├── Bitcoin-SVM-Same-Data.ipynb
├── Bitcoin_ARIMA.ipynb
├── Bitcoin_LinearRegression-Same-Data.ipynb
├── Bitcoin_LinearRegression.ipynb
├── Bitcoin_SVM.ipynb
├── Bitcoin_dataframe.ipynb
├── Bitcoin_price_forecasting_with_LSTM_and_GRU-v-Copy1.2.ipynb
├── Bitcoin_price_forecasting_with_LSTM_and_GRU-v.2.ipynb
├── Naive_Average_Holt_winter-1.ipynb
├── Naive_Average_Holt_winter_Same_Data-Copy1.ipynb
├── Naive_Average_Holt_winter_Same_Data.ipynb
├── Naive_Average_Holt_winter_not_same_data.ipynb
├── Prophet.ipynb
├── README.md
├── RandomForest_and_boosting_ensemble.ipynb
├── SARIMA.ipynb
├── SmallMethodHoltWinter.ipynb
├── bitcoin_dataset.csv
└── bitcoin_price.csv


/Bitcoin-SVM-Same-Data.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 11,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import pandas as pd\n",
 10 |     "import numpy as np\n",
 11 |     "import datetime\n",
 12 |     "from sklearn.linear_model import LinearRegression\n",
 13 |     "from sklearn import preprocessing, cross_validation, svm\n",
 14 |     "import matplotlib.pylab as plt\n",
 15 |     "%matplotlib inline\n",
 16 |     "from matplotlib.pylab import rcParams\n",
 17 |     "rcParams['figure.figsize'] = 15, 6"
 18 |    ]
 19 |   },
 20 |   {
 21 |    "cell_type": "code",
 22 |    "execution_count": 12,
 23 |    "metadata": {},
 24 |    "outputs": [
 25 |     {
 26 |      "data": {
 27 |       "text/html": [
 28 |        "<div>\n",
 29 |        "<style scoped>\n",
 30 |        "    .dataframe tbody tr th:only-of-type {\n",
 31 |        "        vertical-align: middle;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe tbody tr th {\n",
 35 |        "        vertical-align: top;\n",
 36 |        "    }\n",
 37 |        "\n",
 38 |        "    .dataframe thead th {\n",
 39 |        "        text-align: right;\n",
 40 |        "    }\n",
 41 |        "</style>\n",
 42 |        "<table border=\"1\" class=\"dataframe\">\n",
 43 |        "  <thead>\n",
 44 |        "    <tr style=\"text-align: right;\">\n",
 45 |        "      <th></th>\n",
 46 |        "      <th>Timestamp</th>\n",
 47 |        "      <th>Open</th>\n",
 48 |        "      <th>High</th>\n",
 49 |        "      <th>Low</th>\n",
 50 |        "      <th>Close</th>\n",
 51 |        "      <th>Volume_(BTC)</th>\n",
 52 |        "      <th>Volume_(Currency)</th>\n",
 53 |        "      <th>Weighted_Price</th>\n",
 54 |        "    </tr>\n",
 55 |        "  </thead>\n",
 56 |        "  <tbody>\n",
 57 |        "    <tr>\n",
 58 |        "      <th>0</th>\n",
 59 |        "      <td>1325317920</td>\n",
 60 |        "      <td>4.39</td>\n",
 61 |        "      <td>4.39</td>\n",
 62 |        "      <td>4.39</td>\n",
 63 |        "      <td>4.39</td>\n",
 64 |        "      <td>0.455581</td>\n",
 65 |        "      <td>2.0</td>\n",
 66 |        "      <td>4.39</td>\n",
 67 |        "    </tr>\n",
 68 |        "    <tr>\n",
 69 |        "      <th>1</th>\n",
 70 |        "      <td>1325317980</td>\n",
 71 |        "      <td>4.39</td>\n",
 72 |        "      <td>4.39</td>\n",
 73 |        "      <td>4.39</td>\n",
 74 |        "      <td>4.39</td>\n",
 75 |        "      <td>0.455581</td>\n",
 76 |        "      <td>2.0</td>\n",
 77 |        "      <td>4.39</td>\n",
 78 |        "    </tr>\n",
 79 |        "    <tr>\n",
 80 |        "      <th>2</th>\n",
 81 |        "      <td>1325318040</td>\n",
 82 |        "      <td>4.39</td>\n",
 83 |        "      <td>4.39</td>\n",
 84 |        "      <td>4.39</td>\n",
 85 |        "      <td>4.39</td>\n",
