operation_saylor/simulation/loan_simulator.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "loan_simulator",
      "provenance": [],
      "toc_visible": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# Imports"
      ],
      "metadata": {
        "id": "UZQAXxVsoFBZ"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "J3wm4OGNnUex"
      },
      "outputs": [],
      "source": [
        "import io\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "import seaborn as sns\n",
        "from google.colab import files\n",
        "from datetime import datetime, timedelta\n",
        "from functools import partial\n",
        "from enum import Enum\n",
        "from typing import Callable, List\n",
        "import itertools\n",
        "from tqdm import tqdm\n",
        "\n",
        "pd.set_option('display.float_format', lambda x: '%.3f' % x)"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Load historical data"
      ],
      "metadata": {
        "id": "ihUxKhWLoHJX"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "uploaded = files.upload()"
      ],
      "metadata": {
        "colab": {
          "resources": {
            "http://localhost:8080/nbextensions/google.colab/files.js": {
              "data": "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",
              "ok": true,
              "headers": [
                [
                  "content-type",
                  "application/javascript"
                ]
              ],
              "status": 200,
              "status_text": "OK"
            }
          },
          "base_uri": "https://localhost:8080/",
          "height": 73
        },
        "id": "Qp8SNDarnid_",
        "outputId": "3e617c16-84bb-4a3d-cc2e-a0b8227ad561"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-a9aa92fd-bb19-431d-8c57-51c7713b1fb7\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-a9aa92fd-bb19-431d-8c57-51c7713b1fb7\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script src=\"/nbextensions/google.colab/files.js\"></script> "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Saving BTC-USD.csv to BTC-USD.csv\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "price_history_df = pd.read_csv(io.BytesIO(uploaded['BTC-USD.csv']))"
      ],
      "metadata": {
        "id": "sGc2sI28njWx"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "price_history_df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "3xBa_p3SpJMS",
        "outputId": "17747ec5-bbe9-4aaf-9d44-732c5227e322"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "         Date  Year       Price\n",
              "0  2014-09-17  2014  465.864014\n",
              "1  2014-09-18  2014  456.859985\n",
              "2  2014-09-19  2014  424.102997\n",
              "3  2014-09-20  2014  394.673004\n",
              "4  2014-09-21  2014  408.084991"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-9b110124-187b-4d42-9eaa-9977b9df54b0\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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 th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Date</th>\n",
              "      <th>Year</th>\n",
              "      <th>Price</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>2014-09-17</td>\n",
              "      <td>2014</td>\n",
              "      <td>465.864014</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2014-09-18</td>\n",
              "      <td>2014</td>\n",
              "      <td>456.859985</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2014-09-19</td>\n",
              "      <td>2014</td>\n",
              "      <td>424.102997</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>2014-09-20</td>\n",
              "      <td>2014</td>\n",
              "      <td>394.673004</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>2014-09-21</td>\n",
              "      <td>2014</td>\n",
              "      <td>408.084991</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-9b110124-187b-4d42-9eaa-9977b9df54b0')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-9b110124-187b-4d42-9eaa-9977b9df54b0 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-9b110124-187b-4d42-9eaa-9977b9df54b0');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Pre-process\n"
      ],
      "metadata": {
        "id": "g4QARpNBoRbg"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Rolling returns"
      ],
      "metadata": {
        "id": "NxZqF3UKoUbO"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "class TimeWindow:\n",
        "\n",
        "  time_units_meta = {\n",
        "      \"months\": {\n",
        "          \"singular\": \"month\",\n",
        "          \"plural\": \"months\",\n",
        "          \"days_contained\": 30\n",
        "      },\n",
        "      \"years\": {\n",
        "          \"singular\": \"year\",\n",
        "          \"plural\": \"years\",\n",
        "          \"days_contained\": 365\n",
        "      }\n",
        "  }\n",
        "\n",
        "  def __init__(self, time_unit: str, length: int):\n",
        "    if time_unit not in self.time_units_meta:\n",
        "      raise ValueError(f\"Invalid time unit: {time_unit}\")\n",
        "    self.unit = time_unit\n",
        "    self.length = length\n",
        "\n",
        "  @property\n",
        "  def days(self):\n",
