├── .gitattributes
├── 9781484271094.jpg
├── errata.md
├── README.md
├── Contributing.md
├── LICENSE.txt
└── Chapter_5_Stock_Clustering.ipynb


/.gitattributes:
--------------------------------------------------------------------------------
1 | # Auto detect text files and perform LF normalization
2 | * text=auto
3 | 


--------------------------------------------------------------------------------
/9781484271094.jpg:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Apress/implementing-machine-learning-finance/HEAD/9781484271094.jpg


--------------------------------------------------------------------------------
/errata.md:
--------------------------------------------------------------------------------
 1 | # Errata for *Implementing Machine Learning for Finance*
 2 | 
 3 | On **page xx** [Summary of error]:
 4 |  
 5 | Details of error here. Highlight key pieces in **bold**.
 6 | 
 7 | ***
 8 | 
 9 | On **page xx** [Summary of error]:
10 |  
11 | Details of error here. Highlight key pieces in **bold**.
12 | 
13 | ***


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Apress Source Code
 2 | 
 3 | This repository accompanies [*Implementing Machine Learning for Finance*](https://www.apress.com/9781484271094) by Tshepo Chris Nokeri (Apress, 2021).
 4 | 
 5 | [comment]: #cover
 6 | ![Cover image](9781484271094.jpg)
 7 | 
 8 | Download the files as a zip using the green button, or clone the repository to your machine using Git.
 9 | 
10 | ## Releases
11 | 
12 | Release v1.0 corresponds to the code in the published book, without corrections or updates.
13 | 
14 | ## Contributions
15 | 
16 | See the file Contributing.md for more information on how you can contribute to this repository.


--------------------------------------------------------------------------------
/Contributing.md:
--------------------------------------------------------------------------------
 1 | # Contributing to Apress Source Code
 2 | 
 3 | Copyright for Apress source code belongs to the author(s). However, under fair use you are encouraged to fork and contribute minor corrections and updates for the benefit of the author(s) and other readers.
 4 | 
 5 | ## How to Contribute
 6 | 
 7 | 1. Make sure you have a GitHub account.
 8 | 2. Fork the repository for the relevant book.
 9 | 3. Create a new branch on which to make your change, e.g. 
10 | `git checkout -b my_code_contribution`
11 | 4. Commit your change. Include a commit message describing the correction. Please note that if your commit message is not clear, the correction will not be accepted.
12 | 5. Submit a pull request.
13 | 
14 | Thank you for your contribution!


--------------------------------------------------------------------------------
/LICENSE.txt:
--------------------------------------------------------------------------------
 1 | Freeware License, some rights reserved
 2 | 
 3 | Copyright (c) 2021 Tshepo Chris Nokeri
 4 | 
 5 | Permission is hereby granted, free of charge, to anyone obtaining a copy 
 6 | of this software and associated documentation files (the "Software"), 
 7 | to work with the Software within the limits of freeware distribution and fair use. 
 8 | This includes the rights to use, copy, and modify the Software for personal use. 
 9 | Users are also allowed and encouraged to submit corrections and modifications 
10 | to the Software for the benefit of other users.
11 | 
12 | It is not allowed to reuse,  modify, or redistribute the Software for 
13 | commercial use in any way, or for a user’s educational materials such as books 
14 | or blog articles without prior permission from the copyright holder. 
15 | 
16 | The above copyright notice and this permission notice need to be included 
17 | in all copies or substantial portions of the software.
18 | 
19 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
20 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
21 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
22 | AUTHORS OR COPYRIGHT HOLDERS OR APRESS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
23 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
24 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
25 | SOFTWARE.
26 | 
27 | 
28 | 


--------------------------------------------------------------------------------
/Chapter_5_Stock_Clustering.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "Data Science Revealed by Tshepo Chris Nokeri, Apress. 2021"
  8 |    ]
  9 |   },
 10 |   {
 11 |    "cell_type": "markdown",
 12 |    "metadata": {},
 13 |    "source": [
 14 |     "# Chapter 5: Stock Clustering"
 15 |    ]
 16 |   },
 17 |   {
 18 |    "cell_type": "markdown",
 19 |    "metadata": {},
 20 |    "source": [
 21 |     "The K-Means model partitions the data into k (clusters) with the nearest mean (centroids), it then finds the distance between subgroups to produce a cluster. It simultaneously shrinks the intra-cluster distances and improves the inter-cluster"
