ml-finance-python
python scripts for finance machine learning
git clone https://9o.is/git/ml-finance-python.git
lab_103.ipynb
(136684B)
1 {
2 "cells": [
3 {
4 "cell_type": "markdown",
5 "metadata": {},
6 "source": [
7 "# Computing Maximum Drawdown\n",
8 "\n",
9 "In this lab, we'll develop the code to compute the maximum drawdown of a return series, and we'll start to develop our own module which will act as a toolkit that we will add to during the course.\n",
10 "\n",
11 "First, let's read the return series we processed in the previous lab:\n"
12 ]
13 },
14 {
15 "cell_type": "code",
16 "execution_count": 2,
17 "metadata": {},
18 "outputs": [
19 {
20 "data": {
21 "text/plain": [
22 "<AxesSubplot:>"
23 ]
24 },
25 "execution_count": 2,
26 "metadata": {},
27 "output_type": "execute_result"
28 },
29 {
30 "data": {
31 "image/png": "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\n",
32 "text/plain": [
33 "<Figure size 432x288 with 1 Axes>"
34 ]
35 },
36 "metadata": {
37 "needs_background": "light"
38 },
39 "output_type": "display_data"
40 }
41 ],
42 "source": [
43 "import pandas as pd\n",
44 "\n",
45 "me_m = pd.read_csv(\"../data/Portfolios_Formed_on_ME_monthly_EW.csv\",\n",
46 " header=0, index_col=0, parse_dates=True, na_values=-99.99)\n",
47 "rets = me_m[['Lo 10', 'Hi 10']]\n",
48 "rets.columns = ['SmallCap', 'LargeCap']\n",
49 "rets = rets/100\n",
50 "rets.plot.line()"
51 ]
52 },
53 {
54 "cell_type": "markdown",
55 "metadata": {},
56 "source": [
57 "## Timeseries - forcing the index to be a datetime\n",
58 "\n",
59 "We asked Pandas to `parse_dates` in `read_csv()`. Let's check if it was able to do so with the index:"
60 ]
61 },
62 {
63 "cell_type": "code",
64 "execution_count": 2,
65 "metadata": {},
66 "outputs": [
67 {
68 "data": {
69 "text/plain": [
70 "Int64Index([192607, 192608, 192609, 192610, 192611, 192612, 192701, 192702,\n",
71 " 192703, 192704,\n",
72 " ...\n",
73 " 201803, 201804, 201805, 201806, 201807, 201808, 201809, 201810,\n",
74 " 201811, 201812],\n",
75 " dtype='int64', length=1110)"
76 ]
77 },
78 "execution_count": 2,
79 "metadata": {},
80 "output_type": "execute_result"
81 }
82 ],
83 "source": [
84 "rets.index"
85 ]
86 },
87 {
88 "cell_type": "markdown",
89 "metadata": {},
90 "source": [
91 "The `dtype` is `int64` which suggests that it was not automatically converted to a date time index, so let's do that now manually. The simplest way to force it to be a timeseries is by reformatting the index data to a `datetime` type as follows:"
92 ]
93 },
94 {
95 "cell_type": "code",
96 "execution_count": 3,
97 "metadata": {},
98 "outputs": [
99 {
100 "data": {
101 "text/plain": [
102 "DatetimeIndex(['1926-07-01', '1926-08-01', '1926-09-01', '1926-10-01',\n",
103 " '1926-11-01', '1926-12-01', '1927-01-01', '1927-02-01',\n",
104 " '1927-03-01', '1927-04-01',\n",
105 " ...\n",
106 " '2018-03-01', '2018-04-01', '2018-05-01', '2018-06-01',\n",
107 " '2018-07-01', '2018-08-01', '2018-09-01', '2018-10-01',\n",
108 " '2018-11-01', '2018-12-01'],\n",
109 " dtype='datetime64[ns]', length=1110, freq=None)"
110 ]
111 },
112 "execution_count": 3,
113 "metadata": {},
114 "output_type": "execute_result"
115 }
116 ],
117 "source": [
118 "rets.index = pd.to_datetime(rets.index, format=\"%Y%m\")\n",
119 "rets.index"
120 ]
121 },
122 {
123 "cell_type": "markdown",
