Add extraction-yahoo-finance.ipynb

extraction-yahoo-finance.ipynb

@@ -0,0 +1,497 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import yfinance as yf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define the list of stock symbols\n",
+    "stock_symbols = ['JPM', 'GS', 'MS', 'BLK', 'C']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[*********************100%%**********************]  5 of 5 completed\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Download historical stock price data\n",
+    "stock_data = yf.download(stock_symbols, start=\"2020-01-01\", end=\"2023-11-30\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead tr th {\n",
+       "        text-align: left;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead tr:last-of-type th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr>\n",
+       "      <th>Price</th>\n",
+       "      <th colspan=\"5\" halign=\"left\">Adj Close</th>\n",
+       "      <th colspan=\"5\" halign=\"left\">Close</th>\n",
+       "      <th>...</th>\n",
+       "      <th colspan=\"5\" halign=\"left\">Open</th>\n",
+       "      <th colspan=\"5\" halign=\"left\">Volume</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Ticker</th>\n",
+       "      <th>BLK</th>\n",
+       "      <th>C</th>\n",
+       "      <th>GS</th>\n",
+       "      <th>JPM</th>\n",
+       "      <th>MS</th>\n",
+       "      <th>BLK</th>\n",
+       "      <th>C</th>\n",
+       "      <th>GS</th>\n",
+       "      <th>JPM</th>\n",
+       "      <th>MS</th>\n",
+       "      <th>...</th>\n",
+       "      <th>BLK</th>\n",
+       "      <th>C</th>\n",
+       "      <th>GS</th>\n",
+       "      <th>JPM</th>\n",
+       "      <th>MS</th>\n",
+       "      <th>BLK</th>\n",
+       "      <th>C</th>\n",
+       "      <th>GS</th>\n",
+       "      <th>JPM</th>\n",
+       "      <th>MS</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Date</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2020-01-02</th>\n",
+       "      <td>457.110931</td>\n",
+       "      <td>68.963692</td>\n",
+       "      <td>210.857330</td>\n",
+       "      <td>123.533600</td>\n",
+       "      <td>45.443264</td>\n",
+       "      <td>508.980011</td>\n",
+       "      <td>81.230003</td>\n",
+       "      <td>234.320007</td>\n",
+       "      <td>141.089996</td>\n",
+       "      <td>52.040001</td>\n",
+       "      <td>...</td>\n",
+       "      <td>510.000000</td>\n",
+       "      <td>80.129997</td>\n",
+       "      <td>231.000000</td>\n",
+       "      <td>139.789993</td>\n",
+       "      <td>51.200001</td>\n",
+       "      <td>560400</td>\n",
+       "      <td>12728900</td>\n",
+       "      <td>3736300</td>\n",
+       "      <td>10803700</td>\n",
+       "      <td>7808000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2020-01-03</th>\n",
+       "      <td>452.252197</td>\n",
+       "      <td>67.664719</td>\n",
+       "      <td>208.391678</td>\n",
+       "      <td>121.903435</td>\n",
+       "      <td>44.709740</td>\n",
+       "      <td>503.570007</td>\n",
+       "      <td>79.699997</td>\n",
+       "      <td>231.580002</td>\n",
+       "      <td>138.339996</td>\n",
+       "      <td>51.200001</td>\n",
+       "      <td>...</td>\n",
+       "      <td>501.720001</td>\n",
+       "      <td>79.800003</td>\n",
+       "      <td>231.600006</td>\n",
+       "      <td>137.500000</td>\n",
+       "      <td>51.220001</td>\n",
+       "      <td>337300</td>\n",
+       "      <td>12437400</td>\n",
+       "      <td>2274500</td>\n",
+       "      <td>10386800</td>\n",
+       "      <td>6706000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2020-01-06</th>\n",
+       "      <td>452.638397</td>\n",
+       "      <td>67.452461</td>\n",
+       "      <td>210.524353</td>\n",
+       "      <td>121.806473</td>\n",