 86 |        "      <td>0.455581</td>\n",
 87 |        "      <td>2.0</td>\n",
 88 |        "      <td>4.39</td>\n",
 89 |        "    </tr>\n",
 90 |        "    <tr>\n",
 91 |        "      <th>3</th>\n",
 92 |        "      <td>1325318100</td>\n",
 93 |        "      <td>4.39</td>\n",
 94 |        "      <td>4.39</td>\n",
 95 |        "      <td>4.39</td>\n",
 96 |        "      <td>4.39</td>\n",
 97 |        "      <td>0.455581</td>\n",
 98 |        "      <td>2.0</td>\n",
 99 |        "      <td>4.39</td>\n",
100 |        "    </tr>\n",
101 |        "    <tr>\n",
102 |        "      <th>4</th>\n",
103 |        "      <td>1325318160</td>\n",
104 |        "      <td>4.39</td>\n",
105 |        "      <td>4.39</td>\n",
106 |        "      <td>4.39</td>\n",
107 |        "      <td>4.39</td>\n",
108 |        "      <td>0.455581</td>\n",
109 |        "      <td>2.0</td>\n",
110 |        "      <td>4.39</td>\n",
111 |        "    </tr>\n",
112 |        "    <tr>\n",
113 |        "      <th>5</th>\n",
114 |        "      <td>1325318220</td>\n",
115 |        "      <td>4.39</td>\n",
116 |        "      <td>4.39</td>\n",
117 |        "      <td>4.39</td>\n",
118 |        "      <td>4.39</td>\n",
119 |        "      <td>0.455581</td>\n",
120 |        "      <td>2.0</td>\n",
121 |        "      <td>4.39</td>\n",
122 |        "    </tr>\n",
123 |        "    <tr>\n",
124 |        "      <th>6</th>\n",
125 |        "      <td>1325318280</td>\n",
126 |        "      <td>4.39</td>\n",
127 |        "      <td>4.39</td>\n",
128 |        "      <td>4.39</td>\n",
129 |        "      <td>4.39</td>\n",
130 |        "      <td>0.455581</td>\n",
131 |        "      <td>2.0</td>\n",
132 |        "      <td>4.39</td>\n",
133 |        "    </tr>\n",
134 |        "    <tr>\n",
135 |        "      <th>7</th>\n",
136 |        "      <td>1325318340</td>\n",
137 |        "      <td>4.39</td>\n",
138 |        "      <td>4.39</td>\n",
139 |        "      <td>4.39</td>\n",
140 |        "      <td>4.39</td>\n",
141 |        "      <td>0.455581</td>\n",
142 |        "      <td>2.0</td>\n",
143 |        "      <td>4.39</td>\n",
144 |        "    </tr>\n",
145 |        "    <tr>\n",
146 |        "      <th>8</th>\n",
147 |        "      <td>1325318400</td>\n",
148 |        "      <td>4.39</td>\n",
149 |        "      <td>4.39</td>\n",
150 |        "      <td>4.39</td>\n",
151 |        "      <td>4.39</td>\n",
152 |        "      <td>0.455581</td>\n",
153 |        "      <td>2.0</td>\n",
154 |        "      <td>4.39</td>\n",
155 |        "    </tr>\n",
156 |        "    <tr>\n",
157 |        "      <th>9</th>\n",
158 |        "      <td>1325318460</td>\n",
159 |        "      <td>4.39</td>\n",
160 |        "      <td>4.39</td>\n",
161 |        "      <td>4.39</td>\n",
162 |        "      <td>4.39</td>\n",
163 |        "      <td>0.455581</td>\n",
164 |        "      <td>2.0</td>\n",
165 |        "      <td>4.39</td>\n",
166 |        "    </tr>\n",
167 |        "  </tbody>\n",
168 |        "</table>\n",
169 |        "</div>"
170 |       ],
171 |       "text/plain": [
172 |        "    Timestamp  Open  High   Low  Close  Volume_(BTC)  Volume_(Currency)  \\\n",
173 |        "0  1325317920  4.39  4.39  4.39   4.39      0.455581                2.0   \n",
174 |        "1  1325317980  4.39  4.39  4.39   4.39      0.455581                2.0   \n",
175 |        "2  1325318040  4.39  4.39  4.39   4.39      0.455581                2.0   \n",
176 |        "3  1325318100  4.39  4.39  4.39   4.39      0.455581                2.0   \n",