 22 |    ]
 23 |   },
 24 |   {
 25 |    "cell_type": "markdown",
 26 |    "metadata": {},
 27 |    "source": [
 28 |     "# Import Dependencies"
 29 |    ]
 30 |   },
 31 |   {
 32 |    "cell_type": "code",
 33 |    "execution_count": 3,
 34 |    "metadata": {},
 35 |    "outputs": [],
 36 |    "source": [
 37 |     "import numpy as np\n",
 38 |     "import pandas as pd\n",
 39 |     "import matplotlib.pyplot as plt\n",
 40 |     "%matplotlib inline\n",
 41 |     "import seaborn as sns\n",
 42 |     "sns.set(\"talk\",\"ticks\",font_scale=1,font=\"Calibri\")\n",
 43 |     "from pylab import rcParams\n",
 44 |     "plt.rcParams[\"figure.dpi\"] = 300\n",
 45 |     "import warnings\n",
 46 |     "warnings.filterwarnings(\"ignore\")\n",
 47 |     "import pandas as pd\n",
 48 |     "import numpy as np\n",
 49 |     "import datetime as dt\n",
 50 |     "import scipy\n",
 51 |     "from pandas_datareader import data\n",
 52 |     "from sklearn.cluster import KMeans"
 53 |    ]
 54 |   },
 55 |   {
 56 |    "cell_type": "code",
 57 |    "execution_count": 12,
 58 |    "metadata": {},
 59 |    "outputs": [
 60 |     {
 61 |      "data": {
 62 |       "text/html": [
 63 |        "<div>\n",
 64 |        "<style scoped>\n",
 65 |        "    .dataframe tbody tr th:only-of-type {\n",
 66 |        "        vertical-align: middle;\n",
 67 |        "    }\n",
 68 |        "\n",
 69 |        "    .dataframe tbody tr th {\n",
 70 |        "        vertical-align: top;\n",
 71 |        "    }\n",
 72 |        "\n",
 73 |        "    .dataframe thead tr th {\n",
 74 |        "        text-align: left;\n",
 75 |        "    }\n",
 76 |        "\n",
 77 |        "    .dataframe thead tr:last-of-type th {\n",
 78 |        "        text-align: right;\n",
 79 |        "    }\n",
 80 |        "</style>\n",
 81 |        "<table border=\"1\" class=\"dataframe\">\n",
 82 |        "  <thead>\n",
 83 |        "    <tr>\n",
 84 |        "      <th>Attributes</th>\n",
 85 |        "      <th colspan=\"21\" halign=\"left\">Adj Close</th>\n",
 86 |        "    </tr>\n",
 87 |        "    <tr>\n",
 88 |        "      <th>Symbols</th>\n",
 89 |        "      <th>AMZN</th>\n",
 90 |        "      <th>AAPL</th>\n",
 91 |        "      <th>WBA</th>\n",
 92 |        "      <th>NOC</th>\n",
 93 |        "      <th>BA</th>\n",
 94 |        "      <th>LMT</th>\n",
 95 |        "      <th>MCD</th>\n",
 96 |        "      <th>INTC</th>\n",
 97 |        "      <th>NAV</th>\n",
 98 |        "      <th>IBM</th>\n",
 99 |        "      <th>...</th>\n",
100 |        "      <th>JNJ</th>\n",
101 |        "      <th>TM</th>\n",
102 |        "      <th>HMC</th>\n",
103 |        "      <th>SNE</th>\n",
104 |        "      <th>XOM</th>\n",
105 |        "      <th>CVX</th>\n",
106 |        "      <th>VLO</th>\n",
107 |        "      <th>F</th>\n",
108 |        "      <th>BAC</th>\n",
109 |        "      <th>MSBHY</th>\n",
110 |        "    </tr>\n",
111 |        "    <tr>\n",
112 |        "      <th>Date</th>\n",
113 |        "      <th></th>\n",
114 |        "      <th></th>\n",
115 |        "      <th></th>\n",
116 |        "      <th></th>\n",
117 |        "      <th></th>\n",
118 |        "      <th></th>\n",
119 |        "      <th></th>\n",
120 |        "      <th></th>\n",
121 |        "      <th></th>\n",
122 |        "      <th></th>\n",
123 |        "      <th></th>\n",
124 |        "      <th></th>\n",
125 |        "      <th></th>\n",
126 |        "      <th></th>\n",
127 |        "      <th></th>\n",
128 |        "      <th></th>\n",
129 |        "      <th></th>\n",
130 |        "      <th></th>\n",
131 |        "      <th></th>\n",
132 |        "      <th></th>\n",
133 |        "      <th></th>\n",
134 |        "    </tr>\n",
135 |        "  </thead>\n",
136 |        "  <tbody>\n",
137 |        "    <tr>\n",
138 |        "      <th>2010-01-04</th>\n",
139 |        "      <td>133.899994</td>\n",
140 |        "      <td>6.583586</td>\n",
141 |        "      <td>28.326071</td>\n",
142 |        "      <td>39.991074</td>\n",
143 |        "      <td>43.777542</td>\n",
144 |        "      <td>53.263012</td>\n",
145 |        "      <td>45.185108</td>\n",
146 |        "      <td>14.864470</td>\n",
147 |        "      <td>40.150002</td>\n",
148 |        "      <td>92.528694</td>\n",
149 |        "      <td>...</td>\n",
150 |        "      <td>46.298389</td>\n",
151 |        "      <td>72.314583</td>\n",
152 |        "      <td>34.525009</td>\n",
153 |        "      <td>30.020000</td>\n",
154 |        "      <td>45.575386</td>\n",
155 |        "      <td>50.816982</td>\n",
156 |        "      <td>11.529408</td>\n",
157 |        "      <td>6.968545</td>\n",
158 |        "      <td>13.663458</td>\n",
159 |        "      <td>NaN</td>\n",
160 |        "    </tr>\n",
161 |        "    <tr>\n",
162 |        "      <th>2010-01-05</th>\n",
163 |        "      <td>134.690002</td>\n",
