{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b48ba179",
   "metadata": {},
   "source": [
    "# Time offsets\n",
    "\n",
    "This notebook introduces the concept of _time offsets_ and how they are used in `gwrefpy`.\n",
    "\n",
    "This notebook can be downloaded from the source code [here](https://github.com/andersretznerSGU/gwrefpy/blob/main/docs/user_guide/3_time_offsets.ipynb).\n",
    "\n",
    "Time offsets are a concept to handle time series with different timestamps. If two time series share the same timestamps, they can be compared directly. If not, we need to introduce a time offset to align them. The offset represents an interval for which all data points will be considered as having the same timestamp.\n",
    "\n",
    "In the following notebook, we will illustrate this concept with a simple example. The example is inspired by section _3.3_ in [Strandanger (2024)](https://svenskageotekniskaforeningen.se/wp-content/uploads/Publikationer/SGF_Rapporter/2024_2_Akvifars_refmetod.pdf).\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2495328d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import gwrefpy as gr\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "99c421cb",
   "metadata": {},
   "source": [
    "# Data\n",
    "\n",
    "Let's start by declaring the data we will explore as an example. We create `Well` objects and add to a `Model` object. Finally, we plot the data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "c78901d3",
   "metadata": {},
   "outputs": [],
   "source": [
    "obs_ts = pd.Series(\n",
    "    index=[\n",
    "        pd.Timestamp(\"2023-01-07\"),\n",
    "        pd.Timestamp(\"2023-02-01\"),\n",
    "        pd.Timestamp(\"2023-02-25\"),\n",
    "    ],\n",
    "    data=[10.4, 10.7, 10.8],\n",
    "    name=\"obs\",\n",
    ")\n",
    "ref_ts = pd.Series(\n",
    "    index=[\n",
    "        pd.Timestamp(\"2023-01-08\"),\n",
    "        pd.Timestamp(\"2023-02-03\"),\n",
    "        pd.Timestamp(\"2023-02-09\"),\n",
    "        pd.Timestamp(\"2023-02-25\"),\n",
    "        pd.Timestamp(\"2023-02-28\"),\n",
    "    ],\n",
    "    data=[8.9, 9.2, 9.3, 9.3, 9.5],\n",
    "    name=\"ref\",\n",
    ")\n",
    "obs = gr.Well(\"obs\", False, obs_ts)\n",
    "ref = gr.Well(\"ref\", True, ref_ts)\n",
    "\n",
    "model = gr.Model(\"offset test\")\n",
    "model.add_well([obs, ref])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "15679a86",
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, (up, down) = plt.subplots(nrows=2, sharex=True)\n",
    "\n",
    "obs_ts.plot(ax=up, marker=\"o\", linestyle=\"\", label=\"obs\", color=\"black\")\n",
    "ref_ts.plot(ax=down, marker=\"o\", linestyle=\"\", label=\"ref\", color=\"blue\")\n",
    "_ = [ax.legend() for ax in (up, down)]\n",
    "_ = [ax.grid() for ax in (up, down)]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "80dd73cb",
   "metadata": {},
   "source": [
    "As we can see, the wells share some timestamps, but not all. In fact, only one timestamp (2023-02-25) is shared between the two wells. The table below shows an outer join between the two wells."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "e09331cd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.microsoft.datawrangler.viewer.v0+json": {
       "columns": [
        {
         "name": "index",
         "rawType": "datetime64[ns]",
         "type": "datetime"
        },
        {
         "name": "obs",
         "rawType": "float64",
         "type": "float"
        },
        {
         "name": "ref",
         "rawType": "float64",
         "type": "float"
        }
       ],
       "ref": "6874f5ae-464a-4c0b-9672-b74e4214d625",
       "rows": [
        [
         "2023-01-07 00:00:00",
         "10.4",
         null
        ],
        [
         "2023-01-08 00:00:00",
         null,
         "8.9"
        ],
        [
         "2023-02-01 00:00:00",
         "10.7",
         null
        ],
        [
         "2023-02-03 00:00:00",
         null,
         "9.2"
        ],
        [
         "2023-02-09 00:00:00",
         null,
         "9.3"
        ],
        [
         "2023-02-25 00:00:00",
         "10.8",
         "9.3"
        ],
        [
         "2023-02-28 00:00:00",
         null,
         "9.5"
        ]
       ],
       "shape": {
        "columns": 2,
        "rows": 7
       }
      },
      "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 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>obs</th>\n",
       "      <th>ref</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2023-01-07</th>\n",
       "      <td>10.4</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2023-01-08</th>\n",
       "      <td>NaN</td>\n",
       "      <td>8.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2023-02-01</th>\n",
       "      <td>10.7</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2023-02-03</th>\n",
