{ "cells": [ { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "# Concentration de CO2 dans l'atmosphère depuis 1958" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "## Bibliotheques " ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "%matplotlib inline\n", "import matplotlib.pyplot as plt\n", "import pandas as pd\n", "import isoweek\n", "import numpy as np" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "## Presentation des donnèes" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Les données de l'évolution de la concentration de CO2 dans l'atmosphère sont disponibles du site Web de [l'Institut Scripps](https://scrippsco2.ucsd.edu/data/atmospheric_co2/primary_mlo_co2_record.html). Nous les récupérons sous forme d'un fichier en format CSV. Le fichier contient 10 colonnes. Les colonnes 1-4 donnent les dates en différentes formats. La colonne 5 montre la concentration de CO2 à Mauna Loa en micro-mol per mol (ppm), reporté sur l'échelle 2008A SIO. Les valeurs reportées dans le tableau sont prises à minuit (24:00) du 15 de chaque mois, entre les années 1958 et 2020. La colonne 6 montre la même information de la colonne 5 avec un ajustement pour retirer l'effet quasi régulier saisonnier (4 harmonica fit avec un facteur linéaire de croissance). \n", "La colonne 7 est une version adouci de la même information de la colonne 5 avec une courbe spline cubique plus une fonction 4-harmonic gain avec facteur linéaire de croissance. La colonne 8 présente la donnée de la colonne 7 sans l'effet du cycle saisonnier. \n", "Les valeurs manquantes sont indiqués avec \"-99.99\". La colonne 9 est identique à la colonne 5 avec les valeurs manquantes substitués par les valeurs de colonne 7. La colonne 10 est identique à la colonne 6 avec les valeurs manquantes substitués par les valeurs de colonne 8.\n" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "data_url = \"https://scrippsco2.ucsd.edu/assets/data/atmospheric/stations/in_situ_co2/monthly/monthly_in_situ_co2_mlo.csv\"" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
YrMnDateDateCO2seasonallyfitseasonallyCO2seasonally
0adjustedadjusted fitfilledadjusted filled
1Excel[ppm][ppm][ppm][ppm][ppm][ppm]
2195801212001958.0411-99.99-99.99-99.99-99.99-99.99-99.99
3195802212311958.1260-99.99-99.99-99.99-99.99-99.99-99.99
4195803212591958.2027315.70314.44316.18314.90315.70314.44
5195804212901958.2877317.45315.16317.29314.98317.45315.16
6195805213201958.3699317.51314.71317.86315.06317.51314.71
7195806213511958.4548-99.99-99.99317.24315.14317.24315.14
8195807213811958.5370315.86315.19315.86315.21315.86315.19
9195808214121958.6219314.93316.19313.99315.28314.93316.19
10195809214431958.7068313.21316.08312.45315.35313.21316.08
11195810214731958.7890-99.99-99.99312.43315.40312.43315.40
12195811215041958.8740313.33315.20313.61315.46313.33315.20
13195812215341958.9562314.67315.43314.76315.51314.67315.43
14195901215651959.0411315.58315.54315.62315.57315.58315.54
15195902215961959.1260316.49315.86316.26315.63316.49315.86
16195903216241959.2027316.65315.38316.97315.69316.65315.38
17195904216551959.2877317.72315.42318.08315.76317.72315.42
18195905216851959.3699318.29315.49318.65315.84318.29315.49
19195906217161959.4548318.15316.03318.04315.93318.15316.03
20195907217461959.5370316.54315.86316.67316.02316.54315.86
21195908217771959.6219314.80316.06314.82316.12314.80316.06
22195909218081959.7068313.84316.73313.31316.21313.84316.73
23195910218381959.7890313.33316.33313.32316.30313.33316.33
24195911218691959.8740314.81316.68314.54316.39314.81316.68
25195912218991959.9562315.58316.35315.72316.47315.58316.35
26196001219301960.0410316.43316.39316.61316.55316.43316.39
27196002219611960.1257316.98316.35317.27316.64316.98316.35
28196003219901960.2049317.58316.28318.02316.71317.58316.28
29196004220211960.2896319.03316.70319.14316.79319.03316.70
.................................
728201807432962018.5370408.90408.08409.43408.65408.90408.08
729201808433272018.6219407.10408.63407.33408.90407.10408.63
730201809433582018.7068405.59409.08405.66409.18405.59409.08
731201810433882018.7890405.99409.61405.84409.44405.99409.61
732201811434192018.8740408.12410.38407.48409.72408.12410.38
733201812434492018.9562409.23410.15409.07409.98409.23410.15
734201901434802019.0411410.92410.87410.30410.24410.92410.87
735201902435112019.1260411.66410.90411.25410.48411.66410.90
736201903435392019.2027412.00410.46412.25410.69412.00410.46
737201904435702019.2877413.52410.72413.73410.92413.52410.72
738201905436002019.3699414.83411.42414.54411.14414.83411.42
739201906436312019.4548413.96411.38413.91411.36413.96411.38
740201907436612019.5370411.85411.03412.36411.57411.85411.03
741201908436922019.6219410.08411.62410.22411.79410.08411.62
742201909437232019.7068408.55412.06408.49412.02408.55412.06
743201910437532019.7890408.43412.06408.62412.23408.43412.06
744201911437842019.8740410.29412.56410.21412.46410.29412.56
745201912438142019.9562411.85412.78411.76412.67411.85412.78
746202001438452020.0410413.37413.32412.95412.89413.37413.32
747202002438762020.1257414.09413.33413.87413.10414.09413.33
748202003439052020.2049414.51412.94414.89413.30414.51412.94
749202004439362020.2896416.18413.35416.35413.50416.18413.35
750202005439662020.3716417.16413.75-99.99-99.99417.16413.75
751202006439972020.4563-99.99-99.99-99.99-99.99-99.99-99.99
752202007440272020.5383-99.99-99.99-99.99-99.99-99.99-99.99
753202008440582020.6230-99.99-99.99-99.99-99.99-99.99-99.99
754202009440892020.7077-99.99-99.99-99.99-99.99-99.99-99.99
755202010441192020.7896-99.99-99.99-99.99-99.99-99.99-99.99
756202011441502020.8743-99.99-99.99-99.99-99.99-99.99-99.99
757202012441802020.9563-99.99-99.99-99.99-99.99-99.99-99.99
\n", "

758 rows × 10 columns

\n", "
" ], "text/plain": [ " Yr Mn Date Date CO2 seasonally fit \\\n", "0 adjusted \n", "1 Excel [ppm] [ppm] [ppm] \n", "2 1958 01 21200 1958.0411 -99.99 -99.99 -99.99 \n", "3 1958 02 21231 1958.1260 -99.99 -99.99 -99.99 \n", "4 1958 03 21259 1958.2027 315.70 314.44 316.18 \n", "5 1958 04 21290 1958.2877 317.45 315.16 317.29 \n", "6 1958 05 21320 1958.3699 317.51 314.71 317.86 \n", "7 1958 06 21351 1958.4548 -99.99 -99.99 317.24 \n", "8 1958 07 21381 1958.5370 315.86 315.19 315.86 \n", "9 1958 08 21412 1958.6219 314.93 316.19 313.99 \n", "10 1958 09 21443 1958.7068 313.21 316.08 312.45 \n", "11 1958 10 21473 1958.7890 -99.99 -99.99 312.43 \n", "12 1958 11 21504 1958.8740 313.33 315.20 313.61 \n", "13 1958 12 21534 1958.9562 314.67 315.43 314.76 \n", "14 1959 01 21565 1959.0411 315.58 315.54 315.62 \n", "15 1959 02 21596 1959.1260 316.49 315.86 316.26 \n", "16 1959 03 21624 1959.2027 316.65 315.38 316.97 \n", "17 1959 04 21655 1959.2877 317.72 315.42 318.08 \n", "18 1959 05 21685 1959.3699 318.29 315.49 318.65 \n", "19 1959 06 21716 1959.4548 318.15 316.03 318.04 \n", "20 1959 07 21746 1959.5370 316.54 315.86 316.67 \n", "21 1959 08 21777 1959.6219 314.80 316.06 314.82 \n", "22 1959 09 21808 1959.7068 313.84 316.73 313.31 \n", "23 1959 10 21838 1959.7890 313.33 316.33 313.32 \n", "24 1959 11 21869 1959.8740 314.81 316.68 314.54 \n", "25 1959 12 21899 1959.9562 315.58 316.35 315.72 \n", "26 1960 01 21930 1960.0410 316.43 316.39 316.61 \n", "27 1960 02 21961 1960.1257 316.98 316.35 317.27 \n", "28 1960 03 21990 1960.2049 317.58 316.28 318.02 \n", "29 1960 04 22021 1960.2896 319.03 316.70 319.14 \n", ".. ... ... ... ... ... ... ... \n", "728 2018 07 43296 2018.5370 408.90 408.08 409.43 \n", "729 2018 08 43327 2018.6219 407.10 408.63 407.33 \n", "730 2018 09 43358 2018.7068 405.59 409.08 405.66 \n", "731 2018 10 43388 2018.7890 405.99 409.61 405.84 \n", "732 2018 11 43419 2018.8740 408.12 410.38 407.48 \n", "733 2018 12 43449 2018.9562 409.23 410.15 409.07 \n", "734 2019 01 43480 2019.0411 410.92 410.87 410.30 \n", "735 2019 02 43511 2019.1260 411.66 410.90 411.25 \n", "736 2019 03 43539 2019.2027 412.00 410.46 412.25 \n", "737 2019 04 43570 2019.2877 413.52 410.72 413.73 \n", "738 2019 05 43600 2019.3699 414.83 411.42 414.54 \n", "739 2019 06 43631 2019.4548 413.96 411.38 413.91 \n", "740 2019 07 43661 2019.5370 411.85 411.03 412.36 \n", "741 2019 08 43692 2019.6219 410.08 411.62 410.22 \n", "742 2019 09 43723 2019.7068 408.55 412.06 408.49 \n", "743 2019 10 43753 2019.7890 408.43 412.06 408.62 \n", "744 2019 11 43784 2019.8740 410.29 412.56 410.21 \n", "745 2019 12 43814 2019.9562 411.85 412.78 411.76 \n", "746 2020 01 43845 2020.0410 413.37 413.32 412.95 \n", "747 2020 02 43876 2020.1257 414.09 413.33 413.87 \n", "748 2020 03 43905 2020.2049 414.51 412.94 414.89 \n", "749 2020 04 43936 2020.2896 416.18 413.35 416.35 \n", "750 2020 05 43966 2020.3716 417.16 413.75 -99.99 \n", "751 2020 06 43997 2020.4563 -99.99 -99.99 -99.99 \n", "752 2020 07 44027 2020.5383 -99.99 -99.99 -99.99 \n", "753 2020 08 44058 2020.6230 -99.99 -99.99 -99.99 \n", "754 2020 09 44089 2020.7077 -99.99 -99.99 -99.99 \n", "755 2020 10 44119 2020.7896 -99.99 -99.99 -99.99 \n", "756 2020 11 44150 2020.8743 -99.99 -99.99 -99.99 \n", "757 2020 12 44180 2020.9563 -99.99 -99.99 -99.99 \n", "\n", " seasonally CO2 seasonally \n", "0 adjusted fit filled adjusted filled \n", "1 [ppm] [ppm] [ppm] \n", "2 -99.99 -99.99 -99.99 \n", "3 -99.99 -99.99 -99.99 \n", "4 314.90 315.70 314.44 \n", "5 314.98 317.45 315.16 \n", "6 315.06 317.51 314.71 \n", "7 315.14 317.24 315.14 \n", "8 315.21 315.86 315.19 \n", "9 315.28 314.93 316.19 \n", "10 315.35 313.21 316.08 \n", "11 315.40 312.43 315.40 \n", "12 315.46 313.33 315.20 \n", "13 315.51 314.67 315.43 \n", "14 315.57 315.58 315.54 \n", "15 315.63 316.49 315.86 \n", "16 315.69 316.65 315.38 \n", "17 315.76 317.72 315.42 \n", "18 315.84 318.29 315.49 \n", "19 315.93 318.15 316.03 \n", "20 316.02 316.54 315.86 \n", "21 316.12 314.80 316.06 \n", "22 316.21 313.84 316.73 \n", "23 316.30 313.33 316.33 \n", "24 316.39 314.81 316.68 \n", "25 316.47 315.58 316.35 \n", "26 316.55 316.43 316.39 \n", "27 316.64 316.98 316.35 \n", "28 316.71 317.58 316.28 \n", "29 316.79 319.03 316.70 \n", ".. ... ... ... \n", "728 408.65 408.90 408.08 \n", "729 408.90 407.10 408.63 \n", "730 409.18 405.59 409.08 \n", "731 409.44 405.99 409.61 \n", "732 409.72 408.12 410.38 \n", "733 409.98 409.23 410.15 \n", "734 410.24 410.92 410.87 \n", "735 410.48 411.66 410.90 \n", "736 410.69 412.00 410.46 \n", "737 410.92 413.52 410.72 \n", "738 411.14 414.83 411.42 \n", "739 411.36 413.96 411.38 \n", "740 411.57 411.85 411.03 \n", "741 411.79 410.08 411.62 \n", "742 412.02 408.55 412.06 \n", "743 412.23 408.43 412.06 \n", "744 412.46 410.29 412.56 \n", "745 412.67 411.85 412.78 \n", "746 412.89 413.37 413.32 \n", "747 413.10 414.09 413.33 \n", "748 413.30 414.51 412.94 \n", "749 413.50 416.18 413.35 \n", "750 -99.99 417.16 413.75 \n", "751 -99.99 -99.99 -99.99 \n", "752 -99.99 -99.99 -99.99 \n", "753 -99.99 -99.99 -99.99 \n", "754 -99.99 -99.99 -99.99 \n", "755 -99.99 -99.99 -99.99 \n", "756 -99.99 -99.99 -99.99 \n", "757 -99.99 -99.99 -99.99 \n", "\n", "[758 rows x 10 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data = pd.read_csv(data_url, skiprows=54)\n", "raw_data" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "## Traitement des données" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "On visualise les noms des colonnes." ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "text/plain": [ "[' Yr',\n", " ' Mn',\n", " ' Date',\n", " ' Date',\n", " ' CO2',\n", " 'seasonally',\n", " ' fit',\n", " ' seasonally',\n", " ' CO2',\n", " ' seasonally']" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "list(raw_data.columns) " ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "On modifie les noms des colonnes, pour mettre au propre le tableau." ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "text/plain": [ "['year',\n", " 'Month',\n", " 'data1',\n", " 'data2',\n", " 'CO2',\n", " 'seasonally_adjusted',\n", " 'fit',\n", " 'seasonally_adjusted_fit',\n", " 'CO2_filled',\n", " 'seasonally_adjusted_filled']" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data_new = raw_data.rename(columns={' Yr': 'year',' Mn':'Month',' Date':'data1',' Date':'data2',' CO2':'CO2','seasonally':'seasonally_adjusted',' fit':'fit',' seasonally':'seasonally_adjusted_fit', ' CO2':'CO2_filled',' seasonally':'seasonally_adjusted_filled'})\n", "list(raw_data_new.columns) " ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "On supprime les premières quatre lignes. Les premières deux lignes sont vides, et les lignes 3 et 4 n'ont pas d'échantillon." ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "raw_data_new=raw_data_new.drop([0, 1,2,3])" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "On Supprime le format de data 'data1' et 'data2', qui ne sont pas intéressantes pour notre analyse." ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "raw_data_new=raw_data_new.drop(columns=['data1', 'data2'])" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Nous vérifions qu'il n'y a pas des valeurs nulles dans le tableau." ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearMonthCO2seasonally_adjustedfitseasonally_adjusted_fitCO2_filledseasonally_adjusted_filled
\n", "
" ], "text/plain": [ "Empty DataFrame\n", "Columns: [year, Month, CO2, seasonally_adjusted, fit, seasonally_adjusted_fit, CO2_filled, seasonally_adjusted_filled]\n", "Index: []" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data_new[raw_data_new.isnull().any(axis=1)]" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "On voit qu'il n'y a pas des valeurs nulles. On vérifie le type de donné :" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "text/plain": [ "year object\n", "Month object\n", "CO2 object\n", "seasonally_adjusted object\n", "fit object\n", "seasonally_adjusted_fit object\n", "CO2_filled object\n", "seasonally_adjusted_filled object\n", "dtype: object" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data_new.dtypes" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "On voit que le tableau est composé par des 'object'. On va le convertir en valeurs numériques." ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "raw_data_new['year']=raw_data_new['year'].astype(int)\n", "raw_data_new['Month']=raw_data_new['Month'].astype(int)\n", "raw_data_new['CO2'] = pd.to_numeric(raw_data_new['CO2'], errors='coerce').fillna(0)\n", "raw_data_new['seasonally_adjusted'] = pd.to_numeric(raw_data_new['seasonally_adjusted'], errors='coerce').fillna(0)\n", "raw_data_new['fit'] = pd.to_numeric(raw_data_new['fit'], errors='coerce').fillna(0)\n", "raw_data_new['seasonally_adjusted_fit'] = pd.to_numeric(raw_data_new['seasonally_adjusted_fit'], errors='coerce').fillna(0)\n", "raw_data_new['CO2_filled'] = pd.to_numeric(raw_data_new['CO2_filled'], errors='coerce').fillna(0)\n", "raw_data_new['seasonally_adjusted_filled'] = pd.to_numeric(raw_data_new['seasonally_adjusted_filled'], errors='coerce').fillna(0)\n", "\n" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "On verifie la conversion: \n" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "text/plain": [ "year int64\n", "Month int64\n", "CO2 float64\n", "seasonally_adjusted float64\n", "fit float64\n", "seasonally_adjusted_fit float64\n", "CO2_filled float64\n", "seasonally_adjusted_filled float64\n", "dtype: object" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data_new.dtypes" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Les 6 dernières lignes sont vides, on peut les retirer." ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "raw_data_new=raw_data_new.drop([751,752,753,754,755,756,757])" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "On peut aussi retirer les lignes sans valeurs :(-99,99)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "raw_data_new = raw_data_new.drop(raw_data_new[raw_data_new.CO2 < 0].index)" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "On réinitialise les index de nos listes." ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "raw_data_new=raw_data_new.reset_index(drop=True)" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "## Point 1 - Evolution Annuelle de la CO2\n", "Le graphique suivant nous montrera une oscillation périodique superposée à une évolution systématique plus lente." ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "x = raw_data_new['year']\n", "y1 = raw_data_new['CO2_filled']\n", "y2 = raw_data_new['seasonally_adjusted_filled']\n", "\n", "fig, ax = plt.subplots()\n", "ax.plot(x, y1, '-b', label='CO2 evolution - per year (ppm)')\n", "ax.plot(x, y2, '--r', label='CO2 evolution - without seasonal influence (ppm)')\n", "leg = ax.legend();\n", "fig.set_size_inches(12, 8)" ] }, { "attachments": { "Screenshot%202020-07-19%20at%2009.15.53.png": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAp0AAAFRCAYAAAA2FxZsAAAYWmlDQ1BJQ0MgUHJvZmlsZQAAWIWVWQdUU0u3nnPSE0IJvffee0d6B+lNEEIPndBBqogiigqKFFEpIiCKjSqiIHZEBEXsKCKo6EUUERF4h6L3/vdf6731Zq1z8mXPnl1m9szsnQDAm0WNiYmAmQGIjIqnO1kYC3l4egnh3gII8AMKQAEFakBcjJGDgy1A2u/P/2zfRxBupA3Lr8r67/7/tbEEBsUFAAA5INg/MC4gEsEXAUDnBsTQ4wHAaiF00aT4mFXsjWA2OmIggmNWccg6zl3F/uu4dI3HxckEwU0A4BmoVHoIAIztCF0oMSAEkcM4ivRRogJpUQjrNIINAkKpgQDwyiE8cpGR0avYA8FS/v+QE/IfMv3/yKRSQ/7gdV/WGt6UFhcTQU35f07H/90iIxJ+65BAHoZQuqXTqs/IvI2GR9usYgYET0f5229GMAXBP2iBa/wIhomhCZau6/wwX0CcCTJngAPBSoFUUxsE8yHYPCrC3naD7h9MM7dCMBIhcDIt3splY+yuoDgz5w2ZR+jRTpt/42C6idHG2DNU+preVf6+hHBXow35o6FBVr/lf0sNdXFftxlFTKS52SOYEcEcceHONus8KLHUUBP73zz0BKdV+8UQrBMUZWG8Lh+1NZhu7rTBT4+M++0valcozcp+A5fHh7pYbshpCqCu2c+F4PagKCPX33KC4jxsf/sSGGRqtu47ajAoynXDX9RYTLyx08bY2ZgIhw1+NDEowmKVLoJgvrhE542xaIN4JCDX5aPtY+IdXNbtRPuHUa0d1u1BJwNbYAJMgRBIQB5/EA3CAG1gum0a+bbeYw6ogA5CQBCQ36D8HuG+1hOFvJ1BKviEoCAQ92ec8VpvEEhE6Et/qOtveRC81pu4NiIcvENwJLABEcj3hLVRUX+0uYG3CIX2X9oDEFsjkGe1779pRgjFdoOS8FuuENNvTqwZ1hRriTXHSqN50AZoXbQt8jZEHhW0Flr7t7V/82PeYR5g3mAeYcYwT3xpOfR/+SME7MAYosF8w2f/f/qMlkCkqqON0fqIfEQ2mgPNA+TRaogmI/QmRLc6QjXZsHzV+3/L/g8f/jHrG3wEJQJM4CQYEqT+PZJRhlH9j5TVOf3nDK3b6v9nXk3+9Pxbv8k/ZjoQ+bT5NydqF+oC6iaqB3Ub1YVqA0KoK6h2VD/q8ir+E0Vv16LotzanNXvCETm0/9JH3dC5OpNxSqeU3iv9Wu+LD0qOX91gJtExKXRaSGi8kBFy8gcJWUUFKMgJqSipKAGweo+sH1NfndbuB4jj/t+0sDQANAUR4rW/aUEjAHS+QI5O4t80iR3IcYAG4LZfQAI9cZ2GXn1hABEwITuKGwgAUSCF+KMCNIAuMARmwBpsBi7AE2xFZjkUiWc6SALbQDbIAwVgPzgEysExUAPqwWlwHrSBLtADboC7YBA8As+Q6JkAH8EM+A4WIQjCQWSIFeKGBCFxSBZSgbQgA8gMsoWcIE/IDwqBoqAEaBu0HSqAiqByqApqgM5BHVAPdBt6AD2BXkPvoVnoJ4yCGWA2mB+WgBVhLdgItoFdYB84BI6FU+FcuBAuhavhJrgV7oHvwo/gMfgjPIcCKBKKAyWMkkdpoUxQm1FeqGAUHZWB2o0qQVWjzqA6kXUeRo2hplELaCyaFS2Elkci2BLtig5Ax6Iz0HvQ5eh6dCu6Dz2Mfo2eQS9jyBg+jCxGB2OF8cCEYJIweZgSTB2mBXMd2U0TmO9YLJYDK4nVRHajJzYMm4bdg63ENmOvYh9gx7FzOByOGyeL08dtxlFx8bg8XBmuCXcFN4SbwP3Ak/CCeBW8Od4LH4XPwZfgG/Hd+CH8JH6RwEwQJ+gQNhMCCSmEfYRaQifhPmGCsEhkIUoS9YkuxDBiNrGUeIZ4nfic+JVEIomQtEmOJBopi1RKOku6RXpNWmCgMMgwmDB4MyQwFDKcZLjK8IThK5lMliAbkr3I8eRCcgP5Gvkl+QcjK6MCoxVjIGMmYwVjK+MQ42cmApM4kxHTVqZUphKmC0z3maaZCcwSzCbMVOYM5grmDubHzHMsrCzKLJtZIln2sDSy3GaZouAoEhQzSiAll1JDuUYZZ0WxirKasAawbmetZb3OOsGGZZNks2ILYytgO802wDbDTmFXY3djT2avYL/MPsaB4pDgsOKI4NjHcZ5jhOMnJz+nEWcQZz7nGc4hznkuXi5DriCu3VzNXI+4fnILcZtxh3Mf4G7jfsGD5pHhceRJ4jnKc51nmpeNV5c3gHc373nep3wwnwyfE18aXw1fP98cvwC/BX8Mfxn/Nf5pAQ4BQ4EwgYMC3QLvBVkFDQRpggcFrwh+EGIXMhKKECoV6hOaEeYTthROEK4SHhBeFJEUcRXJEWkWeSFKFNUSDRY9KNorOiMmKGYntk3slNhTcYK4lnio+GHxm+LzEpIS7hI7JdokpiS5JK0kUyVPST6XIkttkoqVqpZ6KI2V1pIOl66UHpSBZdRlQmUqZO7LwrIasjTZStkHchg5bbkouWq5x/IM8kbyifKn5F8rcCjYKuQotCl8VhRT9FI8oHhTcVlJXSlCqVbpmTJF2Vo5R7lTeVZFRiVApULloSpZ1Vw1U7Vd9YuarFqQ2lG1UXVWdTv1neq96ksamhp0jTMa7zXFNP00j2g+1mLTctDao3VLG6NtrJ2p3aW9oKOhE69zXucvXXndcN1G3Sk9Sb0gvVq9cX0Rfap+lf6YgZCBn8Fxg7FNwpuom6o3vTEUNQw0rDOcNJI2CjNqMvpsrGRMN24xnjfRMUk3uWqKMrUw3W06YEYxczUrN3tpLmIeYn7KfMZC3SLN4qolxtLG8oDlYyt+qwCrBqsZa03rdOs+GwYbZ5tymze2MrZ020472M7artjuub24fZR922aw2Wpz8eYXDpIOsQ6XHLGODo4Vju+clJ22Od10ZnX2dW50/u5i7LLP5ZmrlGuCa68bk5u3W4PbvLupe5H7mIeiR7rHXU8eT5pnuxfOy82rzmtui9mWQ1smvNW987xHfCR9kn1ub+XZGrH1si+TL9X3gh/Gz92v0e8XdTO1mjrnb+V/xH8mwCTgcMDHQMPAg4Hvg/SDioImg/WDi4KnQvRDikPeh24KLQmdppnQymlfwizDjoXNh28OPxm+EuEe0RyJj/SL7IiiRIVH9UULRCdHP4iRjcmLGYvViT0UO0O3odfFQXE+ce3xbEjC3p8glbAj4XWiQWJF4o8kt6QLySzJUcn9KTIp+SmTqeapJ9LQaQFpvduEt2Vve51ulF6VAWX4Z/RmimbmZk5kWWTVZxOzw7Pv5SjlFOV82+6+vTOXPzcrd3yHxY5TeYx59LzHO3V3HtuF3kXbNZCvml+Wv7w7cPedAqWCkoJfewL23NmrvLd070phcOHAPo19R/dj90ftHzmw6UB9EUtRatF4sV1x60Ghg7sPfjvke+h2iVrJscPEwwmHx0ptS9vLxMr2l/0qDy1/VGFc0XyE70j+kfnKwMqho4ZHzxzjP1Zw7Odx2vHRKouq1mqJ6pIabE1izbtat9qbJ7RONNTx1BXULZ2MOjlW71Tf16DZ0NDI17jvFHwq4dT7Ju+mwdOmp9vPyJ+pauZoLjgLziac/XDO79zIeZvzvRe0Lpy5KH7xSAtry+5WqDWldaYttG2s3bP9QYd1R2+nbmfLJYVLJ7uEuyous1/e103szu1euZJ6Ze5qzNXpnpCe8V7f3mfXPK497HPsG7huc/3WDfMb124a3bxyS/9W122d2x13tO603dW429qv3t9yT/1ey4DGQOt9zfvtg9qDnQ/0HnQPbRrqGTYdvvHQ6uHdR/aPHoy4jow+9n48Nho4OvUk4smXp4lPF59lPcc83/2C+UXJS76X1a+kXzWPaYxdfm36uv+N85tn4wHjH9/Gvf01kfuO/K5kUnCyYUplquu9+fvBD1s+THyM+bg4nfeJ5dORz1KfL/5l+Ff/jMfMxBf6l5XZPV+5v578pvatd85h7uX3yO+L87t/cP+oX9BauPnT/efkYtIv3K/SJemlzmWb5ecrkSsrMVQ6dS0VQCEPHBwMwOxJAMieALAOAkDcsl7nbTQUknzAa7xkJJ/RQzKtYjAAUSAPqB6G4Uh4HBWEmkUXYJQwY9hKXBjelCBBZCTBDCgyC6MskxUznaWK8oJNgN2f4zwXmtuP5yqfIH++wBchH+G7ojpiJyTYJLOkJmXsZZvlGRUCFC8oLaroqsapHVPv03ituaDNoMOjK6OnpW9qYL/JyzDUKNE4z6TEtN6s0/yOxVPLKat5G7Qtsx2fveRmZQcdR2MnK2d7FydXVzd3dw8PT08vL68tXt5ePl5bPXzd/Jyodv7mAQaB6kEywYIhrKG40EXa57DX4Q8jbiK78lR0Zcze2BQ6Nc4onjv+c0JP4uGk6GTrFNGUpdTHac3bdqX7ZWhmMiJ761J2UU7odv1c1typHd15xTtDd+nlc+QvFaD3GOw9vU9r//kDS8WCB2UPKZQoHVYuVS1TK1evUD+iUalz1PxY0PHSqtEa9lqjEz51USdT6/MaDjRWnDrR1Hy648y15qGzn84LX4i5ONgq3RbRXtrR2nn/0mTXcjfHFeWrbj1FvVN9ltcrbty7+frWzB3sXfF+i3uBA3H3IwZdH2gOCQwThxcejj+6N3Llcedo15MrT3uedT9vfnHgZcQr4zHusdnXg286xuvfVkzsf7djMmUq8r3fB7uPqtOU6Y+fbnyu/StvJuyL/azaV5Fv0nM+37t/KC0c/PnqF/eSx3LtyspqnAAS4EWyRCekRmoC7yBJKBq6CvPCOfAsKgb1A70LI4y5jo3HKeC+4nsJlcR0UiCDB9mZ0YPJnzmBpYBSzzrI9oNDktOHq5j7Pi+Zz5Z/j8CAEFnYUeSA6KA4ScJMMlGqTvqBzDc5ZnkpBTVFbSVtZVUVaVUBNWZ1SP2bxgRyW93S7tBp0C3XK9BPMwjbtMXQ3sjYWNNEwVTMjMec2QJrsWg5YzVhPWrTb9ttd9a+enOxQ65jnBPV2cHFwFXWjcsd4/7F47nnLa8LW4555/vEbfXxNfOTo7JSf/i/COgJrA3aFRweYheqSGOhfQ17FN4aURqZEuURrRFDiXkfe4VeHBcYr56ASRhJPJGUkGyWwpYynno+LWubfTpf+oeMzsy9WWHZTjmmSGTo7NDIU9opu0s8X3A3dwFlD2kveu9S4fd9X/bPHlgoxh3kOiRVonnYtNShbEt5SAX9SHrlzqNFx44cP1nVXj1Us3BCus77ZEF9S8PTxuUm4dNmZ0Kb955tO/f5gvrFHS0P2sjt+h20zrJLd7tWutWvRFyt7Xl+jaXP8DrtRsHNxlu3br+/S+5Xvec1kHO/afDxEHZY7aHvo9yR2sd9o++eEp8pPnd5kfLy6KubY/NvlMfpby9MzE7KTYW8r/nwapr3k8fnI3/NfEn8Kj9HmScuwD8//rq0TNtYfyLgBHLAEql2DoM7EBaygA5A47A+XIUio3agcegijATmKjYQR8Hdxu8i2BMFiQukhwzt5BOMZUxFzPtYiijlrCfYWtlvcbzkXOCm8MjzmvNR+bcJHBY8I9Qr/FBkQvST2Kz4DJI1jUr1Sp+Q2S7rJacoD8kPKdQqJilZKwspz6sMqNapZai7ashpwpqjWqe1c3TcdGV0l/QG9WsMkjZZGwoazhn1G58wyTB1M1Mwx5g/t7houdvKz1rDhmQzZttil2/vg5wUGIcnjk1OWc7OLuIu311vuZW7h3voepI8n3md2pLqbenD4fN26znfTD8bKid13P9MQGqgeRBL0LPgupDYUF0amjYQdjjcL0I64ktke1RWtHkMIaY/dg/dOg4fdz0+J8EgYTGxLSkuWSH5fUptqm8aT9rDbYXplhlwRndmRpZlNn/2Ys7Y9lu553ZU5OXujNzllm+wW6KAXDC35/nea4WN+w7uzz6QVEQvjjmIpAUlsYdjS2PKosppFX5HnCutj9oe8zmeUlVZfb3m8wn2Os2TtvVODY6NW06lNV08vdhscbb43KsLshcTW3raSO3OHaWdz7qEL0d0X77K2hPWe62P93r8jYFbErfT7zzsl7mXMzA+6PZgZDjg4dzIrlGeJ6efGT4feZk1ZvfG+e3+d/PvD05f/+Iy/2R1/dd/71ttWA0ATpgD4HYQAGdtBBcCIF6P3B96ADiQAXDRBjB3GYAuxwDIW+rP/SEAjJC7YzuoBdeR0wOLnB9WUDi0F2pGar1vMCesC/vC2+F6eAD+iuJBGaFCUfuR6vsNmoTWQFPRe9Ed6EkMO8YMk4BUXaNYBqwRNgl7BjuFE8H54o7iXuJF8KH4s/glgi3hOOE70YF4mkQmRZGGGLQYqsgkciJ5nNGRsYdJhamWmZt5PwuBZQcFpuSwYljz2ZjZytjF2S9wmHKMckZz4blquU243/Ls5JXnfcSXyS/H/1ygUNBUcEmoUzhVxEAUI3pf7Ih4uIS+JEXyg1SfdLVMjmyQnK28toKCoqKSgbKrSoTqduTIb9EY1vyuza9joZuo16D/ahO3obtRmfErUymzBPMbljxWIdaHbA7bJtoZ2q3Y92ze4xDmSHPKdT7r8taNx93Zo9CzfwvZ29GnZOuoHxNV1d8iwDUwMCgz+FTIFE05LDt8OFIKibynsZr0krgfCe6JTUmfUjhTldKMt3mmZ2Z0ZBGyQ3Pu5WrsqN7JtCsjf7LAaE/u3pbCsf2MB+yLzh5UO3T9sH3pvXLLihuVjkd/HL9V3V17vu5wfWojrWnLGaOz7OdeXzjdktm2tcPr0rbLbVcWerX7Im/svlV2p7a/eaB78MHQ5CP8Y/0ne599e+k11jJOmqBOdn7AT0t+Bn9VfhGYLf3GN9c6H7mg/vPXr9Zl37XzQwzYgFhQArrAGwgPKUAuUCpUjVT6X2Bu2BgOhw/BV+GPSM1ugtwmlah+1CJaFu2NLkT3oOcwMhgqphTzAEvCWmB3YPtwWJw1bh9uFC+Gj8NfJ/ARkggjRG3icRKRlESaZPBguEc2IXcxajG2MmkwdTBvYr6B1KhPKEGUWdYcNja2evZN7E84EjjZOFu5vLhh7iYeT14CbxdfHLLWUwInBWlCCkLfhXtE9on6iqmKE8XfSvRK1krlS8fJ+Mk6ypnJ6yloKqoraSjrqBir2qltUY/SyNOs07qvvayrphetf8Zg1lDbKNd42FTSLNP8maWuVaX1kq2DXbH9nc2/HBWcAp2PujxF1tjbo8rzwxZ17+0+w77ifnHULv/lQP2g9OCeUALNLexE+HykbVRN9K9YT3p7PHfCtsSnyUopaamX036m62RkZw5ki+SkbB/eoZRXuPNzvv3uxoLFvYaF2/a17J8rMi2uPkQooR8eLTMorzmCr4w+OnJcv6quhq02vw57srBBoPFik93p8ebkc6Tzxy6qtdxp82uf69zVxXe55Yp7D9zb0ke7wXdz4HbWXbX+DwM1g1uGWIavPAp4DEYrnmo/e/Fi5yuVsVdv9rzVnZiePPre/sPc9K5PC39Zzez4cm524OvUt5XvXPOqP1wWtv1sXPywpLV8aG39pYELyAQNYBgsQ9LI6mdBTdAojIXVYH/4ANyDZBGiKDdUPuoy6itaGu2HLkMPY5gwtpgCzF0sGeuELcO+wcnj0nH38RL4bPxrggXhPFGMWEHiIB1i4GAoJwuS6xiVGLuYbJleIfkGE0sTxY7yhbWMzZRtlr2Gw42TxNnDlcqtwf2dp4M3k8+KnxNZ68uCh4ToSAaiJsojhkbunnGJJ5JDUveRyvyR7Eu5j/K/FClKcsrWyI4uVutW/6QppOWuXaQzpMeu72PQuGnRyMG40ZRgFmn+2NLa6oaNre2oPc0BOFY467m8cSv02OQ5t+WcD91Xw2/WvyJQNuh0iExoXZhEeEOkYlRHjEXsaFxkAjaxOtko5VVacjo2ozCLLbtsu0ju6TzdnffyAwqgPacKvfdjD1QUCxw8VII7nFQ6We5VMVzpcfTb8YbqoFrcid113+s9GlpOsTXFnx5p1j579DzmQtTFJ60WbR0dSp2NXWKXK64wXk3v+XDNva/vhsrNqtuUO7l35+9FDLwd9HnwZNj94eMRl8e3n6g8LXr28YXBy8JXL17Lv8kYH5wQfZc8ee+96IfEj1enlz8r/2U94/nFc9b+q9430Tnc3JvvnfNZP/R/zCxk/6T8PL5IWIxdfPLL+FfZr6klzaUdSw+XRZdpy6eXZ1bUVpJXLq2uf1ywqsra9QExGAOAebmy8lUCAFwRAEsHVlYWq1dWlmqQIuM5AFcj1v9DWrtrmAE4cm0V3Uh9XPXv/3L+B32d18xpI+9QAAABnWlUWHRYTUw6Y29tLmFkb2JlLnhtcAAAAAAAPHg6eG1wbWV0YSB4bWxuczp4PSJhZG9iZTpuczptZXRhLyIgeDp4bXB0az0iWE1QIENvcmUgNS40LjAiPgogICA8cmRmOlJERiB4bWxuczpyZGY9Imh0dHA6Ly93d3cudzMub3JnLzE5OTkvMDIvMjItcmRmLXN5bnRheC1ucyMiPgogICAgICA8cmRmOkRlc2NyaXB0aW9uIHJkZjphYm91dD0iIgogICAgICAgICAgICB4bWxuczpleGlmPSJodHRwOi8vbnMuYWRvYmUuY29tL2V4aWYvMS4wLyI+CiAgICAgICAgIDxleGlmOlBpeGVsWERpbWVuc2lvbj42Njk8L2V4aWY6UGl4ZWxYRGltZW5zaW9uPgogICAgICAgICA8ZXhpZjpQaXhlbFlEaW1lbnNpb24+MzM3PC9leGlmOlBpeGVsWURpbWVuc2lvbj4KICAgICAgPC9yZGY6RGVzY3JpcHRpb24+CiAgIDwvcmRmOlJERj4KPC94OnhtcG1ldGE+CjCY960AAEAASURBVHgB7N0HfBzlmT/w32pXq9Wueq+WZNmS3HvFNu4Y0xNqIBAgnZAQ/nfJ3YXkQi7lLkAuBHIJCSWEYsBgG7CxMa64d7nKtqzee69b5v/Musm23KTd1Zbf8Fm82p3yvt+ZnXnmbaNRZAInClCAAhSgAAUoQAEKOFHAz4nr5qopQAEKUIACFKAABShgF2DQyQOBAhSgAAUoQAEKUMDpAgw6nU7MDVCAAhSgAAUoQAEKMOjkMUABClCAAhSgAAUo4HQBBp1OJ+YGKEABClCAAhSgAAUYdPIYoAAFKEABClCAAhRwuoDOUVuwWq1obW1FaGioo1bJ9VCAAhRwMwErYGtE7o6jqC4/jC3b9+KzzcfQ0COVSmAKkjIm4L6vTcZw+Xd4nAnBAdoec/AtBSjgPQLqqJNW1OXsQW5NGY6s24y9m/ZgW2vP0ShDET90BKbddhNmZGRiwugkhBj84bAAzIMwNY4Yp1MNOIuLi/HWW2/h6aefRmBgILRanmQ96DhgUn1ZoKwMMJuB1FRfVrhK3m3obq1GXV421i35GGtPVKHeEI7A0CgkREQgLTUSBnUN5ibUl1aiqLACJc2t8I9Mx9jZCzB72hiMGxKHcH/NVbbDrylAAU8RULqa0FKRK0HmF3hr7X7UtRoRHBSE2IQohKYkIiZArUzuRmtVBWqLSlBRXo8qQwTiJs3DwtlTMWNEClJC9J6SXYekU/tLmfq7ppqaGmzduhV/+MMfMGfOHISFhUGv9y3I/hpyeQoMiEBbG/DFeuDQYSAxAQgOHpBkuPdGbTA3l6M4exs2LP0Ir7/+IVZX6+A/dBKmz52Pe2+/CbcumIlpE8Zj0thhGJ4SgTA0oujgLnyyehvy6ttRb/GHnzEECbGhCPRj4One+5upo8DVBZTuRtScysautZ/g7Xffx9vrSmEJz8LoWXNw81duwS03zcWcKRMwacIYjM5IQLzBgq6Cw1i7Zh02FzSisdkGf70R4bGRiDD4TiFdv0t31VLOo0ePYuXKlcjPz8eqVasQIXf+RqMRfn5sMnr1Q5dzUGAABQoLgWUfAyflX/nd4r57AA2Dogv2iLUDdce3YcsH7+PlV77AftVnwl145OG78cDMoUjU9zjP6cMRlTUNc2PiMTYZ2LnvjyjctQJvl9TieGU3Ygfdg9mxRlD4AmH+QQEPE7Ciu+o49q9djjfe+AhLTzQCxgVY9O2H8dCicZgSE9gjP3oEx4/AuFuiMXRYHEoPHMPrJdux/vVyVJc0oDUyDj+amgC1EsQXzgs9zpY9jK7jbWVlJdasWYN33nnHvpRacLp9+3Y0NspO4EQBCri3wKv/ALYdAg6WA6+9BXR2Anwy7gX7TKnZi7VvLMGbS9afDjgRgqk334Dxg2OR0DPgPLeUFv4RCYi56UH8dGosEoPl3r50L/I2LcPvlh5Cq8xnOzcv31CAAh4nYKtC9op38N7SVacDTjUDU+dj4pgUpEf3DDjP50xjiIQxbSa+9y83ISzcKOfZfBw+uBHP/98qHGyzwtKzCej5xbzuXb+Dzg8//BAbNmy4AEb9Wy395EQBCripgNRQYPXnwGcbgfI6SaQEm9tygI2bgfZ2N020q5OlXgW6UbFnEzbkF2Fnmxoq+gN+KZg2NAGxIVcqsZT5tKFIGh4LgzFAlutEU34O9rz4T3xS2I7mbh+5wrh6l3F7FHCBgFK8F5vXH8WBw7XntmaaPhwpoUaEXba40g8abQCikwYhVqc/3Qa8NhetO9/Db1bloqXLCl84K/Qr6Dxw4AA2b96MU6dOnYNX36hB565du1BfX3/B5/yDAhRwAwE14FRrIn79nFSrV0uC1GBKTncdHcBvngfUjkUWixskdKCTICZKLU7tPoLKsjp02dRLgpRa+iUhKSoIxqv0SNcgACGRQfDTqadZBbbudnQ2FOBUVTu6LLIPOFGAAh4moJ4DLKg9no3s2loUdavnSbWVYhgmJUchzKDH5VtnaqTlkhaBIWq7br/TPdet7TC3VmF/QTVa5ZzgCzUg/Qo6V69ejZKSEiQmJmLChAn2g2fMmDGoq6vD4cOH7W087R/yfxSggPsINDVJY8PdwPYjkHE7JF1qSZycOHXyXv3skLwaeg4C5D5Jd21K5BJgbUblyTK01UuHK/skFw6/YJgMOuh0ly3SkDnV76SaPcBf5j+9pFpqarM1oKKxExarevHiRAEKeJaA+rs1o6GsBFUdbZAzqUzqb92AmCADAmTUniufFSTY9JehkqRd+On5bLDYOlFS2YR2m00GXvL+6dzpsC9Z3bt3L+Li4nDrrbfilltusa/i7rvvxogRI6TQpAMFBQV9WS2XoQAFnClQLaWbq9bIFqTt0Y1jgPRIeSsB57Qh8plUCx/IBtR5OImAWkIp1V72Us7+gpwuJeky26TZLIPO/mpyeQoMlIDNZrWXaPYrgDqTePupoMsMs5wSfOGsoJYL93m6+eabkZ6ebu+lvmPHDvt6Fi9ejPHjx6O5uRnh4eF9XjcXpAAFnCTQIe03S6Xj0GM3ATOmyY37chkqSdomPfAVoEVK9Bqbpapd5vH5SS4pulgMvmEIwoqrpPT3fPutvtEEwE8bg8yEEOj9L18J17d1cykKUMD5AmqYGYDkzOGICz6AYFSdKe3s+5a1Oi2CpY14lDTD8YWBJvsVdD788MP2QeB7tulUB4afMWMGDAaDtF+4UkFz33cSl6QABfohkJkBvPBbGZczUToPnb5ZhL+cChJknM6P3z09UHx0dD824C2LqheYUAybMgVpm/MRdqRWRt80Q7Hko6S6De2D5KbacLmyDrWirBklx0rR3d59GiQ8Cpbx83BjehCC9Aw6veUoYT58TcAPplFTMTdhLYoC8/BlhzxYA9XYVFyDJztjpF2mAb2fFaTWxNaF2pIiFFpkwHg7WwzCTJPwgxnpCNbrrlg17y3K/Qo6AwLUtmDSrv6i8Tj9pc0CB4f3lkOE+bhmgW5pB1kuww898eKVF0nOlHEeZwGjh8i/6VKa1vsp6vRKpKG6WTr9fLlOApxJUhUugWFcb0NydEkJpZTGrdgqQ3fMA5IjAJNUlfc2yQ0hkpNlffKvtse21aeIxcdLO0YJmOQ3zEkV8INx+CwsnHYMZcXlWH5cWnHZynCwqAaLh0VBCZc2m71B2bqhtFfg+P4qdLSqnQ2CERGXjim3TEemSQv7g0p6W46fUYAC7i8QnIWpt87EUWn7fnBDjpR22lB9IB8Vi9LRooQitNeTghVWSytKjueiu1tuXiWX+vhERM+8EYuGhkp70B7nYvcX6HMK+xV09nmrV1qwrRAH1u7C0fwKVFxuPilBDcyaiinJcUhOipQnIAXB0OtOPrsCGzqbylFR0YqatkAMn5ACk3x16SKtKM0+hRZ9MALjE5ASHtjLPGfXyX8pcJGAn/ycAkKA4RJIHpcSxO3SC7xeLeUKAm6XQHCwPO3HIkFLR6UEkVKlvcUIfPUBYJyUPMaFyRnooiNSejaiKh/Yuw04Jd9Nk5OS/9kTk3rKkjvswwVSQhknA7vLutSbP6P0QP/sI2DMdGCEBLVxsu2LJ3U+NeC8eFJrJtRgkwFnDxkNtBHpGC9PGaltaESleTt25NXj4Ppt2JNiQkJIujzGTmp1eiwBayc660tQvG8TVhc3o7HLiJiMiZiyYBEenJuBcOmAdMH8PZflewpQwP0FdOFImT4Hs2ubUdzQiVUHCtC2/0vs3peC1NBAjJImNBfGJBb7Y3Rrj+/B2nUn0Ca1H/qEYRg2Yy7u+soNyArTS+ci98+2I1LofkFnZw3yd2zF+o1ycq+rxIkyuUhL54aQxBTERYYiUvakIk8I6cwoRUHaYIyeNAbDRmdhRGy4FOz0ttes6KotQs6xozha2IlWXQoGnwk6pUhHhivoQHeXBUpEGII08uSR3CPIbfODLSUT5pHDMDhanqwkKehtzY7YAVyHFwnoJKiMHws8NwJY/qy0AVwl1dcybFiwlE4+8q/A4kESJ8qt1G4ptfxwKfDXg0CFBI/fuA+YNUpKH2X5c5OUjtVIwLn7S6ny3g5MeQIYGivBZcDpORT5vr0EWLkHWDgVCJcA0xQFzB0HPPu/EqzK922y7tmSFh97tu85wv6+UeTxl41N6A4JQczYmZgt6+uWR1h2fp6DxsMbZZw+E0ICdVg8YQhiA6WU2D5Z0FlXiPy9W/Hpko04HjcYMaZUjFt4O2656ybcnhUOi5SOmINDpEWD9G4/sxT/oQAFPEBAzgkSNKDBHAhT4hhMm2+Bv0WDNttGnGo4jAPySOFQORdoZo/DhKizhVYKrO11qDi+D5s++Qxf5GnlyWRZyJh8K2669RY8Pi8DYebm0+sM0EHv5dGnQ569rg6RlJOTg/Xr1+OJJ56wP3tdrWLv02RMxPAFCzF7+iAM0Vbi/W1y4UU0pv3wv/Bvz/w7nn/qQTx683h0r/87Xl+6HEuzK1BiCcPIzFQkBF0cQ8sBgnYUf/In/PbDQuTpU3H7vTOQYTzbdqITtYdyUHggF1WZ6Uj0MyE21obyXRuwedVmrNMMxbzRsfYLA4POPu1NH1xIPVIk2CvZKwHnCaCoTUo/par7zjskaAyVwFBKNJOlLaU8nxtHJJjctE+a/kmwmZAEZEpQefZAs0mnldXvSVC5W5a5B3hmwenqcvv3sn6zrPfoCuAPMt+oNCBLltXK8W+U6vGxUrr53idS2lonQXAWkCqlr5ebCgqlRHbX6Y5Ds2cAGUMvN6ePfS7tr8ydqNu0BYVS66EPikJiShbGzJiNBSMGIa5lB9at2ovDlRqEjBmLcVFnbgbQgIL1S7Hsz6/jZ2sM+M6vn8bD33wcD98yDTcOCYdO2nLVbvwSRbHxMpxSAExn97eP6TK7FPBIASnwQs0BrCsJQbjJhJjkwUgdNxV3yc1+anA1dqxcjs+LO1EeloE7h0fbC6zUcZDbjn2Ble+/i+/8ZTfiH30K33vs23jywZtw26Q0RGikNqxmPzaUBMtNrF5eZ29gPVLoqom+OEq76gKumUEDfYARRikNuHjS6EOgTZqKH730Z0T968/w93VbsPbv1ciR5mybnrsDcVIseTpTMuZVew2q1/wBd/+uCQufegj33DkF46UN1ulJqtxzN2HNJ8ex5VQUvn3X6U81UWMw/9EAxMavxkvPfBdPBr2FZ+ckYVBowLl44OI08W8KXJeAfziQNAp4eAqw9XNgnQSIsRKQpkngOU6+U6vNtywFluTIyWgw8NKNatPCM5MEnM1FQPZq4I7/klLMR85+cf7fhInAzWuBDw4Bv3tHgt0fSqehXqrTzy/Bd70JKNK2tesI1u4dhDnD0hCVEAT/wBgMmXM3hsy+Aw/s/Ag76rXIaZWLRs/JfzTGzU3C9hV3Y7I8JlOtTLf3qZT2XJamQqxZlY/Bo2Xfyy7nRAEKeJKAWpDVhgOr9iD8rnEwhsYi1BACU8YNuOvp6bjz4Z1YsaUBJ5uko6HMeT6CMWLk7Dvx+wdewZOjwyAVJlLAoJ4ZpNpd4pSiNRuQPzIdvnDL76ZB51UOQnW05aDBGDttBBJzS2HeV4LatR/ig4dm4hvDQhFh0ELpqkNLwW68/uJ6GGf+AKNGJiNNnoF8umBBAs6SL7Hir29j2TYb6tIW99igHAhBcYgeMhgzp/vjX/60BHOSH8H84QlI9PI7kB4IfOtUAbmTDZSIY4z6QAUJDlEP1BZL6aiUTKpBZ4eU7q/fCcjjEpEmpaKJUnJpn2QYo1ypTl+1Cnj1M+k4JCfAxuXAT7dIdf00qUqXEtFvTZY5peQ0IxOIKQR27QP2lElJqgSv9sjn9Jr4/2sRUC8wDVj1+5/i/U6LtFK4cOBnswwvFTJuHiY+ICXEZydbG1rK9mLnRyuw8vN/IKRnSaYEsTbppFXVsRC/7bBB9hAnClDA4wRsaPzoOfzmMz+0GPUXNpGRavKqyCkYMvMuPCr5Oh10WtDeXI5DG1bhz9v+gY+lI+H5SWpU5EERXbUBuPnFRzhO53mYK7/r7u6WxzWrcb0LJ20wBo0YjozYbMR3ZaOmIhufHavCVwabEG6QoLK2BIXSAeOjQ61Iu38IkmPCEKqT0f87m9GUdwCfvPoGlkuHpT1V/rB1WPHXXxVixdg78dCsdAyRR9yFxiRi9OTB6Fy1HpuOzMWQuHAkyMW/5zXEhbnlprxKQI4inVTHxkhVuP2IsgB1DfL4SQk+1dNOpZRw7smTAs9k6a0upZ9h/mdyLyerEKmWj5bANEwNiNRJgtLxUmo6bRwwRAZ5t09yL6muO0T+rSgCNp8AbpOgs+e57syc/OdqAmZUnDyEU+WNvcwYgtTIcRginQJkr50+N0hgaelsQF1pLvbXXFQCqq7BT0qcU+ahk08k6sWTH1HAMwTMpSdwrKkFxb2FiVnJCBnbgfZzJwWJO6SpTlNNGU7tO4JTl2RRzgl+IzDPoi7g/ZNDSjrVgLPB5Y/N00n/jBSkhIYjSelGhaUOG/JkoNbuQbDKib+pNB9HN+3Ggc54zB0Ug8igQLnmKjBbu9DVUIpDX+7CoYp6VHaZENQgHY32daModBYWT06R7kVGGIIjkCTjGca3rsYeGQph9sgUTJCgk5WU3v+jcEkO1VJHfY+jqbVLCtWknab6eAoJWFAgQU7AECmhlCDzXK92CT5jh0pp6FjpeLRR2oxKe84EKdm872tS1S6Bp1QAnJ5k3UFhUpqql6r4Jgk6jwGdC+Vv+bmfm+fsvPy37wJys23uQH1bl7TaOhPTy5NKbFb10XbXcgGxSNPcJjRVlOFIQY08JFO95QhBlDpyRkY8oqRqnhMFKOBhAu1dUJra0aGeA7RyLpZftVrDYZVnq191UjqkpqQI5aeKUdgtyxvikRIr5Q9S09LcYkZIsBnl9cEYOjIVceHSBNG+/quu1a1mcFjQ2djYW0mAk/OqtvvU+UtlovRol+eWoqBKeoBZ0W2TnmDFBchZfxIa3SIMSQxFiHQeUq+4/qYYJMz4Kh59eBX2vrYDRVVZ8sSRB/HiWw9jcs9eY/pAGCNjka60Y+Pe4zg5R54pPy5ROhs5OU9cve8I9HwUotrIx35syYmpqlzaEkq7Thmpoc9V4uoYuv7yUkOZA1LSWS+lqTFS1BmgngQ5XZOA2uZK6w+DPPDCaJT90cuk+FnkRvf0mHv2r+W9WS42Zn91GQn6L5oUPz1sBnn2suxvjVTFN+VLVfx7b+EHf/4C9RoFFmUC5tx7H374mwdxUzRPNhfx8U8KDLyANO/TGwMRKLGGsZfUKNKbPaClG13n7jvl5lLmtVllzF+jqZcl5DwhNSD+EkBqlBoUrHsX7/zqz3ihtA3W5Ifx5D1aNFe04bA8nGJsVjVe3zwKv3zlKdw7IwPDQs7WgvWyWjf9yCFBp9vlraVBxsmuw4kKuYD3KEy6rnRKMKsNCkGsTQPjgeOoPCG95G8chsQw7yS7LhvO3H8BKRFDq5RCnp1ipPVParT8JSWe+fnSrlOCxCQJGsN6O0mdXeha/lWDJVlfhTR/UY9dGZKD07UIaOAnnRZj7vxvHJbXNU+mYZj54xfsr9eutlDVHmxavx9vvBuI/9iTj6+ltKNm/Q4UW4z2Us+rLc7vKUABFwvopH19/CK8UJiHF6550yEYvPgp/Jv6upZl7rhPOijpceje3+KL8pOojHwaj0lb/f8zSgzy6R9k1J7VWLFjATKlBjdrZPTpZj3Xsl43mcezr0CdbWiVIUiapPhaIwNe+w+JR6Q8SkovQWedvI5JyaUiY+wFSbWiDInX98lWgYbWBtRL8bb9wt33NXFJCoiA3AKbJbisKjv9Xu3GHJUibf3Otskkkk8ISEm0wdguBdrb8fJrS5Hw0HxpOTEd441ys2Hy7FOzT+w/ZpICzhCQAi9/QyAiFamVih2HsSNSMCQhFPr2JkSqTzCSB2hWSKFaVXO7WkTR53I1ZyT9WtbpwWc2qcJqrkddRztqNQHQ6WKwYEic9DDVwU8eO2e2So8xtSZRp5Pnw0uxdX967kqbUZusz2JRW25xokB/BaTKu7VGxsc8ICuSADRdOgFNktdgaYep3rdGyiDv/nKXpFaxS/ug/k1qFa2sT+6cr/jIC/WuLKi/par9S6mvLa2YEjBo4nTc9XAtWvcvx6vPH8KIKbNww9TxmDLi7IgFvqbC/FLAxwWk+l7jJw+OUKvn9UEINhqkeb7UvHbrYQoNk6cpWlEq7f+bpAMjg05XHivS1rK6oEBGmalHvTEcQamTcOuIGIRK9aFGLUGQV5jaZk561pulV5jN3n6uj+3ZNCboZX0BMmQKJwpck4BZAka1nfHFkzwiEXUFwL7tMvj7YamqSZYnFc0Dpo+UNpdqWxCpdk9JlU4/8n2XvFcDzwsmOYblhHTuUZVW+d4ip5426YRklu/Ux2Gqk/r8dLUKXx3QIyxNPpeg89wjNO1zXPi/APk+TEpcOblMQBMQidhhkzEvWKrTlSVYvuMgdq1sQX2z3JSEheHmtBCPqzpzGR43RAEfFFALz9QoxirtxtWYRo1LPW1y25bqigpqDxQvJhVmxYxOGSB7/44DOFVRByU5HWmLvoI7hsujLAPkLkF67kZIr/ZhamP91la0S88v9Rrcc1Kr4+27T92GfVs2iU+lse/Zbdo/kx2r7uGAOISFyDqDPK/Rbs88872TBdRHpFk6ZMijcmlDKSWZbWp/ZJmkcwkapad5ZeXpnunbNwEfrZQB4GXeO74B3D9fniIkQyOppfEaCShTM2WozUBZUI5NaYB+4ZlF5gmQEkm1NFTteSTNPqQBswy3VA15CLB8dmbqlDaccsNlr3yZKetTH4pwpZ6O/lLpERx8dmn+6woBqT2xaeWGNnka7n/2ebzwb1/FTFsBCjetkyetVV24212RHm6DAhRwLwEZiadber1bZUQMmxQwdLQ2y6DzGkSEGe1PL5KGOB43uWn1ulSdd3cIcMuloFJSpLQUYc3v/gM/eW83yuJvwNz7H8IvH5mD+LMhdEg0otIHYcLESLy3/+JVqFGkToqpw6H1l9IdKSWydNSjua0M27O7MUZ6qIeFyjNT1QtCWzOqpUdp2+gMxEjVfWIISzov1uTfPQS6JPDL3QCMfrrHh/K2S0Zme/y2M59JaeboCcA9X5