164 |        "      <td>6.594968</td>\n",
165 |        "      <td>28.098249</td>\n",
166 |        "      <td>40.061401</td>\n",
167 |        "      <td>45.211330</td>\n",
168 |        "      <td>53.817471</td>\n",
169 |        "      <td>44.839626</td>\n",
170 |        "      <td>14.857353</td>\n",
171 |        "      <td>39.720001</td>\n",
172 |        "      <td>91.410950</td>\n",
173 |        "      <td>...</td>\n",
174 |        "      <td>45.761547</td>\n",
175 |        "      <td>71.201118</td>\n",
176 |        "      <td>34.286152</td>\n",
177 |        "      <td>29.879999</td>\n",
178 |        "      <td>45.753330</td>\n",
179 |        "      <td>51.176937</td>\n",
180 |        "      <td>11.825860</td>\n",
181 |        "      <td>7.429503</td>\n",
182 |        "      <td>14.107587</td>\n",
183 |        "      <td>NaN</td>\n",
184 |        "    </tr>\n",
185 |        "    <tr>\n",
186 |        "      <th>2010-01-06</th>\n",
187 |        "      <td>132.250000</td>\n",
188 |        "      <td>6.490066</td>\n",
189 |        "      <td>27.885616</td>\n",
190 |        "      <td>40.216160</td>\n",
191 |        "      <td>46.582798</td>\n",
192 |        "      <td>53.027367</td>\n",
193 |        "      <td>44.227863</td>\n",
194 |        "      <td>14.807525</td>\n",
195 |        "      <td>40.950001</td>\n",
196 |        "      <td>90.817116</td>\n",
197 |        "      <td>...</td>\n",
198 |        "      <td>46.133747</td>\n",
199 |        "      <td>72.110588</td>\n",
200 |        "      <td>33.987579</td>\n",
201 |        "      <td>29.850000</td>\n",
202 |        "      <td>46.148773</td>\n",
203 |        "      <td>51.183357</td>\n",
204 |        "      <td>12.122313</td>\n",
205 |        "      <td>7.707428</td>\n",
206 |        "      <td>14.273045</td>\n",
207 |        "      <td>NaN</td>\n",
208 |        "    </tr>\n",
209 |        "    <tr>\n",
210 |        "      <th>2010-01-07</th>\n",
211 |        "      <td>130.000000</td>\n",
212 |        "      <td>6.478067</td>\n",
213 |        "      <td>28.052691</td>\n",
214 |        "      <td>40.631191</td>\n",
215 |        "      <td>48.468555</td>\n",
216 |        "      <td>51.571884</td>\n",
217 |        "      <td>44.551743</td>\n",
218 |        "      <td>14.665145</td>\n",
219 |        "      <td>41.000000</td>\n",
220 |        "      <td>90.502762</td>\n",
221 |        "      <td>...</td>\n",
222 |        "      <td>45.804497</td>\n",
223 |        "      <td>71.218140</td>\n",
224 |        "      <td>33.410339</td>\n",
225 |        "      <td>29.799999</td>\n",
226 |        "      <td>46.003792</td>\n",
227 |        "      <td>50.990532</td>\n",
228 |        "      <td>12.212536</td>\n",
229 |        "      <td>7.904015</td>\n",
230 |        "      <td>14.743298</td>\n",
231 |        "      <td>NaN</td>\n",
232 |        "    </tr>\n",
233 |        "    <tr>\n",
234 |        "      <th>2010-01-08</th>\n",
235 |        "      <td>133.520004</td>\n",
236 |        "      <td>6.521136</td>\n",
237 |        "      <td>28.090660</td>\n",
238 |        "      <td>40.406101</td>\n",
239 |        "      <td>48.001007</td>\n",
240 |        "      <td>52.403591</td>\n",
241 |        "      <td>44.508553</td>\n",
242 |        "      <td>14.828878</td>\n",
243 |        "      <td>40.549999</td>\n",
244 |        "      <td>91.410950</td>\n",
245 |        "      <td>...</td>\n",
246 |        "      <td>45.961971</td>\n",
247 |        "      <td>72.892555</td>\n",
248 |        "      <td>34.176678</td>\n",
249 |        "      <td>30.410000</td>\n",
250 |        "      <td>45.819229</td>\n",
251 |        "      <td>51.080528</td>\n",
252 |        "      <td>12.044977</td>\n",
253 |        "      <td>7.924348</td>\n",
254 |        "      <td>14.612673</td>\n",
255 |        "      <td>NaN</td>\n",
256 |        "    </tr>\n",
257 |        "  </tbody>\n",
258 |        "</table>\n",
259 |        "<p>5 rows × 27 columns</p>\n",
260 |        "</div>"
261 |       ],
262 |       "text/plain": [
263 |        "Attributes   Adj Close                                                        \\\n",
264 |        "Symbols           AMZN      AAPL        WBA        NOC         BA        LMT   \n",
265 |        "Date                                                                           \n",
266 |        "2010-01-04  133.899994  6.583586  28.326071  39.991074  43.777542  53.263012   \n",
267 |        "2010-01-05  134.690002  6.594968  28.098249  40.061401  45.211330  53.817471   \n",
268 |        "2010-01-06  132.250000  6.490066  27.885616  40.216160  46.582798  53.027367   \n",
269 |        "2010-01-07  130.000000  6.478067  28.052691  40.631191  48.468555  51.571884   \n",
270 |        "2010-01-08  133.520004  6.521136  28.090660  40.406101  48.001007  52.403591   \n",
271 |        "\n",
272 |        "Attributes                                              ...             \\\n",