        "    return self.length * self.time_units_meta[self.unit][\"days_contained\"]\n",
        "\n",
        "  @property\n",
        "  def unit_name(self):\n",
        "    if self.length > 1:\n",
        "      return self.time_units_meta[self.unit][\"plural\"]\n",
        "    return self.time_units_meta[self.unit][\"singular\"]\n",
        "\n",
        "  @property\n",
        "  def years(self):\n",
        "    return self.days / 365"
      ],
      "metadata": {
        "id": "AE420Q0LuWz6"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def add_rolling_returns(\n",
        "    price_history_df: pd.DataFrame, \n",
        "    window: TimeWindow\n",
        "    ) -> pd.DataFrame:\n",
        "  price_history_df[f\"price_{window.length}_{window.unit_name}_ago\"] = price_history_df.shift(window.days)[\"Price\"]\n",
        "  price_history_df[f\"returns_for_{window.length}_{window.unit_name}\"] = (\n",
        "      (price_history_df[\"Price\"] - price_history_df[f\"price_{window.length}_{window.unit_name}_ago\"]) / price_history_df[f\"price_{window.length}_{window.unit_name}_ago\"]\n",
        "  )\n",
        "  price_history_df[f\"annualized_returns_for_{window.length}_{window.unit_name}\"] = ((price_history_df[f\"returns_for_{window.length}_{window.unit_name}\"] + 1)**(1/window.years))-1\n",
        "  return price_history_df\n"
      ],
      "metadata": {
        "id": "mgCSCTMXoT6y"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "windows_to_use = [TimeWindow(\"months\", i) for i in range(1, 2)] # + [TimeWindow(\"years\", i) for i in range(1, 5)]\n",
        "\n",
        "for window in windows_to_use:\n",
        "  price_history_df = add_rolling_returns(price_history_df, window=window)"
      ],
      "metadata": {
        "id": "TnFuSXRdpQzW"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "price_history_df"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "YWWxqIr7pYka",
        "outputId": "b86b51d1-a2b3-48ef-d57c-1d18ed4099f5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "            Date  Year     Price  price_1_month_ago  returns_for_1_month  \\\n",
              "0     2014-09-17  2014   465.864                NaN                  NaN   \n",
              "1     2014-09-18  2014   456.860                NaN                  NaN   \n",
              "2     2014-09-19  2014   424.103                NaN                  NaN   \n",
              "3     2014-09-20  2014   394.673                NaN                  NaN   \n",
              "4     2014-09-21  2014   408.085                NaN                  NaN   \n",
              "...          ...   ...       ...                ...                  ...   \n",
              "2754  2022-04-02  2022 46285.500          43925.195                0.054   \n",
              "2755  2022-04-03  2022 45859.129          42458.141                0.080   \n",
              "2756  2022-04-04  2022 46445.273          39148.449                0.186   \n",
              "2757  2022-04-05  2022 46624.508          39404.199                0.183   \n",
              "2758  2022-04-06  2022 45491.375          38429.305                0.184   \n",
              "\n",
              "      annualized_returns_for_1_month  \n",
              "0                                NaN  \n",
              "1                                NaN  \n",
              "2                                NaN  \n",
              "3                                NaN  \n",
              "4                                NaN  \n",
              "...                              ...  \n",
              "2754                           0.890  \n",
              "2755                           1.554  \n",
              "2756                           7.000  \n",
              "2757                           6.745  \n",
              "2758                           6.788  \n",
              "\n",
              "[2759 rows x 6 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-380dfe8a-fd72-4727-8b43-181201ff866a\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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 th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Date</th>\n",
              "      <th>Year</th>\n",
              "      <th>Price</th>\n",
              "      <th>price_1_month_ago</th>\n",
              "      <th>returns_for_1_month</th>\n",
              "      <th>annualized_returns_for_1_month</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>2014-09-17</td>\n",
              "      <td>2014</td>\n",
              "      <td>465.864</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2014-09-18</td>\n",
              "      <td>2014</td>\n",
              "      <td>456.860</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2014-09-19</td>\n",
              "      <td>2014</td>\n",
              "      <td>424.103</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>2014-09-20</td>\n",
              "      <td>2014</td>\n",
              "      <td>394.673</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>2014-09-21</td>\n",
              "      <td>2014</td>\n",
              "      <td>408.085</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</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",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2754</th>\n",
              "      <td>2022-04-02</td>\n",