177 |        "4  1325318160  4.39  4.39  4.39   4.39      0.455581                2.0   \n",
178 |        "5  1325318220  4.39  4.39  4.39   4.39      0.455581                2.0   \n",
179 |        "6  1325318280  4.39  4.39  4.39   4.39      0.455581                2.0   \n",
180 |        "7  1325318340  4.39  4.39  4.39   4.39      0.455581                2.0   \n",
181 |        "8  1325318400  4.39  4.39  4.39   4.39      0.455581                2.0   \n",
182 |        "9  1325318460  4.39  4.39  4.39   4.39      0.455581                2.0   \n",
183 |        "\n",
184 |        "   Weighted_Price  \n",
185 |        "0            4.39  \n",
186 |        "1            4.39  \n",
187 |        "2            4.39  \n",
188 |        "3            4.39  \n",
189 |        "4            4.39  \n",
190 |        "5            4.39  \n",
191 |        "6            4.39  \n",
192 |        "7            4.39  \n",
193 |        "8            4.39  \n",
194 |        "9            4.39  "
195 |       ]
196 |      },
197 |      "execution_count": 12,
198 |      "metadata": {},
199 |      "output_type": "execute_result"
200 |     }
201 |    ],
202 |    "source": [
203 |     "df = pd.read_csv('bitstampUSD_1-min_data_2012-01-01_to_2018-01-08.csv')\n",
204 |     "df.isnull().values.any()\n",
205 |     "df.head(10)"
206 |    ]
207 |   },
208 |   {
209 |    "cell_type": "code",
210 |    "execution_count": 14,
211 |    "metadata": {},
212 |    "outputs": [
213 |     {
214 |      "data": {
215 |       "text/plain": [
216 |        "Date\n",
217 |        "2011-12-31    4.472579\n",
218 |        "2012-01-01    4.680778\n",
219 |        "2012-01-02    5.000000\n",
220 |        "2012-01-03    5.145917\n",
221 |        "2012-01-04    5.195443\n",
222 |        "Name: Weighted_Price, dtype: float64"
223 |       ]
224 |      },
225 |      "execution_count": 14,
226 |      "metadata": {},
227 |      "output_type": "execute_result"
228 |     }
229 |    ],
230 |    "source": [
231 |     "df['Date'] = pd.to_datetime(df['Timestamp'],unit='s').dt.date\n",
232 |     "group = df.groupby('Date')\n",
233 |     "Daily_Price = group['Weighted_Price'].mean()\n",
234 |     "Daily_Price.head()"
235 |    ]
236 |   },
237 |   {
238 |    "cell_type": "code",
239 |    "execution_count": 15,
240 |    "metadata": {},
241 |    "outputs": [],
242 |    "source": [
243 |     "new_df= pd.DataFrame(list(Daily_Price), index = Daily_Price.index, columns = [\"Close\"])"
244 |    ]
245 |   },
246 |   {
247 |    "cell_type": "code",
248 |    "execution_count": 23,
249 |    "metadata": {},
250 |    "outputs": [
251 |     {
252 |      "data": {
253 |       "text/html": [
254 |        "<div>\n",
255 |        "<style scoped>\n",
256 |        "    .dataframe tbody tr th:only-of-type {\n",
257 |        "        vertical-align: middle;\n",
258 |        "    }\n",
259 |        "\n",
260 |        "    .dataframe tbody tr th {\n",
261 |        "        vertical-align: top;\n",
262 |        "    }\n",
263 |        "\n",
264 |        "    .dataframe thead th {\n",
265 |        "        text-align: right;\n",
266 |        "    }\n",
267 |        "</style>\n",
268 |        "<table border=\"1\" class=\"dataframe\">\n",
269 |        "  <thead>\n",
270 |        "    <tr style=\"text-align: right;\">\n",
271 |        "      <th></th>\n",
272 |        "      <th>Close</th>\n",
273 |        "      <th>Prediction</th>\n",
274 |        "    </tr>\n",
275 |        "    <tr>\n",
276 |        "      <th>Date</th>\n",