273 |        "Symbols           MCD       INTC        NAV        IBM  ...        JNJ   \n",
274 |        "Date                                                    ...              \n",
275 |        "2010-01-04  45.185108  14.864470  40.150002  92.528694  ...  46.298389   \n",
276 |        "2010-01-05  44.839626  14.857353  39.720001  91.410950  ...  45.761547   \n",
277 |        "2010-01-06  44.227863  14.807525  40.950001  90.817116  ...  46.133747   \n",
278 |        "2010-01-07  44.551743  14.665145  41.000000  90.502762  ...  45.804497   \n",
279 |        "2010-01-08  44.508553  14.828878  40.549999  91.410950  ...  45.961971   \n",
280 |        "\n",
281 |        "Attributes                                                                    \\\n",
282 |        "Symbols            TM        HMC        SNE        XOM        CVX        VLO   \n",
283 |        "Date                                                                           \n",
284 |        "2010-01-04  72.314583  34.525009  30.020000  45.575386  50.816982  11.529408   \n",
285 |        "2010-01-05  71.201118  34.286152  29.879999  45.753330  51.176937  11.825860   \n",
286 |        "2010-01-06  72.110588  33.987579  29.850000  46.148773  51.183357  12.122313   \n",
287 |        "2010-01-07  71.218140  33.410339  29.799999  46.003792  50.990532  12.212536   \n",
288 |        "2010-01-08  72.892555  34.176678  30.410000  45.819229  51.080528  12.044977   \n",
289 |        "\n",
290 |        "Attributes                             \n",
291 |        "Symbols            F        BAC MSBHY  \n",
292 |        "Date                                   \n",
293 |        "2010-01-04  6.968545  13.663458   NaN  \n",
294 |        "2010-01-05  7.429503  14.107587   NaN  \n",
295 |        "2010-01-06  7.707428  14.273045   NaN  \n",
296 |        "2010-01-07  7.904015  14.743298   NaN  \n",
297 |        "2010-01-08  7.924348  14.612673   NaN  \n",
298 |        "\n",
299 |        "[5 rows x 27 columns]"
300 |       ]
301 |      },
302 |      "execution_count": 12,
303 |      "metadata": {},
304 |      "output_type": "execute_result"
305 |     }
306 |    ],
307 |    "source": [
308 |     "tickers = ['AMZN','AAPL','WBA',\n",
309 |     "           'NOC','BA','LMT',\n",
310 |     "           'MCD','INTC','NAV',\n",
311 |     "           'IBM','TXN','MA',\n",
312 |     "           'MSFT','GE','AXP',\n",
313 |     "           'PEP','KO','JNJ',\n",
314 |     "           'TM','HMC','MSBHY',\n",
315 |     "           'SNE','XOM','CVX',\n",
316 |     "           'VLO','F','BAC']\n",
317 |     "start_date = '2010-01-01'\n",
318 |     "end_date = '2020-11-01'\n",
319 |     "df = data.get_data_yahoo(tickers, start_date, end_date)[['Adj Close']]\n",
320 |     "df.head()"
321 |    ]
322 |   },
323 |   {
324 |    "cell_type": "markdown",
325 |    "metadata": {},
326 |    "source": [
327 |     "# Data Preprocessing"
328 |    ]
329 |   },
330 |   {
331 |    "cell_type": "code",
332 |    "execution_count": 15,
333 |    "metadata": {},
334 |    "outputs": [],
335 |    "source": [
336 |     "returns = df.pct_change().mean() * (10*12)\n",
337 |     "std = df.pct_change().std() * np.sqrt((10*12))"
338 |    ]
339 |   },
340 |   {
341 |    "cell_type": "code",
342 |    "execution_count": 16,
343 |    "metadata": {},
344 |    "outputs": [],
345 |    "source": [
346 |     "ret_var = pd.concat([returns, std], axis = 1).dropna()\n",
347 |     "ret_var.columns = [\"Returns\",\"Standard Deviation\"]\n",
348 |     "ret_var = ret_var.dropna()"
349 |    ]
350 |   },
351 |   {
352 |    "cell_type": "code",
353 |    "execution_count": 17,
354 |    "metadata": {},
355 |    "outputs": [
356 |     {
357 |      "data": {
358 |       "text/html": [
359 |        "<div>\n",
360 |        "<style scoped>\n",
361 |        "    .dataframe tbody tr th:only-of-type {\n",
362 |        "        vertical-align: middle;\n",
363 |        "    }\n",
364 |        "\n",
365 |        "    .dataframe tbody tr th {\n",
366 |        "        vertical-align: top;\n",
367 |        "    }\n",
368 |        "\n",
369 |        "    .dataframe thead th {\n",
370 |        "        text-align: right;\n",
371 |        "    }\n",
372 |        "</style>\n",
373 |        "<table border=\"1\" class=\"dataframe\">\n",
374 |        "  <thead>\n",
375 |        "    <tr style=\"text-align: right;\">\n",
376 |        "      <th></th>\n",
377 |        "      <th></th>\n",
378 |        "      <th>Returns</th>\n",
379 |        "      <th>Standard Deviation</th>\n",
380 |        "    </tr>\n",
381 |        "    <tr>\n",
382 |        "      <th>Attributes</th>\n",
383 |        "      <th>Symbols</th>\n",
384 |        "      <th></th>\n",
385 |        "      <th></th>\n",
386 |        "    </tr>\n",
387 |        "  </thead>\n",
388 |        "  <tbody>\n",
389 |        "    <tr>\n",
390 |        "      <th rowspan=\"26\" valign=\"top\">Adj Close</th>\n",
391 |        "      <th>AMZN</th>\n",
