{
    "cells": [
        {
            "attachments": {},
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "# Multi variable comparison\n",
                "Assessing both wave height and wind speed at the same time"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 20,
            "metadata": {},
            "outputs": [],
            "source": [
                "import modelskill as ms"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## Define observations\n",
                "Below, the observations will take the default quantity names from the eum type of the item. Alternatively, the user can give another quantity name by providing the `quantity` argument."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 21,
            "metadata": {},
            "outputs": [],
            "source": [
                "# wave height\n",
                "o1 = ms.PointObservation('../tests/testdata/SW/HKNA_Hm0.dfs0', item=0, x=4.2420, y=52.6887, name=\"HKNA_Hm0\")\n",
                "o2 = ms.PointObservation(\"../tests/testdata/SW/eur_Hm0.dfs0\", item=0, x=3.2760, y=51.9990, name=\"EPL_Hm0\")\n",
                "o3 = ms.TrackObservation(\"../tests/testdata/SW/Alti_c2_Dutch.dfs0\", item=3, name=\"c2_Hm0\")\n",
                "\n",
                "# wind speed\n",
                "wind1 = ms.PointObservation('../tests/testdata/SW/HKNA_wind.dfs0', item=0, x=4.2420, y=52.6887, name=\"HKNA_wind\")\n",
                "wind2 = ms.PointObservation('../tests/testdata/SW/F16_wind.dfs0', item=0, x=4.01222, y=54.1167, name=\"F16_wind\")\n",
                "wind3 = ms.TrackObservation(\"../tests/testdata/SW/Alti_c2_Dutch.dfs0\", item=2, name=\"c2_wind\")"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 22,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "Quantity(name='Significant wave height', unit='meter')"
                        ]
                    },
                    "execution_count": 22,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "o1.quantity"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## Define model results\n",
                "Two different simulation runs are used to create four model results:"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 23,
            "metadata": {},
            "outputs": [],
            "source": [
                "fn1 = \"../tests/testdata/SW/HKZN_local_2017_DutchCoast.dfsu\"\n",
                "mr1Hm0 = ms.model_result(fn1, name='SW_1', item='Sign. Wave Height')\n",
                "mr1WS = ms.model_result(fn1, name='SW_1', item='Wind speed')\n",
                "fn2 = \"../tests/testdata/SW/HKZN_local_2017_DutchCoast_v2.dfsu\"\n",
                "mr2Hm0 = ms.model_result(fn2, name='SW_2', item='Sign. Wave Height')\n",
                "mr2WS = ms.model_result(fn2, name='SW_2', item='Wind speed')"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 24,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "<DfsuModelResult> 'SW_1'"
                        ]
                    },
                    "execution_count": 24,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "mr1WS"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## Connect model and observations and extract\n",
                "We connect the observation item and model item by refering to the item name in the ModelResult. Item number can also be used."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 25,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "<ComparerCollection>\n",
                            "Comparer: HKNA_Hm0\n",
                            "Comparer: EPL_Hm0\n",
                            "Comparer: c2_Hm0\n",
                            "Comparer: HKNA_wind\n",
                            "Comparer: F16_wind\n",
                            "Comparer: c2_wind"
                        ]
                    },
                    "execution_count": 25,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "cc1 = ms.match([o1, o2, o3], [mr1Hm0, mr2Hm0])\n",
                "cc2 = ms.match([wind1, wind2, wind3], [mr1WS, mr2WS])\n",
                "cc = cc1 + cc2\n",
                "cc"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 26,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "2"
                        ]
                    },
                    "execution_count": 26,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "cc.n_quantities"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 27,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "['Significant wave height', 'Wind speed']"
                        ]
                    },
                    "execution_count": 27,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "cc.quantity_names"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## Analysis\n",
                "Now that the result has been extracted, we can do analysis. Multiple quantities means an extra level in the multi-index of the skill dataframe. "
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 28,
            "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 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></th>\n",
                            "      <th></th>\n",
                            "      <th>n</th>\n",
                            "      <th>bias</th>\n",
                            "      <th>rmse</th>\n",
                            "      <th>urmse</th>\n",
                            "      <th>mae</th>\n",
                            "      <th>cc</th>\n",
                            "      <th>si</th>\n",
                            "      <th>r2</th>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>model</th>\n",
                            "      <th>observation</th>\n",
                            "      <th>quantity</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 rowspan=\"6\" valign=\"top\">SW_1</th>\n",
                            "      <th>EPL_Hm0</th>\n",
                            "      <th>Significant wave height</th>\n",
                            "      <td>67</td>\n",
                            "      <td>-0.067</td>\n",
                            "      <td>0.224</td>\n",
                            "      <td>0.213</td>\n",
                            "      <td>0.189</td>\n",
                            "      <td>0.970</td>\n",
                            "      <td>0.083</td>\n",
                            "      <td>0.933</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>F16_wind</th>\n",
                            "      <th>Wind speed</th>\n",
                            "      <td>67</td>\n",
                            "      <td>2.102</td>\n",
                            "      <td>2.775</td>\n",