277 |        "      <th></th>\n",
278 |        "      <th></th>\n",
279 |        "    </tr>\n",
280 |        "  </thead>\n",
281 |        "  <tbody>\n",
282 |        "    <tr>\n",
283 |        "      <th>2011-12-31</th>\n",
284 |        "      <td>4.472579</td>\n",
285 |        "      <td>5.505306</td>\n",
286 |        "    </tr>\n",
287 |        "    <tr>\n",
288 |        "      <th>2012-01-01</th>\n",
289 |        "      <td>4.680778</td>\n",
290 |        "      <td>5.603342</td>\n",
291 |        "    </tr>\n",
292 |        "    <tr>\n",
293 |        "      <th>2012-01-02</th>\n",
294 |        "      <td>5.000000</td>\n",
295 |        "      <td>5.562427</td>\n",
296 |        "    </tr>\n",
297 |        "    <tr>\n",
298 |        "      <th>2012-01-03</th>\n",
299 |        "      <td>5.145917</td>\n",
300 |        "      <td>6.100355</td>\n",
301 |        "    </tr>\n",
302 |        "    <tr>\n",
303 |        "      <th>2012-01-04</th>\n",
304 |        "      <td>5.195443</td>\n",
305 |        "      <td>6.200014</td>\n",
306 |        "    </tr>\n",
307 |        "  </tbody>\n",
308 |        "</table>\n",
309 |        "</div>"
310 |       ],
311 |       "text/plain": [
312 |        "               Close  Prediction\n",
313 |        "Date                            \n",
314 |        "2011-12-31  4.472579    5.505306\n",
315 |        "2012-01-01  4.680778    5.603342\n",
316 |        "2012-01-02  5.000000    5.562427\n",
317 |        "2012-01-03  5.145917    6.100355\n",
318 |        "2012-01-04  5.195443    6.200014"
319 |       ]
320 |      },
321 |      "execution_count": 23,
322 |      "metadata": {},
323 |      "output_type": "execute_result"
324 |     }
325 |    ],
326 |    "source": [
327 |     "new_df.head()"
328 |    ]
329 |   },
330 |   {
331 |    "cell_type": "code",
332 |    "execution_count": 24,
333 |    "metadata": {},
334 |    "outputs": [
335 |     {
336 |      "data": {
337 |       "text/plain": [
338 |        "[<matplotlib.lines.Line2D at 0x7fb370631d30>,\n",
339 |        " <matplotlib.lines.Line2D at 0x7fb3706ac780>]"
340 |       ]
341 |      },
342 |      "execution_count": 24,
343 |      "metadata": {},
344 |      "output_type": "execute_result"
345 |     },
346 |     {
347 |      "data": {
348 |       "image/png": "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\n",
349 |       "text/plain": [
350 |        "<matplotlib.figure.Figure at 0x7fb36e45c128>"
351 |       ]
352 |      },
353 |      "metadata": {},
354 |      "output_type": "display_data"
355 |     }
356 |    ],
357 |    "source": [
358 |     "plt.plot(new_df)"
359 |    ]
360 |   },
361 |   {
362 |    "cell_type": "code",
363 |    "execution_count": 25,
364 |    "metadata": {},
365 |    "outputs": [
366 |     {
367 |      "name": "stdout",
368 |      "output_type": "stream",
369 |      "text": [
370 |       "confidence:  0.9268953582520982\n",
371 |       "[20826.59658505 23894.98586365 24681.20340288 24399.09203043\n",
372 |       " 24102.94646788 25622.6386896  26824.3876171  28326.66126768\n",
373 |       " 27630.08083974 27038.61760678 24832.34852704 23923.55366437\n",
374 |       " 20272.84070883 21765.84532383 20114.26207206 20577.46487123\n",
375 |       " 22473.97079832 22974.21589035 20995.37745685 21420.96970709\n",
376 |       " 19454.35034375 19646.59561641 19775.19425291 20448.11547345\n",
377 |       " 22058.07977624 21841.76498198 23287.02469065 24585.36018042\n",
378 |       " 24364.40124654 23779.69150184]\n"
379 |      ]
380 |     }