392 |        "      <td>0.161408</td>\n",
393 |        "      <td>0.219298</td>\n",
394 |        "    </tr>\n",
395 |        "    <tr>\n",
396 |        "      <th>AAPL</th>\n",
397 |        "      <td>0.142520</td>\n",
398 |        "      <td>0.195328</td>\n",
399 |        "    </tr>\n",
400 |        "    <tr>\n",
401 |        "      <th>WBA</th>\n",
402 |        "      <td>0.025443</td>\n",
403 |        "      <td>0.190796</td>\n",
404 |        "    </tr>\n",
405 |        "    <tr>\n",
406 |        "      <th>NOC</th>\n",
407 |        "      <td>0.099019</td>\n",
408 |        "      <td>0.156366</td>\n",
409 |        "    </tr>\n",
410 |        "    <tr>\n",
411 |        "      <th>BA</th>\n",
412 |        "      <td>0.081806</td>\n",
413 |        "      <td>0.241513</td>\n",
414 |        "    </tr>\n",
415 |        "    <tr>\n",
416 |        "      <th>LMT</th>\n",
417 |        "      <td>0.092771</td>\n",
418 |        "      <td>0.144668</td>\n",
419 |        "    </tr>\n",
420 |        "    <tr>\n",
421 |        "      <th>MCD</th>\n",
422 |        "      <td>0.076515</td>\n",
423 |        "      <td>0.132609</td>\n",
424 |        "    </tr>\n",
425 |        "    <tr>\n",
426 |        "      <th>INTC</th>\n",
427 |        "      <td>0.066716</td>\n",
428 |        "      <td>0.195823</td>\n",
429 |        "    </tr>\n",
430 |        "    <tr>\n",
431 |        "      <th>NAV</th>\n",
432 |        "      <td>0.076994</td>\n",
433 |        "      <td>0.390811</td>\n",
434 |        "    </tr>\n",
435 |        "    <tr>\n",
436 |        "      <th>IBM</th>\n",
437 |        "      <td>0.019014</td>\n",
438 |        "      <td>0.154290</td>\n",
439 |        "    </tr>\n",
440 |        "    <tr>\n",
441 |        "      <th>TXN</th>\n",
442 |        "      <td>0.104789</td>\n",
443 |        "      <td>0.185254</td>\n",
444 |        "    </tr>\n",
445 |        "    <tr>\n",
446 |        "      <th>MA</th>\n",
447 |        "      <td>0.127789</td>\n",
448 |        "      <td>0.194159</td>\n",
449 |        "    </tr>\n",
450 |        "    <tr>\n",
451 |        "      <th>MSFT</th>\n",
452 |        "      <td>0.108985</td>\n",
453 |        "      <td>0.175395</td>\n",
454 |        "    </tr>\n",
455 |        "    <tr>\n",
456 |        "      <th>GE</th>\n",
457 |        "      <td>0.006226</td>\n",
458 |        "      <td>0.217377</td>\n",
459 |        "    </tr>\n",
460 |        "    <tr>\n",
461 |        "      <th>AXP</th>\n",
462 |        "      <td>0.061691</td>\n",
463 |        "      <td>0.195526</td>\n",
464 |        "    </tr>\n",
465 |        "    <tr>\n",
466 |        "      <th>PEP</th>\n",
467 |        "      <td>0.055518</td>\n",
468 |        "      <td>0.120928</td>\n",
469 |        "    </tr>\n",
470 |        "    <tr>\n",
471 |        "      <th>KO</th>\n",
472 |        "      <td>0.044974</td>\n",
473 |        "      <td>0.120511</td>\n",
474 |        "    </tr>\n",
475 |        "    <tr>\n",
476 |        "      <th>JNJ</th>\n",
477 |        "      <td>0.054099</td>\n",
478 |        "      <td>0.117171</td>\n",
479 |        "    </tr>\n",
480 |        "    <tr>\n",
481 |        "      <th>TM</th>\n",
482 |        "      <td>0.037129</td>\n",
483 |        "      <td>0.147504</td>\n",
484 |        "    </tr>\n",
485 |        "    <tr>\n",
486 |        "      <th>HMC</th>\n",
487 |        "      <td>-0.002639</td>\n",
488 |        "      <td>0.167707</td>\n",
489 |        "    </tr>\n",
490 |        "    <tr>\n",
491 |        "      <th>SNE</th>\n",
492 |        "      <td>0.070541</td>\n",
493 |        "      <td>0.225907</td>\n",
494 |        "    </tr>\n",
495 |        "    <tr>\n",
496 |        "      <th>XOM</th>\n",
497 |        "      <td>-0.003797</td>\n",
498 |        "      <td>0.159237</td>\n",
499 |        "    </tr>\n",
500 |        "    <tr>\n",
501 |        "      <th>CVX</th>\n",
502 |        "      <td>0.029708</td>\n",
503 |        "      <td>0.184557</td>\n",
504 |        "    </tr>\n",
505 |        "    <tr>\n",
506 |        "      <th>VLO</th>\n",
507 |        "      <td>0.086470</td>\n",
508 |        "      <td>0.263032</td>\n",
509 |        "    </tr>\n",
510 |        "    <tr>\n",
511 |        "      <th>F</th>\n",
512 |        "      <td>0.027856</td>\n",
513 |        "      <td>0.216174</td>\n",
514 |        "    </tr>\n",
515 |        "    <tr>\n",
516 |        "      <th>BAC</th>\n",
517 |        "      <td>0.053830</td>\n",
518 |        "      <td>0.244936</td>\n",
519 |        "    </tr>\n",
520 |        "  </tbody>\n",
521 |        "</table>\n",
522 |        "</div>"
523 |       ],
524 |       "text/plain": [
525 |        "                     Returns  Standard Deviation\n",
526 |        "Attributes Symbols                              \n",
527 |        "Adj Close  AMZN     0.161408            0.219298\n",
528 |        "           AAPL     0.142520            0.195328\n",
529 |        "           WBA      0.025443            0.190796\n",