124 "metadata": {},
125 "source": [
126 "Now that the DataFrame has a datetime index, we can treat the entire dataframe as a timeseries, which makes things very convenient. For instance, we can extract just the returns in 2008 as follows:"
127 ]
128 },
129 {
130 "cell_type": "code",
131 "execution_count": 4,
132 "metadata": {},
133 "outputs": [
134 {
135 "data": {
136 "text/html": [
137 "<div>\n",
138 "<style scoped>\n",
139 " .dataframe tbody tr th:only-of-type {\n",
140 " vertical-align: middle;\n",
141 " }\n",
142 "\n",
143 " .dataframe tbody tr th {\n",
144 " vertical-align: top;\n",
145 " }\n",
146 "\n",
147 " .dataframe thead th {\n",
148 " text-align: right;\n",
149 " }\n",
150 "</style>\n",
151 "<table border=\"1\" class=\"dataframe\">\n",
152 " <thead>\n",
153 " <tr style=\"text-align: right;\">\n",
154 " <th></th>\n",
155 " <th>SmallCap</th>\n",
156 " <th>LargeCap</th>\n",
157 " </tr>\n",
158 " </thead>\n",
159 " <tbody>\n",
160 " <tr>\n",
161 " <th>2008-01-01</th>\n",
162 " <td>-0.0436</td>\n",
163 " <td>-0.0490</td>\n",
164 " </tr>\n",
165 " <tr>\n",
166 " <th>2008-02-01</th>\n",
167 " <td>-0.0203</td>\n",
168 " <td>-0.0250</td>\n",
169 " </tr>\n",
170 " <tr>\n",
171 " <th>2008-03-01</th>\n",
172 " <td>-0.0440</td>\n",
173 " <td>-0.0122</td>\n",
174 " </tr>\n",
175 " <tr>\n",
176 " <th>2008-04-01</th>\n",
177 " <td>0.0027</td>\n",
178 " <td>0.0492</td>\n",
179 " </tr>\n",
180 " <tr>\n",
181 " <th>2008-05-01</th>\n",
182 " <td>0.0286</td>\n",
183 " <td>0.0161</td>\n",
184 " </tr>\n",
185 " <tr>\n",
186 " <th>2008-06-01</th>\n",
187 " <td>-0.0816</td>\n",
188 " <td>-0.1015</td>\n",
189 " </tr>\n",
190 " <tr>\n",
191 " <th>2008-07-01</th>\n",
192 " <td>-0.0079</td>\n",
193 " <td>-0.0140</td>\n",
194 " </tr>\n",
195 " <tr>\n",
196 " <th>2008-08-01</th>\n",
197 " <td>0.0110</td>\n",
198 " <td>0.0087</td>\n",
199 " </tr>\n",
200 " <tr>\n",
201 " <th>2008-09-01</th>\n",
202 " <td>-0.1274</td>\n",
203 " <td>-0.1155</td>\n",
204 " </tr>\n",
205 " <tr>\n",
206 " <th>2008-10-01</th>\n",
207 " <td>-0.2041</td>\n",
208 " <td>-0.1763</td>\n",
209 " </tr>\n",
210 " <tr>\n",
211 " <th>2008-11-01</th>\n",
212 " <td>-0.1650</td>\n",
213 " <td>-0.0735</td>\n",
214 " </tr>\n",
215 " <tr>\n",
216 " <th>2008-12-01</th>\n",
217 " <td>-0.0019</td>\n",
218 " <td>0.0205</td>\n",
219 " </tr>\n",
220 " </tbody>\n",
221 "</table>\n",
222 "</div>"
223 ],
224 "text/plain": [
225 " SmallCap LargeCap\n",
226 "2008-01-01 -0.0436 -0.0490\n",
227 "2008-02-01 -0.0203 -0.0250\n",
228 "2008-03-01 -0.0440 -0.0122\n",
229 "2008-04-01 0.0027 0.0492\n",
230 "2008-05-01 0.0286 0.0161\n",
231 "2008-06-01 -0.0816 -0.1015\n",
232 "2008-07-01 -0.0079 -0.0140\n",
233 "2008-08-01 0.0110 0.0087\n",
234 "2008-09-01 -0.1274 -0.1155\n",
235 "2008-10-01 -0.2041 -0.1763\n",
236 "2008-11-01 -0.1650 -0.0735\n",
237 "2008-12-01 -0.0019 0.0205"
238 ]
239 },
240 "execution_count": 4,
241 "metadata": {},
242 "output_type": "execute_result"
243 }
244 ],
245 "source": [
246 "rets[\"2008\"]"
247 ]
248 },
249 {
250 "cell_type": "markdown",
251 "metadata": {},
252 "source": [
253 "This looks good except that we know this is monthly data, and it's showing up with an index that is date stamped. We can fix this using the `to_period` method. We'll see several more examples of Pandas support for timeseries during the course."
