cryptodatapy 0.2.1__py3-none-any.whl → 0.2.3__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (15) hide show
  1. cryptodatapy/.DS_Store +0 -0
  2. cryptodatapy/conf/fx_tickers.csv +31 -0
  3. cryptodatapy/conf/tickers.csv +6 -0
  4. cryptodatapy/extract/libraries/ccxt_api.py +81 -60
  5. cryptodatapy/extract/libraries/library.py +19 -8
  6. cryptodatapy/transform/clean.py +136 -173
  7. cryptodatapy/transform/clean_perp_futures_ohlcv.ipynb +1639 -0
  8. cryptodatapy/transform/filter.py +56 -143
  9. cryptodatapy/transform/impute.py +36 -83
  10. cryptodatapy/transform/od.py +221 -450
  11. cryptodatapy/transform/wrangle.py +2 -4
  12. {cryptodatapy-0.2.1.dist-info → cryptodatapy-0.2.3.dist-info}/METADATA +1 -1
  13. {cryptodatapy-0.2.1.dist-info → cryptodatapy-0.2.3.dist-info}/RECORD +15 -13
  14. {cryptodatapy-0.2.1.dist-info → cryptodatapy-0.2.3.dist-info}/LICENSE +0 -0
  15. {cryptodatapy-0.2.1.dist-info → cryptodatapy-0.2.3.dist-info}/WHEEL +0 -0
cryptodatapy/transform/clean_perp_futures_ohlcv.ipynb ADDED
@@ -0,0 +1,1639 @@
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 86,
6
+ "id": "9fea9fae",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "import pandas as pd\n",
11
+ "import numpy as np\n",
12
+ "\n",
13
+ "from cryptodatapy.extract.datarequest import DataRequest\n",
14
+ "from cryptodatapy.extract.getdata import GetData\n",
15
+ "from cryptodatapy.transform.od import OutlierDetection\n",
16
+ "from cryptodatapy.transform.impute import Impute\n",
17
+ "from cryptodatapy.transform.filter import Filter\n",
18
+ "from cryptodatapy.transform.clean import CleanData, stitch_dataframes\n",
19
+ "from cryptodatapy.transform.impute import Impute"
20
+ ]
21
+ },
22
+ {
23
+ "cell_type": "code",
24
+ "execution_count": 94,
25
+ "id": "c9876f0b",
26
+ "metadata": {},
27
+ "outputs": [],
28
+ "source": [
29
+ "data_req = DataRequest(source='tiingo')"
30
+ ]
31
+ },
32
+ {
33
+ "cell_type": "code",
34
+ "execution_count": 95,
35
+ "id": "e23c9751",
36
+ "metadata": {},
37
+ "outputs": [
38
+ {
39
+ "ename": "AttributeError",
40
+ "evalue": "'Tiingo' object has no attribute 'get_top_mkt_cap_info'",
41
+ "output_type": "error",
42
+ "traceback": [
43
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
44
+ "\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
45
+ "Cell \u001b[0;32mIn [95], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m GetData(data_req)\u001b[38;5;241m.\u001b[39mget_meta(method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mget_top_mkt_cap_info\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
46
+ "File \u001b[0;32m~/projects/systamental/cryptodatapy/src/cryptodatapy/extract/getdata.py:145\u001b[0m, in \u001b[0;36mGetData.get_meta\u001b[0;34m(self, attr, method, **kwargs)\u001b[0m\n\u001b[1;32m 143\u001b[0m meta \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mgetattr\u001b[39m(ds, attr)\n\u001b[1;32m 144\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m method \u001b[38;5;129;01min\u001b[39;00m valid_meth:\n\u001b[0;32m--> 145\u001b[0m meta \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mgetattr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mds\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m)\u001b[49m(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 146\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 147\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mAttributeError\u001b[39;00m(\n\u001b[1;32m 148\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mSelect a valid attribute or method. Valid attributes: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mvalid_attr\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 149\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m Valid methods include: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mvalid_meth\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 150\u001b[0m )\n",
47
+ "\u001b[0;31mAttributeError\u001b[0m: 'Tiingo' object has no attribute 'get_top_mkt_cap_info'"
48
+ ]
49
+ }
50
+ ],
51
+ "source": [
52
+ "GetData(data_req).get_meta(method='get_top_mkt_cap_info')"
53
+ ]
54
+ },
55
+ {
56
+ "cell_type": "code",
57
+ "execution_count": 89,
58
+ "id": "b8facf81",
59
+ "metadata": {},
60
+ "outputs": [
61
+ {
62
+ "data": {
63
+ "text/html": [
64
+ "<div>\n",
65
+ "<style scoped>\n",
66
+ " .dataframe tbody tr th:only-of-type {\n",
67
+ " vertical-align: middle;\n",
68
+ " }\n",
69
+ "\n",
70
+ " .dataframe tbody tr th {\n",
71
+ " vertical-align: top;\n",
72
+ " }\n",
73
+ "\n",
74
+ " .dataframe thead th {\n",
75
+ " text-align: right;\n",
76
+ " }\n",
77
+ "</style>\n",
78
+ "<table border=\"1\" class=\"dataframe\">\n",
79
+ " <thead>\n",
80
+ " <tr style=\"text-align: right;\">\n",
81
+ " <th></th>\n",
82
+ " <th></th>\n",
83
+ " <th>close</th>\n",
84
+ " </tr>\n",
85
+ " <tr>\n",
86
+ " <th>date</th>\n",
87
+ " <th>ticker</th>\n",
88
+ " <th></th>\n",
89
+ " </tr>\n",
90
+ " </thead>\n",
91
+ " <tbody>\n",
92
+ " <tr>\n",
93
+ " <th>2019-01-31</th>\n",
94
+ " <th>EURUSD</th>\n",
95
+ " <td>1.147579</td>\n",
96
+ " </tr>\n",
97
+ " <tr>\n",
98
+ " <th>2019-02-28</th>\n",
99
+ " <th>EURUSD</th>\n",
100
+ " <td>1.138693</td>\n",
101
+ " </tr>\n",
102
+ " <tr>\n",
103
+ " <th>2019-03-31</th>\n",
104
+ " <th>EURUSD</th>\n",
105
+ " <td>1.122355</td>\n",
106
+ " </tr>\n",
107
+ " <tr>\n",
108
+ " <th>2019-04-30</th>\n",
109
+ " <th>EURUSD</th>\n",
110
+ " <td>1.120699</td>\n",
111
+ " </tr>\n",
112
+ " <tr>\n",
113
+ " <th>2019-05-31</th>\n",
114
+ " <th>EURUSD</th>\n",
115
+ " <td>1.11433</td>\n",
116
+ " </tr>\n",
117
+ " <tr>\n",
118
+ " <th>...</th>\n",
119
+ " <th>...</th>\n",
120
+ " <td>...</td>\n",
121
+ " </tr>\n",
122
+ " <tr>\n",
123
+ " <th>2024-04-30</th>\n",
124
+ " <th>EURUSD</th>\n",
125
+ " <td>1.066605</td>\n",
126
+ " </tr>\n",
127
+ " <tr>\n",
128
+ " <th>2024-05-31</th>\n",
129
+ " <th>EURUSD</th>\n",
130
+ " <td>1.084825</td>\n",
131
+ " </tr>\n",