530 |        "           NOC      0.099019            0.156366\n",
531 |        "           BA       0.081806            0.241513\n",
532 |        "           LMT      0.092771            0.144668\n",
533 |        "           MCD      0.076515            0.132609\n",
534 |        "           INTC     0.066716            0.195823\n",
535 |        "           NAV      0.076994            0.390811\n",
536 |        "           IBM      0.019014            0.154290\n",
537 |        "           TXN      0.104789            0.185254\n",
538 |        "           MA       0.127789            0.194159\n",
539 |        "           MSFT     0.108985            0.175395\n",
540 |        "           GE       0.006226            0.217377\n",
541 |        "           AXP      0.061691            0.195526\n",
542 |        "           PEP      0.055518            0.120928\n",
543 |        "           KO       0.044974            0.120511\n",
544 |        "           JNJ      0.054099            0.117171\n",
545 |        "           TM       0.037129            0.147504\n",
546 |        "           HMC     -0.002639            0.167707\n",
547 |        "           SNE      0.070541            0.225907\n",
548 |        "           XOM     -0.003797            0.159237\n",
549 |        "           CVX      0.029708            0.184557\n",
550 |        "           VLO      0.086470            0.263032\n",
551 |        "           F        0.027856            0.216174\n",
552 |        "           BAC      0.053830            0.244936"
553 |       ]
554 |      },
555 |      "execution_count": 17,
556 |      "metadata": {},
557 |      "output_type": "execute_result"
558 |     }
559 |    ],
560 |    "source": [
561 |     "ret_var"
562 |    ]
563 |   },
564 |   {
565 |    "cell_type": "markdown",
566 |    "metadata": {},
567 |    "source": [
568 |     "# Elbow Curve"
569 |    ]
570 |   },
571 |   {
572 |    "cell_type": "code",
573 |    "execution_count": 19,
574 |    "metadata": {},
575 |    "outputs": [
576 |     {
577 |      "data": {
578 |       "image/png": "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\n",
579 |       "text/plain": [
580 |        "<Figure size 1800x1200 with 1 Axes>"
581 |       ]
582 |      },
583 |      "metadata": {},
584 |      "output_type": "display_data"
585 |     }
586 |    ],
587 |    "source": [
588 |     "X =  ret_var.values\n",
589 |     "sse = []\n",
590 |     "for k in range(1,15):\n",
591 |     "    kmeans = KMeans(n_clusters = k)\n",
592 |     "    kmeans.fit(X)\n",
593 |     "    sse.append(kmeans.inertia_) \n",
594 |     "plt.plot(range(1,15), sse)\n",
595 |     "plt.xlabel(\"Value of k\")\n",
596 |     "plt.ylabel(\"Distortion\")\n",
597 |     "plt.show()"
598 |    ]
599 |   },
600 |   {
601 |    "cell_type": "markdown",
602 |    "metadata": {},
603 |    "source": [
604 |     "## Develop the K-Means Model"
605 |    ]
606 |   },
607 |   {
608 |    "cell_type": "code",
609 |    "execution_count": 20,
610 |    "metadata": {},
611 |    "outputs": [
612 |     {
613 |      "data": {
614 |       "image/png": "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\n",
615 |       "text/plain": [
616 |        "<Figure size 1800x1200 with 1 Axes>"
617 |       ]
618 |      },
619 |      "metadata": {},
620 |      "output_type": "display_data"
621 |     }
622 |    ],
623 |    "source": [
624 |     "stdOrder = ret_var.sort_values('Standard Deviation',ascending=False)\n",
625 |     "first_symbol = stdOrder.index[0]\n",
626 |     "ret_var.drop(first_symbol,inplace=True)\n",
627 |     "X = ret_var.values\n",
628 |     "kmeans =KMeans(n_clusters = 5).fit(X)\n",
629 |     "centroids = kmeans.cluster_centers_\n",
630 |     "plt.scatter(X[:,0],X[:,1], c = kmeans.labels_, cmap =\"viridis\")\n",
631 |     "plt.scatter(centroids[:,0], centroids[:,1],color=\"black\",marker=\"*\",s=200)\n",
632 |     "plt.xlabel(\"y\")\n",
633 |     "plt.show()"
634 |    ]
635 |   },
636 |   {
637 |    "cell_type": "markdown",
638 |    "metadata": {},
639 |    "source": [
640 |     "## Show Cluster, Returns and Volatility"
641 |    ]
642 |   },
643 |   {
644 |    "cell_type": "code",
645 |    "execution_count": 21,
646 |    "metadata": {},
647 |    "outputs": [
648 |     {
649 |      "data": {
650 |       "text/html": [
651 |        "<div>\n",
652 |        "<style scoped>\n",
653 |        "    .dataframe tbody tr th:only-of-type {\n",
654 |        "        vertical-align: middle;\n",
655 |        "    }\n",
656 |        "\n",
657 |        "    .dataframe tbody tr th {\n",
658 |        "        vertical-align: top;\n",
659 |        "    }\n",
660 |        "\n",
661 |        "    .dataframe thead th {\n",
662 |        "        text-align: right;\n",
663 |        "    }\n",
664 |        "</style>\n",
665 |        "<table border=\"1\" class=\"dataframe\">\n",
666 |        "  <thead>\n",
667 |        "    <tr style=\"text-align: right;\">\n",