                            "      <td>1.812</td>\n",
                            "      <td>2.197</td>\n",
                            "      <td>0.825</td>\n",
                            "      <td>0.141</td>\n",
                            "      <td>0.230</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>HKNA_Hm0</th>\n",
                            "      <th>Significant wave height</th>\n",
                            "      <td>386</td>\n",
                            "      <td>-0.194</td>\n",
                            "      <td>0.352</td>\n",
                            "      <td>0.293</td>\n",
                            "      <td>0.252</td>\n",
                            "      <td>0.971</td>\n",
                            "      <td>0.094</td>\n",
                            "      <td>0.905</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>HKNA_wind</th>\n",
                            "      <th>Wind speed</th>\n",
                            "      <td>277</td>\n",
                            "      <td>-0.881</td>\n",
                            "      <td>1.276</td>\n",
                            "      <td>0.923</td>\n",
                            "      <td>1.023</td>\n",
                            "      <td>0.963</td>\n",
                            "      <td>0.066</td>\n",
                            "      <td>0.861</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>c2_Hm0</th>\n",
                            "      <th>Significant wave height</th>\n",
                            "      <td>113</td>\n",
                            "      <td>-0.001</td>\n",
                            "      <td>0.352</td>\n",
                            "      <td>0.352</td>\n",
                            "      <td>0.295</td>\n",
                            "      <td>0.974</td>\n",
                            "      <td>0.128</td>\n",
                            "      <td>0.900</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>c2_wind</th>\n",
                            "      <th>Wind speed</th>\n",
                            "      <td>113</td>\n",
                            "      <td>0.409</td>\n",
                            "      <td>0.638</td>\n",
                            "      <td>0.490</td>\n",
                            "      <td>0.506</td>\n",
                            "      <td>0.960</td>\n",
                            "      <td>0.051</td>\n",
                            "      <td>0.867</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th rowspan=\"6\" valign=\"top\">SW_2</th>\n",
                            "      <th>EPL_Hm0</th>\n",
                            "      <th>Significant wave height</th>\n",
                            "      <td>67</td>\n",
                            "      <td>-0.000</td>\n",
                            "      <td>0.232</td>\n",
                            "      <td>0.232</td>\n",
                            "      <td>0.198</td>\n",
                            "      <td>0.970</td>\n",
                            "      <td>0.090</td>\n",
                            "      <td>0.927</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>F16_wind</th>\n",
                            "      <th>Wind speed</th>\n",
                            "      <td>67</td>\n",
                            "      <td>2.102</td>\n",
                            "      <td>2.775</td>\n",
                            "      <td>1.812</td>\n",
                            "      <td>2.197</td>\n",
                            "      <td>0.825</td>\n",
                            "      <td>0.141</td>\n",
                            "      <td>0.230</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>HKNA_Hm0</th>\n",
                            "      <th>Significant wave height</th>\n",
                            "      <td>386</td>\n",
                            "      <td>-0.100</td>\n",
                            "      <td>0.293</td>\n",
                            "      <td>0.275</td>\n",
                            "      <td>0.214</td>\n",
                            "      <td>0.971</td>\n",
                            "      <td>0.089</td>\n",
                            "      <td>0.934</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>HKNA_wind</th>\n",
                            "      <th>Wind speed</th>\n",
                            "      <td>277</td>\n",
                            "      <td>-0.881</td>\n",
                            "      <td>1.276</td>\n",
                            "      <td>0.923</td>\n",
                            "      <td>1.023</td>\n",
                            "      <td>0.963</td>\n",
                            "      <td>0.066</td>\n",
                            "      <td>0.861</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>c2_Hm0</th>\n",
                            "      <th>Significant wave height</th>\n",
                            "      <td>113</td>\n",
                            "      <td>0.081</td>\n",
                            "      <td>0.430</td>\n",
                            "      <td>0.422</td>\n",
                            "      <td>0.357</td>\n",
                            "      <td>0.974</td>\n",
                            "      <td>0.153</td>\n",
                            "      <td>0.850</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>c2_wind</th>\n",
                            "      <th>Wind speed</th>\n",
                            "      <td>113</td>\n",
                            "      <td>0.409</td>\n",
                            "      <td>0.638</td>\n",
                            "      <td>0.490</td>\n",
                            "      <td>0.506</td>\n",
                            "      <td>0.960</td>\n",
                            "      <td>0.051</td>\n",
                            "      <td>0.867</td>\n",
                            "    </tr>\n",
                            "  </tbody>\n",
                            "</table>\n",
                            "</div>"
                        ],
                        "text/plain": [
                            "                                             n   bias   rmse  urmse    mae  \\\n",
                            "model observation quantity                                                   \n",
                            "SW_1  EPL_Hm0     Significant wave height   67 -0.067  0.224  0.213  0.189   \n",
                            "      F16_wind    Wind speed                67  2.102  2.775  1.812  2.197   \n",