+       "      <td>44.552567</td>\n",
+       "      <td>504.000000</td>\n",
+       "      <td>79.449997</td>\n",
+       "      <td>233.949997</td>\n",
+       "      <td>138.229996</td>\n",
+       "      <td>51.020000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>500.170013</td>\n",
+       "      <td>78.720001</td>\n",
+       "      <td>229.929993</td>\n",
+       "      <td>136.559998</td>\n",
+       "      <td>50.669998</td>\n",
+       "      <td>411300</td>\n",
+       "      <td>10059500</td>\n",
+       "      <td>3329300</td>\n",
+       "      <td>10259000</td>\n",
+       "      <td>7476700</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2020-01-07</th>\n",
+       "      <td>455.530243</td>\n",
+       "      <td>66.866661</td>\n",
+       "      <td>211.910172</td>\n",
+       "      <td>119.735695</td>\n",
+       "      <td>44.465233</td>\n",
+       "      <td>507.220001</td>\n",
+       "      <td>78.760002</td>\n",
+       "      <td>235.490005</td>\n",
+       "      <td>135.880005</td>\n",
+       "      <td>50.919998</td>\n",
+       "      <td>...</td>\n",
+       "      <td>502.880005</td>\n",
+       "      <td>79.290001</td>\n",
+       "      <td>235.000000</td>\n",
+       "      <td>137.279999</td>\n",
+       "      <td>51.040001</td>\n",
+       "      <td>453900</td>\n",
+       "      <td>10469100</td>\n",
+       "      <td>5255200</td>\n",
+       "      <td>10531300</td>\n",
+       "      <td>4538100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2020-01-08</th>\n",
+       "      <td>455.422516</td>\n",
+       "      <td>67.376060</td>\n",
+       "      <td>213.952820</td>\n",
+       "      <td>120.669746</td>\n",
+       "      <td>45.032845</td>\n",
+       "      <td>507.100006</td>\n",
+       "      <td>79.360001</td>\n",
+       "      <td>237.759995</td>\n",
+       "      <td>136.940002</td>\n",
+       "      <td>51.570000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>507.769989</td>\n",
+       "      <td>78.769997</td>\n",
+       "      <td>235.679993</td>\n",
+       "      <td>135.699997</td>\n",
+       "      <td>50.959999</td>\n",
+       "      <td>726500</td>\n",
+       "      <td>11292400</td>\n",
+       "      <td>3564700</td>\n",
+       "      <td>9695300</td>\n",
+       "      <td>6185200</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2023-11-22</th>\n",
+       "      <td>717.865295</td>\n",
+       "      <td>44.594376</td>\n",
+       "      <td>333.518433</td>\n",
+       "      <td>151.506546</td>\n",
+       "      <td>77.728569</td>\n",
+       "      <td>727.140015</td>\n",
+       "      <td>45.020000</td>\n",
+       "      <td>338.640015</td>\n",
+       "      <td>153.330002</td>\n",
+       "      <td>78.489998</td>\n",
+       "      <td>...</td>\n",
+       "      <td>727.000000</td>\n",
+       "      <td>45.310001</td>\n",
+       "      <td>336.940002</td>\n",
+       "      <td>153.410004</td>\n",
+       "      <td>78.790001</td>\n",
+       "      <td>498100</td>\n",
+       "      <td>9441200</td>\n",
+       "      <td>1235200</td>\n",
+       "      <td>5174500</td>\n",
+       "      <td>4265400</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2023-11-24</th>\n",
+       "      <td>720.787537</td>\n",
+       "      <td>44.802391</td>\n",
+       "      <td>334.020691</td>\n",
+       "      <td>151.714050</td>\n",
+       "      <td>77.887024</td>\n",
+       "      <td>730.099976</td>\n",
+       "      <td>45.230000</td>\n",
+       "      <td>339.149994</td>\n",
+       "      <td>153.539993</td>\n",
+       "      <td>78.650002</td>\n",
+       "      <td>...</td>\n",
+       "      <td>726.719971</td>\n",
+       "      <td>44.889999</td>\n",
+       "      <td>338.799988</td>\n",
+       "      <td>153.589996</td>\n",
+       "      <td>78.260002</td>\n",