668 |        "      <th></th>\n",
669 |        "      <th>Cluster</th>\n",
670 |        "      <th>Returns</th>\n",
671 |        "      <th>Volatility</th>\n",
672 |        "    </tr>\n",
673 |        "    <tr>\n",
674 |        "      <th>Symbol</th>\n",
675 |        "      <th></th>\n",
676 |        "      <th></th>\n",
677 |        "      <th></th>\n",
678 |        "    </tr>\n",
679 |        "  </thead>\n",
680 |        "  <tbody>\n",
681 |        "    <tr>\n",
682 |        "      <th>(Adj Close, AMZN)</th>\n",
683 |        "      <td>1</td>\n",
684 |        "      <td>0.161408</td>\n",
685 |        "      <td>0.219298</td>\n",
686 |        "    </tr>\n",
687 |        "    <tr>\n",
688 |        "      <th>(Adj Close, AAPL)</th>\n",
689 |        "      <td>1</td>\n",
690 |        "      <td>0.142520</td>\n",
691 |        "      <td>0.195328</td>\n",
692 |        "    </tr>\n",
693 |        "    <tr>\n",
694 |        "      <th>(Adj Close, WBA)</th>\n",
695 |        "      <td>4</td>\n",
696 |        "      <td>0.025443</td>\n",
697 |        "      <td>0.190796</td>\n",
698 |        "    </tr>\n",
699 |        "    <tr>\n",
700 |        "      <th>(Adj Close, NOC)</th>\n",
701 |        "      <td>1</td>\n",
702 |        "      <td>0.099019</td>\n",
703 |        "      <td>0.156366</td>\n",
704 |        "    </tr>\n",
705 |        "    <tr>\n",
706 |        "      <th>(Adj Close, BA)</th>\n",
707 |        "      <td>3</td>\n",
708 |        "      <td>0.081806</td>\n",
709 |        "      <td>0.241513</td>\n",
710 |        "    </tr>\n",
711 |        "    <tr>\n",
712 |        "      <th>(Adj Close, LMT)</th>\n",
713 |        "      <td>2</td>\n",
714 |        "      <td>0.092771</td>\n",
715 |        "      <td>0.144668</td>\n",
716 |        "    </tr>\n",
717 |        "    <tr>\n",
718 |        "      <th>(Adj Close, MCD)</th>\n",
719 |        "      <td>2</td>\n",
720 |        "      <td>0.076515</td>\n",
721 |        "      <td>0.132609</td>\n",
722 |        "    </tr>\n",
723 |        "    <tr>\n",
724 |        "      <th>(Adj Close, INTC)</th>\n",
725 |        "      <td>4</td>\n",
726 |        "      <td>0.066716</td>\n",
727 |        "      <td>0.195823</td>\n",
728 |        "    </tr>\n",
729 |        "    <tr>\n",
730 |        "      <th>(Adj Close, IBM)</th>\n",
731 |        "      <td>0</td>\n",
732 |        "      <td>0.019014</td>\n",
733 |        "      <td>0.154290</td>\n",
734 |        "    </tr>\n",
735 |        "    <tr>\n",
736 |        "      <th>(Adj Close, TXN)</th>\n",
737 |        "      <td>1</td>\n",
738 |        "      <td>0.104789</td>\n",
739 |        "      <td>0.185254</td>\n",
740 |        "    </tr>\n",
741 |        "    <tr>\n",
742 |        "      <th>(Adj Close, MA)</th>\n",
743 |        "      <td>1</td>\n",
744 |        "      <td>0.127789</td>\n",
745 |        "      <td>0.194159</td>\n",
746 |        "    </tr>\n",
747 |        "    <tr>\n",
748 |        "      <th>(Adj Close, MSFT)</th>\n",
749 |        "      <td>1</td>\n",
750 |        "      <td>0.108985</td>\n",
751 |        "      <td>0.175395</td>\n",
752 |        "    </tr>\n",
753 |        "    <tr>\n",
754 |        "      <th>(Adj Close, GE)</th>\n",
755 |        "      <td>4</td>\n",
756 |        "      <td>0.006226</td>\n",
757 |        "      <td>0.217377</td>\n",
758 |        "    </tr>\n",
759 |        "    <tr>\n",
760 |        "      <th>(Adj Close, AXP)</th>\n",
761 |        "      <td>4</td>\n",
762 |        "      <td>0.061691</td>\n",
763 |        "      <td>0.195526</td>\n",
764 |        "    </tr>\n",
765 |        "    <tr>\n",
766 |        "      <th>(Adj Close, PEP)</th>\n",
767 |        "      <td>2</td>\n",
768 |        "      <td>0.055518</td>\n",
769 |        "      <td>0.120928</td>\n",
770 |        "    </tr>\n",
771 |        "    <tr>\n",
772 |        "      <th>(Adj Close, KO)</th>\n",
773 |        "      <td>2</td>\n",
774 |        "      <td>0.044974</td>\n",
775 |        "      <td>0.120511</td>\n",
776 |        "    </tr>\n",
777 |        "    <tr>\n",
778 |        "      <th>(Adj Close, JNJ)</th>\n",
779 |        "      <td>2</td>\n",
780 |        "      <td>0.054099</td>\n",
781 |        "      <td>0.117171</td>\n",
782 |        "    </tr>\n",
783 |        "    <tr>\n",
784 |        "      <th>(Adj Close, TM)</th>\n",
785 |        "      <td>2</td>\n",
786 |        "      <td>0.037129</td>\n",
787 |        "      <td>0.147504</td>\n",
788 |        "    </tr>\n",
789 |        "    <tr>\n",
790 |        "      <th>(Adj Close, HMC)</th>\n",
791 |        "      <td>0</td>\n",
792 |        "      <td>-0.002639</td>\n",
793 |        "      <td>0.167707</td>\n",
794 |        "    </tr>\n",
795 |        "    <tr>\n",
796 |        "      <th>(Adj Close, SNE)</th>\n",
797 |        "      <td>3</td>\n",
798 |        "      <td>0.070541</td>\n",
799 |        "      <td>0.225907</td>\n",
800 |        "    </tr>\n",
801 |        "    <tr>\n",