381 |    ],
382 |    "source": [
383 |     "# df = df[['Close']]\n",
384 |     "df=new_df\n",
385 |     "forecast_out = int(30)\n",
386 |     "\n",
387 |     "df['Prediction'] = df[['Close']].shift(-forecast_out)\n",
388 |     "\n",
389 |     "X = np.array(df.drop(['Prediction'],1))\n",
390 |     "X = preprocessing.scale(X)\n",
391 |     "\n",
392 |     "X_forecast = X[-forecast_out:]\n",
393 |     "X = X[:-forecast_out]\n",
394 |     "\n",
395 |     "y = np.array(df['Prediction'])\n",
396 |     "y = y[:-forecast_out]\n",
397 |     "\n",
398 |     "X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size = 0.2)\n",
399 |     "\n",
400 |     "clf = LinearRegression()\n",
401 |     "clf.fit(X_train,y_train)\n",
402 |     "\n",
403 |     "cross_validation = clf.predict(X_test)\n",
404 |     "\n",
405 |     "confidence = clf.score(X_test, y_test)\n",
406 |     "print(\"confidence: \", confidence)\n",
407 |     "\n",
408 |     "forecast_prediction = clf.predict(X_forecast)\n",
409 |     "print(forecast_prediction)"
410 |    ]
411 |   },
412 |   {
413 |    "cell_type": "code",
414 |    "execution_count": 27,
415 |    "metadata": {},
416 |    "outputs": [
417 |     {
418 |      "data": {
419 |       "image/png": "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\n",
420 |       "text/plain": [
421 |        "<matplotlib.figure.Figure at 0x7fb36e45cfd0>"
422 |       ]
423 |      },
424 |      "metadata": {},
425 |      "output_type": "display_data"
426 |     }
427 |    ],
428 |    "source": [
429 |     "import matplotlib.pyplot as plt\n",
430 |     "# print(X_test)\n",
431 |     "# print(y_test)\n",
432 |     "# plt.plot(X_test,forecast_set,color='blue', linewidth=1)\n",
433 |     "plt.scatter(X_test, y_test, color='darkorange', label='data')\n",
434 |     "plt.plot(X_test, cross_validation, color='blue', linewidth=1)\n",
435 |     "# plt.plot(X_test, forecast_prediction, color='blue', linew/idth=2)\n",
436 |     "plt.show()"
437 |    ]
438 |   },
439 |   {
440 |    "cell_type": "code",
441 |    "execution_count": 29,
442 |    "metadata": {},
443 |    "outputs": [
444 |     {
445 |      "name": "stdout",
446 |      "output_type": "stream",
447 |      "text": [
448 |       "604.429803272577\n"
449 |      ]
450 |     }
451 |    ],
452 |    "source": [
453 |     "from sklearn.metrics import mean_squared_error\n",
454 |     "from math import sqrt\n",
455 |     "rms = sqrt(mean_squared_error(y_test, cross_validation))\n",
456 |     "print(rms)"
457 |    ]
458 |   },
459 |   {
460 |    "cell_type": "code",
461 |    "execution_count": 64,
462 |    "metadata": {},
463 |    "outputs": [
464 |     {
465 |      "data": {
466 |       "text/plain": [
467 |        "0.9036278554322356"
468 |       ]
469 |      },
470 |      "execution_count": 64,
471 |      "metadata": {},
472 |      "output_type": "execute_result"
473 |     }
474 |    ],
475 |    "source": [
476 |     "pred={}\n",
477 |     "forecast_prediction\n",
478 |     "pred[]"
479 |    ]
480 |   },
481 |   {
482 |    "cell_type": "code",
483 |    "execution_count": 61,
484 |    "metadata": {},
485 |    "outputs": [
486 |     {
487 |      "data": {
488 |       "image/png": "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\n",
489 |       "text/plain": [
490 |        "<matplotlib.figure.Figure at 0x7fdc10ae9278>"
491 |       ]
492 |      },
493 |      "metadata": {},
494 |      "output_type": "display_data"
495 |     }
496 |    ],
497 |    "source": [
498 |     "plt.figure(figsize=(12,8))\n",
499 |     "plt.plot(df['Close'], label='Train')\n",
