From b1dee5d7c6e7a8a606a2e9ff79fa72592a8c8395 Mon Sep 17 00:00:00 2001
From: Alba Vilanova Cortezon <alba.vilanova@outlook.com>
Date: Mon, 8 Jul 2024 14:49:06 +0200
Subject: [PATCH] Update tutorial

---
 .../2.Creation/2.3.Create_Points_XVPCA.ipynb  | 1327 ++++++++++++++---
 1 file changed, 1113 insertions(+), 214 deletions(-)

diff --git a/tutorials/2.Creation/2.3.Create_Points_XVPCA.ipynb b/tutorials/2.Creation/2.3.Create_Points_XVPCA.ipynb
index f5eca19..1055297 100644
--- a/tutorials/2.Creation/2.3.Create_Points_XVPCA.ipynb
+++ b/tutorials/2.Creation/2.3.Create_Points_XVPCA.ipynb
@@ -528,6 +528,612 @@
     "df_pm10"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_pm10 = df_pm10.set_index('Estació')\n",
+    "df_pm10.iloc[1] = df_pm10.columns\n",
+    "df_pm10.columns = df_pm10.iloc[0]\n",
+    "df_pm10 = df_pm10[1:]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "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>Codi europeu</th>\n",
+       "      <th>ES1438A</th>\n",
+       "      <th>ES1928A</th>\n",
+       "      <th>ES2027A</th>\n",
+       "      <th>ES0559A</th>\n",
+       "      <th>ES0691A</th>\n",
+       "      <th>ES0567A</th>\n",
+       "      <th>ES1870A</th>\n",
+       "      <th>ES1852A</th>\n",
+       "      <th>ES1900A</th>\n",
+       "      <th>ES1843A</th>\n",
+       "      <th>...</th>\n",
+       "      <th>ES1123A</th>\n",
+       "      <th>ES1117A</th>\n",
+       "      <th>ES2033A</th>\n",
+       "      <th>ES2011A</th>\n",
+       "      <th>ES1982A</th>\n",
+       "      <th>ES1778A</th>\n",
+       "      <th>ES1680A</th>\n",
+       "      <th>ES1362A</th>\n",
+       "      <th>ES9994A</th>\n",
+       "      <th>ES1874A</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Estació</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>Dia</th>\n",
+       "      <td>PM10 Barcelona (Eixample)</td>\n",
+       "      <td>PM10 Badalona (guàrdia urbana)</td>\n",
+       "      <td>PM10 Badalona (Assamblea de Catalunya)</td>\n",
+       "      <td>PM10 Barcelona (Pl. de la Universitat)</td>\n",
+       "      <td>PM10 Barcelona (Poblenou)</td>\n",
+       "      <td>PM10 Barcelona (Zona Universitària)</td>\n",
+       "      <td>PM10 Barcelona (el Port Vell)</td>\n",
+       "      <td>PM10 Barcelona (IES Goya)</td>\n",
+       "      <td>PM10 Barcelona (IES Verdaguer)</td>\n",
+       "      <td>PM10 Berga (IES Guillem de Berguedà)</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PM10 Constantí (Gaudí)</td>\n",
+       "      <td>PM10 Vila-seca (RENFE)</td>\n",
+       "      <td>PM10 Sitges (Vallcarca-oficines)</td>\n",
+       "      <td>PM10 Sant Vicenç dels Horts (Àlaba)</td>\n",
+       "      <td>PM10 Montsec (OAM)</td>\n",
+       "      <td>PM10 Montseny (la Castanya)</td>\n",
+       "      <td>PM10 Caldes de Montbui (Ajuntament)</td>\n",
+       "      <td>PM10 Sant Feliu de Llobregat (Eugeni d'Ors)</td>\n",
+       "      <td>PM 10 La Seu d'Urgell (CC Les Monges)</td>\n",
+       "      <td>PM10 Vic (Centre Cívic Santa Anna)</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-01-01 00:00:00</th>\n",
+       "      <td>19.6</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>20</td>\n",
+       "      <td>20.2</td>\n",
+       "      <td>25.6</td>\n",
+       "      <td>16.5</td>\n",
+       "      <td>29</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>23.8</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>12.97</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>11</td>\n",
+       "      <td>22.49</td>\n",
+       "      <td>9.500299</td>\n",
+       "      <td>7.936455</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-01-02 00:00:00</th>\n",
+       "      <td>27.2</td>\n",
+       "      <td>20.86</td>\n",
+       "      <td>23</td>\n",
+       "      <td>31.6</td>\n",
+       "      <td>35</td>\n",
+       "      <td>22.8</td>\n",
+       "      <td>28</td>\n",
+       "      <td>17.2</td>\n",
+       "      <td>32.4</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>25.38</td>\n",
+       "      <td>26</td>\n",
+       "      <td>25.39</td>\n",
+       "      <td>1.829618</td>\n",
+       "      <td>9.787004</td>\n",
+       "      <td>32</td>\n",
+       "      <td>22.06</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-01-03 00:00:00</th>\n",
+       "      <td>35.7</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>32</td>\n",
+       "      <td>37</td>\n",
+       "      <td>36.2</td>\n",
+       "      <td>30.9</td>\n",
+       "      <td>31</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>35.8</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>21.8</td>\n",
+       "      <td>36.49</td>\n",
+       "      <td>48</td>\n",
+       "      <td>30.65</td>\n",
+       "      <td>8.094607</td>\n",
+       "      <td>16.97829</td>\n",
+       "      <td>43</td>\n",
+       "      <td>35.84</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-01-04 00:00:00</th>\n",
+       "      <td>30.9</td>\n",
+       "      <td>34.49</td>\n",
+       "      <td>35</td>\n",
+       "      <td>32</td>\n",
+       "      <td>39.3</td>\n",
+       "      <td>26.8</td>\n",
+       "      <td>32</td>\n",
+       "      <td>30.3</td>\n",
+       "      <td>39.4</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>29.17</td>\n",
+       "      <td>34.33</td>\n",
+       "      <td>47</td>\n",
+       "      <td>39.54</td>\n",
+       "      <td>4.377368</td>\n",
+       "      <td>12.56556</td>\n",
+       "      <td>NaN</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",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-12-27 00:00:00</th>\n",
+       "      <td>17.5</td>\n",
+       "      <td>7.59</td>\n",
+       "      <td>10</td>\n",
+       "      <td>16.9</td>\n",
+       "      <td>14</td>\n",
+       "      <td>13.1</td>\n",
+       "      <td>21</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>20.8</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>12</td>\n",
+       "      <td>22.95</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3.066751</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>10.3</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-12-28 00:00:00</th>\n",
+       "      <td>17</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>14</td>\n",
+       "      <td>17.9</td>\n",
+       "      <td>15</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>13</td>\n",
+       "      <td>14.5</td>\n",
+       "      <td>16</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>6.5</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>9.976</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3.351872</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>26.81</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-12-29 00:00:00</th>\n",
+       "      <td>24.6</td>\n",
+       "      <td>21</td>\n",
+       "      <td>24</td>\n",
+       "      <td>23.2</td>\n",
+       "      <td>25.8</td>\n",
+       "      <td>15.3</td>\n",
+       "      <td>21</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>25.9</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>8.86</td>\n",
