==0.7.9
2 | datetime
3 | matplotlib==3.3.1
4 | numpy==1.19.1
5 | pandas==1.2.4
6 | seaborn==0.11.1
7 | 


--------------------------------------------------------------------------------