              "      <td>2022</td>\n",
              "      <td>46285.500</td>\n",
              "      <td>43925.195</td>\n",
              "      <td>0.054</td>\n",
              "      <td>0.890</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2755</th>\n",
              "      <td>2022-04-03</td>\n",
              "      <td>2022</td>\n",
              "      <td>45859.129</td>\n",
              "      <td>42458.141</td>\n",
              "      <td>0.080</td>\n",
              "      <td>1.554</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2756</th>\n",
              "      <td>2022-04-04</td>\n",
              "      <td>2022</td>\n",
              "      <td>46445.273</td>\n",
              "      <td>39148.449</td>\n",
              "      <td>0.186</td>\n",
              "      <td>7.000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2757</th>\n",
              "      <td>2022-04-05</td>\n",
              "      <td>2022</td>\n",
              "      <td>46624.508</td>\n",
              "      <td>39404.199</td>\n",
              "      <td>0.183</td>\n",
              "      <td>6.745</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2758</th>\n",
              "      <td>2022-04-06</td>\n",
              "      <td>2022</td>\n",
              "      <td>45491.375</td>\n",
              "      <td>38429.305</td>\n",
              "      <td>0.184</td>\n",
              "      <td>6.788</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>2759 rows × 6 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-380dfe8a-fd72-4727-8b43-181201ff866a')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-380dfe8a-fd72-4727-8b43-181201ff866a button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-380dfe8a-fd72-4727-8b43-181201ff866a');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Data Exploration\n"
      ],
      "metadata": {
        "id": "8Nei4_COs9hC"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Distributions of total returns"
      ],
      "metadata": {
        "id": "b4gAZooHs_JM"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "for window_years in window_years_to_use:\n",
        "  print(price_history_df[f\"returns_for_{window_years}_years\"].describe())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tkBUK7-pt6Z_",
        "outputId": "a0a1086a-f6bb-47a0-cde0-570b3ce2f7b0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "count    2394.000000\n",
            "mean        2.163473\n",
            "std         3.208595\n",
            "min        -0.832966\n",
            "25%         0.282227\n",
            "50%         1.160037\n",
            "75%         2.831518\n",
            "max        23.804691\n",
            "Name: returns_for_1_years, dtype: float64\n",
            "count    2029.000000\n",
            "mean        6.618032\n",
            "std         7.548360\n",
            "min        -0.652070\n",
            "25%         1.313161\n",
            "50%         3.552320\n",
            "75%         9.278709\n",
            "max        41.956416\n",
            "Name: returns_for_2_years, dtype: float64\n",
            "count    1664.000000\n",
            "mean       13.073746\n",
            "std        11.922938\n",
            "min        -0.002926\n",
            "25%         4.844270\n",
            "50%         8.870996\n",
            "75%        16.546371\n",
            "max        80.238232\n",
            "Name: returns_for_3_years, dtype: float64\n",
            "count    1299.000000\n",
            "mean       20.246075\n",
            "std        12.466027\n",
            "min         1.417540\n",
            "25%        12.310428\n",
            "50%        16.681005\n",
            "75%        25.459926\n",
            "max        59.296171\n",
            "Name: returns_for_4_years, dtype: float64\n",
            "count    934.000000\n",
            "mean      55.868363\n",
            "std       31.396123\n",
            "min       16.830084\n",
            "25%       33.854491\n",
            "50%       44.534378\n",
            "75%       74.665779\n",
            "max      148.669445\n",
            "Name: returns_for_5_years, dtype: float64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "for window_years in window_years_to_use:\n",
        "  sns.displot(price_history_df[f\"returns_for_{window_years}_years\"], kind=\"kde\")\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "ZkNeF0FztD2r",
        "outputId": "b83b2fc1-3b24-4221-e46c-32d055f2c324"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Distributions of annualized returns"
      ],
      "metadata": {
        "id": "HJHlfhojuTDL"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "for window_years in window_years_to_use:\n",
        "  print(price_history_df[f\"annualized_returns_for_{window_years}_years\"].describe())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "af908e96-7d61-4782-dbb1-322918b9cf2a",
        "id": "AhLRz95KuTDQ"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "count    2394.000000\n",
            "mean        2.163473\n",
            "std         3.208595\n",
            "min        -0.832966\n",
            "25%         0.282227\n",
            "50%         1.160037\n",
            "75%         2.831518\n",
            "max        23.804691\n",
            "Name: annualized_returns_for_1_years, dtype: float64\n",