+       "      <td>9.56</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>23.76</td>\n",
+       "      <td>1</td>\n",
+       "      <td>4.219732</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>14.09</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-12-30 00:00:00</th>\n",
+       "      <td>27.4</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>15</td>\n",
+       "      <td>22.3</td>\n",
+       "      <td>16.6</td>\n",
+       "      <td>11.2</td>\n",
+       "      <td>16</td>\n",
+       "      <td>10.7</td>\n",
+       "      <td>18.8</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>19.04</td>\n",
+       "      <td>1.091187</td>\n",
+       "      <td>4.713029</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-12-31 00:00:00</th>\n",
+       "      <td>17.3</td>\n",
+       "      <td>12.5</td>\n",
+       "      <td>13</td>\n",
+       "      <td>16.3</td>\n",
+       "      <td>17.6</td>\n",
+       "      <td>9.9</td>\n",
+       "      <td>14</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>17.4</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>12.77</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>15.23</td>\n",
+       "      <td>2.15659</td>\n",
+       "      <td>5.024302</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>366 rows × 83 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "Codi europeu                           ES1438A  \\\n",
+       "Estació                                          \n",
+       "Dia                  PM10 Barcelona (Eixample)   \n",
+       "2017-01-01 00:00:00                       19.6   \n",
+       "2017-01-02 00:00:00                       27.2   \n",
+       "2017-01-03 00:00:00                       35.7   \n",
+       "2017-01-04 00:00:00                       30.9   \n",
+       "...                                        ...   \n",
+       "2017-12-27 00:00:00                       17.5   \n",
+       "2017-12-28 00:00:00                         17   \n",
+       "2017-12-29 00:00:00                       24.6   \n",
+       "2017-12-30 00:00:00                       27.4   \n",
+       "2017-12-31 00:00:00                       17.3   \n",
+       "\n",
+       "Codi europeu                                ES1928A  \\\n",
+       "Estació                                               \n",
+       "Dia                  PM10 Badalona (guàrdia urbana)   \n",
+       "2017-01-01 00:00:00                             NaN   \n",
+       "2017-01-02 00:00:00                           20.86   \n",
+       "2017-01-03 00:00:00                             NaN   \n",
+       "2017-01-04 00:00:00                           34.49   \n",
+       "...                                             ...   \n",
+       "2017-12-27 00:00:00                            7.59   \n",
+       "2017-12-28 00:00:00                             NaN   \n",
+       "2017-12-29 00:00:00                              21   \n",
+       "2017-12-30 00:00:00                             NaN   \n",
+       "2017-12-31 00:00:00                            12.5   \n",
+       "\n",
+       "Codi europeu                                        ES2027A  \\\n",
+       "Estació                                                       \n",
+       "Dia                  PM10 Badalona (Assamblea de Catalunya)   \n",
+       "2017-01-01 00:00:00                                      20   \n",
+       "2017-01-02 00:00:00                                      23   \n",
+       "2017-01-03 00:00:00                                      32   \n",
+       "2017-01-04 00:00:00                                      35   \n",
+       "...                                                     ...   \n",
+       "2017-12-27 00:00:00                                      10   \n",
+       "2017-12-28 00:00:00                                      14   \n",
+       "2017-12-29 00:00:00                                      24   \n",
+       "2017-12-30 00:00:00                                      15   \n",
+       "2017-12-31 00:00:00                                      13   \n",
+       "\n",
+       "Codi europeu                                        ES0559A  \\\n",
+       "Estació                                                       \n",
+       "Dia                  PM10 Barcelona (Pl. de la Universitat)   \n",
+       "2017-01-01 00:00:00                                    20.2   \n",
+       "2017-01-02 00:00:00                                    31.6   \n",
+       "2017-01-03 00:00:00                                      37   \n",
+       "2017-01-04 00:00:00                                      32   \n",
+       "...                                                     ...   \n",
+       "2017-12-27 00:00:00                                    16.9   \n",
+       "2017-12-28 00:00:00                                    17.9   \n",
+       "2017-12-29 00:00:00                                    23.2   \n",
+       "2017-12-30 00:00:00                                    22.3   \n",
+       "2017-12-31 00:00:00                                    16.3   \n",
+       "\n",
+       "Codi europeu                           ES0691A  \\\n",
+       "Estació                                          \n",
+       "Dia                  PM10 Barcelona (Poblenou)   \n",
+       "2017-01-01 00:00:00                       25.6   \n",
+       "2017-01-02 00:00:00                         35   \n",
+       "2017-01-03 00:00:00                       36.2   \n",
+       "2017-01-04 00:00:00                       39.3   \n",
+       "...                                        ...   \n",
+       "2017-12-27 00:00:00                         14   \n",
+       "2017-12-28 00:00:00                         15   \n",
+       "2017-12-29 00:00:00                       25.8   \n",
+       "2017-12-30 00:00:00                       16.6   \n",
+       "2017-12-31 00:00:00                       17.6   \n",
+       "\n",
+       "Codi europeu                                     ES0567A  \\\n",
+       "Estació                                                    \n",
+       "Dia                  PM10 Barcelona (Zona Universitària)   \n",
+       "2017-01-01 00:00:00                                 16.5   \n",
+       "2017-01-02 00:00:00                                 22.8   \n",
+       "2017-01-03 00:00:00                                 30.9   \n",
+       "2017-01-04 00:00:00                                 26.8   \n",
+       "...                                                  ...   \n",
+       "2017-12-27 00:00:00                                 13.1   \n",
+       "2017-12-28 00:00:00                                  NaN   \n",
+       "2017-12-29 00:00:00                                 15.3   \n",
+       "2017-12-30 00:00:00                                 11.2   \n",
+       "2017-12-31 00:00:00                                  9.9   \n",
+       "\n",
+       "Codi europeu                               ES1870A                    ES1852A  \\\n",
+       "Estació                                                                         \n",
+       "Dia                  PM10 Barcelona (el Port Vell)  PM10 Barcelona (IES Goya)   \n",