254 ]
255 },
256 {
257 "cell_type": "code",
258 "execution_count": 5,
259 "metadata": {},
260 "outputs": [
261 {
262 "data": {
263 "text/html": [
264 "<div>\n",
265 "<style scoped>\n",
266 " .dataframe tbody tr th:only-of-type {\n",
267 " vertical-align: middle;\n",
268 " }\n",
269 "\n",
270 " .dataframe tbody tr th {\n",
271 " vertical-align: top;\n",
272 " }\n",
273 "\n",
274 " .dataframe thead th {\n",
275 " text-align: right;\n",
276 " }\n",
277 "</style>\n",
278 "<table border=\"1\" class=\"dataframe\">\n",
279 " <thead>\n",
280 " <tr style=\"text-align: right;\">\n",
281 " <th></th>\n",
282 " <th>SmallCap</th>\n",
283 " <th>LargeCap</th>\n",
284 " </tr>\n",
285 " </thead>\n",
286 " <tbody>\n",
287 " <tr>\n",
288 " <th>1926-07</th>\n",
289 " <td>-0.0145</td>\n",
290 " <td>0.0329</td>\n",
291 " </tr>\n",
292 " <tr>\n",
293 " <th>1926-08</th>\n",
294 " <td>0.0512</td>\n",
295 " <td>0.0370</td>\n",
296 " </tr>\n",
297 " <tr>\n",
298 " <th>1926-09</th>\n",
299 " <td>0.0093</td>\n",
300 " <td>0.0067</td>\n",
301 " </tr>\n",
302 " <tr>\n",
303 " <th>1926-10</th>\n",
304 " <td>-0.0484</td>\n",
305 " <td>-0.0243</td>\n",
306 " </tr>\n",
307 " <tr>\n",
308 " <th>1926-11</th>\n",
309 " <td>-0.0078</td>\n",
310 " <td>0.0270</td>\n",
311 " </tr>\n",
312 " </tbody>\n",
313 "</table>\n",
314 "</div>"
315 ],
316 "text/plain": [
317 " SmallCap LargeCap\n",
318 "1926-07 -0.0145 0.0329\n",
319 "1926-08 0.0512 0.0370\n",
320 "1926-09 0.0093 0.0067\n",
321 "1926-10 -0.0484 -0.0243\n",
322 "1926-11 -0.0078 0.0270"
323 ]
324 },
325 "execution_count": 5,
326 "metadata": {},
327 "output_type": "execute_result"
328 }
329 ],
330 "source": [
331 "rets.index = rets.index.to_period('M')\n",
332 "rets.head()"
333 ]
334 },
335 {
336 "cell_type": "code",
337 "execution_count": 6,
338 "metadata": {},
339 "outputs": [
340 {
341 "name": "stdout",
342 "output_type": "stream",
343 "text": [
344 "<class 'pandas.core.frame.DataFrame'>\n",
345 "PeriodIndex: 1110 entries, 1926-07 to 2018-12\n",
346 "Freq: M\n",
347 "Data columns (total 2 columns):\n",
348 "SmallCap 1110 non-null float64\n",
349 "LargeCap 1110 non-null float64\n",
350 "dtypes: float64(2)\n",
351 "memory usage: 26.0 KB\n"
352 ]
353 }
354 ],
355 "source": [
356 "rets.info()"
357 ]
358 },
359 {
360 "cell_type": "code",
361 "execution_count": 7,
362 "metadata": {},
363 "outputs": [
364 {
365 "data": {
366 "text/html": [