132
+ " <tr>\n",
133
+ " <th>2024-06-30</th>\n",
134
+ " <th>EURUSD</th>\n",
135
+ " <td>1.073515</td>\n",
136
+ " </tr>\n",
137
+ " <tr>\n",
138
+ " <th>2024-07-31</th>\n",
139
+ " <th>EURUSD</th>\n",
140
+ " <td>1.082395</td>\n",
141
+ " </tr>\n",
142
+ " <tr>\n",
143
+ " <th>2024-08-31</th>\n",
144
+ " <th>EURUSD</th>\n",
145
+ " <td>1.092375</td>\n",
146
+ " </tr>\n",
147
+ " </tbody>\n",
148
+ "</table>\n",
149
+ "<p>68 rows × 1 columns</p>\n",
150
+ "</div>"
151
+ ],
152
+ "text/plain": [
153
+ " close\n",
154
+ "date ticker \n",
155
+ "2019-01-31 EURUSD 1.147579\n",
156
+ "2019-02-28 EURUSD 1.138693\n",
157
+ "2019-03-31 EURUSD 1.122355\n",
158
+ "2019-04-30 EURUSD 1.120699\n",
159
+ "2019-05-31 EURUSD 1.11433\n",
160
+ "... ...\n",
161
+ "2024-04-30 EURUSD 1.066605\n",
162
+ "2024-05-31 EURUSD 1.084825\n",
163
+ "2024-06-30 EURUSD 1.073515\n",
164
+ "2024-07-31 EURUSD 1.082395\n",
165
+ "2024-08-31 EURUSD 1.092375\n",
166
+ "\n",
167
+ "[68 rows x 1 columns]"
168
+ ]
169
+ },
170
+ "execution_count": 89,
171
+ "metadata": {},
172
+ "output_type": "execute_result"
173
+ }
174
+ ],
175
+ "source": [
176
+ "fx_df"
177
+ ]
178
+ },
179
+ {
180
+ "cell_type": "code",
181
+ "execution_count": null,
182
+ "id": "005404ee",
183
+ "metadata": {},
184
+ "outputs": [],
185
+ "source": []
186
+ },
187
+ {
188
+ "cell_type": "code",
189
+ "execution_count": null,
190
+ "id": "8e3dc50d",
191
+ "metadata": {},
192
+ "outputs": [],
193
+ "source": []
194
+ },
195
+ {
196
+ "cell_type": "code",
197
+ "execution_count": 2,
198
+ "id": "3cbdeffc",
199
+ "metadata": {},
200
+ "outputs": [],
201
+ "source": [
202
+ "# get all Binance perp futures tickers\n",
203
+ "data_req = DataRequest(source='ccxt')\n",
204
+ "perp_tickers = GetData(data_req).get_meta(method='get_markets_info', exch='binanceusdm', as_list=True)"
205
+ ]
206
+ },
207
+ {
208
+ "cell_type": "code",
209
+ "execution_count": 3,
210
+ "id": "3d084cf7",
211
+ "metadata": {},
212
+ "outputs": [
213
+ {
214
+ "data": {
215
+ "text/plain": [
216
+ "314"
217
+ ]
218
+ },
219
+ "execution_count": 3,
220
+ "metadata": {},
221
+ "output_type": "execute_result"
222
+ }
223
+ ],
224
+ "source": [
225
+ "len(perp_tickers)"
226
+ ]
227
+ },
228
+ {
229
+ "cell_type": "code",
230
+ "execution_count": 4,
231
+ "id": "fcb74458",
232
+ "metadata": {},
233
+ "outputs": [],
234
+ "source": [
235
+ "# get Binance spot tickers\n",
236
+ "data_req = DataRequest(source='ccxt')\n",
237
+ "spot_tickers = GetData(data_req).get_meta(method='get_markets_info', exch='binance', as_list=True)"
238
+ ]
239
+ },
240
+ {
241
+ "cell_type": "code",
242
+ "execution_count": 5,
243
+ "id": "7962f7e5",
244
+ "metadata": {},
245
+ "outputs": [],
246
+ "source": [
247
+ "# find intersecting tickers\n",
248
+ "binance_tickers = [ticker for ticker in perp_tickers if ticker in spot_tickers]"
249
+ ]
250
+ },
251
+ {
252
+ "cell_type": "code",
253
+ "execution_count": 6,
254
+ "id": "877811c1",
255
+ "metadata": {},
256
+ "outputs": [
257
+ {
258
+ "data": {
259
+ "text/plain": [
260
+ "284"
261
+ ]
262
+ },
263
+ "execution_count": 6,
264
+ "metadata": {},
265
+ "output_type": "execute_result"
266
+ }
267
+ ],
268
+ "source": [
269
+ "# number of tickers\n",
270
+ "len(binance_tickers)"
271
+ ]
272
+ },
273
+ {
274
+ "cell_type": "code",
275
+ "execution_count": 7,
276
+ "id": "fe425163",
277
+ "metadata": {},
278
+ "outputs": [],
279
+ "source": [
280
+ "## # get cryptocompare tickers\n",
281
+ "data_req = DataRequest(source='cryptocompare')\n",
282
+ "cc_tickers = GetData(data_req).get_meta(method='get_assets_info', as_list=True)"
283
+ ]
284
+ },
285
+ {
286
+ "cell_type": "code",
287
+ "execution_count": 8,
288
+ "id": "165053db",
289
+ "metadata": {},
290
+ "outputs": [],
291
+ "source": [
292
+ "# keep only USDT ticker\n",
293
+ "bin_tickers = []\n",
294
+ "for ticker in binance_tickers:\n",
295
+ " if '/' in ticker and ticker.split('/')[1] == 'USDT':\n",
296
+ " bin_tickers.append(ticker.split('/')[0])"
297
+ ]
298
+ },
299
+ {
300
+ "cell_type": "code",
301
+ "execution_count": 9,
302
+ "id": "d6cf8a4c",
303
+ "metadata": {},
304
+ "outputs": [],
305
+ "source": [
306
+ "# usdt tickers\n",
307
+ "usdt_tickers = [ticker.split('/')[0] for ticker in binance_tickers if '/'in ticker and ticker.split('/')[1] == 'USDT']"
308
+ ]
309
+ },
310
+ {
311
+ "cell_type": "code",
312
+ "execution_count": 10,
313
+ "id": "633f7a3e",
314
+ "metadata": {},
315
+ "outputs": [],
316
+ "source": [
317
+ "# intersecting tickers\n",
318
+ "tickers = [ticker for ticker in usdt_tickers if ticker in cc_tickers]"
319
+ ]
320
+ },
321
+ {
322
+ "cell_type": "code",
323
+ "execution_count": 11,
324
+ "id": "30337a71",
325
+ "metadata": {},
326
+ "outputs": [
327
+ {
328
+ "data": {
329
+ "text/plain": [
330
+ "257"
331
+ ]
332
+ },
333
+ "execution_count": 11,
334
+ "metadata": {},
335
+ "output_type": "execute_result"
336
+ }
337
+ ],
338
+ "source": [
339
+ "len(tickers)"
340
+ ]
341
+ },
342
+ {
343
+ "cell_type": "markdown",
344
+ "id": "f80eb97d",
345
+ "metadata": {},
346
+ "source": [
347
+ "### Binance Perp Futures"
348
+ ]
349
+ },
350
+ {
351
+ "cell_type": "code",
352
+ "execution_count": 12,
353
+ "id": "49b09508",
354
+ "metadata": {},
355
+ "outputs": [],
356
+ "source": [
357
+ "# pull daily OHLC and funding rates for perp futures on Binance USDM exchange\n",
358
+ "data_req = DataRequest(source='ccxt',\n",
359
+ " tickers=tickers, \n",
360
+ " fields=['open', 'high', 'low', 'close', 'volume', 'funding_rate'], \n",
361
+ " mkt_type='perpetual_future', \n",
362
+ " freq='d')"
363
+ ]
364
+ },
365
+ {
366
+ "cell_type": "code",
367
+ "execution_count": 13,
368
+ "id": "6ac9365b",
369
+ "metadata": {},
370
+ "outputs": [],
371
+ "source": [
372
+ "# df1 = GetData(data_req).get_series()"
373
+ ]
374
+ },
375
+ {
376
+ "cell_type": "code",
377
+ "execution_count": 14,
378
+ "id": "98a425b2",
379
+ "metadata": {},
380
+ "outputs": [],
381