+       "2017-01-01 00:00:00                             29                        NaN   \n",
+       "2017-01-02 00:00:00                             28                       17.2   \n",
+       "2017-01-03 00:00:00                             31                        NaN   \n",
+       "2017-01-04 00:00:00                             32                       30.3   \n",
+       "...                                            ...                        ...   \n",
+       "2017-12-27 00:00:00                             21                        NaN   \n",
+       "2017-12-28 00:00:00                             13                       14.5   \n",
+       "2017-12-29 00:00:00                             21                        NaN   \n",
+       "2017-12-30 00:00:00                             16                       10.7   \n",
+       "2017-12-31 00:00:00                             14                        NaN   \n",
+       "\n",
+       "Codi europeu                                ES1900A  \\\n",
+       "Estació                                               \n",
+       "Dia                  PM10 Barcelona (IES Verdaguer)   \n",
+       "2017-01-01 00:00:00                            23.8   \n",
+       "2017-01-02 00:00:00                            32.4   \n",
+       "2017-01-03 00:00:00                            35.8   \n",
+       "2017-01-04 00:00:00                            39.4   \n",
+       "...                                             ...   \n",
+       "2017-12-27 00:00:00                            20.8   \n",
+       "2017-12-28 00:00:00                              16   \n",
+       "2017-12-29 00:00:00                            25.9   \n",
+       "2017-12-30 00:00:00                            18.8   \n",
+       "2017-12-31 00:00:00                            17.4   \n",
+       "\n",
+       "Codi europeu                                      ES1843A  ...  \\\n",
+       "Estació                                                    ...   \n",
+       "Dia                  PM10 Berga (IES Guillem de Berguedà)  ...   \n",
+       "2017-01-01 00:00:00                                   NaN  ...   \n",
+       "2017-01-02 00:00:00                                   NaN  ...   \n",
+       "2017-01-03 00:00:00                                   NaN  ...   \n",
+       "2017-01-04 00:00:00                                   NaN  ...   \n",
+       "...                                                   ...  ...   \n",
+       "2017-12-27 00:00:00                                   NaN  ...   \n",
+       "2017-12-28 00:00:00                                   NaN  ...   \n",
+       "2017-12-29 00:00:00                                   NaN  ...   \n",
+       "2017-12-30 00:00:00                                   NaN  ...   \n",
+       "2017-12-31 00:00:00                                   NaN  ...   \n",
+       "\n",
+       "Codi europeu                        ES1123A                 ES1117A  \\\n",
+       "Estació                                                               \n",
+       "Dia                  PM10 Constantí (Gaudí)  PM10 Vila-seca (RENFE)   \n",
+       "2017-01-01 00:00:00                   12.97                     NaN   \n",
+       "2017-01-02 00:00:00                     NaN                   25.38   \n",
+       "2017-01-03 00:00:00                    21.8                   36.49   \n",
+       "2017-01-04 00:00:00                   29.17                   34.33   \n",
+       "...                                     ...                     ...   \n",
+       "2017-12-27 00:00:00                      12                   22.95   \n",
+       "2017-12-28 00:00:00                     NaN                     6.5   \n",
+       "2017-12-29 00:00:00                    8.86                    9.56   \n",
+       "2017-12-30 00:00:00                     NaN                     NaN   \n",
+       "2017-12-31 00:00:00                   12.77                     NaN   \n",
+       "\n",
+       "Codi europeu                                  ES2033A  \\\n",
+       "Estació                                                 \n",
+       "Dia                  PM10 Sitges (Vallcarca-oficines)   \n",
+       "2017-01-01 00:00:00                                11   \n",
+       "2017-01-02 00:00:00                                26   \n",
+       "2017-01-03 00:00:00                                48   \n",
+       "2017-01-04 00:00:00                                47   \n",
+       "...                                               ...   \n",
+       "2017-12-27 00:00:00                               NaN   \n",
+       "2017-12-28 00:00:00                               NaN   \n",
+       "2017-12-29 00:00:00                               NaN   \n",
+       "2017-12-30 00:00:00                               NaN   \n",
+       "2017-12-31 00:00:00                               NaN   \n",
+       "\n",
+       "Codi europeu                                     ES2011A             ES1982A  \\\n",
+       "Estació                                                                        \n",
+       "Dia                  PM10 Sant Vicenç dels Horts (Àlaba)  PM10 Montsec (OAM)   \n",
+       "2017-01-01 00:00:00                                22.49            9.500299   \n",
+       "2017-01-02 00:00:00                                25.39            1.829618   \n",
+       "2017-01-03 00:00:00                                30.65            8.094607   \n",
+       "2017-01-04 00:00:00                                39.54            4.377368   \n",
+       "...                                                  ...                 ...   \n",
+       "2017-12-27 00:00:00                                  NaN                   1   \n",
+       "2017-12-28 00:00:00                                9.976                   1   \n",
+       "2017-12-29 00:00:00                                23.76                   1   \n",
+       "2017-12-30 00:00:00                                19.04            1.091187   \n",
+       "2017-12-31 00:00:00                                15.23             2.15659   \n",
+       "\n",
+       "Codi europeu                             ES1778A  \\\n",
+       "Estació                                            \n",
+       "Dia                  PM10 Montseny (la Castanya)   \n",
+       "2017-01-01 00:00:00                     7.936455   \n",
+       "2017-01-02 00:00:00                     9.787004   \n",
+       "2017-01-03 00:00:00                     16.97829   \n",
+       "2017-01-04 00:00:00                     12.56556   \n",
+       "...                                          ...   \n",
+       "2017-12-27 00:00:00                     3.066751   \n",
+       "2017-12-28 00:00:00                     3.351872   \n",
+       "2017-12-29 00:00:00                     4.219732   \n",
+       "2017-12-30 00:00:00                     4.713029   \n",
+       "2017-12-31 00:00:00                     5.024302   \n",
+       "\n",
+       "Codi europeu                                     ES1680A  \\\n",
+       "Estació                                                    \n",