367 "<div>\n",
368 "<style scoped>\n",
369 " .dataframe tbody tr th:only-of-type {\n",
370 " vertical-align: middle;\n",
371 " }\n",
372 "\n",
373 " .dataframe tbody tr th {\n",
374 " vertical-align: top;\n",
375 " }\n",
376 "\n",
377 " .dataframe thead th {\n",
378 " text-align: right;\n",
379 " }\n",
380 "</style>\n",
381 "<table border=\"1\" class=\"dataframe\">\n",
382 " <thead>\n",
383 " <tr style=\"text-align: right;\">\n",
384 " <th></th>\n",
385 " <th>SmallCap</th>\n",
386 " <th>LargeCap</th>\n",
387 " </tr>\n",
388 " </thead>\n",
389 " <tbody>\n",
390 " <tr>\n",
391 " <th>count</th>\n",
392 " <td>1110.000000</td>\n",
393 " <td>1110.000000</td>\n",
394 " </tr>\n",
395 " <tr>\n",
396 " <th>mean</th>\n",
397 " <td>0.017598</td>\n",
398 " <td>0.008870</td>\n",
399 " </tr>\n",
400 " <tr>\n",
401 " <th>std</th>\n",
402 " <td>0.106288</td>\n",
403 " <td>0.053900</td>\n",
404 " </tr>\n",
405 " <tr>\n",
406 " <th>min</th>\n",
407 " <td>-0.291400</td>\n",
408 " <td>-0.284300</td>\n",
409 " </tr>\n",
410 " <tr>\n",
411 " <th>25%</th>\n",
412 " <td>-0.027350</td>\n",
413 " <td>-0.017025</td>\n",
414 " </tr>\n",
415 " <tr>\n",
416 " <th>50%</th>\n",
417 " <td>0.010450</td>\n",
418 " <td>0.011400</td>\n",
419 " </tr>\n",
420 " <tr>\n",
421 " <th>75%</th>\n",
422 " <td>0.049950</td>\n",
423 " <td>0.037650</td>\n",
424 " </tr>\n",
425 " <tr>\n",
426 " <th>max</th>\n",
427 " <td>1.342900</td>\n",
428 " <td>0.377900</td>\n",
429 " </tr>\n",
430 " </tbody>\n",
431 "</table>\n",
432 "</div>"
433 ],
434 "text/plain": [
435 " SmallCap LargeCap\n",
436 "count 1110.000000 1110.000000\n",
437 "mean 0.017598 0.008870\n",
438 "std 0.106288 0.053900\n",
439 "min -0.291400 -0.284300\n",
440 "25% -0.027350 -0.017025\n",
441 "50% 0.010450 0.011400\n",
442 "75% 0.049950 0.037650\n",
443 "max 1.342900 0.377900"
444 ]
445 },
446 "execution_count": 7,
447 "metadata": {},
448 "output_type": "execute_result"
449 }
450 ],
451 "source": [
452 "rets.describe()"
453 ]
454 },
455 {
456 "cell_type": "markdown",
457 "metadata": {},
458 "source": [
459 "## Computing Drawdowns\n",
460 "\n",
461 "1. Convert the time series of returns to a time series that represents a wealth index\n",
462 "2. Compute a time series of the previous peaks\n",
463 "3. Compute the Drawdown as the difference between the previous peak and the current value\n",
464 "\n",
465 "Let's do this for Large Cap stocks."