            "count    2029.000000\n",
            "mean        1.475877\n",
            "std         1.220164\n",
            "min        -0.410144\n",
            "25%         0.520908\n",
            "50%         1.133617\n",
            "75%         2.206043\n",
            "max         5.554114\n",
            "Name: annualized_returns_for_2_years, dtype: float64\n",
            "count    1664.000000\n",
            "mean        1.246837\n",
            "std         0.622499\n",
            "min        -0.000976\n",
            "25%         0.801261\n",
            "50%         1.145130\n",
            "75%         1.598537\n",
            "max         3.330986\n",
            "Name: annualized_returns_for_3_years, dtype: float64\n",
            "count    1299.000000\n",
            "mean        1.072835\n",
            "std         0.331325\n",
            "min         0.246934\n",
            "25%         0.910064\n",
            "50%         1.050580\n",
            "75%         1.268021\n",
            "max         1.786586\n",
            "Name: annualized_returns_for_4_years, dtype: float64\n",
            "count    934.000000\n",
            "mean       1.194712\n",
            "std        0.230687\n",
            "min        0.779224\n",
            "25%        1.034471\n",
            "50%        1.146189\n",
            "75%        1.375636\n",
            "max        1.722868\n",
            "Name: annualized_returns_for_5_years, dtype: float64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "annualized_return_col_names = [f\"annualized_returns_for_{window_years}_years\" for window_years in window_years_to_use[2:6]]\n",
        "df_for_annualized_dists_plot = price_history_df.melt(id_vars=[\"Date\"], value_vars=annualized_return_col_names, var_name=\"window_years\", value_name=\"annualized_return\")\n",
        "\n",
        "the_plot = sns.displot(data=df_for_annualized_dists_plot, x=\"annualized_return\", hue=\"window_years\", kind='kde', fill=True, height=10,bw_adjust=0.25, aspect=1.5)\n",
        "the_plot.set(xlim=(-1, 3))\n",
        "the_plot"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 629
        },
        "outputId": "2598bd4d-24d8-4170-c553-ac1dc98c7211",
        "id": "r8kCbFm_uTDT"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<seaborn.axisgrid.FacetGrid at 0x7f0d198fd510>"
            ]
          },
          "metadata": {},
          "execution_count": 11
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1274.25x720 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Distribution of monthly deltas"
      ],
      "metadata": {
        "id": "PBU5FIVLuLR1"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "price_history_df[\"returns_for_1_month\"].describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ucpYSvGT-fSd",
        "outputId": "680ce88e-759a-4335-b8e4-c30d5d06c8a5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "count   2729.000\n",
              "mean       0.082\n",
              "std        0.260\n",
              "min       -0.598\n",
              "25%       -0.086\n",
              "50%        0.042\n",
              "75%        0.212\n",
              "max        1.947\n",
              "Name: returns_for_1_month, dtype: float64"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Across all history\n",
        "\n",
        "the_plot = sns.displot(\n",
        "    data=price_history_df, \n",
        "    x=\"returns_for_1_month\", \n",
        "    kind='kde', \n",
        "    fill=True, \n",
        "    height=10,\n",
        "    bw_adjust=0.25, \n",
        "    aspect=1.5\n",
        "    )\n",
        "the_plot"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 740
        },
        "id": "ej_eAQ10uHJM",
        "outputId": "f96a74b7-14cc-4c6b-a07a-1031d72eace2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<seaborn.axisgrid.FacetGrid at 0x7f87246b3250>"
            ]
          },
          "metadata": {},
          "execution_count": 9
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1080x720 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Has it changed significantly over the years?\n",
        "\n",
        "the_plot = sns.catplot(\n",
        "    data=price_history_df, \n",
        "    y=\"returns_for_1_month\",\n",
        "    x=\"Year\",\n",
        "    kind=\"violin\"\n",
        "    )\n",
        "the_plot"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 386
        },
        "id": "5K_ndsBbuKKu",
        "outputId": "c743bf01-813c-41e7-a331-82882c65acb2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<seaborn.axisgrid.FacetGrid at 0x7f87246b3d10>"
            ]
          },
          "metadata": {},
          "execution_count": 10
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 360x360 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Simulation Analysis\n",
        "\n",
        "Factors that come into play:\n",
        "- Loan specifics\n",
        "- Evolution of BTC\n",
        "- Friction in EUR/BTC change\n",
        "- Additional available liquidity\n",
        "\n",
        "Metrics to observe:\n",
        "- Probability \n",
        "\n",
        "Questions to answer:\n",
        "- What is the probability that this loan can pay for itself without additional liquidity?\n",
        "- What is the expected result of the operation?"