                            "      HKNA_Hm0    Significant wave height  386 -0.194  0.352  0.293  0.252   \n",
                            "      HKNA_wind   Wind speed               277 -0.881  1.276  0.923  1.023   \n",
                            "      c2_Hm0      Significant wave height  113 -0.001  0.352  0.352  0.295   \n",
                            "      c2_wind     Wind speed               113  0.409  0.638  0.490  0.506   \n",
                            "SW_2  EPL_Hm0     Significant wave height   67 -0.000  0.232  0.232  0.198   \n",
                            "      F16_wind    Wind speed                67  2.102  2.775  1.812  2.197   \n",
                            "      HKNA_Hm0    Significant wave height  386 -0.100  0.293  0.275  0.214   \n",
                            "      HKNA_wind   Wind speed               277 -0.881  1.276  0.923  1.023   \n",
                            "      c2_Hm0      Significant wave height  113  0.081  0.430  0.422  0.357   \n",
                            "      c2_wind     Wind speed               113  0.409  0.638  0.490  0.506   \n",
                            "\n",
                            "                                              cc     si     r2  \n",
                            "model observation quantity                                      \n",
                            "SW_1  EPL_Hm0     Significant wave height  0.970  0.083  0.933  \n",
                            "      F16_wind    Wind speed               0.825  0.141  0.230  \n",
                            "      HKNA_Hm0    Significant wave height  0.971  0.094  0.905  \n",
                            "      HKNA_wind   Wind speed               0.963  0.066  0.861  \n",
                            "      c2_Hm0      Significant wave height  0.974  0.128  0.900  \n",
                            "      c2_wind     Wind speed               0.960  0.051  0.867  \n",
                            "SW_2  EPL_Hm0     Significant wave height  0.970  0.090  0.927  \n",
                            "      F16_wind    Wind speed               0.825  0.141  0.230  \n",
                            "      HKNA_Hm0    Significant wave height  0.971  0.089  0.934  \n",
                            "      HKNA_wind   Wind speed               0.963  0.066  0.861  \n",
                            "      c2_Hm0      Significant wave height  0.974  0.153  0.850  \n",
                            "      c2_wind     Wind speed               0.960  0.051  0.867  "
                        ]
                    },
                    "execution_count": 28,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "sk = cc.skill()\n",
                "sk.round(3)"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 29,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/html": [
                            "<style type=\"text/css\">\n",
                            "#T_61af9_row0_col1 {\n",
                            "  background-color: #a9c6fd;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row0_col2, #T_61af9_row0_col3, #T_61af9_row0_col4, #T_61af9_row0_col6, #T_61af9_row4_col7, #T_61af9_row5_col5 {\n",
                            "  background-color: #fff7ec;\n",
                            "  color: #000000;\n",
                            "  text-decoration: underline;\n",
                            "  font-style: italic;\n",
                            "  font-weight: bold;\n",
                            "}\n",
                            "#T_61af9_row0_col5, #T_61af9_row3_col5, #T_61af9_row5_col2, #T_61af9_row5_col3, #T_61af9_row5_col4, #T_61af9_row5_col6, #T_61af9_row5_col7 {\n",
                            "  background-color: #7f0000;\n",
                            "  color: #f1f1f1;\n",
                            "}\n",
                            "#T_61af9_row0_col7 {\n",
                            "  background-color: #fff5e6;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row1_col1 {\n",
                            "  background-color: #3b4cc0;\n",
                            "  color: #f1f1f1;\n",
                            "}\n",
                            "#T_61af9_row1_col2 {\n",
                            "  background-color: #ef6548;\n",
                            "  color: #f1f1f1;\n",
                            "}\n",
                            "#T_61af9_row1_col3 {\n",
                            "  background-color: #fdb881;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row1_col4 {\n",
                            "  background-color: #fdba83;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row1_col5, #T_61af9_row4_col5 {\n",
                            "  background-color: #e0442f;\n",
                            "  color: #f1f1f1;\n",
                            "}\n",
                            "#T_61af9_row1_col6 {\n",
                            "  background-color: #fee1b9;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row1_col7 {\n",
                            "  background-color: #fdc28b;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row2_col1 {\n",
                            "  background-color: #dcdddd;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row2_col2 {\n",
                            "  background-color: #f06749;\n",
                            "  color: #f1f1f1;\n",
                            "}\n",
                            "#T_61af9_row2_col3 {\n",
                            "  background-color: #e8553c;\n",
                            "  color: #f1f1f1;\n",
                            "}\n",
                            "#T_61af9_row2_col4 {\n",
                            "  background-color: #ee6246;\n",
                            "  color: #f1f1f1;\n",
                            "}\n",
                            "#T_61af9_row2_col5 {\n",
                            "  background-color: #fff7ec;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row2_col6 {\n",
                            "  background-color: #ec5f43;\n",
                            "  color: #f1f1f1;\n",
                            "}\n",
                            "#T_61af9_row2_col7 {\n",
                            "  background-color: #fdad77;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row3_col1 {\n",
                            "  background-color: #dcdddd;\n",
                            "  color: #000000;\n",
                            "  text-decoration: underline;\n",
                            "  font-style: italic;\n",
                            "  font-weight: bold;\n",
                            "}\n",
                            "#T_61af9_row3_col2 {\n",