466 ]
467 },
468 {
469 "cell_type": "code",
470 "execution_count": 8,
471 "metadata": {},
472 "outputs": [
473 {
474 "data": {
475 "text/plain": [
476 "<matplotlib.axes._subplots.AxesSubplot at 0x105f28358>"
477 ]
478 },
479 "execution_count": 8,
480 "metadata": {},
481 "output_type": "execute_result"
482 },
483 {
484 "data": {
485 "image/png": "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\n",
486 "text/plain": [
487 "<Figure size 432x288 with 1 Axes>"
488 ]
489 },
490 "metadata": {
491 "needs_background": "light"
492 },
493 "output_type": "display_data"
494 }
495 ],
496 "source": [
497 "wealth_index = 1000*(1+rets[\"LargeCap\"]).cumprod()\n",
498 "wealth_index.plot()"
499 ]
500 },
501 {
502 "cell_type": "code",
503 "execution_count": 9,
504 "metadata": {},
505 "outputs": [
506 {
507 "data": {
508 "text/plain": [
509 "<matplotlib.axes._subplots.AxesSubplot at 0x116fa94a8>"
510 ]
511 },
512 "execution_count": 9,
513 "metadata": {},
514 "output_type": "execute_result"
515 },
516 {
517 "data": {
518 "image/png": "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\n",
519 "text/plain": [
520 "<Figure size 432x288 with 1 Axes>"
521 ]
522 },
523 "metadata": {
524 "needs_background": "light"
525 },
526 "output_type": "display_data"
527 }
528 ],
529 "source": [
530 "previous_peaks = wealth_index.cummax()\n",
531 "previous_peaks.plot()"
532 ]
533 },
534 {
535 "cell_type": "code",
536 "execution_count": 10,
537 "metadata": {},
538 "outputs": [
539 {
540 "data": {
541 "text/plain": [
542 "<matplotlib.axes._subplots.AxesSubplot at 0x117179e10>"
543 ]
544 },
545 "execution_count": 10,
546 "metadata": {},
547 "output_type": "execute_result"
548 },
549 {
550 "data": {
551 "image/png": "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\n",
552 "text/plain": [
553 "<Figure size 432x288 with 1 Axes>"
554 ]
555 },
556 "metadata": {
557 "needs_background": "light"
558 },
559 "output_type": "display_data"
560 }
561 ],
562 "source": [
563 "drawdown = (wealth_index - previous_peaks)/previous_peaks\n",
564 "drawdown.plot()"
565 ]
566 },
567 {
568 "cell_type": "code",
569 "execution_count": 11,
570 "metadata": {},
571 "outputs": [
572 {
573 "data": {
574 "text/plain": [
575 "-0.8400375277943123"
576 ]
577 },
578 "execution_count": 11,
579 "metadata": {},
580 "output_type": "execute_result"
581 }
582 ],
583 "source": [
584 "drawdown.min()"
585 ]
586 },
587 {
588 "cell_type": "code",
589 "execution_count": 12,
590 "metadata": {},
591 "outputs": [
592 {
593 "data": {
594 "text/plain": [
595 "<matplotlib.axes._subplots.AxesSubplot at 0x116fc75f8>"
596 ]
597 },
598 "execution_count": 12,
599 "metadata": {},
600 "output_type": "execute_result"
601 },
602 {
603 "data": {
604 "image/png": "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\n",
605 "text/plain": [
606 "<Figure size 432x288 with 1 Axes>"
607 ]
608 },
609 "metadata": {
610 "needs_background": "light"
611 },
612 "output_type": "display_data"
613 }
614 ],
615 "source": [
616 "drawdown[\"1975\":].plot()"
617 ]
618 },
619 {
620 "cell_type": "code",
621 "execution_count": 13,
622 "metadata": {},
623 "outputs": [
624 {
625 "data": {
626 "text/plain": [
627 "-0.5280945042309304"
628 ]
629 },
630 "execution_count": 13,
631 "metadata": {},
632 "output_type": "execute_result"
633 }
634 ],
635 "source": [
636 "drawdown[\"1975\":].min()"
637 ]
638 },
639 {
640 "cell_type": "markdown",
641 "metadata": {},
642 "source": [
643 "# Creating a Drawdown Function\n",
644 "\n",
645 "Redoing this analysis for SmallCap would be tedious, since we would need to re-enter all these commands at the prompt. Instead, let's create our first function that will form the first tool in our financial toolkit.\n",
646 "\n",
647 "The function will take as input, a timeseries of returns, and return a timeseries as a DataFrame that contains the wealth index, the previous peaks and the drawdowns as a percent."