      ],
      "metadata": {
        "id": "h5gKUHbsY6z8"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## General objects"
      ],
      "metadata": {
        "id": "th-LF197C_sq"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "class Currency:\n",
        "\n",
        "  def __init__(self, short_name: str , long_name: str):\n",
        "    self.short_name = short_name\n",
        "    self.long_name = long_name\n",
        "\n",
        "EUR = Currency(\"EUR\", \"euro\")\n",
        "BTC = Currency(\"BTC\", \"bitcoin\")\n",
        "\n",
        "class MoneyAmount(float):\n",
        "\n",
        "  def __new__(cls, amount, currency):\n",
        "        return super(MoneyAmount, cls).__new__(cls, amount)\n",
        "\n",
        "  def __init__(self, amount: float, currency: Currency):\n",
        "    self.amount = amount\n",
        "    self.currency = currency"
      ],
      "metadata": {
        "id": "MfRhcUJ7DCcF"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Loan objects"
      ],
      "metadata": {
        "id": "hUpX-ZR5C9ny"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "class LoanTemplate:\n",
        "\n",
        "  def __init__(\n",
        "      self,\n",
        "      principal: MoneyAmount, \n",
        "      interest_rate: float, \n",
        "      length_in_months: int\n",
        "      ):\n",
        "    \n",
        "    self.principal = principal\n",
        "    self.interest_rate = interest_rate\n",
        "    self.length_in_months = length_in_months\n",
        "\n",
        "  def get_amortization_table(self):\n",
        "    table_input = {\n",
        "        \"period\": [],\n",
        "        \"interest_payed\": [],\n",
        "        \"principal_payed\": [],\n",
        "        \"amortization_amount\": [],\n",
        "        \"remaining_balance_on_period_start\": [],\n",
        "        \"remaining_balance_on_period_end\": [],\n",
        "    }\n",
        "\n",
        "    period = 0\n",
        "    balance = self.principal\n",
        "    while period < self.length_in_months:\n",
        "        table_input[\"period\"].append(period)\n",
        "        table_input[\"remaining_balance_on_period_start\"].append(balance)\n",
        "        interest_in_this_period = balance * self.interest_rate\n",
        "        table_input[\"interest_payed\"].append(interest_in_this_period)\n",
        "        principal_in_this_period = self.amortization_amount - interest_in_this_period\n",
        "        table_input[\"principal_payed\"].append(principal_in_this_period)\n",
        "        balance = balance - principal_in_this_period\n",
        "        table_input[\"amortization_amount\"] = interest_in_this_period + principal_in_this_period\n",
        "        table_input[\"remaining_balance_on_period_end\"].append(balance)\n",
        "        period += 1\n",
        "\n",
        "    return pd.DataFrame(table_input)\n",
        "\n",
        "  @staticmethod\n",
        "  def compute_loan_amortization_amount(\n",
        "      principal: MoneyAmount, \n",
        "      interest_rate: float,\n",
        "      number_of_periods: int\n",
        "      ) -> MoneyAmount:\n",
        "\n",
        "      return (\n",
        "          principal * \n",
        "          (interest_rate * ((1 + interest_rate) ** number_of_periods)) /\n",
        "          (((1 + interest_rate) ** number_of_periods) - 1)\n",
        "      ) \n",
        "\n",
        "  @property\n",
        "  def amortization_amount(self):\n",
        "    return self.compute_loan_amortization_amount(\n",
        "        principal = self.principal,\n",
        "        interest_rate = self.interest_rate,\n",
        "        number_of_periods = self.length_in_months\n",
        "    )\n"
      ],
      "metadata": {
        "id": "RLd6xObIaBlG"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Swap Objects"
      ],
      "metadata": {
        "id": "rqWp2OZYIsu_"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "class ExchangeRateProvider:\n",
        "\n",
        "  def __init__(self, simulated_prices: pd.DataFrame):\n",
        "    self.simulated_prices = simulated_prices\n",
        "\n",
        "  def get_exchange_rate(\n",
        "      self,\n",
        "      period: int, \n",
        "      from_currency: Currency, \n",
        "      to_currency: Currency\n",
        "      ) -> float:\n",
        "    eur_per_btc_at_period = self.simulated_prices.loc[\n",
        "      self.simulated_prices[\"period\"] == period,\n",
        "      \"price\"\n",
        "    ].values[0]\n",
        "\n",
        "    if from_currency == EUR and to_currency == BTC:\n",
        "      return 1/eur_per_btc_at_period\n",
        "    if from_currency == BTC and to_currency == EUR:\n",
        "      return eur_per_btc_at_period\n",
        "\n",
        "class Swap:\n",
        "\n",
        "  def __init__(self, input: MoneyAmount, output: MoneyAmount):\n",
        "    self.input = input\n",
        "    self.output = output\n",
        "\n",
        "\n",
        "class Swapper:\n",
        "\n",
        "  def input_defined_swap(\n",
        "      self,\n",
        "      input_amount: MoneyAmount,\n",
        "      exchange_rate: float,\n",
        "      output_currency: Currency\n",
        "  ) -> Swap:\n",
        "\n",
        "    output_amount = MoneyAmount(\n",
        "        input_amount * exchange_rate,\n",
        "        output_currency\n",
        "    )\n",
        "\n",
        "    return Swap(\n",
        "        input_amount, \n",
        "        output_amount\n",
        "        )\n",
        "\n",
        "  def output_defined_swap(\n",
        "      self,\n",
        "      input_currency: Currency,\n",
        "      exchange_rate: float,\n",
        "      output_amount: MoneyAmount\n",
        "  ) -> Swap:\n",
        "    input_amount = MoneyAmount(\n",
        "        output_amount * exchange_rate,\n",
        "        input_currency\n",
        "    )\n",
        "\n",
        "    return Swap(\n",
        "        input_amount,\n",
        "        output_amount\n",
        "    )\n",
        "\n",
        "\n",
        "\n"
      ],
      "metadata": {
        "id": "MEZahgjIduqC"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Price Simulation"
      ],
      "metadata": {
        "id": "UJkiuh_TQlw5"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "class PriceSimulation:\n",
        "\n",
        "  def __init__(\n",
        "      self, \n",
        "      length_in_periods: int, \n",
        "      starting_price: MoneyAmount, \n",
        "      delta_generator: Callable,\n",
        "      scenario_tag: str = None\n",
        "      ):\n",
        "    \n",
        "    self.scenario_tag = scenario_tag\n",
        "\n",
        "    self.starting_price = starting_price\n",
        "    self.periods = range(0, length_in_periods)\n",
        "    self.simulated_deltas = [delta_generator() for i in range(1, length_in_periods)]\n",
        "    \n",
        "    self.simulated_prices = [starting_price]\n",
        "    for delta in self.simulated_deltas:\n",
        "      next_price = self.simulated_prices[-1] * (1 + delta)\n",
        "      self.simulated_prices.append(next_price)\n",
        "\n",
        "  @property\n",
        "  def price_simulation_result(self):\n",
        "    return pd.DataFrame(\n",
        "        {\"period\": self.periods,\n",
        "         \"price\": self.simulated_prices\n",
        "        }\n",
        "    )\n",
        "\n",
        "    "
      ],
      "metadata": {
        "id": "oQozeBwtuD5f"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Balances \n",
        "\n"
      ],
      "metadata": {
        "id": "LufmTWT6ORyk"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "class Balances:\n",
        "\n",
        "  def __init__(\n",
        "      self,\n",
        "      starting_eur_balance: MoneyAmount = 0, \n",
        "      starting_btc_balance: MoneyAmount = 0\n",
        "      ):\n",
        "      \n",
        "    self.balances = {\n",
        "        EUR: starting_eur_balance,\n",
        "        BTC: starting_btc_balance\n",
        "    }\n",
        "    self.total_payed_to_bank = 0\n",
        "    self.total_emergency_line_contribution = 0\n",
        "\n",
        "  def update_with_swap(self, swap: Swap) -> None:\n",
        "    self.balances[swap.input.currency] -= swap.input\n",
        "    self.balances[swap.output.currency] += swap.output\n",
        "\n",
        "  def pay_bank(self, amount: MoneyAmount) -> None:\n",
        "    self.balances[EUR] -= amount\n",
        "    self.total_payed_to_bank += amount\n",
        "\n",
        "  def bite_emergency_line(self, amount: MoneyAmount) -> None:\n",
        "    self.balances[EUR] += amount\n",
        "    self.total_emergency_line_contribution += amount\n",
        "\n",
        "class BalanceHistory:\n",
        "  def __init__(self):\n",
        "    self.period = []\n",
        "    self.eur_balance = []\n",
        "    self.btc_balance = []\n",
        "    self.eur_networth = []\n",
        "    self.total_payed_to_bank = []\n",
        "    self.total_emergency_line_contribution = []\n",
        "  \n",
        "  def snapshot(self, period, balances, exchange_rate_to_eur):\n",
        "\n",
        "    self.period.append(period)\n",
        "    self.eur_balance.append(balances.balances[EUR])\n",
        "    self.btc_balance.append(balances.balances[BTC])\n",
        "    self.eur_networth.append(\n",
        "        balances.balances[EUR] +\n",
        "        balances.balances[BTC] * exchange_rate_to_eur\n",
        "    )\n",
        "    self.total_payed_to_bank.append(\n",
        "        balances.total_payed_to_bank\n",
        "    )\n",
        "    self.total_emergency_line_contribution.append(\n",
        "        balances.total_emergency_line_contribution\n",
        "    )\n",
        "\n",
        "\n",
        "  @property\n",
        "  def as_df(self):\n",