+       "Dia                  PM10 Caldes de Montbui (Ajuntament)   \n",
+       "2017-01-01 00:00:00                                  NaN   \n",
+       "2017-01-02 00:00:00                                   32   \n",
+       "2017-01-03 00:00:00                                   43   \n",
+       "2017-01-04 00:00:00                                  NaN   \n",
+       "...                                                  ...   \n",
+       "2017-12-27 00:00:00                                  NaN   \n",
+       "2017-12-28 00:00:00                                  NaN   \n",
+       "2017-12-29 00:00:00                                  NaN   \n",
+       "2017-12-30 00:00:00                                  NaN   \n",
+       "2017-12-31 00:00:00                                  NaN   \n",
+       "\n",
+       "Codi europeu                                             ES1362A  \\\n",
+       "Estació                                                            \n",
+       "Dia                  PM10 Sant Feliu de Llobregat (Eugeni d'Ors)   \n",
+       "2017-01-01 00:00:00                                          NaN   \n",
+       "2017-01-02 00:00:00                                        22.06   \n",
+       "2017-01-03 00:00:00                                        35.84   \n",
+       "2017-01-04 00:00:00                                          NaN   \n",
+       "...                                                          ...   \n",
+       "2017-12-27 00:00:00                                         10.3   \n",
+       "2017-12-28 00:00:00                                        26.81   \n",
+       "2017-12-29 00:00:00                                        14.09   \n",
+       "2017-12-30 00:00:00                                          NaN   \n",
+       "2017-12-31 00:00:00                                          NaN   \n",
+       "\n",
+       "Codi europeu                                       ES9994A  \\\n",
+       "Estació                                                      \n",
+       "Dia                  PM 10 La Seu d'Urgell (CC Les Monges)   \n",
+       "2017-01-01 00:00:00                                    NaN   \n",
+       "2017-01-02 00:00:00                                    NaN   \n",
+       "2017-01-03 00:00:00                                    NaN   \n",
+       "2017-01-04 00:00:00                                    NaN   \n",
+       "...                                                    ...   \n",
+       "2017-12-27 00:00:00                                    NaN   \n",
+       "2017-12-28 00:00:00                                    NaN   \n",
+       "2017-12-29 00:00:00                                    NaN   \n",
+       "2017-12-30 00:00:00                                    NaN   \n",
+       "2017-12-31 00:00:00                                    NaN   \n",
+       "\n",
+       "Codi europeu                                    ES1874A  \n",
+       "Estació                                                  \n",
+       "Dia                  PM10 Vic (Centre Cívic Santa Anna)  \n",
+       "2017-01-01 00:00:00                                 NaN  \n",
+       "2017-01-02 00:00:00                                 NaN  \n",
+       "2017-01-03 00:00:00                                 NaN  \n",
+       "2017-01-04 00:00:00                                 NaN  \n",
+       "...                                                 ...  \n",
+       "2017-12-27 00:00:00                                 NaN  \n",
+       "2017-12-28 00:00:00                                 NaN  \n",
+       "2017-12-29 00:00:00                                 NaN  \n",
+       "2017-12-30 00:00:00                                 NaN  \n",
+       "2017-12-31 00:00:00                                 NaN  \n",
+       "\n",
+       "[366 rows x 83 columns]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_pm10"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -537,7 +1143,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -680,7 +1286,7 @@
        "[134 rows x 4 columns]"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -702,42 +1308,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array(['ES1438A', 'ES1928A', 'ES2027A', 'ES0559A', 'ES0691A', 'ES0567A',\n",
-       "       'ES1870A', 'ES1852A', 'ES1900A', 'ES1843A', 'ES1839A', 'ES0963A',\n",
-       "       'ES0266A', 'ES1891A', 'ES1135A', 'ES1397A', 'ES0392A', 'ES1861A',\n",
-       "       'ES1126A', 'ES1390A', 'ES1413A', 'ES0586A', 'ES1931A', 'ES0704A',\n",
-       "       'ES2012A', 'ES1871A', 'ES1929A', 'ES1895A', 'ES0971A', 'ES1231A',\n",
-       "       'ES1453A', 'ES0700A', 'ES1663A', 'ES1775A', 'ES1018A', 'ES1842A',\n",
-       "       'ES1887A', 'ES1936A', 'ES0991A', 'ES1999A', 'ES2034A', 'ES1588A',\n",
-       "       'ES2009A', 'ES2017A', 'ES1909A', 'ES0977A', 'ES1754A', 'ES1120A',\n",
-       "       'ES2071A', 'ES1855A', 'ES1841A', 'ES1814A', 'ES1965A', 'ES2079A',\n",
-       "       'ES1559A', 'ES1665A', 'ES1220A', 'ES1555A', 'ES1248A', 'ES1896A',\n",
-       "       'ES1480A', 'ES1856A', 'ES1851A', 'ES1964A', 'ES1225A', 'ES1312A',\n",
-       "       'ES1262A', 'ES1910A', 'ES1983A', 'ES1899A', 'ES1903A', 'ES1396A',\n",
-       "       'ES1348A', 'ES1123A', 'ES1117A', 'ES2033A', 'ES2011A', 'ES1982A',\n",
-       "       'ES1778A', 'ES1680A', 'ES1362A', 'ES9994A', 'ES1874A'],\n",
-       "      dtype=object)"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "station_codes_pm10 = df_pm10.iloc[0].values[1:]\n",
-    "station_codes_pm10"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -760,48 +1331,174 @@
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
+       "      <th>Codi europeu</th>\n",
+       "      <th>ES0266A</th>\n",
+       "      <th>ES0392A</th>\n",
+       "      <th>ES0395A</th>\n",
+       "      <th>ES0559A</th>\n",
+       "      <th>ES0567A</th>\n",
+       "      <th>ES0584A</th>\n",
+       "      <th>ES0586A</th>\n",
+       "      <th>ES0691A</th>\n",
+       "      <th>ES0692A</th>\n",
+       "      <th>ES0694A</th>\n",
+       "      <th>...</th>\n",
+       "      <th>ES2090A</th>\n",
+       "      <th>ES0554A</th>\n",
+       "      <th>ES0977A</th>\n",
+       "      <th>ES1398A</th>\n",
+       "      <th>ES1200A</th>\n",
+       "      <th>ES2087A</th>\n",
+       "      <th>ES2091A</th>\n",
+       "      <th>ES2088A</th>\n",
+       "      <th>ES1908A</th>\n",
+       "      <th>ES9994A</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Estació</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
        "      <th></th>\n",
-       "      <th>station.code</th>\n",
-       "      <th>lat</th>\n",
-       "      <th>lon</th>\n",
-       "      <th>standardised_network_provided_area_classification</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>ES0266A</td>\n",
-       "      <td>41.379322</td>\n",
-       "      <td>2.086140</td>\n",
-       "      <td>urban-centre</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>ES0392A</td>\n",
-       "      <td>41.727704</td>\n",
-       "      <td>1.838531</td>\n",
-       "      <td>urban-suburban</td>\n",