+ "source": [
382
+ "# df1.to_csv('binance_perp_futures.csv')\n",
383
+ "df1 = pd.read_csv('../../../../factorlab/notebooks/binance_perp_futures.csv', index_col=['date', 'ticker'], parse_dates=['date'])"
384
+ ]
385
+ },
386
+ {
387
+ "cell_type": "code",
388
+ "execution_count": 15,
389
+ "id": "0e04da4a",
390
+ "metadata": {},
391
+ "outputs": [
392
+ {
393
+ "data": {
394
+ "text/html": [
395
+ "<div>\n",
396
+ "<style scoped>\n",
397
+ " .dataframe tbody tr th:only-of-type {\n",
398
+ " vertical-align: middle;\n",
399
+ " }\n",
400
+ "\n",
401
+ " .dataframe tbody tr th {\n",
402
+ " vertical-align: top;\n",
403
+ " }\n",
404
+ "\n",
405
+ " .dataframe thead th {\n",
406
+ " text-align: right;\n",
407
+ " }\n",
408
+ "</style>\n",
409
+ "<table border=\"1\" class=\"dataframe\">\n",
410
+ " <thead>\n",
411
+ " <tr style=\"text-align: right;\">\n",
412
+ " <th></th>\n",
413
+ " <th></th>\n",
414
+ " <th>open</th>\n",
415
+ " <th>high</th>\n",
416
+ " <th>low</th>\n",
417
+ " <th>close</th>\n",
418
+ " <th>volume</th>\n",
419
+ " <th>funding_rate</th>\n",
420
+ " </tr>\n",
421
+ " <tr>\n",
422
+ " <th>date</th>\n",
423
+ " <th>ticker</th>\n",
424
+ " <th></th>\n",
425
+ " <th></th>\n",
426
+ " <th></th>\n",
427
+ " <th></th>\n",
428
+ " <th></th>\n",
429
+ " <th></th>\n",
430
+ " </tr>\n",
431
+ " </thead>\n",
432
+ " <tbody>\n",
433
+ " <tr>\n",
434
+ " <th>2019-09-08</th>\n",
435
+ " <th>BTC</th>\n",
436
+ " <td>10000.00</td>\n",
437
+ " <td>10412.65</td>\n",
438
+ " <td>10000.00</td>\n",
439
+ " <td>10391.63</td>\n",
440
+ " <td>3096.291</td>\n",
441
+ " <td>NaN</td>\n",
442
+ " </tr>\n",
443
+ " <tr>\n",
444
+ " <th>2019-09-09</th>\n",
445
+ " <th>BTC</th>\n",
446
+ " <td>10316.62</td>\n",
447
+ " <td>10475.54</td>\n",
448
+ " <td>10077.22</td>\n",
449
+ " <td>10307.00</td>\n",
450
+ " <td>14824.373</td>\n",
451
+ " <td>NaN</td>\n",
452
+ " </tr>\n",
453
+ " <tr>\n",
454
+ " <th>2019-09-10</th>\n",
455
+ " <th>BTC</th>\n",
456
+ " <td>10307.00</td>\n",
457
+ " <td>10382.97</td>\n",
458
+ " <td>9940.87</td>\n",
459
+ " <td>10102.02</td>\n",
460
+ " <td>9068.955</td>\n",
461
+ " <td>0.0002</td>\n",
462
+ " </tr>\n",
463
+ " <tr>\n",
464
+ " <th>2019-09-11</th>\n",
465
+ " <th>BTC</th>\n",
466
+ " <td>10094.27</td>\n",
467
+ " <td>10293.11</td>\n",
468
+ " <td>9884.31</td>\n",
469
+ " <td>10159.55</td>\n",
470
+ " <td>10897.922</td>\n",
471
+ " <td>0.0003</td>\n",
472
+ " </tr>\n",
473
+ " <tr>\n",
474
+ " <th>2019-09-12</th>\n",
475
+ " <th>BTC</th>\n",
476
+ " <td>10163.06</td>\n",
477
+ " <td>10450.13</td>\n",
478
+ " <td>10042.12</td>\n",
479
+ " <td>10415.13</td>\n",
480
+ " <td>15609.634</td>\n",
481
+ " <td>0.0003</td>\n",
482
+ " </tr>\n",
483
+ " </tbody>\n",
484
+ "</table>\n",
485
+ "</div>"
486
+ ],
487
+ "text/plain": [
488
+ " open high low close volume \\\n",
489
+ "date ticker \n",
490
+ "2019-09-08 BTC 10000.00 10412.65 10000.00 10391.63 3096.291 \n",
491
+ "2019-09-09 BTC 10316.62 10475.54 10077.22 10307.00 14824.373 \n",
492
+ "2019-09-10 BTC 10307.00 10382.97 9940.87 10102.02 9068.955 \n",
493
+ "2019-09-11 BTC 10094.27 10293.11 9884.31 10159.55 10897.922 \n",
494
+ "2019-09-12 BTC 10163.06 10450.13 10042.12 10415.13 15609.634 \n",
495
+ "\n",
496
+ " funding_rate \n",
497
+ "date ticker \n",
498
+ "2019-09-08 BTC NaN \n",
499
+ "2019-09-09 BTC NaN \n",
500
+ "2019-09-10 BTC 0.0002 \n",
501
+ "2019-09-11 BTC 0.0003 \n",
502
+ "2019-09-12 BTC 0.0003 "
503
+ ]
504
+ },
505
+ "execution_count": 15,
506
+ "metadata": {},
507
+ "output_type": "execute_result"
508
+ }
509
+ ],
510
+ "source": [
511
+ "df1.head()"
512
+ ]
513
+ },
514
+ {
515
+ "cell_type": "markdown",
516
+ "id": "32f15191",
517
+ "metadata": {},
518
+ "source": [
519
+ "### Binance Spot"
520
+ ]
521
+ },
522
+ {
523
+ "cell_type": "code",
524
+ "execution_count": 16,
525
+ "id": "83e9e466",
526
+ "metadata": {},
527
+ "outputs": [],
528
+ "source": [
529
+ "# pull OHLC from Binance\n",
530
+ "data_req = DataRequest(source='ccxt',\n",
531
+ " tickers=tickers, \n",
532
+ " fields=['open', 'high', 'low', 'close', 'volume'], \n",
533
+ " freq='d')"
534
+ ]
535
+ },
536
+ {
537
+ "cell_type": "code",
538
+ "execution_count": 17,
539
+ "id": "82d4bbc7",
540
+ "metadata": {},
541
+ "outputs": [],
542
+ "source": [
543
+ "# df2 = GetData(data_req).get_series()"
544
+ ]
545
+ },
546
+ {
547
+ "cell_type": "code",
548
+ "execution_count": 18,
549
+ "id": "4f63eb21",
550
+ "metadata": {},
551
+ "outputs": [],
552
+ "source": [
553
+ "# df2.to_csv('binance_spot.csv')\n",
554
+ "df2 = pd.read_csv('../../../../factorlab/notebooks/binance_spot.csv', index_col=['date', 'ticker'], parse_dates=['date'])"
555
+ ]
556
+ },
557
+ {
558
+ "cell_type": "code",
559
+ "execution_count": 19,
560
+ "id": "ce8929c1",
561
+ "metadata": {},
562
+ "outputs": [
563
+ {
564
+ "data": {
565
+ "text/html": [
566
+ "<div>\n",
567
+ "<style scoped>\n",
568
+ " .dataframe tbody tr th:only-of-type {\n",
569
+ " vertical-align: middle;\n",
570
+ " }\n",
571
+ "\n",
572
+ " .dataframe tbody tr th {\n",
573
+ " vertical-align: top;\n",
574
+ " }\n",
575
+ "\n",
576
+ " .dataframe thead th {\n",
577
+ " text-align: right;\n",
578
+ " }\n",
579
+ "</style>\n",
580
+ "<table border=\"1\" class=\"dataframe\">\n",
581
+ " <thead>\n",
582
+ " <tr style=\"text-align: right;\">\n",
583
+ " <th></th>\n",
584
+ " <th></th>\n",
585
+ " <th>open</th>\n",
586
+ " <th>high</th>\n",
587
+ " <th>low</th>\n",
588
+ " <th>close</th>\n",
589
+ " <th>volume</th>\n",
590
+ " </tr>\n",
591
+ " <tr>\n",
592
+ " <th>date</th>\n",
593
+ " <th>ticker</th>\n",
594
+ " <th></th>\n",
595
+ " <th></th>\n",
596
+ " <th></th>\n",
597
+ " <th></th>\n",
598
+ " <th></th>\n",
599
+ " </tr>\n",
600
+ " </thead>\n",
601
+ " <tbody>\n",
602
+ " <tr>\n",
603
+ " <th rowspan=\"2\" valign=\"top\">2017-08-17</th>\n",
604
+ " <th>BTC</th>\n",
605
+ " <td>4261.48</td>\n",
606
+ " <td>4485.39</td>\n",
607
+ " <td>4200.74</td>\n",
608