       "      <td>NaN</td>\n",
       "      <td>9.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2023-02-09</th>\n",
       "      <td>NaN</td>\n",
       "      <td>9.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2023-02-25</th>\n",
       "      <td>10.8</td>\n",
       "      <td>9.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2023-02-28</th>\n",
       "      <td>NaN</td>\n",
       "      <td>9.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             obs  ref\n",
       "2023-01-07  10.4  NaN\n",
       "2023-01-08   NaN  8.9\n",
       "2023-02-01  10.7  NaN\n",
       "2023-02-03   NaN  9.2\n",
       "2023-02-09   NaN  9.3\n",
       "2023-02-25  10.8  9.3\n",
       "2023-02-28   NaN  9.5"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.concat([obs_ts, ref_ts], axis=\"columns\", join=\"outer\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "49fcae26",
   "metadata": {},
   "source": [
    "# Using time offsets\n",
    "\n",
    "Our two wells have only one shared timestamp, but we know that they have several timestamps that are close to each other. To compare the two time series, we can introduce a time offset.\n",
    "\n",
    "A time offset is defined as a time interval. All data points within this interval will be considered as having the same timestamp. For example, if we set an offset of 1 day, all data points within 1 day of each other will be considered as having the same timestamp. If multiple data points fall within the same interval, the mean value will be used default. As of version 0.2.0 we also include median, max and min as aggregation method within an offset (see the API reference for the `Model` class and its `fit` method). \n",
    "\n",
    "```{important}\n",
    "The offset extends in both directions. For example, if we have a timestamp of 2023-02-25 and an offset of 1 day, all data points between 2023-02-24 and 2023-02-26 will be considered as having the same timestamp.\n",
    "```\n",
    "\n",
    "The offset argument can be given as a string or a `pandas.Timedelta` object. Refer to the [pandas documentation](https://pandas.pydata.org/docs/reference/api/pandas.Timedelta.html) for more information about the accepted strings.\n",
    "\n",
    "We provide a helper function for analyzing multiple time offsets at once: `analyze_offsets`. This function takes a list of offsets and computes the number of matching data pairs. Let's see how it works by analyzing offsets of 0, 1, and 3 days."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "6c15a111",
   "metadata": {},
   "outputs": [],
   "source": [
    "offsets = [\"0D\", \"1D\", \"3D\"]\n",
    "results = gr.analyze_offsets(ref, obs, offsets)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "66bdd3e4",
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [],
   "source": [
    "results = results.reset_index().set_index(\"index\", drop=True)\n",
    "results.index.name = \"offset\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "57b8ef7f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.microsoft.datawrangler.viewer.v0+json": {
       "columns": [
        {
         "name": "offset",
         "rawType": "object",
         "type": "string"
        },
        {
         "name": "n_pairs",
         "rawType": "int64",
         "type": "integer"
        }
       ],
       "ref": "87fade79-7e39-40e8-b340-fb988537e2e3",
       "rows": [
        [
         "0D",
         "1"
        ],
        [
         "1D",
         "2"
        ],
        [
         "3D",
         "3"
        ]
       ],
       "shape": {
        "columns": 1,
        "rows": 3
       }
      },
      "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 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>n_pairs</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>offset</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0D</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1D</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3D</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        n_pairs\n",
       "offset         \n",
       "0D            1\n",
       "1D            2\n",
       "3D            3"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "results"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b8ddc4c8",
   "metadata": {},
   "source": [
    "Let's plot the width of the offset to understand the results better."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "aeef46fc",
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 6 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axs = plt.subplots(nrows=len(offsets), ncols=1, sharex=True)\n",
    "\n",
    "for i, (ax, offset) in enumerate(zip(axs, offsets)):\n",
    "    ax2 = ax.twinx()\n",
    "    \n",
    "    for ts, value in obs_ts.items():\n",
    "        x_start = ts - pd.Timedelta(offset)\n",
    "        x_end = ts + pd.Timedelta(offset)\n",