        "    return pd.DataFrame(\n",
        "        {\n",
        "            \"period\": self.period,\n",
        "            \"eur_balance\": self.eur_balance,\n",
        "            \"btc_balance\": self.btc_balance,\n",
        "            \"eur_networth\": self.eur_networth,\n",
        "            \"total_payed_to_bank\": self.total_payed_to_bank,\n",
        "            \"total_emergency_line_contribution\": self.total_emergency_line_contribution\n",
        "        }\n",
        "    )"
      ],
      "metadata": {
        "id": "qKDjTWm0OWhc"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Full Operation Simulation"
      ],
      "metadata": {
        "id": "vGB-OFgxhwWG"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "def run_full_simulation(\n",
        "    loan_template: LoanTemplate,\n",
        "    simulated_prices: pd.DataFrame\n",
        "):\n",
        "  swapper = Swapper()\n",
        "  exchange_rate_provider=ExchangeRateProvider(simulated_prices)\n",
        "  balances = Balances(starting_eur_balance=loan_template.principal)\n",
        "  balance_history = BalanceHistory()\n",
        "\n",
        "  for period_index in range(0, loan_template.length_in_months):\n",
        "    balance_history.snapshot(\n",
        "        period=period_index,\n",
        "        balances=balances,\n",
        "        exchange_rate_to_eur=exchange_rate_provider.get_exchange_rate(\n",
        "              period=period_index,\n",
        "              from_currency=BTC,\n",
        "              to_currency=EUR\n",
        "              )\n",
        "    )\n",
        "\n",
        "    if period_index == 0:\n",
        "      # Buy BTC in first period\n",
        "      swap = swapper.input_defined_swap(\n",
        "          input_amount=MoneyAmount(\n",
        "              loan_template.principal-loan_template.amortization_amount,\n",
        "              EUR),\n",
        "          exchange_rate=exchange_rate_provider.get_exchange_rate(\n",
        "              period=period_index,\n",
        "              from_currency=EUR,\n",
        "              to_currency=BTC\n",
        "              ),\n",
        "          output_currency=BTC\n",
        "      )\n",
        "      balances.update_with_swap(swap)\n",
        "\n",
        "    if balances.balances[EUR] <= loan_template.amortization_amount:\n",
        "\n",
        "      \n",
        "      # Change to EUR if we are running out of cash to pay back loan\n",
        "      swap = swapper.output_defined_swap(\n",
        "          input_currency=BTC,\n",
        "          exchange_rate=exchange_rate_provider.get_exchange_rate(\n",
        "              period=period_index,\n",
        "              from_currency=EUR,\n",
        "              to_currency=BTC\n",
        "              ),\n",
        "          output_amount=MoneyAmount(\n",
        "              loan_template.amortization_amount,\n",
        "              EUR\n",
        "          )\n",
        "      )\n",
        "      if swap.input < balances.balances[BTC]:\n",
        "        # We still have enough BTC stash\n",
        "        balances.update_with_swap(swap)\n",
        "      else:\n",
        "        # We fucked and must get liquidity from emergency line\n",
        "        balances.bite_emergency_line(loan_template.amortization_amount)\n",
        "    \n",
        "    balances.pay_bank(\n",
        "          amount=MoneyAmount(\n",
        "              loan_template.amortization_amount,\n",
        "              EUR\n",
        "          )\n",
        "      )\n",
        "\n",
        "  return balance_history.as_df\n",
        "\n",
        "\n",
        "\n",
        "principal_options = [20_000, 30_000, 40_000]\n",
        "interest_rate_options = [0.04, 0.05, 0.06,]\n",
        "length_in_months_options = [84, 106, 120]\n",
        "\n",
        "all_options = [\n",
        "               principal_options, \n",
        "               interest_rate_options, \n",
        "               length_in_months_options\n",
        "               ]\n",
        "all_combinations = list(itertools.product(*all_options))\n",
        "\n",
        "possible_loans = [\n",
        "  LoanTemplate(\n",
        "      principal=a_principal,\n",
        "      interest_rate=an_interest_rate / 12, # To monthly\n",
        "      length_in_months=a_length\n",
        "  )\n",
        "  for a_principal, an_interest_rate, a_length\n",
        "  in all_combinations\n",
        "]\n",
        "\n",
        "operation_duration_in_months=120\n",
        "starting_btc_price_in_eur=40_000\n",
        "n_simulations = 100\n",
        "\n",
        "historical_price_simulations = [PriceSimulation(\n",
        "    length_in_periods=operation_duration_in_months, \n",
        "    starting_price=starting_btc_price_in_eur,\n",
        "    delta_generator= lambda: price_history_df[\"returns_for_1_month\"].quantile(np.random.uniform(0,1)),\n",
        "    scenario_tag=\"Historical\"\n",