+ " <td>4285.08</td>\n",
609
+ " <td>795.150377</td>\n",
610
+ " </tr>\n",
611
+ " <tr>\n",
612
+ " <th>ETH</th>\n",
613
+ " <td>301.13</td>\n",
614
+ " <td>312.18</td>\n",
615
+ " <td>298.00</td>\n",
616
+ " <td>302.00</td>\n",
617
+ " <td>7030.710340</td>\n",
618
+ " </tr>\n",
619
+ " <tr>\n",
620
+ " <th rowspan=\"2\" valign=\"top\">2017-08-18</th>\n",
621
+ " <th>BTC</th>\n",
622
+ " <td>4285.08</td>\n",
623
+ " <td>4371.52</td>\n",
624
+ " <td>3938.77</td>\n",
625
+ " <td>4108.37</td>\n",
626
+ " <td>1199.888264</td>\n",
627
+ " </tr>\n",
628
+ " <tr>\n",
629
+ " <th>ETH</th>\n",
630
+ " <td>302.00</td>\n",
631
+ " <td>311.79</td>\n",
632
+ " <td>283.94</td>\n",
633
+ " <td>293.96</td>\n",
634
+ " <td>9537.846460</td>\n",
635
+ " </tr>\n",
636
+ " <tr>\n",
637
+ " <th>2017-08-19</th>\n",
638
+ " <th>BTC</th>\n",
639
+ " <td>4108.37</td>\n",
640
+ " <td>4184.69</td>\n",
641
+ " <td>3850.00</td>\n",
642
+ " <td>4139.98</td>\n",
643
+ " <td>381.309763</td>\n",
644
+ " </tr>\n",
645
+ " </tbody>\n",
646
+ "</table>\n",
647
+ "</div>"
648
+ ],
649
+ "text/plain": [
650
+ " open high low close volume\n",
651
+ "date ticker \n",
652
+ "2017-08-17 BTC 4261.48 4485.39 4200.74 4285.08 795.150377\n",
653
+ " ETH 301.13 312.18 298.00 302.00 7030.710340\n",
654
+ "2017-08-18 BTC 4285.08 4371.52 3938.77 4108.37 1199.888264\n",
655
+ " ETH 302.00 311.79 283.94 293.96 9537.846460\n",
656
+ "2017-08-19 BTC 4108.37 4184.69 3850.00 4139.98 381.309763"
657
+ ]
658
+ },
659
+ "execution_count": 19,
660
+ "metadata": {},
661
+ "output_type": "execute_result"
662
+ }
663
+ ],
664
+ "source": [
665
+ "df2.head()"
666
+ ]
667
+ },
668
+ {
669
+ "cell_type": "markdown",
670
+ "id": "05f93b91",
671
+ "metadata": {},
672
+ "source": [
673
+ "### CryptoCompare - Historical Prices"
674
+ ]
675
+ },
676
+ {
677
+ "cell_type": "code",
678
+ "execution_count": 20,
679
+ "id": "7f14d874",
680
+ "metadata": {},
681
+ "outputs": [],
682
+ "source": [
683
+ "# pull OHLC from CryptoCompare\n",
684
+ "data_req = DataRequest(source='cryptocompare',\n",
685
+ " tickers=tickers, \n",
686
+ " fields=['open', 'high', 'low', 'close', 'volume'], \n",
687
+ " freq='d')"
688
+ ]
689
+ },
690
+ {
691
+ "cell_type": "code",
692
+ "execution_count": 21,
693
+ "id": "3a8708d3",
694
+ "metadata": {},
695
+ "outputs": [],
696
+ "source": [
697
+ "# df3 = GetData(data_req).get_series()"
698
+ ]
699
+ },
700
+ {
701
+ "cell_type": "code",
702
+ "execution_count": 22,
703
+ "id": "aa265538",
704
+ "metadata": {},
705
+ "outputs": [],
706
+ "source": [
707
+ "# df3.to_csv('cc_spot.csv')\n",
708
+ "df3 = pd.read_csv('../../../../factorlab/notebooks/cc_spot.csv', index_col=['date', 'ticker'], parse_dates=['date'])"
709
+ ]
710
+ },
711
+ {
712
+ "cell_type": "markdown",
713
+ "id": "5664e968",
714
+ "metadata": {},
715
+ "source": [
716
+ "### Clean Data"
717
+ ]
718
+ },
719
+ {
720
+ "cell_type": "code",
721
+ "execution_count": 61,
722
+ "id": "f5ee4f6d",
723
+ "metadata": {},
724
+ "outputs": [],
725
+ "source": [
726
+ "df = stitch_dataframes([df1, df2, df3])\n",
727
+ "df.funding_rate = df.funding_rate.fillna(0)"
728
+ ]
729
+ },
730
+ {
731
+ "cell_type": "code",
732
+ "execution_count": 62,
733
+ "id": "cbe07c91",
734
+ "metadata": {},
735
+ "outputs": [
736
+ {
737
+ "data": {
738
+ "text/html": [
739
+ "<div>\n",
740
+ "<style scoped>\n",
741
+ " .dataframe tbody tr th:only-of-type {\n",
742
+ " vertical-align: middle;\n",
743
+ " }\n",
744
+ "\n",
745
+ " .dataframe tbody tr th {\n",
746
+ " vertical-align: top;\n",
747
+ " }\n",
748
+ "\n",
749
+ " .dataframe thead th {\n",
750
+ " text-align: right;\n",
751
+ " }\n",
752
+ "</style>\n",
753
+ "<table border=\"1\" class=\"dataframe\">\n",
754
+ " <thead>\n",
755
+ " <tr style=\"text-align: right;\">\n",
756
+ " <th></th>\n",
757
+ " <th></th>\n",
758
+ " <th>open</th>\n",
759
+ " <th>high</th>\n",
760
+ " <th>low</th>\n",
761
+ " <th>close</th>\n",
762
+ " <th>volume</th>\n",
763
+ " <th>funding_rate</th>\n",
764
+ " </tr>\n",
765
+ " <tr>\n",
766
+ " <th>date</th>\n",
767
+ " <th>ticker</th>\n",
768
+ " <th></th>\n",
769
+ " <th></th>\n",
770
+ " <th></th>\n",
771
+ " <th></th>\n",
772
+ " <th></th>\n",
773
+ " <th></th>\n",
774
+ " </tr>\n",
775
+ " </thead>\n",
776
+ " <tbody>\n",
777
+ " <tr>\n",
778
+ " <th>2010-07-17</th>\n",
779
+ " <th>BTC</th>\n",
780
+ " <td>0.04951</td>\n",
781
+ " <td>0.04951</td>\n",
782
+ " <td>0.04951</td>\n",
783
+ " <td>0.04951</td>\n",
784
+ " <td>20.00</td>\n",
785
+ " <td>0.0</td>\n",
786
+ " </tr>\n",
787
+ " <tr>\n",
788
+ " <th>2010-07-18</th>\n",
789
+ " <th>BTC</th>\n",
790
+ " <td>0.04951</td>\n",
791
+ " <td>0.08585</td>\n",
792
+ " <td>0.04951</td>\n",
793
+ " <td>0.08584</td>\n",
794
+ " <td>75.01</td>\n",
795
+ " <td>0.0</td>\n",
796
+ " </tr>\n",
797
+ " <tr>\n",
798
+ " <th>2010-07-19</th>\n",
799
+ " <th>BTC</th>\n",
800
+ " <td>0.08584</td>\n",
801
+ " <td>0.09307</td>\n",
802
+ " <td>0.07723</td>\n",
803
+ " <td>0.08080</td>\n",
804
+ " <td>574.00</td>\n",
805
+ " <td>0.0</td>\n",
806
+ " </tr>\n",
807
+ " <tr>\n",
808
+ " <th>2010-07-20</th>\n",
809
+ " <th>BTC</th>\n",
810
+ " <td>0.08080</td>\n",
811
+ " <td>0.08181</td>\n",
812
+ " <td>0.07426</td>\n",
813
+ " <td>0.07474</td>\n",
814
+ " <td>262.00</td>\n",
815
+ " <td>0.0</td>\n",
816
+ " </tr>\n",
817
+ " <tr>\n",
818
+ " <th>2010-07-21</th>\n",
819
+ " <th>BTC</th>\n",
820
+ " <td>0.07474</td>\n",
821
+ " <td>0.07921</td>\n",
822
+ " <td>0.06634</td>\n",
823
+ " <td>0.07921</td>\n",
824
+ " <td>575.00</td>\n",
825
+ " <td>0.0</td>\n",
826
+ " </tr>\n",
827
+ " </tbody>\n",
828
+ "</table>\n",
829
+ "</div>"
830
+ ],
831
+ "text/plain": [
832
+ " open high low close volume funding_rate\n",
833
+ "date ticker \n",
834
+ "2010-07-17 BTC 0.04951 0.04951 0.04951 0.04951 20.00 0.0\n",
835
+ "2010-07-18 BTC 0.04951 0.08585 0.04951 0.08584 75.01 0.0\n",
836
+ "2010-07-19 BTC 0.08584 0.09307 0.07723 0.08080 574.00 0.0\n",
837