    "        ax.plot([x_start, x_end], [value, value], \n",
    "                color=\"gray\", alpha=0.75, linewidth=5)\n",
    "    \n",
    "    for ts, value in ref_ts.items():\n",
    "        x_start = ts - pd.Timedelta(offset)\n",
    "        x_end = ts + pd.Timedelta(offset)\n",
    "        ax2.plot([x_start, x_end], [value, value], \n",
    "                 color=\"blue\", alpha=0.5, linewidth=5)\n",
    "    \n",
    "    obs_ts.plot(ax=ax, marker=\"o\", linestyle=\"\", label=\"obs\", color=\"black\")\n",
    "    ref_ts.plot(ax=ax2, marker=\"o\", linestyle=\"\", label=\"ref\", color=\"blue\")\n",
    "    \n",
    "    ax.set_ylabel(\"obs\", color=\"black\")\n",
    "    ax2.set_ylabel(\"ref\", color=\"blue\")\n",
    "    \n",
    "    ax.tick_params(axis=\"y\", labelcolor=\"black\")\n",
    "    ax2.tick_params(axis=\"y\", labelcolor=\"blue\")\n",
    "\n",
    "    ax.set_title(f\"{pd.to_timedelta(offset).days} days\")\n",
    "    ax.grid()\n",
    "\n",
    "fig.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "05ce9cd5",
   "metadata": {},
   "source": [
    "For this simple example, we can demonstrate that a time offset of 3 days seems reasonable. This offset allows for several matching data pairs, while still being small enough to avoid grouping timestamps that are too far apart.\n",
    "\n",
    "As mentioned, any points within the offset interval are averaged. The newly constructed timestamps are taken as the mean of the grouped timestamps. Given an offset of 3 days:\n",
    "\n",
    "- for the first period (January), a data pair is formed because the data point from each well fall within their respective offsets\n",
    "- for the second period (February), the first data point from the reference well is paired with the data point from the observation well, because their offset intervals intersect\n",
    "- for the third period (March), **two** data points and their offset interval fall within the offset interval of the single data point from the observation well. This means that a single data pair will be formed between the average of the data points from the reference well, and the single data point from the observation well.\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "ed70b670",
   "metadata": {
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x300 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "offset = \"3D\"\n",
    "\n",
    "fig, ax = plt.subplots(figsize=(6, 3))\n",
    "ax2 = ax.twinx()\n",
    "\n",
    "for ts, value in obs_ts.items():\n",
    "    x_start = ts - pd.Timedelta(offset)\n",
    "    x_end = ts + pd.Timedelta(offset)\n",
    "    ax.plot([x_start, x_end], [value, value], \n",
    "            color=\"gray\", alpha=0.5, linewidth=5)\n",
    "\n",
    "for ts, value in ref_ts.items():\n",
    "    x_start = ts - pd.Timedelta(offset)\n",
    "    x_end = ts + pd.Timedelta(offset)\n",
    "    ax2.plot([x_start, x_end], [value, value], \n",
    "             color=\"blue\", alpha=0.5, linewidth=5)\n",
    "\n",
    "obs_ts.plot(ax=ax, marker=\"o\", linestyle=\"\", label=\"obs\", color=\"black\")\n",
    "ref_ts.plot(ax=ax2, marker=\"o\", linestyle=\"\", label=\"ref\", color=\"blue\")\n",
    "\n",
    "ax.set_ylabel(\"obs\", color=\"black\")\n",
    "ax2.set_ylabel(\"ref\", color=\"blue\")\n",
    "\n",
    "ax.tick_params(axis=\"y\", labelcolor=\"black\")\n",
    "ax2.tick_params(axis=\"y\", labelcolor=\"blue\")\n",
    "\n",
    "periods = [\n",
    "    (\"2023-01-05\", \"2023-01-20\", \"Period 1\"),\n",
    "    (\"2023-01-28\", \"2023-02-12\", \"Period 2\"),\n",
    "    (\"2023-02-20\", \"2023-03-05\", \"Period 3\")\n",
    "]\n",
    "\n",
    "colors = [\"lightblue\", \"lightgreen\", \"grey\"]\n",
    "y_positions = [0.9, 0.1, 0.1]\n",
    "\n",
    "for i, (start_date, end_date, label) in enumerate(periods):\n",
    "    start = pd.Timestamp(start_date)\n",
    "    end = pd.Timestamp(end_date)\n",
    "    \n",
    "    ax.axvspan(start, end, alpha=0.25, color=colors[i], zorder=0)\n",
    "    \n",
    "    center = start + (end - start) / 2\n",
    "    y_min, y_max = ax.get_ylim()\n",
    "    y_pos = y_min + (y_max - y_min) * y_positions[i]\n",
    "    ax.text(center, y_pos, label, \n",
    "            ha=\"center\", va=\"center\", fontweight=\"bold\",\n",
    "            bbox=dict(boxstyle=\"round,pad=0.3\", facecolor=\"white\", alpha=0.8))\n",
    "\n",
    "ax.grid()\n",
    "\n",
    "plt.xticks(rotation=45)\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f41ba285",
   "metadata": {},
   "source": [
    "When fitting these two wells with an offset of 3 days, three data pairs will formed as explained above.\n",
    "\n",
    "This concludes this notebook on time offsets in `gwrefpy`. Happy fitting!"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "gwrefpy",
   "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": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}