+       "      <th>Dia</th>\n",
+       "      <td>PM10 Esplugues de Llobregat (CEIP Isidre Martí)</td>\n",
+       "      <td>PM10 Manresa (CEIP La Font)</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>PM10 Barcelona (Pl. de la Universitat)</td>\n",
+       "      <td>PM10 Barcelona (Zona Universitària)</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>PM10 Molins de Rei (Ajuntament)</td>\n",
+       "      <td>PM10 Barcelona (Poblenou)</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>PM10 L'Arboç (CEIP Sant Julià)</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>PM 10 La Seu d'Urgell (CC Les Monges)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>ES0559A</td>\n",
-       "      <td>41.387424</td>\n",
-       "      <td>2.164918</td>\n",
-       "      <td>urban-centre</td>\n",
+       "      <th>2017-01-01 00:00:00</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>20.2</td>\n",
+       "      <td>16.5</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>25.6</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>29.77</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>ES0567A</td>\n",
-       "      <td>41.384906</td>\n",
-       "      <td>2.119574</td>\n",
-       "      <td>urban-centre</td>\n",
+       "      <th>2017-01-02 00:00:00</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>31.6</td>\n",
+       "      <td>22.8</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>23.82</td>\n",
+       "      <td>35</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>ES0586A</td>\n",
-       "      <td>41.413621</td>\n",
-       "      <td>2.015986</td>\n",
-       "      <td>urban-centre</td>\n",
+       "      <th>2017-01-03 00:00:00</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>27.63</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>37</td>\n",
+       "      <td>30.9</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>36.07</td>\n",
+       "      <td>36.2</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2017-01-04 00:00:00</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>32</td>\n",
+       "      <td>26.8</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>29.59</td>\n",
+       "      <td>39.3</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>28.28</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
@@ -809,85 +1506,287 @@
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>78</th>\n",
-       "      <td>ES2034A</td>\n",
-       "      <td>41.544105</td>\n",
-       "      <td>0.829933</td>\n",
-       "      <td>rural</td>\n",
+       "      <th>2017-12-27 00:00:00</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>16.9</td>\n",
+       "      <td>13.1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>6.63</td>\n",
+       "      <td>14</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>18.22</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>79</th>\n",
-       "      <td>ES2071A</td>\n",
-       "      <td>41.120064</td>\n",
-       "      <td>1.254472</td>\n",
-       "      <td>urban-centre</td>\n",
+       "      <th>2017-12-28 00:00:00</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>11.91</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>17.9</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>22.56</td>\n",
+       "      <td>15</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.74</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>80</th>\n",
-       "      <td>ES2079A</td>\n",
-       "      <td>41.559607</td>\n",
-       "      <td>1.995963</td>\n",
-       "      <td>urban-suburban</td>\n",
+       "      <th>2017-12-29 00:00:00</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>23.2</td>\n",
+       "      <td>15.3</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>16.12</td>\n",
+       "      <td>25.8</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>8.21</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>81</th>\n",
-       "      <td>ES0977A</td>\n",
-       "      <td>41.604722</td>\n",
-       "      <td>1.604722</td>\n",
+       "      <th>2017-12-30 00:00:00</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>23.71</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>22.3</td>\n",
+       "      <td>11.2</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>16.6</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>82</th>\n",
-       "      <td>ES9994A</td>\n",
-       "      <td>42.358363</td>\n",
-       "      <td>1.459455</td>\n",
+       "      <th>2017-12-31 00:00:00</th>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>16.3</td>\n",
+       "      <td>9.9</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>17.6</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>83 rows × 4 columns</p>\n",
+       "<p>366 rows × 134 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "   station.code        lat       lon  \\\n",
-       "0       ES0266A  41.379322  2.086140   \n",
-       "1       ES0392A  41.727704  1.838531   \n",
-       "2       ES0559A  41.387424  2.164918   \n",
-       "3       ES0567A  41.384906  2.119574   \n",
-       "4       ES0586A  41.413621  2.015986   \n",
-       "..          ...        ...       ...   \n",
-       "78      ES2034A  41.544105  0.829933   \n",
-       "79      ES2071A  41.120064  1.254472   \n",
-       "80      ES2079A  41.559607  1.995963   \n",
-       "81      ES0977A  41.604722  1.604722   \n",
-       "82      ES9994A  42.358363  1.459455   \n",
+       "Codi europeu                                                 ES0266A  \\\n",
+       "Estació                                                                \n",
+       "Dia                  PM10 Esplugues de Llobregat (CEIP Isidre Martí)   \n",
+       "2017-01-01 00:00:00                                              NaN   \n",
+       "2017-01-02 00:00:00                                              NaN   \n",
+       "2017-01-03 00:00:00                                              NaN   \n",
+       "2017-01-04 00:00:00                                              NaN   \n",
+       "...                                                              ...   \n",
+       "2017-12-27 00:00:00                                              NaN   \n",
+       "2017-12-28 00:00:00                                              NaN   \n",
+       "2017-12-29 00:00:00                                              NaN   \n",
+       "2017-12-30 00:00:00                                              NaN   \n",
+       "2017-12-31 00:00:00                                              NaN   \n",
        "\n",
-       "   standardised_network_provided_area_classification  \n",
-       "0                                       urban-centre  \n",
-       "1                                     urban-suburban  \n",
-       "2                                       urban-centre  \n",
-       "3                                       urban-centre  \n",
-       "4                                       urban-centre  \n",
-       "..                                               ...  \n",
-       "78                                             rural  \n",