802 |        "      <th>(Adj Close, XOM)</th>\n",
803 |        "      <td>0</td>\n",
804 |        "      <td>-0.003797</td>\n",
805 |        "      <td>0.159237</td>\n",
806 |        "    </tr>\n",
807 |        "    <tr>\n",
808 |        "      <th>(Adj Close, CVX)</th>\n",
809 |        "      <td>4</td>\n",
810 |        "      <td>0.029708</td>\n",
811 |        "      <td>0.184557</td>\n",
812 |        "    </tr>\n",
813 |        "    <tr>\n",
814 |        "      <th>(Adj Close, VLO)</th>\n",
815 |        "      <td>3</td>\n",
816 |        "      <td>0.086470</td>\n",
817 |        "      <td>0.263032</td>\n",
818 |        "    </tr>\n",
819 |        "    <tr>\n",
820 |        "      <th>(Adj Close, F)</th>\n",
821 |        "      <td>4</td>\n",
822 |        "      <td>0.027856</td>\n",
823 |        "      <td>0.216174</td>\n",
824 |        "    </tr>\n",
825 |        "    <tr>\n",
826 |        "      <th>(Adj Close, BAC)</th>\n",
827 |        "      <td>3</td>\n",
828 |        "      <td>0.053830</td>\n",
829 |        "      <td>0.244936</td>\n",
830 |        "    </tr>\n",
831 |        "  </tbody>\n",
832 |        "</table>\n",
833 |        "</div>"
834 |       ],
835 |       "text/plain": [
836 |        "                   Cluster   Returns  Volatility\n",
837 |        "Symbol                                          \n",
838 |        "(Adj Close, AMZN)        1  0.161408    0.219298\n",
839 |        "(Adj Close, AAPL)        1  0.142520    0.195328\n",
840 |        "(Adj Close, WBA)         4  0.025443    0.190796\n",
841 |        "(Adj Close, NOC)         1  0.099019    0.156366\n",
842 |        "(Adj Close, BA)          3  0.081806    0.241513\n",
843 |        "(Adj Close, LMT)         2  0.092771    0.144668\n",
844 |        "(Adj Close, MCD)         2  0.076515    0.132609\n",
845 |        "(Adj Close, INTC)        4  0.066716    0.195823\n",
846 |        "(Adj Close, IBM)         0  0.019014    0.154290\n",
847 |        "(Adj Close, TXN)         1  0.104789    0.185254\n",
848 |        "(Adj Close, MA)          1  0.127789    0.194159\n",
849 |        "(Adj Close, MSFT)        1  0.108985    0.175395\n",
850 |        "(Adj Close, GE)          4  0.006226    0.217377\n",
851 |        "(Adj Close, AXP)         4  0.061691    0.195526\n",
852 |        "(Adj Close, PEP)         2  0.055518    0.120928\n",
853 |        "(Adj Close, KO)          2  0.044974    0.120511\n",
854 |        "(Adj Close, JNJ)         2  0.054099    0.117171\n",
855 |        "(Adj Close, TM)          2  0.037129    0.147504\n",
856 |        "(Adj Close, HMC)         0 -0.002639    0.167707\n",
857 |        "(Adj Close, SNE)         3  0.070541    0.225907\n",
858 |        "(Adj Close, XOM)         0 -0.003797    0.159237\n",
859 |        "(Adj Close, CVX)         4  0.029708    0.184557\n",
860 |        "(Adj Close, VLO)         3  0.086470    0.263032\n",
861 |        "(Adj Close, F)           4  0.027856    0.216174\n",
862 |        "(Adj Close, BAC)         3  0.053830    0.244936"
863 |       ]
864 |      },
865 |      "execution_count": 21,
866 |      "metadata": {},
867 |      "output_type": "execute_result"
868 |     }
869 |    ],
870 |    "source": [
871 |     "stocks = pd.DataFrame(ret_var.index)\n",
872 |     "cluster_labels = pd.DataFrame(kmeans.labels_)\n",
873 |     "stockClusters = pd.concat([stocks, cluster_labels],axis = 1)\n",
874 |     "stockClusters.columns = ['Symbol','Cluster']\n",
875 |     "x_df = pd.DataFrame(X, columns = [\"Returns\", \"Volatility\"])\n",
876 |     "closerv = pd.concat([stockClusters,x_df],axis=1)\n",
877 |     "closerv = closerv.set_index(\"Symbol\")\n",
878 |     "closerv"
879 |    ]
880 |   },
881 |   {
882 |    "cell_type": "code",
883 |    "execution_count": 26,
884 |    "metadata": {},
885 |    "outputs": [
886 |     {
887 |      "data": {
888 |       "text/plain": [
889 |        "0.4260002825147118"
890 |       ]
891 |      },
892 |      "execution_count": 26,
893 |      "metadata": {},
894 |      "output_type": "execute_result"
895 |     }
896 |    ],
897 |    "source": [
898 |     "from sklearn import metrics\n",
899 |     "y_predkmeans = pd.DataFrame(kmeans.predict(X))\n",
900 |     "y_predkmeans = y_predkmeans.dropna()\n",
901 |     "metrics.silhouette_score(X,y_predkmeans)"
902 |    ]
903 |   }
904 |  ],
905 |  "metadata": {
906 |   "kernelspec": {
907 |    "display_name": "Python 3",
908 |    "language": "python",
909 |    "name": "python3"
910 |   },
911 |   "language_info": {
912 |    "codemirror_mode": {
913 |     "name": "ipython",
914 |     "version": 3
915 |    },
916 |    "file_extension": ".py",
917 |    "mimetype": "text/x-python",
918 |    "name": "python",
919 |    "nbconvert_exporter": "python",
920 |    "pygments_lexer": "ipython3",
921 |    "version": "3.7.6"
922 |   }
923 |  },
924 |  "nbformat": 4,
925 |  "nbformat_minor": 4
926 | }
927 | 


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