        ")\n",
        "for i in range(0,n_simulations)\n",
        "] \n",
        "softer_1_price_simulations = [PriceSimulation(\n",
        "    length_in_periods=operation_duration_in_months, \n",
        "    starting_price=starting_btc_price_in_eur,\n",
        "    delta_generator= lambda: np.random.normal(0.082/2, 0.260/2),\n",
        "    scenario_tag=\"softer_1\"\n",
        ")\n",
        "for i in range(0,n_simulations)\n",
        "]\n",
        "softer_2_price_simulations = [PriceSimulation(\n",
        "    length_in_periods=operation_duration_in_months, \n",
        "    starting_price=starting_btc_price_in_eur,\n",
        "    delta_generator= lambda: np.random.normal(0.082/8, 0.260/8),\n",
        "    scenario_tag=\"softer_2\"\n",
        ")\n",
        "for i in range(0,n_simulations)\n",
        "]\n",
        "black_swan_price_simulations = [PriceSimulation(\n",
        "    length_in_periods=operation_duration_in_months, \n",
        "    starting_price=starting_btc_price_in_eur,\n",
        "    delta_generator= lambda: np.random.normal(-0.02, 0.260),\n",
        "    scenario_tag=\"black_swan\"\n",
        ")\n",
        "for i in range(0,n_simulations)\n",
        "]\n",
        "\n",
        "many_price_simulations = historical_price_simulations + softer_1_price_simulations + softer_2_price_simulations + black_swan_price_simulations\n",
        "\n",
        "\n",
        "def sweep_options(\n",
        "    possible_loans: List[LoanTemplate],\n",
        "    price_simulations: List[pd.DataFrame]\n",
        ") -> pd.DataFrame:\n",
        "\n",
        "  all_options_results = {\n",
        "      \"loan_principal\": [],\n",
        "      \"loan_interest_rate\": [],\n",
        "      \"loan_length_in_months\": [],\n",
        "      \"amortization_amount\": [],\n",
        "      \"price_scenario\": [],\n",
        "      \"final_btc_balance\": [],\n",
        "      \"final_networth\": [],\n",
        "      \"total_payed_to_bank\": [],\n",
        "      \"total_emergency_line_contribution\":[],\n",
        "      \"mean_monthly_emergency_line_contribution\": []\n",
        "  }\n",
        "\n",
        "  for a_loan in tqdm(possible_loans):\n",
        "    for a_simulation in price_simulations:\n",
        "      detailed_results = run_full_simulation(\n",
        "          a_loan,\n",
        "          a_simulation.price_simulation_result\n",
        "          )\n",
        "      last_period_index = detailed_results[\"period\"] == detailed_results[\"period\"].max()\n",
        "      final_btc_balance = detailed_results.loc[last_period_index, \"btc_balance\"].values[0]\n",
        "      final_networth = detailed_results.loc[last_period_index,\"eur_networth\"].values[0]\n",
        "      total_payed_to_bank = detailed_results.loc[last_period_index, \"total_payed_to_bank\"].values[0]\n",
        "      total_emergency_line_contribution = detailed_results.loc[last_period_index, \"total_emergency_line_contribution\"].values[0]\n",
        "\n",
        "      all_options_results[\"loan_principal\"].append(a_loan.principal)\n",
        "      all_options_results[\"loan_interest_rate\"].append(a_loan.interest_rate)\n",
        "      all_options_results[\"loan_length_in_months\"].append(a_loan.length_in_months)\n",
        "      all_options_results[\"amortization_amount\"].append(a_loan.amortization_amount)\n",
        "      all_options_results[\"price_scenario\"].append(a_simulation.scenario_tag)\n",
        "      all_options_results[\"final_btc_balance\"].append(final_btc_balance)\n",
        "      all_options_results[\"final_networth\"].append(final_networth - total_emergency_line_contribution)\n",
        "      all_options_results[\"total_payed_to_bank\"].append(total_payed_to_bank)\n",
        "      all_options_results[\"total_emergency_line_contribution\"].append(total_emergency_line_contribution)\n",
        "      all_options_results[\"mean_monthly_emergency_line_contribution\"].append(total_emergency_line_contribution / a_loan.length_in_months)\n",
        "\n",
        "  \n",
        "  return pd.DataFrame(all_options_results)\n",
        "\n",
        "\n",
        "all_options_results = sweep_options(possible_loans, many_price_simulations)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "M4E4b9DpAVuQ",
        "outputId": "33e66be4-a55e-4405-c988-866d410ccde7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 27/27 [12:02<00:00, 26.76s/it]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "all_options_results.to_excel(\"final_loan_check.xlsx\")\n",
        "files.download(\"final_loan_check.xlsx\")\n"
      ],
      "metadata": {
        "id": "vc9N9YD1kMTD",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 17
        },
        "outputId": "74e9518b-09cc-48fd-9f7d-39e8ac16ad6d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "download(\"download_74956796-876b-4bb0-8152-63df12771f1e\", \"final_loan_check.xlsx\", 733892)"
            ]
          },
          "metadata": {}
        }
      ]
    }
  ]
}