                            "  background-color: #fff2e0;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row3_col3 {\n",
                            "  background-color: #feecd2;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row3_col4 {\n",
                            "  background-color: #fff0dc;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row3_col6 {\n",
                            "  background-color: #feebcf;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row3_col7 {\n",
                            "  background-color: #feedd4;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row4_col1 {\n",
                            "  background-color: #89acfd;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row4_col2 {\n",
                            "  background-color: #fdc38c;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row4_col3 {\n",
                            "  background-color: #fdcb95;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row4_col4 {\n",
                            "  background-color: #fee4bf;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row4_col6 {\n",
                            "  background-color: #feedd3;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "#T_61af9_row5_col1 {\n",
                            "  background-color: #f7a98b;\n",
                            "  color: #000000;\n",
                            "}\n",
                            "</style>\n",
                            "<table id=\"T_61af9\">\n",
                            "  <thead>\n",
                            "    <tr>\n",
                            "      <th class=\"blank\" >&nbsp;</th>\n",
                            "      <th class=\"blank level0\" >&nbsp;</th>\n",
                            "      <th id=\"T_61af9_level0_col0\" class=\"col_heading level0 col0\" >n</th>\n",
                            "      <th id=\"T_61af9_level0_col1\" class=\"col_heading level0 col1\" >bias</th>\n",
                            "      <th id=\"T_61af9_level0_col2\" class=\"col_heading level0 col2\" >rmse</th>\n",
                            "      <th id=\"T_61af9_level0_col3\" class=\"col_heading level0 col3\" >urmse</th>\n",
                            "      <th id=\"T_61af9_level0_col4\" class=\"col_heading level0 col4\" >mae</th>\n",
                            "      <th id=\"T_61af9_level0_col5\" class=\"col_heading level0 col5\" >cc</th>\n",
                            "      <th id=\"T_61af9_level0_col6\" class=\"col_heading level0 col6\" >si</th>\n",
                            "      <th id=\"T_61af9_level0_col7\" class=\"col_heading level0 col7\" >r2</th>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th class=\"index_name level0\" >model</th>\n",
                            "      <th class=\"index_name level1\" >observation</th>\n",
                            "      <th class=\"blank col0\" >&nbsp;</th>\n",
                            "      <th class=\"blank col1\" >&nbsp;</th>\n",
                            "      <th class=\"blank col2\" >&nbsp;</th>\n",
                            "      <th class=\"blank col3\" >&nbsp;</th>\n",
                            "      <th class=\"blank col4\" >&nbsp;</th>\n",
                            "      <th class=\"blank col5\" >&nbsp;</th>\n",
                            "      <th class=\"blank col6\" >&nbsp;</th>\n",
                            "      <th class=\"blank col7\" >&nbsp;</th>\n",
                            "    </tr>\n",
                            "  </thead>\n",
                            "  <tbody>\n",
                            "    <tr>\n",
                            "      <th id=\"T_61af9_level0_row0\" class=\"row_heading level0 row0\" rowspan=\"3\">SW_1</th>\n",
                            "      <th id=\"T_61af9_level1_row0\" class=\"row_heading level1 row0\" >EPL_Hm0</th>\n",
                            "      <td id=\"T_61af9_row0_col0\" class=\"data row0 col0\" >67</td>\n",
                            "      <td id=\"T_61af9_row0_col1\" class=\"data row0 col1\" >-0.067</td>\n",
                            "      <td id=\"T_61af9_row0_col2\" class=\"data row0 col2\" >0.224</td>\n",
                            "      <td id=\"T_61af9_row0_col3\" class=\"data row0 col3\" >0.213</td>\n",
                            "      <td id=\"T_61af9_row0_col4\" class=\"data row0 col4\" >0.189</td>\n",
                            "      <td id=\"T_61af9_row0_col5\" class=\"data row0 col5\" >0.970</td>\n",
                            "      <td id=\"T_61af9_row0_col6\" class=\"data row0 col6\" >0.083</td>\n",
                            "      <td id=\"T_61af9_row0_col7\" class=\"data row0 col7\" >0.933</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th id=\"T_61af9_level1_row1\" class=\"row_heading level1 row1\" >HKNA_Hm0</th>\n",
                            "      <td id=\"T_61af9_row1_col0\" class=\"data row1 col0\" >386</td>\n",
                            "      <td id=\"T_61af9_row1_col1\" class=\"data row1 col1\" >-0.194</td>\n",
                            "      <td id=\"T_61af9_row1_col2\" class=\"data row1 col2\" >0.352</td>\n",
                            "      <td id=\"T_61af9_row1_col3\" class=\"data row1 col3\" >0.293</td>\n",
                            "      <td id=\"T_61af9_row1_col4\" class=\"data row1 col4\" >0.252</td>\n",
                            "      <td id=\"T_61af9_row1_col5\" class=\"data row1 col5\" >0.971</td>\n",
                            "      <td id=\"T_61af9_row1_col6\" class=\"data row1 col6\" >0.094</td>\n",
                            "      <td id=\"T_61af9_row1_col7\" class=\"data row1 col7\" >0.905</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th id=\"T_61af9_level1_row2\" class=\"row_heading level1 row2\" >c2_Hm0</th>\n",
                            "      <td id=\"T_61af9_row2_col0\" class=\"data row2 col0\" >113</td>\n",
                            "      <td id=\"T_61af9_row2_col1\" class=\"data row2 col1\" >-0.001</td>\n",
                            "      <td id=\"T_61af9_row2_col2\" class=\"data row2 col2\" >0.352</td>\n",
                            "      <td id=\"T_61af9_row2_col3\" class=\"data row2 col3\" >0.352</td>\n",
                            "      <td id=\"T_61af9_row2_col4\" class=\"data row2 col4\" >0.295</td>\n",
                            "      <td id=\"T_61af9_row2_col5\" class=\"data row2 col5\" >0.974</td>\n",
                            "      <td id=\"T_61af9_row2_col6\" class=\"data row2 col6\" >0.128</td>\n",
                            "      <td id=\"T_61af9_row2_col7\" class=\"data row2 col7\" >0.900</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th id=\"T_61af9_level0_row3\" class=\"row_heading level0 row3\" rowspan=\"3\">SW_2</th>\n",