+ "2010-07-20 BTC 0.08080 0.08181 0.07426 0.07474 262.00 0.0\n",
838
+ "2010-07-21 BTC 0.07474 0.07921 0.06634 0.07921 575.00 0.0"
839
+ ]
840
+ },
841
+ "execution_count": 62,
842
+ "metadata": {},
843
+ "output_type": "execute_result"
844
+ }
845
+ ],
846
+ "source": [
847
+ "df.head()"
848
+ ]
849
+ },
850
+ {
851
+ "cell_type": "code",
852
+ "execution_count": 63,
853
+ "id": "bcbd3394",
854
+ "metadata": {},
855
+ "outputs": [],
856
+ "source": [
857
+ "# Filter data\n",
858
+ "clean_df = CleanData(df).filter_outliers(od_method='mad', excl_cols=['volume', 'funding_rate'], thresh_val=10).\\\n",
859
+ " repair_outliers(imp_method='fcst').\\\n",
860
+ " filter_avg_trading_val(thresh_val=1000000).\\\n",
861
+ " filter_missing_vals_gaps().\\\n",
862
+ " filter_min_nobs(ts_obs=1000, cs_obs=3).\\\n",
863
+ " get(attr='df').dropna(how='all')"
864
+ ]
865
+ },
866
+ {
867
+ "cell_type": "code",
868
+ "execution_count": 64,
869
+ "id": "66c762a3",
870
+ "metadata": {},
871
+ "outputs": [
872
+ {
873
+ "data": {
874
+ "text/html": [
875
+ "<div>\n",
876
+ "<style scoped>\n",
877
+ " .dataframe tbody tr th:only-of-type {\n",
878
+ " vertical-align: middle;\n",
879
+ " }\n",
880
+ "\n",
881
+ " .dataframe tbody tr th {\n",
882
+ " vertical-align: top;\n",
883
+ " }\n",
884
+ "\n",
885
+ " .dataframe thead th {\n",
886
+ " text-align: right;\n",
887
+ " }\n",
888
+ "</style>\n",
889
+ "<table border=\"1\" class=\"dataframe\">\n",
890
+ " <thead>\n",
891
+ " <tr style=\"text-align: right;\">\n",
892
+ " <th></th>\n",
893
+ " <th></th>\n",
894
+ " <th>open</th>\n",
895
+ " <th>high</th>\n",
896
+ " <th>low</th>\n",
897
+ " <th>close</th>\n",
898
+ " <th>volume</th>\n",
899
+ " <th>funding_rate</th>\n",
900
+ " </tr>\n",
901
+ " <tr>\n",
902
+ " <th>date</th>\n",
903
+ " <th>ticker</th>\n",
904
+ " <th></th>\n",
905
+ " <th></th>\n",
906
+ " <th></th>\n",
907
+ " <th></th>\n",
908
+ " <th></th>\n",
909
+ " <th></th>\n",
910
+ " </tr>\n",
911
+ " </thead>\n",
912
+ " <tbody>\n",
913
+ " <tr>\n",
914
+ " <th rowspan=\"4\" valign=\"top\">2017-03-21</th>\n",
915
+ " <th>BTC</th>\n",
916
+ " <td>1047.51</td>\n",
917
+ " <td>1125.53</td>\n",
918
+ " <td>1043.87</td>\n",
919
+ " <td>1121.29</td>\n",
920
+ " <td>9.259127e+04</td>\n",
921
+ " <td>0.000000</td>\n",
922
+ " </tr>\n",
923
+ " <tr>\n",
924
+ " <th>ETC</th>\n",
925
+ " <td>1.867</td>\n",
926
+ " <td>2.39</td>\n",
927
+ " <td>1.867</td>\n",
928
+ " <td>2.378</td>\n",
929
+ " <td>2.151590e+06</td>\n",
930
+ " <td>0.000000</td>\n",
931
+ " </tr>\n",
932
+ " <tr>\n",
933
+ " <th>ETH</th>\n",
934
+ " <td>42.51</td>\n",
935
+ " <td>43.8</td>\n",
936
+ " <td>41.68</td>\n",
937
+ " <td>42.67</td>\n",
938
+ " <td>4.843660e+05</td>\n",
939
+ " <td>0.000000</td>\n",
940
+ " </tr>\n",
941
+ " <tr>\n",
942
+ " <th>LTC</th>\n",
943
+ " <td>4.121</td>\n",
944
+ " <td>4.155</td>\n",
945
+ " <td>4.014</td>\n",
946
+ " <td>4.09</td>\n",
947
+ " <td>1.932581e+05</td>\n",
948
+ " <td>0.000000</td>\n",
949
+ " </tr>\n",
950
+ " <tr>\n",
951
+ " <th>2017-03-22</th>\n",
952
+ " <th>BTC</th>\n",
953
+ " <td>1121.29</td>\n",
954
+ " <td>1121.88</td>\n",
955
+ " <td>997.78</td>\n",
956
+ " <td>1044.72</td>\n",
957
+ " <td>1.152861e+05</td>\n",
958
+ " <td>0.000000</td>\n",
959
+ " </tr>\n",
960
+ " <tr>\n",
961
+ " <th>...</th>\n",
962
+ " <th>...</th>\n",
963
+ " <td>...</td>\n",
964
+ " <td>...</td>\n",
965
+ " <td>...</td>\n",
966
+ " <td>...</td>\n",
967
+ " <td>...</td>\n",
968
+ " <td>...</td>\n",
969
+ " </tr>\n",
970
+ " <tr>\n",
971
+ " <th rowspan=\"5\" valign=\"top\">2024-08-04</th>\n",
972
+ " <th>YFI</th>\n",
973
+ " <td>5341.0</td>\n",
974
+ " <td>5341.0</td>\n",
975
+ " <td>5196.0</td>\n",
976
+ " <td>5198.0</td>\n",
977
+ " <td>4.281050e+02</td>\n",
978
+ " <td>0.000169</td>\n",
979
+ " </tr>\n",
980
+ " <tr>\n",
981
+ " <th>ZEC</th>\n",
982
+ " <td>31.76</td>\n",
983
+ " <td>34.44</td>\n",
984
+ " <td>31.28</td>\n",
985
+ " <td>31.55</td>\n",
986
+ " <td>1.348085e+06</td>\n",
987
+ " <td>0.000191</td>\n",
988
+ " </tr>\n",
989
+ " <tr>\n",
990
+ " <th>ZEN</th>\n",
991
+ " <td>9.657</td>\n",
992
+ " <td>9.112</td>\n",
993
+ " <td>8.285</td>\n",
994
+ " <td>8.462</td>\n",
995
+ " <td>2.071124e+06</td>\n",
996
+ " <td>0.000194</td>\n",
997
+ " </tr>\n",
998
+ " <tr>\n",
999
+ " <th>ZIL</th>\n",
1000
+ " <td>0.01422</td>\n",
1001
+ " <td>0.01441</td>\n",
1002
+ " <td>0.01392</td>\n",
1003
+ " <td>0.01396</td>\n",
1004
+ " <td>2.048626e+08</td>\n",
1005
+ " <td>-0.000031</td>\n",
1006
+ " </tr>\n",
1007
+ " <tr>\n",
1008
+ " <th>ZRX</th>\n",
1009
+ " <td>0.3055</td>\n",
1010
+ " <td>0.3121</td>\n",
1011
+ " <td>0.2983</td>\n",
1012
+ " <td>0.2988</td>\n",
1013
+ " <td>9.810764e+06</td>\n",
1014
+ " <td>0.000186</td>\n",
1015
+ " </tr>\n",
1016
+ " </tbody>\n",
1017
+ "</table>\n",
1018
+ "<p>193002 rows × 6 columns</p>\n",
1019
+ "</div>"
1020
+ ],
1021
+ "text/plain": [
1022
+ " open high low close volume \\\n",
1023
+ "date ticker \n",
1024
+ "2017-03-21 BTC 1047.51 1125.53 1043.87 1121.29 9.259127e+04 \n",
1025
+ " ETC 1.867 2.39 1.867 2.378 2.151590e+06 \n",
1026
+ " ETH 42.51 43.8 41.68 42.67 4.843660e+05 \n",
1027
+ " LTC 4.121 4.155 4.014 4.09 1.932581e+05 \n",
1028
+ "2017-03-22 BTC 1121.29 1121.88 997.78 1044.72 1.152861e+05 \n",
1029
+ "... ... ... ... ... ... \n",
1030
+ "2024-08-04 YFI 5341.0 5341.0 5196.0 5198.0 4.281050e+02 \n",
1031
+ " ZEC 31.76 34.44 31.28 31.55 1.348085e+06 \n",
1032
+ " ZEN 9.657 9.112 8.285 8.462 2.071124e+06 \n",
1033
+ " ZIL 0.01422 0.01441 0.01392 0.01396 2.048626e+08 \n",
1034
+ " ZRX 0.3055 0.3121 0.2983 0.2988 9.810764e+06 \n",
1035
+ "\n",
1036
+ " funding_rate \n",
1037
+ "date ticker \n",
1038
+ "2017-03-21 BTC 0.000000 \n",
1039
+ " ETC 0.000000 \n",
1040
+ " ETH 0.000000 \n",
1041
+ " LTC 0.000000 \n",
1042
+ "2017-03-22 BTC 0.000000 \n",
1043
+ "... ... \n",
1044
+ "2024-08-04 YFI 0.000169 \n",
1045
+ " ZEC 0.000191 \n",
1046
+ " ZEN 0.000194 \n",
1047