500 |     "# plt.plot(X_test['Close'], label='Test')\n",
501 |     "# plt.plot(y_hat_avg['avg_forecast'], label='Average Forecast')\n",
502 |     "plt.legend(loc='best')\n",
503 |     "plt.show()"
504 |    ]
505 |   }
506 |  ],
507 |  "metadata": {
508 |   "kernelspec": {
509 |    "display_name": "Python 3",
510 |    "language": "python",
511 |    "name": "python3"
512 |   },
513 |   "language_info": {
514 |    "codemirror_mode": {
515 |     "name": "ipython",
516 |     "version": 3
517 |    },
518 |    "file_extension": ".py",
519 |    "mimetype": "text/x-python",
520 |    "name": "python",
521 |    "nbconvert_exporter": "python",
522 |    "pygments_lexer": "ipython3",
523 |    "version": "3.6.4"
524 |   }
525 |  },
526 |  "nbformat": 4,
527 |  "nbformat_minor": 2
528 | }
529 | 


--------------------------------------------------------------------------------
/Bitcoin_LinearRegression.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 56,
  6 |    "metadata": {},
  7 |    "outputs": [
  8 |     {
  9 |      "name": "stdout",
 10 |      "output_type": "stream",
 11 |      "text": [
 12 |       "<class 'pandas.core.frame.DataFrame'>\n",
 13 |       "DatetimeIndex: 1655 entries, 2013-04-28 to 2017-11-07\n",
 14 |       "Data columns (total 6 columns):\n",
 15 |       "Open          1655 non-null float64\n",
 16 |       "High          1655 non-null float64\n",
 17 |       "Low           1655 non-null float64\n",
 18 |       "Close         1655 non-null float64\n",
 19 |       "Volume        1655 non-null object\n",
 20 |       "Market Cap    1655 non-null object\n",
 21 |       "dtypes: float64(4), object(2)\n",
 22 |       "memory usage: 90.5+ KB\n",
 23 |       "              Close\n",
 24 |       "Date               \n",
 25 |       "2017-11-03  7207.76\n",
 26 |       "2017-11-04  7379.95\n",
 27 |       "2017-11-05  7407.41\n",
 28 |       "2017-11-06  7022.76\n",
 29 |       "2017-11-07  7144.38\n"
 30 |      ]
 31 |     }
 32 |    ],
 33 |    "source": [
 34 |     "# import quandl\n",
 35 |     "import pandas as pd\n",
 36 |     "import numpy as np\n",
 37 |     "import datetime\n",
 38 |     "from sklearn.linear_model import LinearRegression\n",
 39 |     "from sklearn import preprocessing, cross_validation, svm\n",
 40 |     "\n",
 41 |     "# df = quandl.get(\"WIKI/AMZN\")\n",
 42 |     "df = pd.read_csv('bitcoin_price.csv', parse_dates=['Date'],)\n",
 43 |     "df=df.iloc[::-1]\n",
 44 |     "df.index = df['Date']\n",
 45 |     "del df['Date']\n",
 46 |     "df.info()\n",
 47 |     "df = df[['Close']]\n",
 48 |     "print(df.tail())"
 49 |    ]
 50 |   },
 51 |   {
 52 |    "cell_type": "code",
 53 |    "execution_count": 57,
 54 |    "metadata": {},
 55 |    "outputs": [
 56 |     {
 57 |      "data": {
 58 |       "text/html": [
 59 |        "<div>\n",
 60 |        "<style scoped>\n",
 61 |        "    .dataframe tbody tr th:only-of-type {\n",
 62 |        "        vertical-align: middle;\n",
 63 |        "    }\n",
 64 |        "\n",
 65 |        "    .dataframe tbody tr th {\n",
 66 |        "        vertical-align: top;\n",
 67 |        "    }\n",
 68 |        "\n",
 69 |        "    .dataframe thead th {\n",
 70 |        "        text-align: right;\n",
 71 |        "    }\n",
 72 |        "</style>\n",
 73 |        "<table border=\"1\" class=\"dataframe\">\n",
 74 |        "  <thead>\n",
 75 |        "    <tr style=\"text-align: right;\">\n",
 76 |        "      <th></th>\n",
 77 |        "      <th>Close</th>\n",