-       "79                                      urban-centre  \n",
-       "80                                    urban-suburban  \n",
-       "81                                               NaN  \n",
-       "82                                               NaN  \n",
+       "Codi europeu                             ES0392A  ES0395A  \\\n",
+       "Estació                                                     \n",
+       "Dia                  PM10 Manresa (CEIP La Font)      NaN   \n",
+       "2017-01-01 00:00:00                          NaN      NaN   \n",
+       "2017-01-02 00:00:00                          NaN      NaN   \n",
+       "2017-01-03 00:00:00                        27.63      NaN   \n",
+       "2017-01-04 00:00:00                          NaN      NaN   \n",
+       "...                                          ...      ...   \n",
+       "2017-12-27 00:00:00                          NaN      NaN   \n",
+       "2017-12-28 00:00:00                        11.91      NaN   \n",
+       "2017-12-29 00:00:00                          NaN      NaN   \n",
+       "2017-12-30 00:00:00                        23.71      NaN   \n",
+       "2017-12-31 00:00:00                          NaN      NaN   \n",
        "\n",
-       "[83 rows x 4 columns]"
+       "Codi europeu                                        ES0559A  \\\n",
+       "Estació                                                       \n",
+       "Dia                  PM10 Barcelona (Pl. de la Universitat)   \n",
+       "2017-01-01 00:00:00                                    20.2   \n",
+       "2017-01-02 00:00:00                                    31.6   \n",
+       "2017-01-03 00:00:00                                      37   \n",
+       "2017-01-04 00:00:00                                      32   \n",
+       "...                                                     ...   \n",
+       "2017-12-27 00:00:00                                    16.9   \n",
+       "2017-12-28 00:00:00                                    17.9   \n",
+       "2017-12-29 00:00:00                                    23.2   \n",
+       "2017-12-30 00:00:00                                    22.3   \n",
+       "2017-12-31 00:00:00                                    16.3   \n",
+       "\n",
+       "Codi europeu                                     ES0567A  ES0584A  \\\n",
+       "Estació                                                             \n",
+       "Dia                  PM10 Barcelona (Zona Universitària)      NaN   \n",
+       "2017-01-01 00:00:00                                 16.5      NaN   \n",
+       "2017-01-02 00:00:00                                 22.8      NaN   \n",
+       "2017-01-03 00:00:00                                 30.9      NaN   \n",
+       "2017-01-04 00:00:00                                 26.8      NaN   \n",
+       "...                                                  ...      ...   \n",
+       "2017-12-27 00:00:00                                 13.1      NaN   \n",
+       "2017-12-28 00:00:00                                  NaN      NaN   \n",
+       "2017-12-29 00:00:00                                 15.3      NaN   \n",
+       "2017-12-30 00:00:00                                 11.2      NaN   \n",
+       "2017-12-31 00:00:00                                  9.9      NaN   \n",
+       "\n",
+       "Codi europeu                                 ES0586A  \\\n",
+       "Estació                                                \n",
+       "Dia                  PM10 Molins de Rei (Ajuntament)   \n",
+       "2017-01-01 00:00:00                              NaN   \n",
+       "2017-01-02 00:00:00                            23.82   \n",
+       "2017-01-03 00:00:00                            36.07   \n",
+       "2017-01-04 00:00:00                            29.59   \n",
+       "...                                              ...   \n",
+       "2017-12-27 00:00:00                             6.63   \n",
+       "2017-12-28 00:00:00                            22.56   \n",
+       "2017-12-29 00:00:00                            16.12   \n",
+       "2017-12-30 00:00:00                              NaN   \n",
+       "2017-12-31 00:00:00                              NaN   \n",
+       "\n",
+       "Codi europeu                           ES0691A  ES0692A  ES0694A  ... ES2090A  \\\n",
+       "Estació                                                           ...           \n",
+       "Dia                  PM10 Barcelona (Poblenou)      NaN      NaN  ...     NaN   \n",
+       "2017-01-01 00:00:00                       25.6      NaN      NaN  ...     NaN   \n",
+       "2017-01-02 00:00:00                         35      NaN      NaN  ...     NaN   \n",
+       "2017-01-03 00:00:00                       36.2      NaN      NaN  ...     NaN   \n",
+       "2017-01-04 00:00:00                       39.3      NaN      NaN  ...     NaN   \n",
+       "...                                        ...      ...      ...  ...     ...   \n",
+       "2017-12-27 00:00:00                         14      NaN      NaN  ...     NaN   \n",
+       "2017-12-28 00:00:00                         15      NaN      NaN  ...     NaN   \n",
+       "2017-12-29 00:00:00                       25.8      NaN      NaN  ...     NaN   \n",
+       "2017-12-30 00:00:00                       16.6      NaN      NaN  ...     NaN   \n",
+       "2017-12-31 00:00:00                       17.6      NaN      NaN  ...     NaN   \n",
+       "\n",
+       "Codi europeu        ES0554A                         ES0977A ES1398A ES1200A  \\\n",
+       "Estació                                                                       \n",
+       "Dia                     NaN  PM10 L'Arboç (CEIP Sant Julià)     NaN     NaN   \n",
+       "2017-01-01 00:00:00     NaN                           29.77     NaN     NaN   \n",
+       "2017-01-02 00:00:00     NaN                             NaN     NaN     NaN   \n",
+       "2017-01-03 00:00:00     NaN                             NaN     NaN     NaN   \n",
+       "2017-01-04 00:00:00     NaN                           28.28     NaN     NaN   \n",
+       "...                     ...                             ...     ...     ...   \n",
+       "2017-12-27 00:00:00     NaN                           18.22     NaN     NaN   \n",
+       "2017-12-28 00:00:00     NaN                            2.74     NaN     NaN   \n",
+       "2017-12-29 00:00:00     NaN                            8.21     NaN     NaN   \n",
+       "2017-12-30 00:00:00     NaN                             NaN     NaN     NaN   \n",
+       "2017-12-31 00:00:00     NaN                             NaN     NaN     NaN   \n",
+       "\n",
+       "Codi europeu        ES2087A ES2091A ES2088A  ES1908A  \\\n",
+       "Estació                                                \n",
+       "Dia                     NaN     NaN     NaN      NaN   \n",
+       "2017-01-01 00:00:00     NaN     NaN     NaN      NaN   \n",
+       "2017-01-02 00:00:00     NaN     NaN     NaN      NaN   \n",
+       "2017-01-03 00:00:00     NaN     NaN     NaN      NaN   \n",
+       "2017-01-04 00:00:00     NaN     NaN     NaN      NaN   \n",