+ " ZIL -0.000031 \n",
1048
+ " ZRX 0.000186 \n",
1049
+ "\n",
1050
+ "[193002 rows x 6 columns]"
1051
+ ]
1052
+ },
1053
+ "execution_count": 64,
1054
+ "metadata": {},
1055
+ "output_type": "execute_result"
1056
+ }
1057
+ ],
1058
+ "source": [
1059
+ "clean_df"
1060
+ ]
1061
+ },
1062
+ {
1063
+ "cell_type": "code",
1064
+ "execution_count": 65,
1065
+ "id": "bec999ba",
1066
+ "metadata": {},
1067
+ "outputs": [],
1068
+ "source": [
1069
+ "# Filter data\n",
1070
+ "clean = CleanData(df)"
1071
+ ]
1072
+ },
1073
+ {
1074
+ "cell_type": "code",
1075
+ "execution_count": 66,
1076
+ "id": "34372e70",
1077
+ "metadata": {},
1078
+ "outputs": [
1079
+ {
1080
+ "data": {
1081
+ "text/plain": [
1082
+ "<cryptodatapy.transform.clean.CleanData at 0x7face8e7eb50>"
1083
+ ]
1084
+ },
1085
+ "execution_count": 66,
1086
+ "metadata": {},
1087
+ "output_type": "execute_result"
1088
+ }
1089
+ ],
1090
+ "source": [
1091
+ "clean.filter_outliers(od_method='mad', excl_cols=['volume', 'funding_rate'], thresh_val=10).\\\n",
1092
+ " repair_outliers(imp_method='fcst').\\\n",
1093
+ " filter_avg_trading_val(thresh_val=1000000).\\\n",
1094
+ " filter_missing_vals_gaps().\\\n",
1095
+ " filter_min_nobs(ts_obs=1000, cs_obs=3)"
1096
+ ]
1097
+ },
1098
+ {
1099
+ "cell_type": "code",
1100
+ "execution_count": 79,
1101
+ "id": "ba73590b",
1102
+ "metadata": {},
1103
+ "outputs": [
1104
+ {
1105
+ "data": {
1106
+ "text/html": [
1107
+ "<div>\n",
1108
+ "<style scoped>\n",
1109
+ " .dataframe tbody tr th:only-of-type {\n",
1110
+ " vertical-align: middle;\n",
1111
+ " }\n",
1112
+ "\n",
1113
+ " .dataframe tbody tr th {\n",
1114
+ " vertical-align: top;\n",
1115
+ " }\n",
1116
+ "\n",
1117
+ " .dataframe thead th {\n",
1118
+ " text-align: right;\n",
1119
+ " }\n",
1120
+ "</style>\n",
1121
+ "<table border=\"1\" class=\"dataframe\">\n",
1122
+ " <thead>\n",
1123
+ " <tr style=\"text-align: right;\">\n",
1124
+ " <th></th>\n",
1125
+ " <th>1000SATS</th>\n",
1126
+ " <th>1INCH</th>\n",
1127
+ " <th>AAVE</th>\n",
1128
+ " <th>ACE</th>\n",
1129
+ " <th>ACH</th>\n",
1130
+ " <th>ADA</th>\n",
1131
+ " <th>AEVO</th>\n",
1132
+ " <th>AGIX</th>\n",
1133
+ " <th>AGLD</th>\n",
1134
+ " <th>AI</th>\n",
1135
+ " <th>...</th>\n",
1136
+ " <th>XVG</th>\n",
1137
+ " <th>XVS</th>\n",
1138
+ " <th>YFI</th>\n",
1139
+ " <th>YGG</th>\n",
1140
+ " <th>ZEC</th>\n",
1141
+ " <th>ZEN</th>\n",
1142
+ " <th>ZIL</th>\n",
1143
+ " <th>ZK</th>\n",
1144
+ " <th>ZRO</th>\n",
1145
+ " <th>ZRX</th>\n",
1146
+ " </tr>\n",
1147
+ " </thead>\n",
1148
+ " <tbody>\n",
1149
+ " <tr>\n",
1150
+ " <th>n_obs</th>\n",
1151
+ " <td>237.000000</td>\n",
1152
+ " <td>1319.000000</td>\n",
1153
+ " <td>1395.000000</td>\n",
1154
+ " <td>326.000000</td>\n",
1155
+ " <td>1419.000000</td>\n",
1156
+ " <td>2500.000000</td>\n",
1157
+ " <td>278.000000</td>\n",
1158
+ " <td>536.000000</td>\n",
1159
+ " <td>1040.000000</td>\n",
1160
+ " <td>524.000000</td>\n",
1161
+ " <td>...</td>\n",
1162
+ " <td>3101.000000</td>\n",
1163
+ " <td>1399.000000</td>\n",
1164
+ " <td>1466.000000</td>\n",
1165
+ " <td>1067.000000</td>\n",
1166
+ " <td>2838.000000</td>\n",
1167
+ " <td>2617.000000</td>\n",
1168
+ " <td>2379.000000</td>\n",
1169
+ " <td>49.000000</td>\n",
1170
+ " <td>46.000000</td>\n",
1171
+ " <td>2551.000000</td>\n",
1172
+ " </tr>\n",
1173
+ " <tr>\n",
1174
+ " <th>%_NaN_start</th>\n",
1175
+ " <td>95.382817</td>\n",
1176
+ " <td>74.303526</td>\n",
1177
+ " <td>72.822911</td>\n",
1178
+ " <td>93.648938</td>\n",
1179
+ " <td>72.355348</td>\n",
1180
+ " <td>51.295539</td>\n",
1181
+ " <td>94.584064</td>\n",
1182
+ " <td>89.557763</td>\n",
1183
+ " <td>79.738944</td>\n",
1184
+ " <td>89.791545</td>\n",
1185
+ " <td>...</td>\n",
1186
+ " <td>39.586986</td>\n",
1187
+ " <td>72.744983</td>\n",
1188
+ " <td>71.439704</td>\n",
1189
+ " <td>79.212936</td>\n",
1190
+ " <td>44.710695</td>\n",
1191
+ " <td>49.016170</td>\n",
1192
+ " <td>53.652835</td>\n",
1193
+ " <td>99.045393</td>\n",
1194
+ " <td>99.103838</td>\n",
1195
+ " <td>50.301968</td>\n",
1196
+ " </tr>\n",
1197
+ " <tr>\n",
1198
+ " <th>%_outliers</th>\n",
1199
+ " <td>0.038964</td>\n",
1200
+ " <td>0.642899</td>\n",
1201
+ " <td>0.370154</td>\n",
1202
+ " <td>0.253263</td>\n",
1203
+ " <td>0.584454</td>\n",
1204
+ " <td>0.876680</td>\n",
1205
+ " <td>0.331190</td>\n",
1206
+ " <td>0.253263</td>\n",
1207
+ " <td>0.526008</td>\n",
1208
+ " <td>0.253263</td>\n",
1209
+ " <td>...</td>\n",
1210
+ " <td>2.824859</td>\n",
1211
+ " <td>0.642899</td>\n",
1212
+ " <td>0.389636</td>\n",
1213
+ " <td>0.467563</td>\n",
1214
+ " <td>0.857199</td>\n",
1215
+ " <td>1.207871</td>\n",
1216
+ " <td>0.974089</td>\n",
1217
+ " <td>0.000000</td>\n",
1218
+ " <td>0.019482</td>\n",
1219
+ " <td>0.993571</td>\n",
1220
+ " </tr>\n",
1221
+ " <tr>\n",
1222
+ " <th>%_imputed</th>\n",
1223
+ " <td>0.175336</td>\n",
1224
+ " <td>1.052016</td>\n",
1225
+ " <td>0.584454</td>\n",
1226
+ " <td>0.370154</td>\n",
1227
+ " <td>0.701344</td>\n",
1228
+ " <td>1.246834</td>\n",
1229
+ " <td>0.545490</td>\n",
1230
+ " <td>1.188389</td>\n",
1231
+ " <td>0.779271</td>\n",
1232
+ " <td>0.662381</td>\n",
1233
+ " <td>...</td>\n",
1234
+ " <td>3.779466</td>\n",
1235
+ " <td>0.779271</td>\n",
1236
+ " <td>0.701344</td>\n",
1237
+ " <td>0.740308</td>\n",
1238
+ " <td>1.207871</td>\n",
1239
+ " <td>1.461134</td>\n",
1240
+ " <td>1.422170</td>\n",
1241
+ " <td>0.116891</td>\n",
1242
+ " <td>0.136372</td>\n",
1243
+ " <td>1.363725</td>\n",
1244
+ " </tr>\n",
1245
+ " <tr>\n",
1246
+ " <th>%_below_avg_trading_val</th>\n",
1247
+ " <td>0.564972</td>\n",
1248
+ " <td>0.564972</td>\n",
1249
+ " <td>0.603935</td>\n",
1250
+ " <td>1.753361</td>\n",
1251
+ " <td>6.409507</td>\n",
1252
+ " <td>0.564972</td>\n",
1253
+ " <td>2.591077</td>\n",
1254
+ " <td>1.110462</td>\n",
1255
+ " <td>1.636470</td>\n",
1256
+ " <td>6.019871</td>\n",
1257
+ " <td>...</td>\n",
1258
+ " <td>41.671537</td>\n",
1259
+ " <td>4.227547</td>\n",
1260