                            "      <th id=\"T_61af9_level1_row3\" class=\"row_heading level1 row3\" >EPL_Hm0</th>\n",
                            "      <td id=\"T_61af9_row3_col0\" class=\"data row3 col0\" >67</td>\n",
                            "      <td id=\"T_61af9_row3_col1\" class=\"data row3 col1\" >-0.000</td>\n",
                            "      <td id=\"T_61af9_row3_col2\" class=\"data row3 col2\" >0.232</td>\n",
                            "      <td id=\"T_61af9_row3_col3\" class=\"data row3 col3\" >0.232</td>\n",
                            "      <td id=\"T_61af9_row3_col4\" class=\"data row3 col4\" >0.198</td>\n",
                            "      <td id=\"T_61af9_row3_col5\" class=\"data row3 col5\" >0.970</td>\n",
                            "      <td id=\"T_61af9_row3_col6\" class=\"data row3 col6\" >0.090</td>\n",
                            "      <td id=\"T_61af9_row3_col7\" class=\"data row3 col7\" >0.927</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th id=\"T_61af9_level1_row4\" class=\"row_heading level1 row4\" >HKNA_Hm0</th>\n",
                            "      <td id=\"T_61af9_row4_col0\" class=\"data row4 col0\" >386</td>\n",
                            "      <td id=\"T_61af9_row4_col1\" class=\"data row4 col1\" >-0.100</td>\n",
                            "      <td id=\"T_61af9_row4_col2\" class=\"data row4 col2\" >0.293</td>\n",
                            "      <td id=\"T_61af9_row4_col3\" class=\"data row4 col3\" >0.275</td>\n",
                            "      <td id=\"T_61af9_row4_col4\" class=\"data row4 col4\" >0.214</td>\n",
                            "      <td id=\"T_61af9_row4_col5\" class=\"data row4 col5\" >0.971</td>\n",
                            "      <td id=\"T_61af9_row4_col6\" class=\"data row4 col6\" >0.089</td>\n",
                            "      <td id=\"T_61af9_row4_col7\" class=\"data row4 col7\" >0.934</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th id=\"T_61af9_level1_row5\" class=\"row_heading level1 row5\" >c2_Hm0</th>\n",
                            "      <td id=\"T_61af9_row5_col0\" class=\"data row5 col0\" >113</td>\n",
                            "      <td id=\"T_61af9_row5_col1\" class=\"data row5 col1\" >0.081</td>\n",
                            "      <td id=\"T_61af9_row5_col2\" class=\"data row5 col2\" >0.430</td>\n",
                            "      <td id=\"T_61af9_row5_col3\" class=\"data row5 col3\" >0.422</td>\n",
                            "      <td id=\"T_61af9_row5_col4\" class=\"data row5 col4\" >0.357</td>\n",
                            "      <td id=\"T_61af9_row5_col5\" class=\"data row5 col5\" >0.974</td>\n",
                            "      <td id=\"T_61af9_row5_col6\" class=\"data row5 col6\" >0.153</td>\n",
                            "      <td id=\"T_61af9_row5_col7\" class=\"data row5 col7\" >0.850</td>\n",
                            "    </tr>\n",
                            "  </tbody>\n",
                            "</table>\n"
                        ],
                        "text/plain": [
                            "<pandas.io.formats.style.Styler at 0x7f55b8253760>"
                        ]
                    },
                    "execution_count": 29,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "sk = cc.sel(quantity='Significant wave height').skill()\n",
                "sk.style()"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 30,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/html": [
                            "<style type=\"text/css\">\n",
                            "#T_4e63c_row0_col2 {\n",
                            "  background-color: #dbdcde;\n",
                            "  color: #000000;\n",
                            "  text-decoration: underline;\n",
                            "  font-style: italic;\n",
                            "  font-weight: bold;\n",
                            "}\n",
                            "#T_4e63c_row0_col3, #T_4e63c_row0_col4, #T_4e63c_row0_col5, #T_4e63c_row0_col7, #T_4e63c_row0_col8, #T_4e63c_row1_col6 {\n",
                            "  background-color: #fff7ec;\n",
                            "  color: #000000;\n",
                            "  text-decoration: underline;\n",
                            "  font-style: italic;\n",
                            "  font-weight: bold;\n",
                            "}\n",
                            "#T_4e63c_row0_col6, #T_4e63c_row1_col3, #T_4e63c_row1_col4, #T_4e63c_row1_col5, #T_4e63c_row1_col7, #T_4e63c_row1_col8 {\n",
                            "  background-color: #7f0000;\n",
                            "  color: #f1f1f1;\n",
                            "}\n",
                            "#T_4e63c_row1_col2 {\n",
                            "  background-color: #b40426;\n",
                            "  color: #f1f1f1;\n",
                            "}\n",
                            "</style>\n",
                            "<table id=\"T_4e63c\">\n",
                            "  <thead>\n",
                            "    <tr>\n",
                            "      <th class=\"blank level0\" >&nbsp;</th>\n",
                            "      <th id=\"T_4e63c_level0_col0\" class=\"col_heading level0 col0\" >observation</th>\n",
                            "      <th id=\"T_4e63c_level0_col1\" class=\"col_heading level0 col1\" >n</th>\n",
                            "      <th id=\"T_4e63c_level0_col2\" class=\"col_heading level0 col2\" >bias</th>\n",
                            "      <th id=\"T_4e63c_level0_col3\" class=\"col_heading level0 col3\" >rmse</th>\n",
                            "      <th id=\"T_4e63c_level0_col4\" class=\"col_heading level0 col4\" >urmse</th>\n",
                            "      <th id=\"T_4e63c_level0_col5\" class=\"col_heading level0 col5\" >mae</th>\n",
                            "      <th id=\"T_4e63c_level0_col6\" class=\"col_heading level0 col6\" >cc</th>\n",
                            "      <th id=\"T_4e63c_level0_col7\" class=\"col_heading level0 col7\" >si</th>\n",
                            "      <th id=\"T_4e63c_level0_col8\" class=\"col_heading level0 col8\" >r2</th>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th class=\"index_name level0\" >model</th>\n",
                            "      <th class=\"blank col0\" >&nbsp;</th>\n",
                            "      <th class=\"blank col1\" >&nbsp;</th>\n",
                            "      <th class=\"blank col2\" >&nbsp;</th>\n",
                            "      <th class=\"blank col3\" >&nbsp;</th>\n",