 78 |        "    </tr>\n",
 79 |        "    <tr>\n",
 80 |        "      <th>Date</th>\n",
 81 |        "      <th></th>\n",
 82 |        "    </tr>\n",
 83 |        "  </thead>\n",
 84 |        "  <tbody>\n",
 85 |        "    <tr>\n",
 86 |        "      <th>2013-04-28</th>\n",
 87 |        "      <td>134.21</td>\n",
 88 |        "    </tr>\n",
 89 |        "    <tr>\n",
 90 |        "      <th>2013-04-29</th>\n",
 91 |        "      <td>144.54</td>\n",
 92 |        "    </tr>\n",
 93 |        "    <tr>\n",
 94 |        "      <th>2013-04-30</th>\n",
 95 |        "      <td>139.00</td>\n",
 96 |        "    </tr>\n",
 97 |        "    <tr>\n",
 98 |        "      <th>2013-05-01</th>\n",
 99 |        "      <td>116.99</td>\n",
100 |        "    </tr>\n",
101 |        "    <tr>\n",
102 |        "      <th>2013-05-02</th>\n",
103 |        "      <td>105.21</td>\n",
104 |        "    </tr>\n",
105 |        "  </tbody>\n",
106 |        "</table>\n",
107 |        "</div>"
108 |       ],
109 |       "text/plain": [
110 |        "             Close\n",
111 |        "Date              \n",
112 |        "2013-04-28  134.21\n",
113 |        "2013-04-29  144.54\n",
114 |        "2013-04-30  139.00\n",
115 |        "2013-05-01  116.99\n",
116 |        "2013-05-02  105.21"
117 |       ]
118 |      },
119 |      "execution_count": 57,
120 |      "metadata": {},
121 |      "output_type": "execute_result"
122 |     }
123 |    ],
124 |    "source": [
125 |     "df.head()"
126 |    ]
127 |   },
128 |   {
129 |    "cell_type": "code",
130 |    "execution_count": 58,
131 |    "metadata": {},
132 |    "outputs": [
133 |     {
134 |      "name": "stdout",
135 |      "output_type": "stream",
136 |      "text": [
137 |       "confidence:  0.9036278554322356\n",
138 |       "[5691.10004813 5703.08055399 5756.54220957 6502.08536461 6742.77697197\n",
139 |       " 6964.57855404 6780.00426102 6836.96273426 6692.66793539 6674.85940009\n",
140 |       " 6816.45047396 7180.46799077 7204.68135018 7176.82697445 7082.97767572\n",
141 |       " 6597.89336189 6867.25647076 7052.34747566 6903.42630292 6870.00826198\n",
142 |       " 7351.58374159 7323.56113408 7729.56449594 8088.75135743 8462.69454911\n",
143 |       " 8618.02054596 8824.93361571 8857.93107721 8395.71426856 8541.85961698]\n"
144 |      ]
145 |     }
146 |    ],
147 |    "source": [
148 |     "df = df[['Close']]\n",
149 |     "\n",
150 |     "forecast_out = int(30)\n",
151 |     "\n",
152 |     "df['Prediction'] = df[['Close']].shift(-forecast_out)\n",
153 |     "\n",
154 |     "X = np.array(df.drop(['Prediction'],1))\n",
155 |     "X = preprocessing.scale(X)\n",
156 |     "\n",
157 |     "X_forecast = X[-forecast_out:]\n",
158 |     "X = X[:-forecast_out]\n",
159 |     "\n",
160 |     "y = np.array(df['Prediction'])\n",
161 |     "y = y[:-forecast_out]\n",
162 |     "\n",
163 |     "X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size = 0.2)\n",
164 |     "\n",
165 |     "clf = LinearRegression()\n",
166 |     "clf.fit(X_train,y_train)\n",
167 |     "\n",
168 |     "confidence = clf.score(X_test, y_test)\n",
169 |     "print(\"confidence: \", confidence)\n",
170 |     "\n",
171 |     "forecast_prediction = clf.predict(X_forecast)\n",
172 |     "print(forecast_prediction)"
173 |    ]
174 |   },
175 |   {
176 |    "cell_type": "code",
177 |    "execution_count": 63,
178 |    "metadata": {},
179 |    "outputs": [
180 |     {
181 |      "data": {
182 |       "image/png": "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\n",