+       "      <td>279600</td>\n",
+       "      <td>5941000</td>\n",
+       "      <td>460100</td>\n",
+       "      <td>3496900</td>\n",
+       "      <td>2398000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2023-11-27</th>\n",
+       "      <td>721.360168</td>\n",
+       "      <td>44.653809</td>\n",
+       "      <td>332.602478</td>\n",
+       "      <td>151.368225</td>\n",
+       "      <td>77.193810</td>\n",
+       "      <td>730.679993</td>\n",
+       "      <td>45.080002</td>\n",
+       "      <td>337.709991</td>\n",
+       "      <td>153.190002</td>\n",
+       "      <td>77.949997</td>\n",
+       "      <td>...</td>\n",
+       "      <td>727.200012</td>\n",
+       "      <td>44.959999</td>\n",
+       "      <td>339.190002</td>\n",
+       "      <td>153.429993</td>\n",
+       "      <td>78.269997</td>\n",
+       "      <td>868100</td>\n",
+       "      <td>14679700</td>\n",
+       "      <td>1250500</td>\n",
+       "      <td>6259100</td>\n",
+       "      <td>5237800</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2023-11-28</th>\n",
+       "      <td>727.362610</td>\n",
+       "      <td>44.435886</td>\n",
+       "      <td>332.543396</td>\n",
+       "      <td>151.714050</td>\n",
+       "      <td>76.134186</td>\n",
+       "      <td>736.760010</td>\n",
+       "      <td>44.860001</td>\n",
+       "      <td>337.649994</td>\n",
+       "      <td>153.539993</td>\n",
+       "      <td>76.879997</td>\n",
+       "      <td>...</td>\n",
+       "      <td>725.859985</td>\n",
+       "      <td>45.029999</td>\n",
+       "      <td>337.380005</td>\n",
+       "      <td>153.220001</td>\n",
+       "      <td>77.360001</td>\n",
+       "      <td>610200</td>\n",
+       "      <td>14064700</td>\n",
+       "      <td>1419000</td>\n",
+       "      <td>6582700</td>\n",
+       "      <td>9197900</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2023-11-29</th>\n",
+       "      <td>737.768188</td>\n",
+       "      <td>45.317474</td>\n",
+       "      <td>337.865692</td>\n",
+       "      <td>152.484787</td>\n",
+       "      <td>77.787994</td>\n",
+       "      <td>747.299988</td>\n",
+       "      <td>45.750000</td>\n",
+       "      <td>340.260010</td>\n",
+       "      <td>154.320007</td>\n",
+       "      <td>78.550003</td>\n",
+       "      <td>...</td>\n",
+       "      <td>742.280029</td>\n",
+       "      <td>45.230000</td>\n",
+       "      <td>337.000000</td>\n",
+       "      <td>154.169998</td>\n",
+       "      <td>77.480003</td>\n",
+       "      <td>750000</td>\n",
+       "      <td>14027600</td>\n",
+       "      <td>2038100</td>\n",
+       "      <td>9126100</td>\n",
+       "      <td>7420700</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>985 rows × 30 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "Price        Adj Close                                                \\\n",
+       "Ticker             BLK          C          GS         JPM         MS   \n",
+       "Date                                                                   \n",
+       "2020-01-02  457.110931  68.963692  210.857330  123.533600  45.443264   \n",
+       "2020-01-03  452.252197  67.664719  208.391678  121.903435  44.709740   \n",
+       "2020-01-06  452.638397  67.452461  210.524353  121.806473  44.552567   \n",
+       "2020-01-07  455.530243  66.866661  211.910172  119.735695  44.465233   \n",
+       "2020-01-08  455.422516  67.376060  213.952820  120.669746  45.032845   \n",
+       "...                ...        ...         ...         ...        ...   \n",
+       "2023-11-22  717.865295  44.594376  333.518433  151.506546  77.728569   \n",
+       "2023-11-24  720.787537  44.802391  334.020691  151.714050  77.887024   \n",
+       "2023-11-27  721.360168  44.653809  332.602478  151.368225  77.193810   \n",