                            "      <th class=\"blank col4\" >&nbsp;</th>\n",
                            "      <th class=\"blank col5\" >&nbsp;</th>\n",
                            "      <th class=\"blank col6\" >&nbsp;</th>\n",
                            "      <th class=\"blank col7\" >&nbsp;</th>\n",
                            "      <th class=\"blank col8\" >&nbsp;</th>\n",
                            "    </tr>\n",
                            "  </thead>\n",
                            "  <tbody>\n",
                            "    <tr>\n",
                            "      <th id=\"T_4e63c_level0_row0\" class=\"row_heading level0 row0\" >SW_1</th>\n",
                            "      <td id=\"T_4e63c_row0_col0\" class=\"data row0 col0\" >c2_Hm0</td>\n",
                            "      <td id=\"T_4e63c_row0_col1\" class=\"data row0 col1\" >113</td>\n",
                            "      <td id=\"T_4e63c_row0_col2\" class=\"data row0 col2\" >-0.001</td>\n",
                            "      <td id=\"T_4e63c_row0_col3\" class=\"data row0 col3\" >0.352</td>\n",
                            "      <td id=\"T_4e63c_row0_col4\" class=\"data row0 col4\" >0.352</td>\n",
                            "      <td id=\"T_4e63c_row0_col5\" class=\"data row0 col5\" >0.295</td>\n",
                            "      <td id=\"T_4e63c_row0_col6\" class=\"data row0 col6\" >0.974</td>\n",
                            "      <td id=\"T_4e63c_row0_col7\" class=\"data row0 col7\" >0.128</td>\n",
                            "      <td id=\"T_4e63c_row0_col8\" class=\"data row0 col8\" >0.900</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th id=\"T_4e63c_level0_row1\" class=\"row_heading level0 row1\" >SW_2</th>\n",
                            "      <td id=\"T_4e63c_row1_col0\" class=\"data row1 col0\" >c2_Hm0</td>\n",
                            "      <td id=\"T_4e63c_row1_col1\" class=\"data row1 col1\" >113</td>\n",
                            "      <td id=\"T_4e63c_row1_col2\" class=\"data row1 col2\" >0.081</td>\n",
                            "      <td id=\"T_4e63c_row1_col3\" class=\"data row1 col3\" >0.430</td>\n",
                            "      <td id=\"T_4e63c_row1_col4\" class=\"data row1 col4\" >0.422</td>\n",
                            "      <td id=\"T_4e63c_row1_col5\" class=\"data row1 col5\" >0.357</td>\n",
                            "      <td id=\"T_4e63c_row1_col6\" class=\"data row1 col6\" >0.974</td>\n",
                            "      <td id=\"T_4e63c_row1_col7\" class=\"data row1 col7\" >0.153</td>\n",
                            "      <td id=\"T_4e63c_row1_col8\" class=\"data row1 col8\" >0.850</td>\n",
                            "    </tr>\n",
                            "  </tbody>\n",
                            "</table>\n"
                        ],
                        "text/plain": [
                            "<pandas.io.formats.style.Styler at 0x7f55b83a3f70>"
                        ]
                    },
                    "execution_count": 30,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "sk.sel(observation='c2_Hm0').style(columns='rmse')"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 31,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "image/png": "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",
                        "text/plain": [
                            "<Figure size 640x480 with 1 Axes>"
                        ]
                    },
                    "metadata": {},
                    "output_type": "display_data"
                }
            ],
            "source": [
                "sk['rmse'].plot.line(ylabel='Hm0 RMSE [m]');"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 32,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "image/png": "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",
                        "text/plain": [
                            "<Figure size 800x800 with 1 Axes>"
                        ]
                    },
                    "metadata": {},
                    "output_type": "display_data"
                }
            ],
            "source": [
                "cc.sel(model=1).plot.scatter();"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## mean skill\n",
                "The `mean_skill()` method will return a weighted average of the skill score per model and quantity. You can get the \"normal\" mean_skill (per model) by selecting a specific quantity either by id or name."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 33,
            "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 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></th>\n",
                            "      <th>n</th>\n",
                            "      <th>bias</th>\n",
                            "      <th>rmse</th>\n",
                            "      <th>urmse</th>\n",
                            "      <th>mae</th>\n",
                            "      <th>cc</th>\n",
                            "      <th>si</th>\n",
                            "      <th>r2</th>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>model</th>\n",
                            "      <th>quantity</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 rowspan=\"2\" valign=\"top\">SW_1</th>\n",
                            "      <th>Significant wave height</th>\n",
                            "      <td>566</td>\n",
                            "      <td>-0.087356</td>\n",
                            "      <td>0.309119</td>\n",
                            "      <td>0.286247</td>\n",
                            "      <td>0.244979</td>\n",
                            "      <td>0.971791</td>\n",
                            "      <td>0.101595</td>\n",
                            "      <td>0.912468</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>Wind speed</th>\n",
                            "      <td>457</td>\n",
                            "      <td>0.543226</td>\n",
                            "      <td>1.563076</td>\n",
                            "      <td>1.075053</td>\n",
                            "      <td>1.241847</td>\n",
                            "      <td>0.915916</td>\n",
                            "      <td>0.086039</td>\n",
                            "      <td>0.652388</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th rowspan=\"2\" valign=\"top\">SW_2</th>\n",
                            "      <th>Significant wave height</th>\n",
                            "      <td>566</td>\n",
                            "      <td>-0.006398</td>\n",
                            "      <td>0.318593</td>\n",