+       "...                     ...     ...     ...      ...   \n",
+       "2017-12-27 00:00:00     NaN     NaN     NaN      NaN   \n",
+       "2017-12-28 00:00:00     NaN     NaN     NaN      NaN   \n",
+       "2017-12-29 00:00:00     NaN     NaN     NaN      NaN   \n",
+       "2017-12-30 00:00:00     NaN     NaN     NaN      NaN   \n",
+       "2017-12-31 00:00:00     NaN     NaN     NaN      NaN   \n",
+       "\n",
+       "Codi europeu                                       ES9994A  \n",
+       "Estació                                                     \n",
+       "Dia                  PM 10 La Seu d'Urgell (CC Les Monges)  \n",
+       "2017-01-01 00:00:00                                    NaN  \n",
+       "2017-01-02 00:00:00                                    NaN  \n",
+       "2017-01-03 00:00:00                                    NaN  \n",
+       "2017-01-04 00:00:00                                    NaN  \n",
+       "...                                                    ...  \n",
+       "2017-12-27 00:00:00                                    NaN  \n",
+       "2017-12-28 00:00:00                                    NaN  \n",
+       "2017-12-29 00:00:00                                    NaN  \n",
+       "2017-12-30 00:00:00                                    NaN  \n",
+       "2017-12-31 00:00:00                                    NaN  \n",
+       "\n",
+       "[366 rows x 134 columns]"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df_stations_pm10 = df_stations[df_stations['station.code'].isin(station_codes_pm10)].reset_index(drop=True)\n",
-    "df_stations_pm10"
+    "df_pm10 = df_pm10.reindex(columns=list(df_stations['station.code']))\n",
+    "df_pm10"
    ]
   },
   {
@@ -908,18 +1807,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
-    "times = df_pm10['Estació'].iloc[2:]\n",
-    "lat = df_stations_pm10['lat']\n",
-    "lon = df_stations_pm10['lon']"
+    "times = df_pm10.index[1:]\n",
+    "lat = df_stations['lat']\n",
+    "lon = df_stations['lon']"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -935,27 +1834,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
-    "variables = {'station_name': {'data': df_pm10.columns.str.replace('PM10 ', '').str.replace('PM 10 ', '').to_numpy()[1:],\n",
-    "                             'dimensions': ('station',),\n",
-    "                             'dtype': str},\n",
-    "            'station_code': {'data': df_stations_pm10['station.code'],\n",
+    "variables = {'station_name': {'data': df_pm10.iloc[0].str.replace('PM10 ', '').str.replace('PM 10 ', '').to_numpy(),\n",
+    "                              'dimensions': ('station',),\n",
+    "                              'dtype': str},\n",
+    "            'station_code': {'data': df_pm10.columns,\n",
     "                             'dimensions': ('station',),\n",
     "                             'dtype': str},\n",
-    "            'area_classification': {'data': df_stations_pm10['standardised_network_provided_area_classification'],\n",
+    "            'area_classification': {'data': df_stations['standardised_network_provided_area_classification'],\n",
     "                                    'dimensions': ('station',),\n",
     "                                    'dtype': str},\n",
-    "            'pm10': {'data': df_pm10.iloc[2:, 1:].to_numpy().T,\n",
-    "                     'dimensions': ('station', 'time',),\n",
+    "            'pm10': {'data': df_pm10.iloc[1:, :].to_numpy(),\n",
+    "                     'dimensions': ('time', 'station',),\n",
     "                     'dtype': float}}"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -971,7 +1870,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -1013,43 +1912,43 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>POINT (2.16492 41.38742)</td>\n",
+       "      <td>POINT (2.01460 41.56782)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
-       "      <td>POINT (2.11957 41.38491)</td>\n",
+       "      <td>POINT (2.16492 41.38742)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>POINT (2.01599 41.41362)</td>\n",
+       "      <td>POINT (2.11957 41.38491)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>78</th>\n",
-       "      <td>POINT (0.82993 41.54410)</td>\n",
+       "      <th>129</th>\n",
+       "      <td>POINT (2.25730 41.92928)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>79</th>\n",
-       "      <td>POINT (1.25447 41.12006)</td>\n",
+       "      <th>130</th>\n",
+       "      <td>POINT (0.55350 40.57990)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>80</th>\n",
-       "      <td>POINT (1.99596 41.55961)</td>\n",
+       "      <th>131</th>\n",
+       "      <td>POINT (2.25065 41.77106)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>81</th>\n",
-       "      <td>POINT (1.60472 41.60472)</td>\n",
+       "      <th>132</th>\n",
+       "      <td>POINT (1.85656 41.23907)</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>82</th>\n",
+       "      <th>133</th>\n",
        "      <td>POINT (1.45945 42.35836)</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>83 rows × 1 columns</p>\n",
+       "<p>134 rows × 1 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
@@ -1057,20 +1956,20 @@
        "FID                          \n",
        "0    POINT (2.08614 41.37932)\n",
        "1    POINT (1.83853 41.72770)\n",
-       "2    POINT (2.16492 41.38742)\n",
-       "3    POINT (2.11957 41.38491)\n",
-       "4    POINT (2.01599 41.41362)\n",
+       "2    POINT (2.01460 41.56782)\n",
+       "3    POINT (2.16492 41.38742)\n",
+       "4    POINT (2.11957 41.38491)\n",
        "..                        ...\n",
-       "78   POINT (0.82993 41.54410)\n",
-       "79   POINT (1.25447 41.12006)\n",
-       "80   POINT (1.99596 41.55961)\n",
-       "81   POINT (1.60472 41.60472)\n",
-       "82   POINT (1.45945 42.35836)\n",
+       "129  POINT (2.25730 41.92928)\n",
+       "130  POINT (0.55350 40.57990)\n",
+       "131  POINT (2.25065 41.77106)\n",
+       "132  POINT (1.85656 41.23907)\n",
+       "133  POINT (1.45945 42.35836)\n",
        "\n",
-       "[83 rows x 1 columns]"
+       "[134 rows x 1 columns]"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1081,7 +1980,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -1124,7 +2023,7 @@
        "      <td>POINT (2.08614 41.37932)</td>\n",
        "      <td>ES0266A</td>\n",
        "      <td>urban-centre</td>\n",
-       "      <td>19.600000</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
@@ -1135,24 +2034,24 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>POINT (2.16492 41.38742)</td>\n",
-       "      <td>ES0559A</td>\n",
+       "      <td>POINT (2.01460 41.56782)</td>\n",
+       "      <td>ES0395A</td>\n",
        "      <td>urban-centre</td>\n",
-       "      <td>20.000000</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
-       "      <td>POINT (2.11957 41.38491)</td>\n",
-       "      <td>ES0567A</td>\n",
+       "      <td>POINT (2.16492 41.38742)</td>\n",
+       "      <td>ES0559A</td>\n",
        "      <td>urban-centre</td>\n",