+       "2023-11-28  727.362610  44.435886  332.543396  151.714050  76.134186   \n",
+       "2023-11-29  737.768188  45.317474  337.865692  152.484787  77.787994   \n",
+       "\n",
+       "Price            Close                                                ...  \\\n",
+       "Ticker             BLK          C          GS         JPM         MS  ...   \n",
+       "Date                                                                  ...   \n",
+       "2020-01-02  508.980011  81.230003  234.320007  141.089996  52.040001  ...   \n",
+       "2020-01-03  503.570007  79.699997  231.580002  138.339996  51.200001  ...   \n",
+       "2020-01-06  504.000000  79.449997  233.949997  138.229996  51.020000  ...   \n",
+       "2020-01-07  507.220001  78.760002  235.490005  135.880005  50.919998  ...   \n",
+       "2020-01-08  507.100006  79.360001  237.759995  136.940002  51.570000  ...   \n",
+       "...                ...        ...         ...         ...        ...  ...   \n",
+       "2023-11-22  727.140015  45.020000  338.640015  153.330002  78.489998  ...   \n",
+       "2023-11-24  730.099976  45.230000  339.149994  153.539993  78.650002  ...   \n",
+       "2023-11-27  730.679993  45.080002  337.709991  153.190002  77.949997  ...   \n",
+       "2023-11-28  736.760010  44.860001  337.649994  153.539993  76.879997  ...   \n",
+       "2023-11-29  747.299988  45.750000  340.260010  154.320007  78.550003  ...   \n",
+       "\n",
+       "Price             Open                                                Volume  \\\n",
+       "Ticker             BLK          C          GS         JPM         MS     BLK   \n",
+       "Date                                                                           \n",
+       "2020-01-02  510.000000  80.129997  231.000000  139.789993  51.200001  560400   \n",
+       "2020-01-03  501.720001  79.800003  231.600006  137.500000  51.220001  337300   \n",
+       "2020-01-06  500.170013  78.720001  229.929993  136.559998  50.669998  411300   \n",
+       "2020-01-07  502.880005  79.290001  235.000000  137.279999  51.040001  453900   \n",
+       "2020-01-08  507.769989  78.769997  235.679993  135.699997  50.959999  726500   \n",
+       "...                ...        ...         ...         ...        ...     ...   \n",
+       "2023-11-22  727.000000  45.310001  336.940002  153.410004  78.790001  498100   \n",
+       "2023-11-24  726.719971  44.889999  338.799988  153.589996  78.260002  279600   \n",
+       "2023-11-27  727.200012  44.959999  339.190002  153.429993  78.269997  868100   \n",
+       "2023-11-28  725.859985  45.029999  337.380005  153.220001  77.360001  610200   \n",
+       "2023-11-29  742.280029  45.230000  337.000000  154.169998  77.480003  750000   \n",
+       "\n",
+       "Price                                             \n",
+       "Ticker             C       GS       JPM       MS  \n",
+       "Date                                              \n",
+       "2020-01-02  12728900  3736300  10803700  7808000  \n",
+       "2020-01-03  12437400  2274500  10386800  6706000  \n",
+       "2020-01-06  10059500  3329300  10259000  7476700  \n",
+       "2020-01-07  10469100  5255200  10531300  4538100  \n",
+       "2020-01-08  11292400  3564700   9695300  6185200  \n",
+       "...              ...      ...       ...      ...  \n",
+       "2023-11-22   9441200  1235200   5174500  4265400  \n",
+       "2023-11-24   5941000   460100   3496900  2398000  \n",
+       "2023-11-27  14679700  1250500   6259100  5237800  \n",
+       "2023-11-28  14064700  1419000   6582700  9197900  \n",
+       "2023-11-29  14027600  2038100   9126100  7420700  \n",
+       "\n",
+       "[985 rows x 30 columns]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "stock_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "py312",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}