                            "      <td>0.310086</td>\n",
                            "      <td>0.256618</td>\n",
                            "      <td>0.971791</td>\n",
                            "      <td>0.110653</td>\n",
                            "      <td>0.903722</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>Wind speed</th>\n",
                            "      <td>457</td>\n",
                            "      <td>0.543226</td>\n",
                            "      <td>1.563076</td>\n",
                            "      <td>1.075053</td>\n",
                            "      <td>1.241847</td>\n",
                            "      <td>0.915916</td>\n",
                            "      <td>0.086039</td>\n",
                            "      <td>0.652388</td>\n",
                            "    </tr>\n",
                            "  </tbody>\n",
                            "</table>\n",
                            "</div>"
                        ],
                        "text/plain": [
                            "                                 n      bias      rmse     urmse       mae  \\\n",
                            "model quantity                                                               \n",
                            "SW_1  Significant wave height  566 -0.087356  0.309119  0.286247  0.244979   \n",
                            "      Wind speed               457  0.543226  1.563076  1.075053  1.241847   \n",
                            "SW_2  Significant wave height  566 -0.006398  0.318593  0.310086  0.256618   \n",
                            "      Wind speed               457  0.543226  1.563076  1.075053  1.241847   \n",
                            "\n",
                            "                                     cc        si        r2  \n",
                            "model quantity                                               \n",
                            "SW_1  Significant wave height  0.971791  0.101595  0.912468  \n",
                            "      Wind speed               0.915916  0.086039  0.652388  \n",
                            "SW_2  Significant wave height  0.971791  0.110653  0.903722  \n",
                            "      Wind speed               0.915916  0.086039  0.652388  "
                        ]
                    },
                    "execution_count": 33,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "sk = cc.mean_skill()\n",
                "sk"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 34,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "image/png": "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",
                        "text/plain": [
                            "<Figure size 640x480 with 1 Axes>"
                        ]
                    },
                    "metadata": {},
                    "output_type": "display_data"
                }
            ],
            "source": [
                "sk['si'].plot.bar(title='scatter index');"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 35,
            "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 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</th>\n",
                            "      <th>bias</th>\n",
                            "      <th>rmse</th>\n",
                            "      <th>urmse</th>\n",
                            "      <th>mae</th>\n",
                            "      <th>cc</th>\n",
                            "      <th>si</th>\n",
                            "      <th>r2</th>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>quantity</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>Significant wave height</th>\n",
                            "      <td>566</td>\n",
                            "      <td>-0.006398</td>\n",
                            "      <td>0.318593</td>\n",
                            "      <td>0.310086</td>\n",
                            "      <td>0.256618</td>\n",
                            "      <td>0.971791</td>\n",
                            "      <td>0.110653</td>\n",
                            "      <td>0.903722</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>Wind speed</th>\n",
                            "      <td>457</td>\n",
                            "      <td>0.543226</td>\n",
                            "      <td>1.563076</td>\n",
                            "      <td>1.075053</td>\n",
                            "      <td>1.241847</td>\n",
                            "      <td>0.915916</td>\n",
                            "      <td>0.086039</td>\n",
                            "      <td>0.652388</td>\n",
                            "    </tr>\n",
                            "  </tbody>\n",
                            "</table>\n",
                            "</div>"
                        ],
                        "text/plain": [
                            "                           n      bias      rmse     urmse       mae  \\\n",
                            "quantity                                                               \n",
                            "Significant wave height  566 -0.006398  0.318593  0.310086  0.256618   \n",
                            "Wind speed               457  0.543226  1.563076  1.075053  1.241847   \n",
                            "\n",
                            "                               cc        si        r2  \n",
                            "quantity                                               \n",
                            "Significant wave height  0.971791  0.110653  0.903722  \n",
                            "Wind speed               0.915916  0.086039  0.652388  "
                        ]
                    },
                    "execution_count": 35,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "cc.sel(model='SW_2').mean_skill()"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 36,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/html": [
                            "<style type=\"text/css\">\n",
                            "#T_0a5a3_row0_col1 {\n",
                            "  background-color: #3b4cc0;\n",
                            "  color: #f1f1f1;\n",
                            "}\n",
                            "#T_0a5a3_row0_col2, #T_0a5a3_row0_col3, #T_0a5a3_row0_col4, #T_0a5a3_row0_col5, #T_0a5a3_row0_col6, #T_0a5a3_row0_col7 {\n",
                            "  background-color: #fff7ec;\n",
                            "  color: #000000;\n",
                            "  text-decoration: underline;\n",
                            "  font-style: italic;\n",
                            "  font-weight: bold;\n",
                            "}\n",
                            "#T_0a5a3_row1_col1 {\n",
                            "  background-color: #d3dbe7;\n",
                            "  color: #000000;\n",
                            "  text-decoration: underline;\n",
                            "  font-style: italic;\n",
                            "  font-weight: bold;\n",
                            "}\n",
                            "#T_0a5a3_row1_col2, #T_0a5a3_row1_col3, #T_0a5a3_row1_col4, #T_0a5a3_row1_col5, #T_0a5a3_row1_col6, #T_0a5a3_row1_col7 {\n",
                            "  background-color: #7f0000;\n",
                            "  color: #f1f1f1;\n",
                            "}\n",
                            "</style>\n",
                            "<table id=\"T_0a5a3\">\n",
                            "  <thead>\n",
                            "    <tr>\n",
                            "      <th class=\"blank level0\" >&nbsp;</th>\n",
                            "      <th id=\"T_0a5a3_level0_col0\" class=\"col_heading level0 col0\" >n</th>\n",
                            "      <th id=\"T_0a5a3_level0_col1\" class=\"col_heading level0 col1\" >bias</th>\n",
                            "      <th id=\"T_0a5a3_level0_col2\" class=\"col_heading level0 col2\" >rmse</th>\n",
                            "      <th id=\"T_0a5a3_level0_col3\" class=\"col_heading level0 col3\" >urmse</th>\n",
                            "      <th id=\"T_0a5a3_level0_col4\" class=\"col_heading level0 col4\" >mae</th>\n",
                            "      <th id=\"T_0a5a3_level0_col5\" class=\"col_heading level0 col5\" >cc</th>\n",
                            "      <th id=\"T_0a5a3_level0_col6\" class=\"col_heading level0 col6\" >si</th>\n",
                            "      <th id=\"T_0a5a3_level0_col7\" class=\"col_heading level0 col7\" >r2</th>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th class=\"index_name level0\" >model</th>\n",
                            "      <th class=\"blank col0\" >&nbsp;</th>\n",
                            "      <th class=\"blank col1\" >&nbsp;</th>\n",
                            "      <th class=\"blank col2\" >&nbsp;</th>\n",
                            "      <th class=\"blank col3\" >&nbsp;</th>\n",
                            "      <th class=\"blank col4\" >&nbsp;</th>\n",
                            "      <th class=\"blank col5\" >&nbsp;</th>\n",
                            "      <th class=\"blank col6\" >&nbsp;</th>\n",
                            "      <th class=\"blank col7\" >&nbsp;</th>\n",
                            "    </tr>\n",
                            "  </thead>\n",
                            "  <tbody>\n",
                            "    <tr>\n",
                            "      <th id=\"T_0a5a3_level0_row0\" class=\"row_heading level0 row0\" >SW_1</th>\n",
                            "      <td id=\"T_0a5a3_row0_col0\" class=\"data row0 col0\" >566</td>\n",
                            "      <td id=\"T_0a5a3_row0_col1\" class=\"data row0 col1\" >-0.087</td>\n",
                            "      <td id=\"T_0a5a3_row0_col2\" class=\"data row0 col2\" >0.309</td>\n",
                            "      <td id=\"T_0a5a3_row0_col3\" class=\"data row0 col3\" >0.286</td>\n",
                            "      <td id=\"T_0a5a3_row0_col4\" class=\"data row0 col4\" >0.245</td>\n",
                            "      <td id=\"T_0a5a3_row0_col5\" class=\"data row0 col5\" >0.972</td>\n",
                            "      <td id=\"T_0a5a3_row0_col6\" class=\"data row0 col6\" >0.102</td>\n",
                            "      <td id=\"T_0a5a3_row0_col7\" class=\"data row0 col7\" >0.912</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th id=\"T_0a5a3_level0_row1\" class=\"row_heading level0 row1\" >SW_2</th>\n",
                            "      <td id=\"T_0a5a3_row1_col0\" class=\"data row1 col0\" >566</td>\n",
                            "      <td id=\"T_0a5a3_row1_col1\" class=\"data row1 col1\" >-0.006</td>\n",
                            "      <td id=\"T_0a5a3_row1_col2\" class=\"data row1 col2\" >0.319</td>\n",
                            "      <td id=\"T_0a5a3_row1_col3\" class=\"data row1 col3\" >0.310</td>\n",
                            "      <td id=\"T_0a5a3_row1_col4\" class=\"data row1 col4\" >0.257</td>\n",
                            "      <td id=\"T_0a5a3_row1_col5\" class=\"data row1 col5\" >0.972</td>\n",
                            "      <td id=\"T_0a5a3_row1_col6\" class=\"data row1 col6\" >0.111</td>\n",
                            "      <td id=\"T_0a5a3_row1_col7\" class=\"data row1 col7\" >0.904</td>\n",
                            "    </tr>\n",
                            "  </tbody>\n",
                            "</table>\n"
                        ],
                        "text/plain": [
                            "<pandas.io.formats.style.Styler at 0x7f55b8fa24d0>"
                        ]
                    },
                    "execution_count": 36,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "cc.sel(quantity='Significant wave height').mean_skill().style(columns=[])"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## score\n",
                "\n",
                "**Note:** The score is a single metric for each model, aggregating all quantities."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 37,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "{'SW_1': 0.9360973356120318, 'SW_2': 0.9408344041671327}"
                        ]
                    },
                    "execution_count": 37,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "cc.score()"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "To get the score for a specific varibable, it is possible to filter using the `.sel` method."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 38,
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "{'SW_1': 1.5630757282647778, 'SW_2': 1.5630757282647778}"
                        ]
                    },
                    "execution_count": 38,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "cc.sel(quantity='Wind speed').score()"
            ]
        }
    ],
    "metadata": {
        "kernelspec": {
            "display_name": "base",
            "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": "3.10.12"
        },
        "orig_nbformat": 2,
        "vscode": {
            "interpreter": {
                "hash": "7aec4f91c09090e98e6ae8203c38529831bb4a3ce54cd1b69639b53cb01a6aa9"
            }
        }
    },
    "nbformat": 4,
    "nbformat_minor": 2
}