+ " <td>0.564972</td>\n",
1261
+ " <td>1.402688</td>\n",
1262
+ " <td>4.773037</td>\n",
1263
+ " <td>17.786869</td>\n",
1264
+ " <td>9.526593</td>\n",
1265
+ " <td>0.564972</td>\n",
1266
+ " <td>0.564972</td>\n",
1267
+ " <td>12.195597</td>\n",
1268
+ " </tr>\n",
1269
+ " <tr>\n",
1270
+ " <th>%_missing_vals_gaps</th>\n",
1271
+ " <td>0.000000</td>\n",
1272
+ " <td>0.000000</td>\n",
1273
+ " <td>0.000000</td>\n",
1274
+ " <td>0.019482</td>\n",
1275
+ " <td>0.019482</td>\n",
1276
+ " <td>0.000000</td>\n",
1277
+ " <td>0.000000</td>\n",
1278
+ " <td>0.000000</td>\n",
1279
+ " <td>0.000000</td>\n",
1280
+ " <td>0.000000</td>\n",
1281
+ " <td>...</td>\n",
1282
+ " <td>10.325346</td>\n",
1283
+ " <td>13.598286</td>\n",
1284
+ " <td>0.000000</td>\n",
1285
+ " <td>11.903370</td>\n",
1286
+ " <td>16.540035</td>\n",
1287
+ " <td>6.916034</td>\n",
1288
+ " <td>6.623807</td>\n",
1289
+ " <td>0.000000</td>\n",
1290
+ " <td>0.000000</td>\n",
1291
+ " <td>7.305669</td>\n",
1292
+ " </tr>\n",
1293
+ " <tr>\n",
1294
+ " <th>n_tickers_below_min_obs</th>\n",
1295
+ " <td>129.000000</td>\n",
1296
+ " <td>129.000000</td>\n",
1297
+ " <td>129.000000</td>\n",
1298
+ " <td>129.000000</td>\n",
1299
+ " <td>129.000000</td>\n",
1300
+ " <td>129.000000</td>\n",
1301
+ " <td>129.000000</td>\n",
1302
+ " <td>129.000000</td>\n",
1303
+ " <td>129.000000</td>\n",
1304
+ " <td>129.000000</td>\n",
1305
+ " <td>...</td>\n",
1306
+ " <td>129.000000</td>\n",
1307
+ " <td>129.000000</td>\n",
1308
+ " <td>129.000000</td>\n",
1309
+ " <td>129.000000</td>\n",
1310
+ " <td>129.000000</td>\n",
1311
+ " <td>129.000000</td>\n",
1312
+ " <td>129.000000</td>\n",
1313
+ " <td>129.000000</td>\n",
1314
+ " <td>129.000000</td>\n",
1315
+ " <td>129.000000</td>\n",
1316
+ " </tr>\n",
1317
+ " </tbody>\n",
1318
+ "</table>\n",
1319
+ "<p>7 rows × 256 columns</p>\n",
1320
+ "</div>"
1321
+ ],
1322
+ "text/plain": [
1323
+ " 1000SATS 1INCH AAVE ACE \\\n",
1324
+ "n_obs 237.000000 1319.000000 1395.000000 326.000000 \n",
1325
+ "%_NaN_start 95.382817 74.303526 72.822911 93.648938 \n",
1326
+ "%_outliers 0.038964 0.642899 0.370154 0.253263 \n",
1327
+ "%_imputed 0.175336 1.052016 0.584454 0.370154 \n",
1328
+ "%_below_avg_trading_val 0.564972 0.564972 0.603935 1.753361 \n",
1329
+ "%_missing_vals_gaps 0.000000 0.000000 0.000000 0.019482 \n",
1330
+ "n_tickers_below_min_obs 129.000000 129.000000 129.000000 129.000000 \n",
1331
+ "\n",
1332
+ " ACH ADA AEVO AGIX \\\n",
1333
+ "n_obs 1419.000000 2500.000000 278.000000 536.000000 \n",
1334
+ "%_NaN_start 72.355348 51.295539 94.584064 89.557763 \n",
1335
+ "%_outliers 0.584454 0.876680 0.331190 0.253263 \n",
1336
+ "%_imputed 0.701344 1.246834 0.545490 1.188389 \n",
1337
+ "%_below_avg_trading_val 6.409507 0.564972 2.591077 1.110462 \n",
1338
+ "%_missing_vals_gaps 0.019482 0.000000 0.000000 0.000000 \n",
1339
+ "n_tickers_below_min_obs 129.000000 129.000000 129.000000 129.000000 \n",
1340
+ "\n",
1341
+ " AGLD AI ... XVG \\\n",
1342
+ "n_obs 1040.000000 524.000000 ... 3101.000000 \n",
1343
+ "%_NaN_start 79.738944 89.791545 ... 39.586986 \n",
1344
+ "%_outliers 0.526008 0.253263 ... 2.824859 \n",
1345
+ "%_imputed 0.779271 0.662381 ... 3.779466 \n",
1346
+ "%_below_avg_trading_val 1.636470 6.019871 ... 41.671537 \n",
1347
+ "%_missing_vals_gaps 0.000000 0.000000 ... 10.325346 \n",
1348
+ "n_tickers_below_min_obs 129.000000 129.000000 ... 129.000000 \n",
1349
+ "\n",
1350
+ " XVS YFI YGG ZEC \\\n",
1351
+ "n_obs 1399.000000 1466.000000 1067.000000 2838.000000 \n",
1352
+ "%_NaN_start 72.744983 71.439704 79.212936 44.710695 \n",
1353
+ "%_outliers 0.642899 0.389636 0.467563 0.857199 \n",
1354
+ "%_imputed 0.779271 0.701344 0.740308 1.207871 \n",
1355
+ "%_below_avg_trading_val 4.227547 0.564972 1.402688 4.773037 \n",
1356
+ "%_missing_vals_gaps 13.598286 0.000000 11.903370 16.540035 \n",
1357
+ "n_tickers_below_min_obs 129.000000 129.000000 129.000000 129.000000 \n",
1358
+ "\n",
1359
+ " ZEN ZIL ZK ZRO \\\n",
1360
+ "n_obs 2617.000000 2379.000000 49.000000 46.000000 \n",
1361
+ "%_NaN_start 49.016170 53.652835 99.045393 99.103838 \n",
1362
+ "%_outliers 1.207871 0.974089 0.000000 0.019482 \n",
1363
+ "%_imputed 1.461134 1.422170 0.116891 0.136372 \n",
1364
+ "%_below_avg_trading_val 17.786869 9.526593 0.564972 0.564972 \n",
1365
+ "%_missing_vals_gaps 6.916034 6.623807 0.000000 0.000000 \n",
1366
+ "n_tickers_below_min_obs 129.000000 129.000000 129.000000 129.000000 \n",
1367
+ "\n",
1368
+ " ZRX \n",
1369
+ "n_obs 2551.000000 \n",
1370
+ "%_NaN_start 50.301968 \n",
1371
+ "%_outliers 0.993571 \n",
1372
+ "%_imputed 1.363725 \n",
1373
+ "%_below_avg_trading_val 12.195597 \n",
1374
+ "%_missing_vals_gaps 7.305669 \n",
1375
+ "n_tickers_below_min_obs 129.000000 \n",
1376
+ "\n",
1377
+ "[7 rows x 256 columns]"
1378
+ ]
1379
+ },
1380
+ "execution_count": 79,
1381
+ "metadata": {},
1382
+ "output_type": "execute_result"
1383
+ }
1384
+ ],
1385
+ "source": [
1386
+ "clean.summary.close"
1387
+ ]
1388
+ },
1389
+ {
1390
+ "cell_type": "code",
1391
+ "execution_count": 80,
1392
+ "id": "f89c762c",
1393
+ "metadata": {},
1394
+ "outputs": [
1395
+ {
1396
+ "data": {
1397
+ "text/plain": [
1398
+ "<cryptodatapy.transform.clean.CleanData at 0x7face8e7eb50>"
1399
+ ]
1400
+ },
1401
+ "execution_count": 80,
1402
+ "metadata": {},
1403
+ "output_type": "execute_result"
1404
+ }
1405
+ ],
1406
+ "source": [
1407
+ "clean.filter_tickers(['BTC'])"
1408
+ ]
1409
+ },
1410
+ {
1411
+ "cell_type": "code",
1412
+ "execution_count": 85,
1413
+ "id": "d621e6f3",
1414
+ "metadata": {},
1415
+ "outputs": [
1416
+ {
1417
+ "data": {
1418
+ "text/html": [
1419
+ "<div>\n",
1420
+ "<style scoped>\n",
1421
+ " .dataframe tbody tr th:only-of-type {\n",
1422
+ " vertical-align: middle;\n",
1423
+ " }\n",
1424
+ "\n",
1425
+ " .dataframe tbody tr th {\n",
1426
+ " vertical-align: top;\n",
1427
+ " }\n",
1428
+ "\n",
1429
+ " .dataframe thead th {\n",
1430
+ " text-align: right;\n",