648 ]
649 },
650 {
651 "cell_type": "code",
652 "execution_count": 14,
653 "metadata": {},
654 "outputs": [
655 {
656 "data": {
657 "text/html": [
658 "<div>\n",
659 "<style scoped>\n",
660 " .dataframe tbody tr th:only-of-type {\n",
661 " vertical-align: middle;\n",
662 " }\n",
663 "\n",
664 " .dataframe tbody tr th {\n",
665 " vertical-align: top;\n",
666 " }\n",
667 "\n",
668 " .dataframe thead th {\n",
669 " text-align: right;\n",
670 " }\n",
671 "</style>\n",
672 "<table border=\"1\" class=\"dataframe\">\n",
673 " <thead>\n",
674 " <tr style=\"text-align: right;\">\n",
675 " <th></th>\n",
676 " <th>Wealth</th>\n",
677 " <th>Previous Peak</th>\n",
678 " <th>Drawdown</th>\n",
679 " </tr>\n",
680 " </thead>\n",
681 " <tbody>\n",
682 " <tr>\n",
683 " <th>1926-07</th>\n",
684 " <td>1032.900000</td>\n",
685 " <td>1032.900000</td>\n",
686 " <td>0.0000</td>\n",
687 " </tr>\n",
688 " <tr>\n",
689 " <th>1926-08</th>\n",
690 " <td>1071.117300</td>\n",
691 " <td>1071.117300</td>\n",
692 " <td>0.0000</td>\n",
693 " </tr>\n",
694 " <tr>\n",
695 " <th>1926-09</th>\n",
696 " <td>1078.293786</td>\n",
697 " <td>1078.293786</td>\n",
698 " <td>0.0000</td>\n",
699 " </tr>\n",
700 " <tr>\n",
701 " <th>1926-10</th>\n",
702 " <td>1052.091247</td>\n",
703 " <td>1078.293786</td>\n",
704 " <td>-0.0243</td>\n",
705 " </tr>\n",
706 " <tr>\n",
707 " <th>1926-11</th>\n",
708 " <td>1080.497711</td>\n",
709 " <td>1080.497711</td>\n",
710 " <td>0.0000</td>\n",
711 " </tr>\n",
712 " </tbody>\n",
713 "</table>\n",
714 "</div>"
715 ],
716 "text/plain": [
717 " Wealth Previous Peak Drawdown\n",
718 "1926-07 1032.900000 1032.900000 0.0000\n",
719 "1926-08 1071.117300 1071.117300 0.0000\n",
720 "1926-09 1078.293786 1078.293786 0.0000\n",
721 "1926-10 1052.091247 1078.293786 -0.0243\n",
722 "1926-11 1080.497711 1080.497711 0.0000"
723 ]
724 },
725 "execution_count": 14,
726 "metadata": {},
727 "output_type": "execute_result"
728 }
729 ],
730 "source": [
731 "def drawdown(return_series: pd.Series):\n",
732 " \"\"\"Takes a time series of asset returns.\n",
733 " returns a DataFrame with columns for\n",
734 " the wealth index, \n",
735 " the previous peaks, and \n",
736 " the percentage drawdown\n",
737 " \"\"\"\n",
738 " wealth_index = 1000*(1+return_series).cumprod()\n",
739 " previous_peaks = wealth_index.cummax()\n",
740 " drawdowns = (wealth_index - previous_peaks)/previous_peaks\n",
741 " return pd.DataFrame({\"Wealth\": wealth_index, \n",
742 " \"Previous Peak\": previous_peaks, \n",
743 " \"Drawdown\": drawdowns})\n",
744 "\n",
745 "drawdown(rets[\"LargeCap\"]).head()"
746 ]
747 },
748 {
749 "cell_type": "code",
750 "execution_count": 15,
751 "metadata": {},
752 "outputs": [
753 {
754 "data": {
755 "text/plain": [
756 "Wealth 405.769102\n",
757 "Previous Peak 1032.900000\n",
758 "Drawdown -0.840038\n",
759 "dtype: float64"
760 ]
761 },
762 "execution_count": 15,
763 "metadata": {},
764 "output_type": "execute_result"