-       "      <td>20.200000</td>\n",
+       "      <td>20.2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>POINT (2.01599 41.41362)</td>\n",
-       "      <td>ES0586A</td>\n",
+       "      <td>POINT (2.11957 41.38491)</td>\n",
+       "      <td>ES0567A</td>\n",
        "      <td>urban-centre</td>\n",
-       "      <td>25.600000</td>\n",
+       "      <td>16.5</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
@@ -1162,35 +2061,35 @@
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>78</th>\n",
-       "      <td>POINT (0.82993 41.54410)</td>\n",
-       "      <td>ES2034A</td>\n",
-       "      <td>rural</td>\n",
-       "      <td>7.936455</td>\n",
+       "      <th>129</th>\n",
+       "      <td>POINT (2.25730 41.92928)</td>\n",
+       "      <td>ES2087A</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>79</th>\n",
-       "      <td>POINT (1.25447 41.12006)</td>\n",
-       "      <td>ES2071A</td>\n",
-       "      <td>urban-centre</td>\n",
+       "      <th>130</th>\n",
+       "      <td>POINT (0.55350 40.57990)</td>\n",
+       "      <td>ES2091A</td>\n",
+       "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>80</th>\n",
-       "      <td>POINT (1.99596 41.55961)</td>\n",
-       "      <td>ES2079A</td>\n",
-       "      <td>urban-suburban</td>\n",
+       "      <th>131</th>\n",
+       "      <td>POINT (2.25065 41.77106)</td>\n",
+       "      <td>ES2088A</td>\n",
+       "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>81</th>\n",
-       "      <td>POINT (1.60472 41.60472)</td>\n",
-       "      <td>ES0977A</td>\n",
+       "      <th>132</th>\n",
+       "      <td>POINT (1.85656 41.23907)</td>\n",
+       "      <td>ES1908A</td>\n",
        "      <td>NaN</td>\n",
        "      <td>NaN</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>82</th>\n",
+       "      <th>133</th>\n",
        "      <td>POINT (1.45945 42.35836)</td>\n",
        "      <td>ES9994A</td>\n",
        "      <td>NaN</td>\n",
@@ -1198,28 +2097,28 @@
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>83 rows × 4 columns</p>\n",
+       "<p>134 rows × 4 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "                     geometry station_code area_classification       pm10\n",
-       "FID                                                                      \n",
-       "0    POINT (2.08614 41.37932)      ES0266A        urban-centre  19.600000\n",
-       "1    POINT (1.83853 41.72770)      ES0392A      urban-suburban        NaN\n",
-       "2    POINT (2.16492 41.38742)      ES0559A        urban-centre  20.000000\n",
-       "3    POINT (2.11957 41.38491)      ES0567A        urban-centre  20.200000\n",
-       "4    POINT (2.01599 41.41362)      ES0586A        urban-centre  25.600000\n",
-       "..                        ...          ...                 ...        ...\n",
-       "78   POINT (0.82993 41.54410)      ES2034A               rural   7.936455\n",
-       "79   POINT (1.25447 41.12006)      ES2071A        urban-centre        NaN\n",
-       "80   POINT (1.99596 41.55961)      ES2079A      urban-suburban        NaN\n",
-       "81   POINT (1.60472 41.60472)      ES0977A                 NaN        NaN\n",
-       "82   POINT (1.45945 42.35836)      ES9994A                 NaN        NaN\n",
+       "                     geometry station_code area_classification  pm10\n",
+       "FID                                                                 \n",
+       "0    POINT (2.08614 41.37932)      ES0266A        urban-centre   NaN\n",
+       "1    POINT (1.83853 41.72770)      ES0392A      urban-suburban   NaN\n",
+       "2    POINT (2.01460 41.56782)      ES0395A        urban-centre   NaN\n",
+       "3    POINT (2.16492 41.38742)      ES0559A        urban-centre  20.2\n",
+       "4    POINT (2.11957 41.38491)      ES0567A        urban-centre  16.5\n",
+       "..                        ...          ...                 ...   ...\n",
+       "129  POINT (2.25730 41.92928)      ES2087A                 NaN   NaN\n",
+       "130  POINT (0.55350 40.57990)      ES2091A                 NaN   NaN\n",
+       "131  POINT (2.25065 41.77106)      ES2088A                 NaN   NaN\n",
+       "132  POINT (1.85656 41.23907)      ES1908A                 NaN   NaN\n",
+       "133  POINT (1.45945 42.35836)      ES9994A                 NaN   NaN\n",
        "\n",
-       "[83 rows x 4 columns]"
+       "[134 rows x 4 columns]"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1227,7 +2126,7 @@
    "source": [
     "nessy.shapefile['station_code'] = nessy.variables['station_code']['data']\n",
     "nessy.shapefile['area_classification'] = nessy.variables['area_classification']['data']\n",
-    "nessy.shapefile['pm10'] = pd.to_numeric(nessy.variables['pm10']['data'][:, 0]) # Transform from object to float\n",
+    "nessy.shapefile['pm10'] = pd.to_numeric(nessy.variables['pm10']['data'][0, :]) # Transform from object to float\n",
     "nessy.shapefile"
    ]
   },
@@ -1240,12 +2139,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 1368x504 with 2 Axes>"
       ]
@@ -1276,12 +2175,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 1368x504 with 1 Axes>"
       ]
@@ -1318,7 +2217,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1327,20 +2226,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/esarchive/scratch/avilanova/software/NES/nes/nc_projections/points_nes.py:361: UserWarning: WARNING!!! Different data types for variable station_name. Input dtype=<class 'str'>. Data dtype=object.\n",
+      "/esarchive/scratch/avilanova/software/NES/nes/nc_projections/points_nes.py:357: UserWarning: WARNING!!! Different data types for variable station_name. Input dtype=<class 'str'>. Data dtype=object.\n",
       "  warnings.warn(msg)\n",
-      "/esarchive/scratch/avilanova/software/NES/nes/nc_projections/points_nes.py:361: UserWarning: WARNING!!! Different data types for variable station_code. Input dtype=<class 'str'>. Data dtype=object.\n",
+      "/esarchive/scratch/avilanova/software/NES/nes/nc_projections/points_nes.py:357: UserWarning: WARNING!!! Different data types for variable station_code. Input dtype=<class 'str'>. Data dtype=object.\n",
       "  warnings.warn(msg)\n",
-      "/esarchive/scratch/avilanova/software/NES/nes/nc_projections/points_nes.py:361: UserWarning: WARNING!!! Different data types for variable area_classification. Input dtype=<class 'str'>. Data dtype=object.\n",
+      "/esarchive/scratch/avilanova/software/NES/nes/nc_projections/points_nes.py:357: UserWarning: WARNING!!! Different data types for variable area_classification. Input dtype=<class 'str'>. Data dtype=object.\n",
       "  warnings.warn(msg)\n",
-      "/esarchive/scratch/avilanova/software/NES/nes/nc_projections/points_nes.py:361: UserWarning: WARNING!!! Different data types for variable pm10. Input dtype=<class 'float'>. Data dtype=object.\n",
+      "/esarchive/scratch/avilanova/software/NES/nes/nc_projections/points_nes.py:357: UserWarning: WARNING!!! Different data types for variable pm10. Input dtype=<class 'float'>. Data dtype=object.\n",
       "  warnings.warn(msg)\n"
      ]
     },
-- 
GitLab