1431
+ " }\n",
1432
+ "</style>\n",
1433
+ "<table border=\"1\" class=\"dataframe\">\n",
1434
+ " <thead>\n",
1435
+ " <tr style=\"text-align: right;\">\n",
1436
+ " <th></th>\n",
1437
+ " <th></th>\n",
1438
+ " <th>open</th>\n",
1439
+ " <th>high</th>\n",
1440
+ " <th>low</th>\n",
1441
+ " <th>close</th>\n",
1442
+ " <th>volume</th>\n",
1443
+ " <th>funding_rate</th>\n",
1444
+ " </tr>\n",
1445
+ " <tr>\n",
1446
+ " <th>date</th>\n",
1447
+ " <th>ticker</th>\n",
1448
+ " <th></th>\n",
1449
+ " <th></th>\n",
1450
+ " <th></th>\n",
1451
+ " <th></th>\n",
1452
+ " <th></th>\n",
1453
+ " <th></th>\n",
1454
+ " </tr>\n",
1455
+ " </thead>\n",
1456
+ " <tbody>\n",
1457
+ " <tr>\n",
1458
+ " <th>2013-09-29</th>\n",
1459
+ " <th>LTC</th>\n",
1460
+ " <td>2.56500</td>\n",
1461
+ " <td>2.59000</td>\n",
1462
+ " <td>2.59000</td>\n",
1463
+ " <td>2.59000</td>\n",
1464
+ " <td>5.000000e+00</td>\n",
1465
+ " <td>0.000000</td>\n",
1466
+ " </tr>\n",
1467
+ " <tr>\n",
1468
+ " <th>2013-09-30</th>\n",
1469
+ " <th>LTC</th>\n",
1470
+ " <td>2.59000</td>\n",
1471
+ " <td>2.55400</td>\n",
1472
+ " <td>2.55400</td>\n",
1473
+ " <td>2.55400</td>\n",
1474
+ " <td>5.623000e+01</td>\n",
1475
+ " <td>0.000000</td>\n",
1476
+ " </tr>\n",
1477
+ " <tr>\n",
1478
+ " <th>2013-10-01</th>\n",
1479
+ " <th>LTC</th>\n",
1480
+ " <td>2.55400</td>\n",
1481
+ " <td>2.66600</td>\n",
1482
+ " <td>2.52500</td>\n",
1483
+ " <td>2.66600</td>\n",
1484
+ " <td>1.000000e+00</td>\n",
1485
+ " <td>0.000000</td>\n",
1486
+ " </tr>\n",
1487
+ " <tr>\n",
1488
+ " <th>2013-10-02</th>\n",
1489
+ " <th>LTC</th>\n",
1490
+ " <td>2.66600</td>\n",
1491
+ " <td>2.33700</td>\n",
1492
+ " <td>2.33700</td>\n",
1493
+ " <td>2.33700</td>\n",
1494
+ " <td>1.500000e+00</td>\n",
1495
+ " <td>0.000000</td>\n",
1496
+ " </tr>\n",
1497
+ " <tr>\n",
1498
+ " <th>2013-10-03</th>\n",
1499
+ " <th>LTC</th>\n",
1500
+ " <td>2.33700</td>\n",
1501
+ " <td>2.50200</td>\n",
1502
+ " <td>2.48900</td>\n",
1503
+ " <td>2.50200</td>\n",
1504
+ " <td>9.274000e+01</td>\n",
1505
+ " <td>0.000000</td>\n",
1506
+ " </tr>\n",
1507
+ " <tr>\n",
1508
+ " <th>...</th>\n",
1509
+ " <th>...</th>\n",
1510
+ " <td>...</td>\n",
1511
+ " <td>...</td>\n",
1512
+ " <td>...</td>\n",
1513
+ " <td>...</td>\n",
1514
+ " <td>...</td>\n",
1515
+ " <td>...</td>\n",
1516
+ " </tr>\n",
1517
+ " <tr>\n",
1518
+ " <th rowspan=\"5\" valign=\"top\">2024-08-04</th>\n",
1519
+ " <th>ZEN</th>\n",
1520
+ " <td>8.40600</td>\n",
1521
+ " <td>9.11200</td>\n",
1522
+ " <td>8.28500</td>\n",
1523
+ " <td>8.46200</td>\n",
1524
+ " <td>2.071124e+06</td>\n",
1525
+ " <td>0.000194</td>\n",
1526
+ " </tr>\n",
1527
+ " <tr>\n",
1528
+ " <th>ZIL</th>\n",
1529
+ " <td>0.01422</td>\n",
1530
+ " <td>0.01441</td>\n",
1531
+ " <td>0.01392</td>\n",
1532
+ " <td>0.01396</td>\n",
1533
+ " <td>2.048626e+08</td>\n",
1534
+ " <td>-0.000031</td>\n",
1535
+ " </tr>\n",
1536
+ " <tr>\n",
1537
+ " <th>ZK</th>\n",
1538
+ " <td>0.11451</td>\n",
1539
+ " <td>0.11673</td>\n",
1540
+ " <td>0.10857</td>\n",
1541
+ " <td>0.10874</td>\n",
1542
+ " <td>3.833253e+08</td>\n",
1543
+ " <td>0.000200</td>\n",
1544
+ " </tr>\n",
1545
+ " <tr>\n",
1546
+ " <th>ZRO</th>\n",
1547
+ " <td>3.63100</td>\n",
1548
+ " <td>3.64800</td>\n",
1549
+ " <td>3.36200</td>\n",
1550
+ " <td>3.36700</td>\n",
1551
+ " <td>7.049472e+07</td>\n",
1552
+ " <td>0.000184</td>\n",
1553
+ " </tr>\n",
1554
+ " <tr>\n",
1555
+ " <th>ZRX</th>\n",
1556
+ " <td>0.30550</td>\n",
1557
+ " <td>0.31210</td>\n",
1558
+ " <td>0.29830</td>\n",
1559
+ " <td>0.29880</td>\n",
1560
+ " <td>9.810764e+06</td>\n",
1561
+ " <td>0.000186</td>\n",
1562
+ " </tr>\n",
1563
+ " </tbody>\n",
1564
+ "</table>\n",
1565
+ "<p>387494 rows × 6 columns</p>\n",
1566
+ "</div>"
1567
+ ],
1568
+ "text/plain": [
1569
+ " open high low close volume \\\n",
1570
+ "date ticker \n",
1571
+ "2013-09-29 LTC 2.56500 2.59000 2.59000 2.59000 5.000000e+00 \n",
1572
+ "2013-09-30 LTC 2.59000 2.55400 2.55400 2.55400 5.623000e+01 \n",
1573
+ "2013-10-01 LTC 2.55400 2.66600 2.52500 2.66600 1.000000e+00 \n",
1574
+ "2013-10-02 LTC 2.66600 2.33700 2.33700 2.33700 1.500000e+00 \n",
1575
+ "2013-10-03 LTC 2.33700 2.50200 2.48900 2.50200 9.274000e+01 \n",
1576
+ "... ... ... ... ... ... \n",
1577
+ "2024-08-04 ZEN 8.40600 9.11200 8.28500 8.46200 2.071124e+06 \n",
1578
+ " ZIL 0.01422 0.01441 0.01392 0.01396 2.048626e+08 \n",
1579
+ " ZK 0.11451 0.11673 0.10857 0.10874 3.833253e+08 \n",
1580
+ " ZRO 3.63100 3.64800 3.36200 3.36700 7.049472e+07 \n",
1581
+ " ZRX 0.30550 0.31210 0.29830 0.29880 9.810764e+06 \n",
1582
+ "\n",
1583
+ " funding_rate \n",
1584
+ "date ticker \n",
1585
+ "2013-09-29 LTC 0.000000 \n",
1586
+ "2013-09-30 LTC 0.000000 \n",
1587
+ "2013-10-01 LTC 0.000000 \n",
1588
+ "2013-10-02 LTC 0.000000 \n",
1589
+ "2013-10-03 LTC 0.000000 \n",
1590
+ "... ... \n",
1591
+ "2024-08-04 ZEN 0.000194 \n",
1592
+ " ZIL -0.000031 \n",
1593
+ " ZK 0.000200 \n",
1594
+ " ZRO 0.000184 \n",
1595
+ " ZRX 0.000186 \n",
1596
+ "\n",
1597
+ "[387494 rows x 6 columns]"
1598
+ ]
1599
+ },
1600
+ "execution_count": 85,
1601
+ "metadata": {},
1602
+ "output_type": "execute_result"
1603
+ }
1604
+ ],
1605
+ "source": [
1606
+ "df.drop(['BTC'], level=1, axis=0)"
1607
+ ]
1608
+ },
1609
+ {
1610
+ "cell_type": "code",
1611
+ "execution_count": null,
1612
+ "id": "fabfa152",
1613
+ "metadata": {},
1614
+ "outputs": [],
1615
+ "source": []
1616
+ }
1617
+ ],
1618
+ "metadata": {
1619
+ "kernelspec": {
1620
+ "display_name": "cryptodatapy",
1621
+ "language": "python",
1622
+ "name": "cryptodatapy"
1623
+ },
1624
+ "language_info": {
1625
+ "codemirror_mode": {
1626
+ "name": "ipython",
1627
+ "version": 3
1628
+ },
1629
+ "file_extension": ".py",
1630
+ "mimetype": "text/x-python",
1631
+ "name": "python",
1632
+ "nbconvert_exporter": "python",
1633
+ "pygments_lexer": "ipython3",
1634
+ "version": "3.9.12"
1635
+ }
1636
+ },
1637
+ "nbformat": 4,
1638
+ "nbformat_minor": 5
1639
+ }