765 }
766 ],
767 "source": [
768 "drawdown(rets[\"LargeCap\"]).min()"
769 ]
770 },
771 {
772 "cell_type": "code",
773 "execution_count": 16,
774 "metadata": {},
775 "outputs": [
776 {
777 "data": {
778 "text/plain": [
779 "Wealth 491.240323\n",
780 "Previous Peak 985.500000\n",
781 "Drawdown -0.833001\n",
782 "dtype: float64"
783 ]
784 },
785 "execution_count": 16,
786 "metadata": {},
787 "output_type": "execute_result"
788 }
789 ],
790 "source": [
791 "drawdown(rets[\"SmallCap\"]).min()"
792 ]
793 },
794 {
795 "cell_type": "code",
796 "execution_count": 17,
797 "metadata": {},
798 "outputs": [
799 {
800 "data": {
801 "text/plain": [
802 "Period('1932-05', 'M')"
803 ]
804 },
805 "execution_count": 17,
806 "metadata": {},
807 "output_type": "execute_result"
808 }
809 ],
810 "source": [
811 "drawdown(rets[\"LargeCap\"])[\"Drawdown\"].idxmin()"
812 ]
813 },
814 {
815 "cell_type": "code",
816 "execution_count": 18,
817 "metadata": {},
818 "outputs": [
819 {
820 "data": {
821 "text/plain": [
822 "Period('1932-05', 'M')"
823 ]
824 },
825 "execution_count": 18,
826 "metadata": {},
827 "output_type": "execute_result"
828 }
829 ],
830 "source": [
831 "drawdown(rets[\"SmallCap\"])[\"Drawdown\"].idxmin()"
832 ]
833 },
834 {
835 "cell_type": "code",
836 "execution_count": 19,
837 "metadata": {},
838 "outputs": [
839 {
840 "data": {
841 "text/plain": [
842 "Period('2009-02', 'M')"
843 ]
844 },
845 "execution_count": 19,
846 "metadata": {},
847 "output_type": "execute_result"
848 }
849 ],
850 "source": [
851 "drawdown(rets[\"LargeCap\"][\"1975\":])[\"Drawdown\"].idxmin()"
852 ]
853 },
854 {
855 "cell_type": "code",
856 "execution_count": 20,
857 "metadata": {},
858 "outputs": [
859 {
860 "data": {
861 "text/plain": [
862 "Period('2009-02', 'M')"
863 ]
864 },
865 "execution_count": 20,
866 "metadata": {},
867 "output_type": "execute_result"
868 }
869 ],
870 "source": [
871 "drawdown(rets[\"SmallCap\"][\"1975\":])[\"Drawdown\"].idxmin()"
872 ]
873 },
874 {
875 "cell_type": "code",
876 "execution_count": 21,
877 "metadata": {},
878 "outputs": [
879 {
880 "data": {
881 "text/plain": [
882 "-0.6312068077252386"
883 ]
884 },
885 "execution_count": 21,
886 "metadata": {},
887 "output_type": "execute_result"
888 }
889 ],
890 "source": [
891 "drawdown(rets[\"SmallCap\"][\"1975\":])[\"Drawdown\"].min()"
892 ]
893 },
894 {
895 "cell_type": "code",
896 "execution_count": null,
897 "metadata": {},
898 "outputs": [],
899 "source": []
900 }
901 ],
902 "metadata": {
903 "kernelspec": {
904 "display_name": "Python 3",
905 "language": "python",
906 "name": "python3"
907 },
908 "language_info": {
909 "codemirror_mode": {
910 "name": "ipython",
911 "version": 3
912 },
913 "file_extension": ".py",
914 "mimetype": "text/x-python",
915 "name": "python",
916 "nbconvert_exporter": "python",
917 "pygments_lexer": "ipython3",
918 "version": "3.8.8"
919 }
920 },
921 "nbformat": 4,
922 "nbformat_minor": 2
923 }