183 |       "text/plain": [
184 |        "<matplotlib.figure.Figure at 0x7fdc10b14470>"
185 |       ]
186 |      },
187 |      "metadata": {},
188 |      "output_type": "display_data"
189 |     }
190 |    ],
191 |    "source": [
192 |     "import matplotlib.pyplot as plt\n",
193 |     "# print(X_test)\n",
194 |     "# print(y_test)\n",
195 |     "# plt.plot(X_test,forecast_set,color='blue', linewidth=1)\n",
196 |     "plt.scatter(X_test, y_test, color='darkorange', label='data')\n",
197 |     "# plt.plot(X_test, y_test, color='darkorange', linewidth=1)\n",
198 |     "# plt.plot(X_test, forecast_prediction, color='blue', linew/idth=2)\n",
199 |     "plt.show()"
200 |    ]
201 |   },
202 |   {
203 |    "cell_type": "code",
204 |    "execution_count": 64,
205 |    "metadata": {},
206 |    "outputs": [
207 |     {
208 |      "data": {
209 |       "text/plain": [
210 |        "0.9036278554322356"
211 |       ]
212 |      },
213 |      "execution_count": 64,
214 |      "metadata": {},
215 |      "output_type": "execute_result"
216 |     }
217 |    ],
218 |    "source": [
219 |     "clf.score(X_test,y_test)"
220 |    ]
221 |   },
222 |   {
223 |    "cell_type": "code",
224 |    "execution_count": 62,
225 |    "metadata": {},
226 |    "outputs": [],
227 |    "source": [
228 |     "# dict_new = {\n",
229 |     "#     'Date': X_train,\n",
230 |     "#     'Close': y_train\n",
231 |     "# }\n",
232 |     "# df1=pd.DataFrame(dict_new).set_index('Date')\n",
233 |     "# df1"
234 |    ]
235 |   },
236 |   {
237 |    "cell_type": "code",
238 |    "execution_count": 61,
239 |    "metadata": {},
240 |    "outputs": [
241 |     {
242 |      "data": {
243 |       "image/png": "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\n",
244 |       "text/plain": [
245 |        "<matplotlib.figure.Figure at 0x7fdc10ae9278>"
246 |       ]
247 |      },
248 |      "metadata": {},
249 |      "output_type": "display_data"
250 |     }
251 |    ],
252 |    "source": [
253 |     "plt.figure(figsize=(12,8))\n",
254 |     "plt.plot(df['Close'], label='Train')\n",
255 |     "# plt.plot(X_test['Close'], label='Test')\n",
256 |     "# plt.plot(y_hat_avg['avg_forecast'], label='Average Forecast')\n",
257 |     "plt.legend(loc='best')\n",
258 |     "plt.show()"
259 |    ]
260 |   },
261 |   {
262 |    "cell_type": "code",
263 |    "execution_count": 7,
264 |    "metadata": {},
265 |    "outputs": [
266 |     {
267 |      "name": "stdout",
268 |      "output_type": "stream",
269 |      "text": [
270 |       "3629.001658095474\n"
271 |      ]
272 |     }
273 |    ],
274 |    "source": [
275 |     "rms = sqrt(mean_squared_error(test.Close, y_hat_avg.avg_forecast))\n",
276 |     "print(rms)"
277 |    ]
278 |   }
279 |  ],
280 |  "metadata": {
281 |   "kernelspec": {
282 |    "display_name": "Python 3",
283 |    "language": "python",
284 |    "name": "python3"
285 |   },
286 |   "language_info": {
287 |    "codemirror_mode": {
288 |     "name": "ipython",
289 |     "version": 3
290 |    },
291 |    "file_extension": ".py",
292 |    "mimetype": "text/x-python",
293 |    "name": "python",
294 |    "nbconvert_exporter": "python",
295 |    "pygments_lexer": "ipython3",
296 |    "version": "3.6.4"
297 |   }
298 |  },
299 |  "nbformat": 4,
300 |  "nbformat_minor": 2
301 | }
302 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # bitcoin-prediction
2 | 
3 | 
4 | [Download datasets](https://www.kaggle.com/mczielinski/bitcoin-historical-data)
5 | 


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