MnEY0HbsyQYPDsgavOIsdnmnw+Ixn4oll6nudLYDlTAsKzx578ZJNHyGM1vynPZT8BvLMV+ETmVduE3pF2ZhsS/NZLWpqlVDUpXuaddHo8H/XQ5+Q2AkppNo7llWN1QxIevmsCEmcvxtzdR2Eu0UJt7cuJAhTwcYH2XBzPL0VRZhSidG2oLilGlQyrNjYhGgnSyVStG/O0yf2CzprteOfnf8WH63Zg17nevXXY9X8/xfG3jPh3KZHRCPWwO+7BIz97FOPHZiJraBISQnrE/JpQRCYNlsdOZUHZfQxHC+sxXYZNSg5Ud5F65dVj0MJH8P3cZhg+zcbukxukIf8YvPjdmQiU4Uyk+xGsXe1olaFrjmuCMfyGURgpPYujedH2tOPbtekNkNLHTAkuc2XszMtOEmAGSCmmSdrsqcfjBQHnmYW0CcCC6bKeXVJ6eQQ4JsORTenRyUgryyZI4PrC+8CzUhJqlJ7vIfLZudi1VZaR5Sol+EyfCsyUgNR+3F82UfxiAAQ0hiCERYVhsF8bDj3/Xfznh0cRIPtr1s034wczB53fnQOQNm6SAhQYeAHFIG04a7dh7Z/W443sQoQkF0kBwxwsmpCJYRLTeGJI4n5BZ1AqJtzzIEKnL8Ttve5zqRbX6KQt1BikRUcgNioEIaaAix624g9TdBIGTxiHWcad2H2sEIukveewaBkLy75ODXRRWZhx7/cQPbkaZV0GRKRnIkbG1Ts9Dnc3OpplvKwjx1AVMha3jE3DkNjgM8907zVR/JACEtfJz0kvVdRD5NWvSYLR8bMlWJTSyt218nz248DkG87HjepjYHUyT6yUcMrAwZdMDbmynFTxG6TKfsE8eWiR8fyyl8zMDwZMIDQBUQERmBorzSiC7sFTyfMREJOK1MGpyAiTWhhOFKCAbwv4hSFm8ESMlwBTO60VhogujLkpAuMnpSLNQ5v7uV/QGZiArHny6tehJsMnhcQiNmsy7r/xEzx/IAcF09JRlxKOuLNP+dCFIn7UDfLqZUPmJjSUl2D/zlLEz74Ps0ckITkswCPvKnrJHT9yewEJKuOHAXOktNNvD3ByK3BkMDBUxvE0XOEna5OxPTulLekXUsXfFiGBq5SG3iQHuPFs1bzbZ9y3EmgIhUl9qbmOjZOe7L6VfeaWAhToRUB9qpnFgg5p2gerFgFR6Rg+dSgGnXl4jTS28ujpXIWco3Kh1brJBU4vxdLJY3H3d+5EZtUpFOUWI6eqVToEy4680iSPyWyrKEDx8XwcKAnHXd++HdNSIhAT4Cb5ulLa+Z33CGikylwt7Vx4owx3JCWXGw/KuJ4t0jlIqsx7neRzs1SrF8gwTJ9IQ+YRUjJ66zyp7g/vdW5+SAEKUIAC7iZgQVdjPWpLy1EudedKRwXKCytkXM4WdEhLKm+YHB50hoeHy2gu7tDL2w/awAhE3/QEXv5+GGpzd2DJZ3twssF8xf2mNORg+0fLsWzDKVh/+Gv854JBiA/Ws5Tzimr80ikCemnHOVYCx1/9p7TZlBLPPYXS+10Cy14n6QnfKN1P3pR2oE/8BnhkETAqptc5+SEFKEABCrihgLUMOV+sxJJfvYYtGhuUuvfxhx8+h9//8XPsbrxy7OKGuek1SRoZlugqRX+9LnfBh5s2bcKrr76Kd955R0Zp6XaToPNsEqVTUGcTKvIOYN/hOhQ1R+Peb99obwp3aSPcKuz6x6co1EbCNGocZmYlIUSqMy+d7+y6+S8FnC0gP091KKYuCSo10o5THcS916GPZD51XM526bGudlTSyf3ktTwQYcNG4LkXT4/r+Vf5d7BU43OiAAUoQIEBELDKaDoyck9bO9rPVWr5y5PLjPLc9oArDrU8AInt0yav0ECsT+uDn4x/6V6TBlqDPEM9dTSmhnZgWKceZ5770ksyQzFk1lwk6AIREBHBgLMXIX7kagG55VHH7pSezleeZD4/+TkHXW2+K6+F31KAAhSgwEAJaKELlKcQqa+BSoKTt+vwoNPJ6e3j6qVjkUme/iEt9nvr7Ht+pQZESkmPVGpyogAFKEABClCAAhRwoIC7FUs6MGtcFQUoQAEKUIACFKCAuwgw6HSXPcF0UIACFKAABShAAS8WYNDpxTuXWaMABShAAQpQgALuIsCg0132BNNBAQpQgAIUoAAFvFiAQacX71xmjQJXFeiWsd+sXjLq8FUzyxkoQAEKUGAgBRh0DqQ+t02BgRZobpZHZ3YPdCq4fQpQgAIU8AEBhwWdDhhj3ge4mUUKuJlAeTnQdLmnHLlZWpkcClCAAhTwaAGHBJ0NDQ0oKSnxaAgmngIUoAAFKEABClDAeQIOCTrVgDM7O9t5qeSaKUABClCAAhSgAAU8WsAhQWdnZydaWlo8GoKJpwAFKEABClCAAhRwnoBDgk7nJY9rpgAFKEABClCAAhTwBgEGnd6wF5kHClCAAhSgAAUo4OYCDDrdfAcxeRSgAAUoQAEKUMAbBBh0esNeZB4oQAEKUIACFKCAmwsw6HTzHcTkUYACFKAABShAAW8QYNDpDXuReaAABShAAQpQgAJuLqBzVPo0Gg30er2jVsf1UIACFKAABShAAQp4kYDDgk6TyYRhw4ZBDT45UYACFKAABShAAQpQoKeAw6rXg4ODMW3atJ7r5nsKUIACFKAABShAAQrYBRwWdKolnAEBAWSlAAUoQAEKUIACFKDAJQIOCzovWTM/oAAFKEABClCAAhSgwBkBBp08FChAAQpQgAIUoAAFnC7AoNPpxNwABShAAQpQgAIUoACDTh4DFKAABShAAQpQgAJOF2DQ6XRiboACFKAABShAAQpQgEEnjwEKUIACFKAABShAAacLMOh0OjE3QAEKUIACFKAABSjAoJPHAAUoQAEKUIACFKCA0wUYdDqdmBugAAUoQAEKUIACFGDQyWOAAhSgAAUoQAEKUMDpAv0OOtvb29HZ2en0hHIDFKCAEwV0OiA42Ikb4KopQAEKUMDXBfoddLa2tjLo9PWjiPn3fAG9HggN9fx8MAcUoAAFKOC2Av0OOs1mMywWi9tmkAmjAAWuQcBPTgVq4MmJAhSgAAUo4CSBfgedTkoXV0sBClCAAhSgAAUo4EUCDDq9aGcyKxSgAAUoQAEKUMBdBRh0uuueYbooQAEKUIACFKCAFwkw6PSincmsUIACFKAABShAAXcVYNDprnuG6aIABShAAQpQgAJeJMCg04t2JrNCAQpQgAIUoAAF3FXAYUGnyWTCuHHjoNFo3DWvTBcFKEABClCAAhSgwAAJOCzo9JNx/gICAgYoG9wsBShAAQpQgAIUoIA7Czgs6HTnTDJtFKAABShAAQpQgAIDK8Cgc2D9uXUKUIACFKAABSjgEwIMOn1iNzOTFKAABShAAQpQYGAFGHQOrD+3TgEKUIACFKAABXxCgEGnT+xmZpICFKAABShAAQoMrACDzoH159YpMLACzS1AR9fApoFbpwAFKEABnxBg0OkTu5mZpMBlBIpKgBoJPDlRgAIUoAAFnCzAoNPJwFw9BdxaYM8hoLHJrZPIxFGAAhSggHcIMOj0jv3IXFCAAhSgAAUoQAG3FmDQ6da7x7sTV1VVhSVLlqCmpgZms9m7M8vcUYACFKAABXxcgEGnjx8AA5n99vZ25OTk4M0330RRURG6u7sHMjncNgUoQAEKUIACThTQOXHdXDUFrihgs9mgBp7vv/c+TEYT5s2fh7S0NPj7+19xOX5JAQpQgAIUoIDnCfS7pFNRFKgvThToq8DJ3JN48U8vYvXq1aivr+fx1FdILkcBClCAAhRwY4F+B50lJSVQ2+ZxokB/BE6cOIHnn38ev3r2V6ioqOjPqrgsBShAAQpQgAJuKNDvoNMN88QkeaDAXOMYhDX64/PPP8cvfv4LVFdXw2KxeGBOmGQKUIACFKAABXoTYNDZmwo/c7nAeONQTNFlILhGg3Xr1uGVv76C4uJidi5y+Z7gBilAAQpQgALOEWDQ6RxXrvU6BRJ0EZhszMJE7RBoq7rx5j/fxJo1a1BQUMDA8zotOTsFKEABClDAHQXYe90d94qPpinZPwoBJn/o/LT4R/4XePlPL8NqteKuu+5CQkIC/Px4j+SjhwazTQEKUIACXiDAq7gX7ERvykKMLhQ3B03Eo+ELUXWqBC+88AJe/OOL9jae3pRP5oUCFKAABSjgawIOK+nU6XSIjIz0NT/m1wkCOo0Wc0xjYIUNW2qOYtmyZahvqMdvfvMbREdHQ6vVOmGrXCUFKEABClCAAs4UcFhJpxp0hoeHOzOtXLePCGigQZCfAVMCMzFdn4WQOj9s3LgRL774IsrKytjG00eOA2aTAhSgAAW8S8BhQafa3s5gMECj0XiXEHMzYALxZzoXTfBLh77SYn9y0aeffMrORQO2R7hhClCAAhSgQN8FHFa93vckcEkKXF5A7Vzkbxph71z0XvEm/PnlP0MKQnHLLbcgOTmZVe2Xp+M3FKAABShAAbcScFhJp1vlionxKoE4XTgWmibga2FzUZJbgD+88Ae8/trrqK2t9ap8MjMUoAAFKEABbxZgSac3710vypvBzx8LgsZL1yIF6yuz8dbbb9kfl/nc888hNDSUzTq8aF8zKxSgAAUo4J0CDDodvF8bGhrQ2dnp4LV65+rUR122tbVdU+bUzkUGjT+mBmbBYrNiX/0pbN22Ff9880089vjjMBqNHMfzmiQ5EwUoQAEKUGBgBBh0Oth99erVyMnJcfBavXN1aoCenZ19XZmL1YXJk4sygXYFeyvzsGTJe0hJScGUqVMRExPDwPO6NDkzBShAAQpQwHUCDDodbL106VKsWLHikrUGyxBABk0A2pROtNu67N/rNToEavQI9NNfMr8vfRAngaS/WFzrpHYu0pmGQ9vmh+V7t+PVv78KjYyeMG3aNERFRbGq/VohOR8FKEABClDAhQLXfqV3YaK8cVPjDEMwwpCKfR252N1xwp5F9Xnjow2D5ZXmjVm+rjypJZjXM6nDKc0NHgetPDLztdVr0NXdjY72dtwpj8wMCAi4nlVxXgpQgAIUoAAFXCDAoNMFyOomkvTRGGtIR4W5/twWQ7RBSA9IwBRj1rnPfPWNH65/IIVgv0D7IzMV6Vz0+dZ9eL7heRQXFeMHP3wSgYGBvkrJfFOAAhSgAAXcUoBBp4t2ixpU+cnA+Rq/84Pnq++00kFG24eAy0XJduvNqH7qIzOnBQ63dy46WFiMDz/6CH5aP/zgySfh7+/PNp5uvQeZOApQgAIU8CWB6y9e8iUd5tUjBKJ1IZgknYtGW5NhzWuWzkVLsPqzz1BTUwObzeYReRjQRMZGAllDBjQJ3DgFKEABCni/AEs6vX8f+0QO1c5FGuMw+LX7YdWhXfj73/4uJZ5aTJkyBdHR0SzxvNJRkJUsQaeMCMCJAhSgAAUo4EQBBp1OxOWqXSuQ5B8JY9Bo+Evnor+sWWV/XKbNasXNixezc5FrdwW3RgEKUIACFLhEgEHnJST8wJMFIqRz1q3BU6RrEfDxF9vx66pq5Ofl43tPfJ+dizx5xzLtFKAABSjg8QL9Djq7urpgNps9HoIZ8C6BGcYRp59cVFiA9z/4AFYp8fzhUz+CXq/nOJ7etauZGwpQgAIU8BCBfnckqq+vR3Nzs4dkl8n0FYFwKfFUOxeNs6VAyW/FB0s/wPJly1BXV8fORb5yEDCfFKAABSjgVgL9LulUA85rfX62W+WcifF6AbWNpyJjoGraNVh/9CBef/11GE0mTJ48mY/M9Pq9zwxSgAIUoIC7CfQ76HS3DDE9FOgpoPZqN5j8oZPORa+vX4sAfQAUGUZp3vz5CAoK6jkr31OAAhSgAAUo4EQBBp1OxOWq3UMgWheKxUGTZBh+DZZ+vgV19XUoKy3DY998HAaDwT0SyVRQgAIUoAAFvFzAYUGnn58fL+BefrB4cva0Gj/MNo2GVf7bdTwXb/7zTbS2tuJHP36KnYs8eccy7RSgAAUo4DEC/e5IdDanOp0OERERZ//kvxRwKwG1lFN9VvuUwCxMRDo0Be3yyMwPseTdd9HY2MjORW61t5gYClCAAhTwRgGHBZ1qSSfbyHnjIeJdeYrXRWB84FAkdYXj0KHDePMfb6K0tBTd3d3elVHmhgIUoAAFKOBmAg4LOt0sX0wOBXoVsMmw8UFaA0K0RpgtZhw7noOqqip0dnb2Oj8/pAAFKEABClDAMQIOa9PpmORwLRRwrkCLrR2ft+7DxtZsREZGYpmM3TlhwgS2R3YuO9dOAQpQgAIUAEs6eRD4hIAiJZwN1la81bheAs6DGDplJN544w1MnDiRz2X3iSOAmaQABShAgYEWYEnnQO8Bbt/pAhbFihZbB5a1bMXBjnxMWngD7nngXkydOpUBp9P1uQEKUIACFKDAaQEGnTwSvFpADThrrE3Y33kKW9uOYvTMifjKvV/FggUL7NXrXp35q2WurQ3Sbf9qc/F7ClCAAhSggEMEGHQ6hJErcUcBG2yos7YguzMfq1p2w5gcju89+X3MmDED0dHR7phk16VJUSAPoof0pnLdNrklClCAAhTwaQEGnT69+7078622TnzZdghrW/ejQd+BtW99hLFjx8Ikz1/3+UkNOtUe+/IPJwpQgAIUoIArBNiRyBXK3IbLBeqlhPOtxnVY3boHiePSsWLFCkyZMgVGo9HlaeEGKUABClCAAhQAWNLJo8CrBKzShrNd6cZ7TZuQrXYamn8D7v/61+y91NWnZnGiAAUoQAEKUGBgBHgVHhh3btUJAmc7De3tOIld7Scwce40fPX+ezBv3jyEh4c7YYtcJQUoQAEKUIAC1yrAoPNapTifWwtYpdOQ2kv90JlOQzFZSfjGNx/F7NmzERMT49ZpZ+IoQAEKUIACviDAoNMX9rIP5LFdOg3t6Thh76VeYq7F1leWY9SoUQgJCfGB3DOLFKAABShAAfcXYEci999HTOFVBE53GlqPZU3bEJYVj82bN2P69OkMOK/ixq8pQAEKUIACrhRgSaeLtNuVTjRKj+pOW9e5LZoVC5rlWeB11uZzn/nqm1A/E3Qa7XVlX61Sb5MSziVNG+2dhibOm45HHv8GxowZA41Gc13r4swUoAAFKEABCjhXgEGnc33Prf1IRxEaLC0oMlef+6za0oDd0uGl3Fx/7jNfffPVkBmI1YVdc/a7FDOqLI3Y034cezty7b3U75ZOQ2obztDQ0GteD2ekAAUoQAEKUMA1Av0OOjtlgOnu7m7XpNYDtpKammofgLy3pDbIhyGIw1h59ZxKcb70s+fn3v6+q6sLtbW1qKmpwVzTmGsOOtWAUw3e1WBzU2s2kscMwdcefhBz585lpyFvP2iYPwpQgAIU8FiBfgedasDQ2NiIsLBrL6XyWK1rSPgDDzxgL227hll9fpbKykqsXr0aH3/88TVbKPIInQopId7YehCftO5EQEAA3vjv32HChAkcFumaFTkjBShAAQpQwPUC/Q469+zZg5ycHEybNs31qXfDLU6ePNkNU+WeScrLy0Nubu51Je5UdzneaFhrf556eno63nzzTUydOhVa7fW1B72ujXJmClCAAhSgAAX6LdDvoLPfKeAKKHANAurA78XmGvy1/jMUmisxZ84c/OAHP7B3GvLz4yAM10DIWShAAQpQgAIDKuCQoHPQoEH2xwwOaE64ca8V6JQ2nKUScC5t2oL87grMuWke7r//fsycORNBQUFem29mjAIUoAAFKOBNAg4JOuPi4pCZmelNLsyLmwioAWdBdyW2tR3DlvYj9mYcDz74IBYsWIDo6Gg3SSWTQQEKUIACFKDA1QQcEnRebSP8ngJ9EbAqNpSpTxdqO4qP23YgIiICzzzzDKZMmYLIyMi+rJLLUIACFKAABSgwQAIMOgcInpu9ukChuQrvNG7Azo7jiI+Px9KlSzFp0iTo9fqrL8w5KEABClCAAhRwKwH2wHCr3cHEqAJqCafaS/3/6lfae6mrbTdfeeUVjB8/Hv7+/kSiAAUoQAEKUMADBVjS6YE7zZuTrLbhLDfX4a3G9SiStpxzFs2DOvapOiRXYGCgN2edeaMABShAAQp4tQBLOr1693pW5jrOdBpa13oAezpOYtKsafZe6gsXLkRUVJRnZYappQAFKEABClDgAgGWdF7AwT8GSsACq31YpO0dx/BJ204kJyfjxz/+MW644QYGnAO1U7hdClCAAhSggAMFGHQ6EJOr6rtAifRSP9xRgE3thxASEoIlS5Zg3LhxMBqNfV8pl6QABShAAQpQwG0EWL3uNrvCtxPyWsNqqKWc6nBI77//PtTHibINp28fE8w9BShAAQp4lwBLOr1rf3psbtpt3Vi0aBEeeughe8DJXuou3JV6GRHAYHDhBrkpClCAAhTwRQGWdPriXnfDPM+bd/rRlvPnz7cPAu+GSfTeJAUHA6Gh3ps/5owCFKAABdxCgCWdbrEbfDsR6iNUv/vd72LWrFmIiYnxbYyByH2IPL8+jEHnQNBzmxSgAAV8SYBBpy/tbTfMq06nw2uvvYbRo0cjWC1x40QBClCAAhSggFcKMOj0yt3qGZlSh0V6+umn7UMi+fmxpYdn7DWmkgIUoAAFKNA3AV7p++bGpRwgoHYWCg8PBwNOB2ByFRSgAAUoQAE3F2DQ6eY7yJuTp9Fo+Cx1b97BzBsFKEABClCghwCDzh4YfEsBClCAAhSgAAUo4BwBBp3OceVaKUABClCAAhSgAAV6CDDo7IHBtxSgAAUoQAEKUIACzhHoV9BZW1uLrq4u56SMa6UABShAAQpQgAIU8BqBfgWdbW1tsFqtCAgI4BiLXnNIMCMUoAAFKEABClDA8QL9CjrNZjNsNhuMRiPCwsIcnzqukQIUoAAFKEABClDAKwT6FXSeFQgMDERISMjZP/kvBShAAQpQgAIUoAAFLhBwSNB5wRr5BwUoQAEKUIACFKAABS4SYNB5EQj/pAAFKEABClCAAhRwvACDTsebco0UoAAFKEABClCAAhcJMOi8CIR/UsBnBBqbIMNP+Ex2mVEKUIACFBhYAQadA+vPrVNgYAQUBSgpBTotA7N9bpUCFKAABXxOgEGnz+1yZpgCFKAABShAAQq4XoBBp+vNuUUKUIACFKAABSjgcwIMOn1ulzPDFKAABShAAQpQwPUCDDpdb84tUoACFKAABShAAZ8TYNDpc7ucGaYABShAAQpQgAKuF2DQ6XpzbpECFKAABShAAQr4nACDTp/b5cwwBShAAQpQgAIUcL0Ag07Xm3OLFKAABShAAQpQwOcEGHT63C5nhilAAQpQgAIUoIDrBRh0ut6cW6QABShAAQpQgAI+J8Cg0+d2OTNMAQpQgAIUoAAFXC/AoNP15twiBShAAQpQgAIU8DkBBp0+t8uZYQpQgAIUoAAFKOB6AYcEnVqtFv7+/q5PPbdIAQpQgAIUoAAFKOARAv0KOjs7O2Gz2aDX6xEUFOQRGWYiKUABClCAAhSgAAVcL9CvoLO6uhpdXV0wmUyIiIhwfeq5RQpQgAIUoAAFKEABjxDoV9DZ1tYGi8XiERllIilAAQpQgAIUoAAFBk6gX0HnwCWbW6YABShAAQpQgAIU8CQBBp2etLeYVgpQgAIUoAAFKOChAgw6PXTHMdkUoAAFKEABClDAkwQYdHrS3mJaKUABClCAAhSggIcKMOj00B3HZFOAAhSgAAUoQAFPEmDQ6Ul7i2mlAAUoQAEKUIACHirAoNNDdxyTTQGHCRgMgDHQYavjiihAAQpQgAK9CTDo7E2Fn1HAlwTUgFMe8MCJAhSgAAUo4EwBBp3O1OW6KeAJAoYAIJAlnZ6wq5hGClCAAp4swKDTk/ce004BClCAAhSgAAU8RIBBp4fsKCaTAhSgAAUoQAEKeLIAg05P3ntMOwUoQAEKUIACFPAQAQadHrKjmEwKUIACFKAABSjgyQIMOj157zHtFKAABShAAQpQwEMEGHR6yI5iMilAAQpQgAIUoIAnCzDo9OS9x7RTgAIUoAAFKEABDxFg0OkhO4rJpAAFKEABClCAAp4swKDTk/ce004BClCAAhSgAAU8RMAhQae/vz8CAuSpJpwoQAEKUIACFKAABSjQi4BDgs7g4GDExMT0snp+RAEKUIACFKAABShAAcAhQSchKUABClCAAhSgAAUocCWBfgWdOTk5aGlpudL6+R0FKEABClCAAhSgAAWg649BRUUFOjs7UVNTg8OHD59bVWBgINSXXq8/9xnfnBcwmUwwGAzw8+tXzH9+hXxHgesVUBSgqwtQ/+VEAQpQgAI+JVBZWYnCwkK0tbVh6tSp9pjNFTFJv4JONbEWiwVHjx7F22+/fW6HBQUFQQ2s2LnoHMm5NxqNBmobWKPRyKDznMr5N6qL2j5Y7ZzG6VIB9WbFETcsGvndxhYVw6/DjC6prWiRE1C3FwSg6s2uTqeD+jvjdKGAaqIeO1qt9sIv+BcFKOBzAuXl5di4caM9fmtvb0dmZibi4+Pt8YkzMfoVdKoBQlhYGHJzc+2v60mo1Wq9ntm9cl5FLvI2m83+8soMXkemuqTUTbVISkrCnDlzEBoaeh1L+86ssbGxiI6O7vcNnVZ+f7d/uRWhjZ0ozy/E8c2bUSW/ZU+fEhMT7Td0auDJ6UIBNdhUjx818GRQfqGN+pd6zPBm91KXs5+oxw+Pm7Mal/7raeec1tZWnDp1CsuWLbMHnnfffTcWLFiAESNGOPXmVCOBT5/r19RIuaOjA9cbQKqlo8ePH790r/nYJ83NzaiurkZtba2P5fzS7Kol5WpzDU6uETDKZo4iAoPgjzVox6tow3LYXLNxboUCbigwfvx4zJs3zw1T5h5JUkvCwsPD3SMxbpgKNVjzpKDcbDZDjeG++OILPP/889LSSsGwYcNw22234Vvf+haGDBniFOV+BZ1q8Kgm9HrjVnX+7u5up2TIk1aqluypAbvq6OuTGoD7uoOaf7XJSkNDg9MPBz/Z1qw33oZh2S5U33sDiu9YjNqICKdv91o3oBrwZgwoKiqCWiLhy78N9Vqh3px//vnn13r49Gk+tQRYrb3j1LuA2keDTTN6t1E/9bTmhGocdvaaU19fb8+Yuo/V5pFqE7dnnnkGN998MyIcfF3oVx1Uf4qTPW0HXf5Q4zeOEOA4r7A3L1DvPtXOec6eNLIdw+frAYMW0cmJME2YAEtcnLM3e83rVw3UWhRfn5qamqAeE+oNqq9O6o252uZMrf7z9Um9Ke1L7aI3uanBkvqbUAOl661l9SYHNS9qszTVoa/nyrOOZ4NO9QZP/SwkJMTevtMZzU36FXR62w5kfigwkAJqz0H1ZswlN2RyYoFBniIm/W00sk2TnGSkIe1AZv+CbbNN7wUc/IMCdoGzQacvl3yrEGpwpAZKvu5wNuhUb8qud1JrF9U2nevWrbMvqp5zBw0ahFGjRmH69OkYPny4vW3n9a73avMz6LyaEL+nAAUoQAEKuIGAOiqM+uIEe4BEh74LHDp0CAUFBdi/f7+9g6EaZC5evBiLFi3CyJEj+77iqyzJoPMqQPyaAhSgAAUoQAEKeJNAdnY2VqxYYc/Syy+/jGnTptmDz/40m7wWHwad16LEeShAAQpQgAIUoICXCKi91NVB4dUmCmlpafaH+biioxiDTi85gJgNClCAAhSgAAUocC0Camehs001XPn0SAad17J3OA8FKEABClCAAhTwEgG1VNMVJZsXc/Hh3xeL8G8K+IqAPNkIYwYB0VGQs4+v5Jr5pAAFKECBARLo1+DwA5RmbpYCFOivgIx1h7IyyKCgkEHZIM+zhTTq6e9auTwFKEABClDgsgIMOi9Lwy8o4OUCauCpvjTqYJ3y4kQBClCAAhRwogCDTifictUUoAAFKEABClCAAqcF2KaTRwIFKEABClCAAhSggNMFGHQ6nZgboAAFKEABClCAAhRg0MljgAIUoAAFKEABClDA6QIMOp1OzA1QgAIUoAAFKEABCjDo5DFAAQpQgAIUoAAFKOB0AQadTifmBihAAQpQgAIUoAAFHPMYTGsXutubUV9ThSpjGtIjAhGkd108q1i6YG5vRFnBKZyqbkO3EoSQ6DikpCciOSQALhuBUOlGe70YlFSivKIejdAiPDUTqfFRiAwyIEDnspRceGTbOtFaK+kqqkRL8kgMjzZCr3VFWixoLTuFotJKFNbLIOQ9Jr+weEQlpmDcoDA45iDssfIrvlVg6WhFR1szmpqbUHaiGHUxWRiWFoPkCKNz0qJYAWsz8nZko6S9C222XhLoF4rgyHgMH5uCKKceJwps8nvpbm1ERVEe8mva0Gm2wc8QhMDoZIxMS0B4oA5aPxccH9YOtNZUyBj11SiubkY3DIgfmoGk2DCEmQxw4SnkzA6x2V2aahrRbtPBkJSE2ICLz2Oy8yydaCgrQF5JLeraNNAFRSE1cxAGRZqgk/FOnSMn+83aDbPst/LCeuiTkxEaYkLQJceKzGfuRGdLo5yHGqEfnIYIowGBA/HAKTkftjXWoa7Bgk7FKOfjSARccOgrMkysBe11ZSg5UYSq1g6064MRGJOMsUOSECIHgCsOwwuTZIXS3Ybq8lLU62MQFhKK+GD/C2aRA8B+DmmtrsCJY0VokLOGITIW0fEJGBQTjuBLjpmLFnf4nwqsXe1ol/NZbXkTAjKGIjJAhysnQ8bntTSj7OhJNBljYIqOR0qYix8OoV4v7ceHWX5vgUgdEn3R8SFQig3W+jzsOyr7o60LciY9P/knIC1BEDFfAABAAElEQVQzGYMSwhE0EMf3+ZTw3XUI9Ot6r9gssFrM6G6sQNWpQ9i+/nOsHfEv+PdZiciKMlxHMvoxq5y0zK3VqDm6A0tefg5//CIPNUomxsy/HY/9+H58a1IqDBJgOedC0DPd6g+/EgU7V+HTN1fg/Y93IRtBmPK9f8e3716IuSNT7D9q56ejZ5rU9/KjbS9DwZZVWP7ap8j51it4+aZBiDT2a9dfvJHe/1aaULD2NfzlrU/xl22lPebRwXjD3Vjw9e/hn49OgDwPxzWTnMAsckGpKzqBorwjOHbiCD74zbv48tZf4vffvwkPTklBqDNSopiB1sN474nH8XZBLY539xJ1hkzC6Dn344+vfRNzgp14BrWZ0dlUibIDW7H0H3/B69vLUNUi4V7cYETPvBu//vZ9mJsVjRC5aDn1gi+BuLmhEDkbV+HD5WvxwYYTqEc0Fj3xY9x9+wxMy0pAgtHfuWk4s68VOS4UqwXdXa2oOr4Le9YdRrkSidTHv47bY3peiCVIspphbczDnhX/wN+XfokdRVoEDrkBjz71NXzjpjGICtBC79CB9tVg0yrn2S65QFehOmcPPvz7LiR871uYNDYDw89dbdX5JBgyy01NbQlKj+zDp//ch5T/+FfcMDgWqUYnHlMX/GbEyCbnHLkudLWX49TuLdi8rx0V2kw8+dO5SOg5r5y7rV21yN3yEf7527/hs5MVKIgehqT5X8crP3kYU5ODYPL3c8G5WxIlx6PVItcSuSHtrDyOTR+9j11Jt2P6hPG4e3hEj1SrQX0zGksP48DKFfivn76G/RoTYm68BTd99W48sngmJiebcPGtSo8VOPCtpEXSbDF3oLkiH/kH9mPdR4eR/t+/xo2xfoi7bNQpAaecBywNR7Hqf36Dw5m3YdgtX8H3J8Y4MG2XW5V6oyHHh1k9PiqQv3crNu9tQbFtKJ762QLEy2Lnr5Hqwyuk4GLvO/j5v7yDrXJ8tJ9brQZ+8Q/h6WcfwaP3TcZwrWvEz23e49+o5zIbbDYx9pdCBlfmR+nzZFXacrcqa15+Srl33hgF+nB5pSv3fZirHKvp6PNar3vBhmPKgbefVb4eFybbN/V4pSkRaV9XfrevVmnusl73aq9vAYvM3qQceulRZc7YwT3ScDo9Qbf+UnnmkyNKte361uqQua0VysE3f648PWe0YkyYpty/LE+pbTM7ZNVXXUnTTuXtR25W5oUFX2himKrM/e5flXdPNl51FQ6bwSbHQMtJZcML31MWT56upEy8R/nmS0uV5ftKlZZOi+LUXdPdoijH31a+lpCoxOuDLrQ4c8zqZz6sLHpll+JcEZvSXbpL2Sq/2VkB8nud+3Plz9vzlaK6UqVw85vKH++briD5O8qLO4uVgjb1mHbSZOtSlOb9yt++OlkZl3Wfctu/LFW2VVcqbXv+otwaFq0MXvCU8qN3dioF7U5Mw7msdSlt9XlKzuevKf92Y7oSHyHnEcMMZfIdf1I+rpJ09pxsrUpbxR5lxWNTFdOtLygvbD6plFYeVA6/+ytlrn6U8uC7R5TsyjYHH0stSvnBtcqy//q28vXxg+zHjiboMeUXyw4pR1vO+qhHb7NSvOtj5a1/fUC5c2SizBepaIIeV17cUeLcfdnTR33f3ai0lu5RNrz6jHJzaKQSpR7fY+9RRv16nVJ2wbwWpbPysHLq7R8pCfKb8O957g6Kk2Pz98ryU7VKjdmpv8wzKbIqneVHlexl/6s8++jcM7/PwcqNv3hPef9o3QWpVpRWpXzTa8qfHr/xkt+xPnOuMvwnnyglcqo5u2cuWtiBf6rXtGYl/8v3lFe+e6syPyNe0pNs3+dv5bcoFZ1XuObZOpSu5hz7cZwcm6FM/P6Lyp/3VDkwbVdYVXeT0l6+z3583BoRo0Sr+330XUrWL9faj48L97ZZ7gUrlU0/maMMGxTTw1s9hyYqY3/6gfLBoUrFhdHGFTLmaV+1KZV79yr731+t7HLJb+y8T9+Ku6RYHNZCfPzSWhS3npIqpjZXxsk9ttUq1TKVaNZm4K6lG/CvYRo0HPwEH0qJ3qptuShs3Ydnl+zCLc/MQYY+8NKi+x5r6vtbudvs7kRX3n7kjvoOfvXqjxDi14rGokP48vVX8EspeW0/WYPaskY0SQFXtMtuKeQORu4LKzZ8hPc//RIrsmuAQFPfs3ndS9rQceIQimc8iAU3/wQvjIjucfcfgKDwcEREBV/3Wvu0gFTjWlsKsfJ/fo7/+VKP5PmP4dlbZmB+ZhyCjSYYpRrv/N11n7ZwhYWkdNXcjfJT3Vj4yhJ8KzoYkaYe1XWt2fj42fdRmDAE6SOT4VyRNqmROIyD+/div5QM+I0ai8z4UESFmmBLHoIp07KAlTuxI6ccExPDpXQs6Ar56utXcofd3YGOI19CLhg4GTsFmRmJGBQeDEPgVCyeFIPCU9uwc0MiVmakSulLbI/jpq/bvPxySs1JFB7eiT9sPQVNUZOUhF9QgddjQanJqCtG+c41+PWqXAQ8nIrkSLELD4JfejpujKnGn//4EabEPYDw8HQMclDbAOX4Wny0KxcHD5aiubKlR3p6vLVJlXDOSryxIw8lRyvQIk0m4NqyizOJMaMx7zBObPoMmyuqkS8lnpe9MnRXoaa2CV+Wz8S7e74ltR0NKNu8Cqs+WYO/bikADnyIZTvnIDHQgKgEJ5+35Fq265MtOLhnP8obGnrAXvzWhi6pJSkPzETaoy8g+0d6+HUUYePfXsK7mw9jd30b6g+VoUZKj2KkmsCZp3q1CQByV+KlbSfQcrwSbQ1qGeC11BmZ0VF5Evnrl9iP49qWEMRenE2n/W1GU8FRnNz4KTaXVyNPjtvLHh9qGqySp+YibMtfgF/89VdITAqHXOLPTFoYouIRE2Zy0nX97Ha88V9pRlS8Bzs25mDbiWDc8xXX5rFvQadGirL9IjHqlgUY0p0AnV6Llpyt2N3h2sSr7T0CpB1avDEZQ9LTpDpOg84oOZCLylFTLye9knZ01ragS04CvVRoOiixUnWv9Yd/dBpGRkYgPtSIYH8z2qR5QeCpLfjVujxoIo0wBhtgOPeDcdCmL7satYqrGy0nt2F7VSc6uhRESDVF5WXnd/QXcuFWmnFy5x5k72pHlSUeDceHYcrC8cgaPFQCjECYHHRRvnrKpT1ZfRFKt36MP31ai8hFD2HhopmYNyYNiT2Dv6uvqI9zSDWQfyBCh03FrLAUxMhxoFYZnp4UdB/dj2b9IJhi0jA6NcypAZba1MLSKe3m2trRKid8vyPHkFc1HpkxJkT4adVaFjnRG2EK8IdedzaNfcz2ZReTavXuRhTu24u8pg60JfpDa9DL9qQq3RSLtIwo+d0U4nheLjYeLsNDEnSGXXZd/f9CI+3ZotMn4k7/odCaT2H/uzvQUt3beuX3VFOG/IMHcKzBD6mRwQgxyO9enHQGg/zmrWg6lY280gWobkmR9p09q+V7W981fhY1HFMnJ2GwIQCnTF3YvGQnmi5eVD0fx4zG3BmpaA4E9hjM2L3yOFovns/pf/tJIJCCpMkLsKBbAmSxemdPMU71sl3FoocpJBYZcwZh3Khkac3bKXmUNnvN9cjZU4jNbXVokGYfHRbnnbnPJUsTjpRJU2CSoCa5KAqFX+Zh3fl63HOzqRW/utAEJElThRj/YCSFSX8BcwI0MzZhy8ky7O3WwxATAqPT2vWeT4pGq4ci+/zmOSkwG7sQqFdwZFP1Vfa5FV01eSjOP45t9VokyzXhhBOvjOdTe/adHB+Rg5CoHh9dLfA7fBDv7i6SNPQ2ybmqrQHNx3ZhXfYmRC6pxOCJEzByxCiMTUlExpAYqL8wl11Se0uiR34m15yqbGx6fxk+WdeKorBZuMfF+ehb0Kl2t5Cgc+TCGUBnDMxygcgxbHd90CmHXXBCMkw2LUxn2iwZ4oYiY0Qqhg6OhF95G/xiQmHy83PqXad6AtDJyTbDvvOs0qlKLupNLeiQpnxRGVMweu5ojMuMQYirfiHWTlhay7F7ZwFaYxKQGCknVYMfjrnq4JK2vmguwLaNh5CzMw+H6wKQvXUwjkhbqVGZEzBt2kSMzkhAsgSfziwNsGe3qwG10t543QersKE0BI9FSwls6UFsbyqEKS4N4zMlEJTg03kdZ84EnYOHXdReVL2YmlF1JFuCiRgMGjQIQyMv7Gbh+N3lD0NwKELDw2CQoLPz0EZ8tjIFQZ3DkIUSFBQ1y8V3FianRSLaaQG5tJ0zt6LsZD5apN3f+UkCJ40REfFh8DdY0FRRhVM5ZahVxvco3Tg/t8PeiX20vG5NlhIgZRfiVh1Cbq9BZxdaG6pQcrxI6g8CER1khEGnlYtej5JRKfUqr2lAXYvky0FBpyYqCxOjpPNbhA0R7fkIlpqb3oJOTfQIzIhWYA5rg7k6DyEDEnSqpU/JSIySc46EP/6Tk/HFSdmPve0srXSCijBgZFKQBGnqDAaEpqZjaGY6Jkh7882dYYgKkRt3f6efIeRaJufH8fIyxyHpoAUHA9/ExssEndqwuDMlg2rbRDNa6hvR0WmRYDMFw2IyMHN+BqLkUHZ6qrUS8Mo+X6Du8+AqlOafhOkqQaci7WeL80pwokRuRwYNwZggHba1u+qipO5jLQIiE5EQGSdte+X4mPImNuRWXSbolBuO+grkbd6GA8Xb0FK8HxGHjmDYmPGYPDQN4xbchBtHJCHaGDAAHQ7VvHjaJO03pe1ve2Uedqz4AB98tB6bC/3RnW7E2qWByE2bjFnD4xAvv7k+BoXXDNL/9ftLqYjeH6ZLelFecxr6PqNGTkqGixeXAFMuBlqd9H41GDFPegNHy4mrR4XmxQs48G+1Z3QdKqUKc//G9Vj36T4MuuEnePjOmZg9PB7Brvh9qw3i2+rRkH8Eq08k4Bvz4lC0LUw6NbluUuTgthZnY932YlQ2qMXfHWiq2Y9Vr8sLyZj++JN45IGb8JWpaYg6V+rnjPRJCbeUchZn78a7y49Ak7IYnTmf4oOVhchtCoFp4u345Tfvw6IxiQiXTisu6dB/Lptq0Nkijf+PyQ//DkRnykgLl234f26hfr4xIDIxHUNGjkJGxDGcqN+Fj//mh7ayMZiY5Ieukxbc/MTXcdOIOCRe0mO3n5s+t7h02pGLdZf0RIXaiF06ySgWq5S3qD8O6QUcHGD//aK6HYo0SWmwyjyuOLdIaWGA0YgA+bfXgEHpQJfaO7hYrX71R2hggHRQvKhZhlKHsoYm1LWqIzU4skpYqmr9pTQ4QEbAkDVf/jQiJXH2+eRCLPMN3HRmX8qIHeq5uLdJExAIf8nMBR33NFr4+Umvayn11gYPw8jkSBn1w4U50UrnOTFWe81f3ljNjdqBR46HlnJkb1qFNat2Sw/w8Zg19zZ895ZRiJCFr7x8byJ9/UyODUmzXq+/8jVOfnPtZcdxOFdqnqzJWDw3EMsUV3Sw7S1fp4+PwCApdFBrVHorzLa2SHOSfOxas0dGgVGnDtTk7LK/tuilNvFQO/7yHw9gdkaM1HT6u9C7t/x4wmdqLVc9ag+vxz+efxsbpAa40qqD7tgKvPyztei88zm8+0QQwiXodEajqp5C/Q86e67NHd7b6lCRK22vioGg+Jl45MY0qS7Uueig7EDJmr/gpX8sx/+uOXN/n/0elsdHIMQUiHnDYqSMxMmTuRJFR49h5T/LcP9z38GQAOnN79DetFdLv1SfdjajeM9WfGnpRt0ls5dg+2svwdrZDmvwY/je2J49Qy+ZuZ8fWGRomzwczz2KLVJ3rP/qw3jyyUlIr9qI1W+/g5/8+QV8fV0BXvroGdw2QoYMcVkPXzVbUkJmbURpjg2T7kjF+LRY5x8b8ivwT5mIqXeHYIm0oXzyGy9iT+MOrHvnILIzJmHy/d/BH27JkmYqWife7fpLYBSGpKxECaQKgfxadBXWoVY44nrGJ6FyNxkfjGCndqG/jsNLLtrdLW1oKVHbVV6m7ZxSi8PVNShqapO9G9l78Hodm/S5WWW4uerSUuxu1iHo3ttwQ0Yk4qQ0zv0m6VFdvA8H3/kdZv36y9PJ07Qiq8aEWKn6TV2Uab9wuy7wvJqQ3Li1HpHRDKQt8tjRWLAwA7HtR6+20MB+LyPi1JzMwac7pS/CRZBKdzuaP/4lHpV+AS99cyG+PinZBefOgeXo/9bl+hcsx+bib+On/28XSl/bicqKoRg250G8+s4jmOyKG/szmZDbDO+aFLmbO3SoCfWmUfjK0w/i5li1ROKio9ZpWQ5E8k3fxQ+ffQ4f/vcT+N546TxjO4DPXnoO//fqcnyUc/qezWmbl5KW3PV7kbO/HIk/uhdjTFLd5bSNXW7FUqocnICU+36PAwcOoODkfhzc/DFWvvyf+P1jM+BvH9qiAntyZLiiL4+h6nKrccTnaslTznGc3H0SGgm8AyOCYZRqqfD04RgxajQWB0ukU7sBy3fK+K5VrVJ+4cJJOtMohdlYfWo4YqNlvLkYp9+OnMmcDv5SnRwnbUzv+s79+OodYzAkVY+Ggt3Y9MrP8NX/XIodpY1S9e0sDTk+DBEYPv9WzJTOfTH1+3BChjv7ZFfFBQUeOmkzGZ0aLR0yXLhPuKkBFDCjofgkjpY04cig2/A/T81HRrgRga46dV9XziUoHjQeE77/v9j4xn/h3xdkYWSUdIzZuwx/+7df4o87qtHc1Vvx3XVtxDEzS6dfxVKBL377KXSzp2DoDSOR6rrOBX3PQ3gWhn/l/+GfuUfkGnIExzd9iJV//wX+48H5mCQltOpkXfEljuwtwPHmHk1c+r5FLukiAXe8jexj1uVHrjTi/7d3HvBRXNf+/6muVqvee0MNSQgkRDPVGGNwxQZ3Jy6JE/vZeXlOXl5iO07s1H+KUxw7duK4JC64G1zAppleRRFIqPfe66qudv+/WVEECJBgZ7WGM5/Pwu5qdu6Z79y5c+65pxzduBnlLvS7WTQDt8yJgs4qOTqPi8zlLVc/hMRNhZu7DyZMoOfKT5/FusoyZJeXYh+X5u6c6KWeBYTLPWX7d2LNp/uQs20LVikZoZkrsy4rG8X6XibfrsTuF57A4/0/xINzEjA11EOVwBU7LpE5MWE20+xxo4+rfyDCmQh+YkYa3PzfwOp3t+FAXSs66TzXxOXTQLUmBUZGSbe0o/NY1K8dfXuVBSV7Lf0a/f0RHcYl0BzmzaxkdgHyGeBin3UW84zMB8hiCkcPICd9Em4M8UGAy3Az3/H+ZOn/GUjQkI/8XfvwydtH4XbHXbjbqwmzt23A2rVb8HFWDQo//w/emhYL1/mJmBrsdrqRwQIC8Qo4apld7Up860flCFm3HfsrNuDdZ2tQeWQukjIr0NrhgujYCEyjy4G60fxjOR0uRdGXR8vCCmedKdl5ItrLkz7CLqrcV2OR9mu3b3sRsraXoKLOAwsfYM7LKE94WCtH55hhcQxhH9b60Cd84U0IYNyAz8qPsGrDAeyrO4o1efV4YJIXc906q3D/jFFYZu6grxW2r/oEB7JzYOfpBk9H5kdlMF9BSx/aGahl2PI+VtozIX7XnXhqQZR6z6exiG5PdxK6VgS6KWGEzBzh5wn/yFjExE7CjOREvPLaG9hUWc3CA/Sh7qIPtYc1xs+xnIDsezYCl4jSqSQ6ZSBA2R6sPUoP8LgZuGLOdGSEqPHQPBvK498zObTOB37RbvAL88fd2zai4KMjqGCVkK7e4YETx/e34P+MGG1vqELBwUxsoR/jmVsryrZ9hvdm3YlrGL099cwdVPiGPFypzLl6wDs8Cve40t+toh69Je4wuHJgUXvpXzm+8mKmA0NvP5iREyZaO53d3eCrWBdz6P86wMTgin+h1bZ+9NPvtmhXAdxnXIcgP1bQssaYadKjqeAg9q/bhHd3afGj32cgLciIyZ70o2OFpoKcz5Bdyr5TWIdr0/hAVUXpJGR7elh7RGHOilvhERKGCdklyOschK6nmqmB6tDjnoLklBTMj/c/t5+a1a4XG7JT+ow7vMO4tJ7did5+Jtdmnzm11/gwM4OXOUPBkC3GmgJ+XdsiQVM3ag7sRG7DIOxi0nHHjRlmVxfbZsgJrJ0zPFhUIYkV+FiOD231jTicSZ9epXKOVceTc1x7JaiztxUVhYXYy6j1M2Pk+tBbeBCZbr7oSb0GP10QdY6Djdef6LeqY4o95cVKgzFRgeivPoycj5gRxpkGDrWMFuN1upd4u5eE0mkyl4erR+42pm3STsOS6dOxiMEhHsojwUD/D6ay0CqdUxW/BUaFsVqIniXR6k1e8KWvnLuWfmucqUEThrnXz0H41jaYXOnH5qlVd+br4MpBMAyRExOQdGLEpmyNTWhr7WLYCqP9g8OQzPyY7ipGhZpY7cLY1YwyPkRcfWixcGcaHnPAkCPcE+Zg7ryvUBrphoo4prtSc/nUXsv2PeAe6A5TbTu6mzqg58x+QAlYYNCAM68TLxICuOzuzjRBVrsZBvXmcqkHdnbhymciEMI0W1Zpm2ms6vOO4sjBIhT4LENiqI7lEe3gmpyGaTNLsPT9Dciu7kdbHwN9WK1C3Y1LlKGTccWtfC0fwEBnHVoPfoh7Gp3gvXAuZs7OwIwISwbjXOTZMGhR5+WDoAmBvFZNtIzTis4AqFM2Z0bl+nIMsGbwyykCfN0+KAqngWl88rF/Rw7aQ6YgfuZCXB3jxXGSQZn6LhgYbWSvBEedGM/G8xxZspPlhFv77TGocUcQc7SaM7/xusdOmYzUnEL4HziKRH9+b3YjGk9Zj7XNsY51WhGanIAEOxP8zF8rFbh60VLKEsAG+m970Xc2KASxzCZiE5gVGZnyr4/Xv6W2DUaWGPXhs1PDoCN7Jx2c/RNw7Q1z8bfD/YgMYSCRl3XChI8Rlf8ukoCaj/yLFG20P2ckYWc1Wo58jsc3R+PhbyzFzdMnIEAZDYx9MNXtxRcHmeqESwmqbIxq7a7Lwqan7sZVT76NDw5VovlEmUPmJXNj0mvHWEwMjmWqh+EJ0lWQxnsKFj/xO/wri8vrh469Mj/Aq/dfgxuo2Lh4x2PpH5mf68F5WDzBW6UlQKXsZhMa1j+LZTf+BE+/uQ17ajuG+es5Qcul90nx0ZjPZOiqRsrZucMvgnkDJ4azL3BykFeFJlo7e5QScH1UxltpebaLwlWs8xxOPla7GTqbmPO4AmtKUzEjwRdeblYaNOnf1ddGhbf+tJTMGm94hIYiOSOIndINEZwkuHGSZq0HkKmX7g25W/Hc089j/cRbcOPd1+LWKyaYo4BVuEsu8JAu8AqIwMT0yQjg9K2igzlGqXSeYun0SkFEqD8CrV3D+gLPaPx/xqwFA23I/fcL+CpoCZKvWoo7poUyKEShyiDAXVuRU1aF4l61J0CjJGGsw/6Xn8QTT/4Kj762HaU9xycdDNBjBLmWbl1emmRcn85xzYr3zzmlZ9CeXfCV+FXWXmw9/kw4uInZVf6JHwcwm4WTN1KWfx8/+unTeGfFRNtYWldOSF+Okg1v4meLbsWP38hEFgsedJtvNrrnUJF24aqDbmEaouKCrJD145yE5Y9jJHDxBpa2FrS0t6Oin2Z8eg3WtXej79hgbJWHVkchjq77CC88+Rw21xmwe83TzLnIGZHSuL0bTN7L8MJHqdCq9SAw9WGAiYzL6I/UUvdL/LSlCNm3rcDDS9OQ6N2FPWsyEbRiKVJnz8DcYOuH9YyxP1hgd6Wurh6NZUWoa9iJfz9Tipw9N+HOh1mXeE4k7As3YHNfOvyj43D9JG8LtHeuQ7giMCUDsxeU4Y5PD+OdnWux/dBMRFIFNlaU41BlLzyWfw8rpkcgmjkDrbMZWCe5HEWVedi14kq87K2hj5VV7hSmyfNHeEYqkuflwrjqY/zryxV4Yk4wQvqLUX6YKa72MdfAzHvwrYVJmMTIcfWkGlIqmo7uRcHhnfjsiy34aFs5OmZ/B6t+fB9mRHKJWnfxQ9Por6eSxqkfjZWV6GL1KAMnkgOGLnTolTHtuJcv/bUDJyB8/i34461b8Z2sQpQuSkC9dy8LH+Thy9pA3Pj8PXRbCUeU2fw1+tbPvyctbB1taGloYOIYZf7UBn1PH/rMk9vhfhmMquZ43NrcxFyiSoEIBoTp6cqhWlDY2SSnksi2a4qb0avnxM6xl+72XGlRdMcTMzv6ejcUoGbLG7jj16tQbfc5XmaGCUdaCI/vor391/jtvRrczBzDVtl69OhtbkB+n4EjRB9amG+5g5PUE2IPtqL+MHOxbsnBzl2HcUtNLf7z4zuRxHG+9kg+7d8aTPv5Q1gew2IgVlvyNaCziUv7bW2UmJMgcm8nc4OSasxmt6H+UVvchB72T1ByU1unuX8cX/kydbahrbEc25nMvvSZ76K08BHcezuNJ1OD4NtdiQ8/scNj90xHcoTfOATL2izYUQjGFSau2Dgw1SUG+5jikQn49dXYnj2AlJQgeKq9GksJHZ7mNgpJT92F6UNgrMQXP/gh/vr2KqzccoipQjgQ0oLUVZWHg5sOoExPsz2XciPcVXx49FXj6JersWrlx3gnq5LLHkxr0teLXlZd6enha9AevVEL8eBd0xDJFCyqREIyrx+9yqH1sEdbJQdRpvzIP3QIB/cfQU6nA307pyB9WhqmRAfAR8s8cKeSVP8TU0iVbt6OQ1xSzWXljYRrb8G1sZ5wVS0/Jp3sFR5eHrBrqkBFbQ1KyvNRXHQUu5uMCPJg4ujYWCSSh1IOUl0enBU7cWnfOwDxCaz6YyjCjp3bsHENEw6XG6CbeS2+dd+NmDvBD94ujtbJ08lgt9pDB3B0ZwEGZt6AO5J94cIZknoK3vAuxuTMtBB4BQciiqXX61avxCeff4KVH2/F7pJ+6GYsxt3fvBXXpYYzVQ0LHqiSrojWVpa22//iM3jqnwdRacfAhsR0TJu/FA/eshAzabnwNrunWIcIWgqQu3kVnnr8j3j9y504WNaETqZk0XdWIH//LpbTNSIiLQKebsyCwapNDhodAsIDoaujH9xXX+CdVXuws8QR8ctvwT03z2KCcJZVtWA1J2PJOrz4pxfxwivv46OdjORlfj2DsQMN5VnYtYsTuhp7xEwNg1fJWvz2mb/in299gs/35aOS7jSDxnaWX92PrTuqWa7YGZGTQtVNtE/rZAezIOz/+EU8+uvXsWbHYRTQQtXb3YGe6qPMafkFtmgmIcGfFbp6y1CwZS3+/od3sbGqmYU0qBwrY7cybvewilqPA8IW34brpkQhicFbqo4Tg5W0YL6IN154GX9hOcw9ZQ1opeGku6EchXuzGIBTiwFmvEhiZTkHRyXJNnNIcuJ4NDcXR3bsRk4rJwXaYETRTWX+1HiumjDX7PDbTo33nNgbS9fjJz/4DV77eB2r9pSguqOT17yNBQz2YuO2JrTa6xAWN1JREkXZaEDmy+8wObwzPCfPQlpaCqapXW6U/aOzPBOHVr2IR371Ou8tlkxt6GL/YNXAmlwc2sL+4ZSEWPq4+7G8pZNGg2BdLwq2HUJNfTmycypRWNYBe08PhKVOGXqGaDlOWWmoUOMyWveYCiglH7EjDPXV9EGuRVVnH/q94rB4JleWPBjgaYXJ0oVphObgDFpoImMQ5R4Mlzhak06h54tQf0+4q+2IQ79JF5YPjJ+9BLfHX3mKBOYPjDA0Rl2BWA4CrqqNWs7QeLAs1/W34pvOPkip6kATzREu7n4IptNz5KREpsNxs2Ku0NMwKNU25i7BdZooRMAHyXGecFFN4VTaptLpTEUifi5W3NMDr0nlKG/Ww0HrDm2gL7x5vSJZbs6DQUSqD8yKOPRn8ghNRPr1dCegv53fgUq06R3hExSFBPr+zkmPYvEYJgS32sDlBNeQeMTPcsa9GSHQWk3hNMOAxieKSoobbvMKRrjrRuT0mtBtdIV3YAQSprHax6R4BDM3ogX1JqXhYRsVbAcmIA6MwsQ0HSKmxCM2gSVs/fwxIXAcAv9YRELrFcDymwlw52vS/OGiOsLk6cNx7HjCeE5M6IoQlL4IK/QmeGWVo6zNiX7UcZh79QxMZ5CRxsKKup3GE4FhUYg3uCI0bRbmXHtSPpMLJ/VBdN/heGyn8UJoZDR6XX3BVKxYeHI3+pOHIowPcrXrXSlNOlIpd/OPQHy8A1+TMGeYHMpbT/oNurBz2dmxFC5djhIWLsOjw4U176/cjBpELkhAop9O/XGCAUG6wGAEx6dicvgkTJ612CzF0D/u8AmhT6FivWZ2gojZi7GY7kGBkwswo0Fx2XJBWDBz/MbFIp6TkTAfV+tMILnErFzz8JhYOAVHIGY6sGSY1Ca3IPqcMgH/sO9OvmXVGfaJjAcfxn91ucB72lSkBTIrgxU2Bz4bdOb+YT9i//BiUJZW6R8u3vCLTcfSOx3Qax+NKsrW6xyIwIgg+PgEMoo90srjthXgWKUJe7hygFi0TA+3mBLk690QHOxvDmZVvTbJsfOzM3GzyrlKI0JACAgBISAEhIAQEAKXLQHV7H+XLVE5cSEgBISAEBACQkAICIEzCIjSeQYS+UIICAEhIASEgBAQAkLA0gRE6bQ0UTmeEBACQkAICAEhIASEwBkEROk8A4l8IQSEgBAQAkJACAgBIWBpAqJ0WpqoHE8ICAEhIASEgBAQAkLgDAKidJ6BRL4QAkJACAgBISAEhIAQsDQBUTotTVSOJwSEgBAQAkJACAgBIXAGgQtLDn/GYeQLISAEvhYEWHMeLKeI4hIgJhoIYr115+OlHr8WZyBCCgEhIASEwNeUgFg6v6YXTsQWAhdEoLcXyMkF/vQ8UFoG9Cu1j2UTAkJACAgBIaA+AVE61WcsLQgB2yFgMADV1cCnu4CmZkD5LJsQEAJCQAgIASsQEKXTCpClCSEgBISAEBACQkAIXO4EROm83HuAnL8QEAJCQAgIASEgBKxAQJROK0CWJoSAEBACQkAICAEhcLkTEKXzcu8Bcv5CQAgIASEgBISAELACAVE6rQBZmhACQkAICAEhIASEwOVOQJTOy70HyPkLASEgBISAEBACQsAKBETptAJkaUIICAEhIASEgBAQApc7AVE6L/ceIOcvBISAEBACQkAICAErEBCl0wqQpQkhIASEgBAQAkJACFzuBETpvNx7gJy/EBACQkAICAEhIASsQECUTitAliaEgBAQAkJACAgBIXC5ExCl83LvAXL+QkAICAEhIASEgBCwAgFROq0AWZoQAkJACAgBISAEhMDlTkCUzsu9B8j5CwEhIASEgBAQAkLACgRE6bQCZGlCCAgBISAEhIAQEAKXOwFROi/3HiDnf3kRsOct7+UFpIQDOh2gfJZNCAgBISAEhIAVCNiZuFmhHWlCCAgBWyDQ0wPU1ABHcoDkiUBEBKDR2IJkIoMQEAJCQAhc4gRE6bzEL7CcnhAQAkJACAgBISAEbIGArK3ZwlUQGYSAEBACQkAICAEhcIkTEKXzEr/AcnpCQAgIASEgBISAELAFAqJ02sJVEBmEgBAQAkJACAgBIXCJE3C02PmZjDAZ+tDe1YuzRSbZOWrgxKAFV2cH2Fms4REORFmMxkEYDIMY7O9Dr8EBGlcXaJwd4aBqw8dlMcGktN/Xg65ew/Evj/1vBzsXHdw0jnC0t4IwpkEM9PXBYARMTi5wdbLyPIPXYtDQj/7+AfT2Kywc4eSigTOvhZODvbr94DTyykeT0QDDwJA8/Qb2VDsnuOhc4Oxoz75hhesxgkxDcg3COGjAQP8g7LWuUC6TOtKwb7IdhYG+px8mnr+TxnncrgcvyNB581412Ctjg/X7xJmXxGSWydDfj+5eMgL7hrPSZ52gcVJ57DpTmBG/MQ0OYOBYPx4Y5C4cW11ceB15TzlYY1wZUaqxfDk0Rg7296Jz0BluWifzeKhOnx+LXKfvy/45MIA+fTd6T3mwUVI7B44dbtA42sG2kXMMHjBgkH2mj53FaHKAk1Zr/WfB6WhPfCZjA2XrOp3xiR3I2hkaPjc0fG5a5xk+rG15a1ECFtJAOEh3VEO/9VmkhkQiKCgcPiO8Am99HA99cASdFj2FEQ5GWapztmHVyr/jFzdMRWTMw3jiP3uQ1aGMztbY+tBVlYmdT9+EgNCIU1j4hkYj8JebsLumA/3WEKW7ANueewq/eexx/HhTlTVaPLWNtjLkr3sFf3jkpiEOoTfj/mfexSdHqtF8yiB+6s/U+WREb8UBfPWPx/HwjTPgExIHn0nfxTNf5iC3ueeskyV1ZBl+VAO66wuRs/Y9/P2Rn2F1Qz+a+zlLUGPrb0Vr/mZs+NN/IzkoAgET78RdT6/EJzm10KvR3vmO2V6Jsu0f4N1//h4PfV6G3gGVzvt8cgz/e18zmnM2YM3vHh5iFDQTi7/zZ7y0qRANNiAeMIDWom1Y88fv49vzJrEfR8Hnpqfw27VZyGvSj2M/Hg7xfO/70Vm+B3v++h34PPoxvqpqG5/+dz4x+6pRsfU1/GJi7CnjuE9QIoJjr8OT2+tRrx8431HG7++mAU4yG5C15lOsYn+5fcnVSF76EL6/rnL8ZDq95f5a1O5+C78kY//gkXUHn6RH8NjL25DdYxM34OlnIJ/HQMBClk4jLTR6NFVXooFD3si3YAjSoidgVkII3MYg4Oh3VTSYbtTsXIVVr32C9aV9aJ6yAA9+8/f4aMoUxEYFIcjdYfSHu5g9B9rQWVOMHZ/m0ZAzXLPygINTEr63OBnhnlo4XUwb5/0tb05jA/a+8jxe/TQT2W5TMPe8v7HwDj0F2PLai1i5eiM+yq0dOvjgYXz5xoto7W5H03234TvpAbQjWWEzGWBq2IHXnvgtPszMxf7GDvKh5bVlE179wSC6HnsAt980G3NDXK0gjNKEMnj2oDJzM7avXoW1e45gZ4kR+u40PPf/VBLB1IqSLR/iszW78Je6yXh1/w/gVb4DGz7YgdW/KUTeI5yczQ1V+XrQwsUVkd6qbGxe+z7+88V+7M9tgINPNNJ+/A2VTnwMhzW1oGjDu1j1zod47qs883g2iDocXv8GOrvqUdL1IH67PBlKLxkfq5wRPTkf4aWfvYZP2WeOdnSxK7EvHXwPLz2jR/cjd+Ke5VdgiqeFhvYxoBv9rgboC3dh16fv4amXdgALbhr9T626J59ljTWoLszF6vbTTASe/hhMvRrXpnjD3cUWWVP29nJUHNiC1a+/ieePxmLFbVOx/Cd34bHwaCRPCLYqyXM21qNHT3MTclupIA9/XA77kdPsFERNDEWEi1WeFsNalreWJmCZu8XUyyVsAyo6E/DEH/4Eb64NOpvXG5QlFAP6Ctbhpc+cMTEiEhPDPFR4qHHJwECld88qvPSPdSju90fognTcPD8Ds8OD4B/mBy2XTy1zsue7BCYMtjeho7MLRxf8F577n2AuvXBJ3fwzZ9g7+GFash/8uZyk3kNL4dGNpt2fY+VntCbkN2Fg0lnu5vOdzgX9XWmrFzV5NbCLmYl596dicncHDE25eO+Fd5HdWoSjFWXIqu3gFCXggloY24+UpWs9inaWwGv+LbhtHnBzdz2aCjLxzmubUEKLy2c7psB3QjQmh8TCY2wHv6C9TZykoXYvVlJxqN9zGAWHC1Hc6gl7F0UZVWPjQ6jiEPZs34VPDlShedZtyEhOgi6oE1Ubd+FI5l588mYKbpl2G2I1vH/V6pymHvR2VmLLW1twtOYwcgsKUVjeAy8E2oCFzoT+slxUwReauXdRATfCrqMEGz9cjd2FjSjdfwjbXHbgyKJETOUE1tqeKjBS8RloRE6pFok33I2gJd3oaqtBU9Z2/O39PWgpykdZJS1vnZz226zSaYKhpQCHN2/E2tVbkdMwLvb1Ud5gfWira0V3jwfmPvl7fD9gWD5bjQccA+KR6uUMF5tb7yXj1gJkrVuLL9ftxvrueHzzoWWYlx6BqLBA+Hl4wIP3uG1sg+ju6EOfnR+mPvUbXBOg5XPx2OBj7IaxpxKf/PJD2E+egPhQX7jbiti2Ae9rKYWF9DA7OLh4wjVmHr69IA1+GgcqnQoPxc+zCxXvHMFHpSGIjApFlLezxUGZ+rvQW5+Ldf/5EJsqvJF83VW47oa5WJjoh2HDhMXbHfmAfbRyVqDsaB4OmUJxtS4CMUnhCAoO4M3uDm9Xde2b9FrEYF8nerhcm5lbgvKKZnRx+ce6HIYUXKOdB8IykpHs6w1vx24MNGSide061BR0Q6/48p1tWjsy2Iv4lv2Qy0xdpkBMum4mQvw94N5bjfrDoWjbmYXXSppRXlWDvJpWqsqwitKpnIxp0ASNbwSi46JQWt8ETevZVgku4tRP/LQfrQWHcCi7CDktGkRFBcCLkyF7L1/4UkFxaa9CwVYqny3LEMGHqzP91NTZjk1+XHwRkRCPxMNVaKjooc3XFjYj+ntMcA1PQVpqBGaHucKuvRBh+ip0dO/CV/nNqM0qQWXPIKa4UekcD5GVe8YrEbPmhMHb0wn2zcWo3W6PNe/tRa4y3vLvxwiPh3TnbdPUU4+iXFrVC8pR3dLGtSnb3Ux9TagtLkZuTgUMKXHQRScjJcIfQQE+8HDXwdXmlM1jLA2tqNj3FTZu2ovN5Y4IWr4CD949H/58KA89l22JOXursyc8IlNx9fSJmBaoO+Efa+ppQF/FZmz5Yw6SEiIQ6aezkuHIlvhcerJYRum0c4WbtysyloafRshAi1sbcndnYzBlJoImBCLY4r2ewRft1ajbtw5/f/0QnB79OaZNjUGcaz8aapvh6e0BHZ2PT1obTxPR0h95w9eWFGDP5+uQs6Uc972ehuvvv5oPiRlIT0zEtPhg+Lg5H5/LWbp16vn96G2pQenBvcjUxiDZW4vyxgE0W76lcxxRmXFoETYlfWgfc7CIA0yeoYiL8od/hxNCQyKQGuihHofh0nFcs7d3Rtj8RfDhg9pRUag0wQiYPB/Lr5uA917JQoejIxUtBxWs8MMFOfneztmdVuBF+H6MEX0T7eng34XtebkqXidaNAvyUV3bgn6nWIS6u5jZn1At2b6hvRgFVd242ofqFFmostnpoPVOwJIfJgBdKTBll6H9aCN2q9LYWA/KCVtwKlIY7Kh11Qz1Ta8ELFwyBxsOlGFPEZeyGXTFWKLxWVtnH4ZLGDLmDJ2Xsoo06OwKj+gYxLA/tUTEISwkAAFulhnWx0rv3PsrqjCtWmWHsCu7HXqdJyJTQoCSknP/bNz+yr7QVIKinEx8smoVNr7xIV7NuBsPL5mKObPSkJgQh4QgPlusbu4+HxDK3ZyDrR9/ji/yHNCScj0evyoahoZ6tLm5wVWnhdZqAbXnk1X5uyNcAyPMr1O1BwY/6dvQlncYW93TsTjCD0GeljdYjUZC2ceyBNQ1VnPJ29hWhK0f6TErmn4kIT5wsaz8NBe1oT4/E2uffxO77DzhXvIxXnr0DkxLuQqp1/4cL24vQiMjggct3e7ZjkcLY+7eLHyx+ZijtvEgPnvl93jy/gdx/wM/wQ8/ygUfXWaPvrMd4qK+7ypFcX4hXtkSiAduy0A0fUctznysAho60F2TjV3vvonXP/fG5Nsfw4++dxcemBZoHSWPEdp2Dh4I8HUeUjjN8tubFVF3Hze6PHggYUI4JscEwmes53bR+9P6wGh1rYYR9Bd9rHMcwEgf2rJGdDb1ULnWwN/d9TT2/RikD/DR6jb0K6kOrLFpdPSHc4bOZnQkR/Mk1fW4wmlmYM8IZXdonRgZ7u8NY0YiEpV+pO7IOQr6yhJqJcrpE/zemx/h/RnfwHf/8gM8eusspHuNiw32PDJzyd9Yhw3PbYZHaiqSpicj2s0W5Tx+Gv1ozN6LHbl52Nh57OmR+RZe/NUPcPft38O9j/0TH5TRL9ymNuW+7UfZF2/i1d1HsZurF71lH+NVrj5GxV+Db/7iTXyQWY66Pivd3xfFhsG4rTXI2bkbzTfPRmyIJwIsbrC6KAHlxxdIQNXh3sR0RcamOuQ4zsKyuGCE+aqg/jRXozYvH19ktgN+1+Caxx7CXJ96VK75BK/+5UP89v4cFNHP9KH5cUgPdlPZssaBqvAIsipLcMDu9Bu7DY3FO7Hqqce5nPo6HpzkjRBLD7q9Jdi7Ph9FVUYs/+HVCLYrH58lwOGd0ViFnA/exgfP/gt/r+pEB9PQbP4yDD1+bvDznoNZwbrhe1vvPf2QB7jUd5STkn5tBuZMTsGsON/TFDHriaN6S4NM31Xbjr52OhB4jdRaHwYGG7GN7hh6QwiXaNX0OR6pfVv8TrHODaCmOA/lbUboYiZiyQ0ZiKHCqZIdeNQQjMVf4t//WIm/v/0VynrpnNB/lBa5SPi5OME9IwZBNuOzp5wSU0/VlaJ01bsouvO7WJbgBacjmXQHsOHNWIsC+ltX5x0zHgwXVZ+PvK0f4IlvATFrfoh0Vwfoxn0SogjIwEjKfWDNfrQ3umLightwx7dX4IGYLiz4v//Gnz9/Fk9ytWPHrXfhV/dOR6BNyDwc7LD3SpxIVxfjAky476EkhHGSbMtTlGGSy9vzEFBR6WR+SH0L6gqykTd7KkK5lOpDX0/LbgZ01legtKwI+5RUK1o/ePvR5yaaDsdpxZidvhGr1ufis/VZmBPnhwlBbvRjs6wEpx7NAe6JV+Hmh7n0cn0r/9SP+qM5qCw+hK0H87G/qBUdTTl4dX0OFkVmwJdKp8V8LRl1m/9FJpoMbvC5IgnJ9I1xUJ6Zqp7vqWc/4ic7KtdT52Hxw0YYMvdj9b8Z6FW0HV+tZJ7SNhPcH1uMFO04jH69neivLsbWAyak3HIdFmTEIdHTYldjRBTj+6WSe5I+f6dkUzhVIhNzuuoHB80RpLbQdU6Vbjw+kYKpCcXMdtDtHo2k1AW4dXqo+eE33reVfUAyZi25AYMuHth3cA9eWcfgvHW0cDkNos14Ax6ZGzX+KxzmSzaIvtoCVObn4nPX6Yz2DkGwhxFt43DLj6kHMbAlYdl38Gj6MtzYSc9Tpho7ejgXxXu2IrO4BkXtDOAq2oIvjnwTcZN9oVPdV38U0g9wQtmYxzGtDq0dfoh2ZXheYAh8wxyx4OqpeOPQWpQfOoK8YPp2L52Ma4JseLzrakZ7dTN2lk/AFUm+8NDaRn7cUVwF2eU8BFRUOvugb+GAvb8E3nNvQbCXqwqzwUH0tDWhqbkB9cqJOjDRNf31HDRe8AoKRXwS00KsL0XdwSJU1k9HBwM3vFQLkDALABfmb5uivMwL6ANoVPzoyichJm4HQjbuxoF9JajYXYS625PRbXKHxiJPLz4c9RU49MVmZJlcqUxRET/AUZ2z3r3Mf1fPJNKddcwDuXE13gi6FTdP9IdO7QT9xzseffi8J0xGmn8QfCdOhE+HHh9sPYwjWfuxxz0c2d9cgJQwFSzgx9sf6X8TE6M3VKI08yBKQudi6Q0zkRHLpXXVQrZHEsLK39nRZ1WngT39m0felKTiWkS7M5UXM09YpFuO3NDX5FsG5Az2o6d0HzaUcdl94jSkXZnB1RKdbbBxD0PCDFcEhoUgaVI0Otr/hQ3Zedi79SACwlJx++wohNmEYseCIRV5XFHYgNU1UdD1VGEbJ+PtxftwiFk1OBMCCr/Cp6u84Lw4DWkJAfC0hc5n54ag1Nl8sbsa6RrANHj5kwtRnhyG2K3bsX5PPjLrCrC9oBkPJHrBRKVzvMU2sQgHWmqRXd+Dzn47umWzAIcj5bLTIjwlAWGuW5BbWo+WilLkN/basNJJP/fmWtQ01uEgL8BDgS426Dv7NRnGbFDMsz2BzhSVUeitNY1o6eg+JeLQpGP0q48nnXy1py450Y+vg87Lh/f2YPEvuezjSj+oM496nm8Ue8sgOqvLUNfJABmlgox5U25vdwRFeqCblW4MrBhh3jiAGWnJMVESjZZWzQDfoe+b2tHDSkk9VDpxUUqnUj2FCkttJao62O4Jq5FiwdUhLI45SKnMOZlHH2XEp+9cfCpfSUhIVJb33fGX4jfwQVMX+mmZNZ/OKEcqI1PsdHe0oLRuuB8R00BpGMQVEIRwfQ1KsvbiswP5ODJS/GrRPmz9dzlv4mmYF+1tVjqH4FzIv3RWp6Wwva0V1TyXkxu5u7nD3S8AwcNdBxzoV+odhfgrIhDu1Qt9x/Po3N6M7vZ6VDdzoLSE0snl486mFrQ0tmE4IdASpPPyQcSJyEdF9gZUl+RjW2YZfO98BNdnRCLKcyiw5uS5XOQ7+jO31TWitU1v9uE9fjSTqw+8fbw4CdNewP1w/CgX8D8VSh1XG1xozVUinA20ep66OVPp9MXkYG+40GFxlN3y1ENcSp+oaAx2N6Hgy83Y45KBq6+4AtdPjbQNhcjMmUoFx16/+OmYzWV//44i1P7hc2Q2tKG9kvcBr3GYTVzFXnQ0ViF/5xbs3PgWdo7UR/Yxj2QNq814+nAMpdJp6QWxkdocy3f2XNjV+CNhCl+Tk5EUF4YQl/dQ9l4W6vR00znxHBjLQVXYV8lcwApPSiI6ZiXms5DBOGbZ7KHxCUQIjTIeLM3SZ+hEC5+ntrsxVVVNFWqaG9G8YBZimJvThm2ytovRRiUbvR7YvA/v/+8f8Pqq7QzYGfbAmvff+M6Dt+HXt02B3/CTbGUexIpGpjCahO8l+UDnciEjCX1U0IgtP7sLT20ow6G64wk2+FB0vg2/ev/7WMAADBdX+gXyhgNTBelZdnLAQGXMiSX1GK1n3jSM2lNKaF10pCHziXUUYtMT9+K7n5WyEoUin7IxCtv5Wvxr7+9xTbQXQs9IYOsIbfgkTLxSjweLucTskETlSwvPUVsiBllJJxN7Vr+KRU98ONSk+V83+CfNwqKfP4u3pw/7WvW3RnTnbcDHb7+Bb/91/bDWvBBz5TLc9MMf409XnxqLOLSTPbRJi3HjTTtQ0pmHnSYPeOoupF8Ma/L427ZsbHv+X3jhdyuxZnj/nLwcs+94AO//YD6G0iEzEXz+HuzNLsbrLjfizW9dgVj6ZA1NFI4fzAL/t+zDqsf/jFff/Qrbhssz+yF841t34dm70+FvgWZGfQh7D/gxAtSdftX9XX1o6uox2+JPdkElKjsACSEeDDQ6+e2oj3+J7Wjqa0F3+V688Jc2XP/SQ1g8NRoT3Ec/XFoPBzNzMBAuccVduOOdvVz5YZonPwamjWNJV+ud+zi0xGDVsOlzcVVrNyrWU4FjwnJPrh7YwiTNzp5L0DoPhNMzvcLUhx6lxGgPDTKKcPzey8GBOUWcMOjgAi+uetjsxiIWdUW1aC/swbK74mleku1SIjD6UTRgLu57fTruYg3X46qWGQQjYTWsSXzqAinLtFUy6XNLJTKXzzcnUtZd0F2puA4H4Zq/bcR8mgUHFcXyxOYErc4Zxup2dEew0pExE7taSlHbwITJ0f3woH+LvmPI5uW8KAkREd7wv+hnKRVcr2Rc+9JWFNBSeVL1Vk6OqR+YqkS//2089/5+fJTnheXPPIiH04LNNb1pl4Aj05p4+YXhwSkpCOcy5uijlTlYxMzG/EenofXbz50goIwm9vY8rgvpO4TjsfVz8SgtWOZYS/rnwZCHd+94BK8dqEfNpMVY8j//h2evTbDA0roD3CbdgG/84hosf3J4b6BrA5dzHB04z65Zh5+ueBYtV92N2csWYfnUEA54yuYMV+a4c06kHO5TMSvKQhWAfNJw9ZN/xvz//f2pFbE4u3dk5PFQuBLLYOZ9ire2NKPKfhZee2o+Eqn0musYtDEAq74PefpQXJ9+zEI+jPSY3/rPwV3/mIYVz592vzgM1fAeYjHmo17EDzwRmzYVsdsLoD3UgcI2Jl7m0U7cli5ezNk5GVNidOb64hfR0Nf/p/1MObZ3H9a+vAvp7/4ayxP94cdiDjBxlaeTk+DPqzF9WQY8tReyenOheOgj31qBlm2vYuGTzbjjF9/GTfOTkepD5UFRMLUcW5grOTU9zaqCBAAACyxJREFUHsEz4hF90WPdhcp5+u+8EXPNw3jsygfw0ImVqj7U7XwPn73zJn70QRErNfwRHz5xDebHBsDbQnPQ06UY82e6Ju176Q94O6cXhRFX4+n7liKDy7zmjQYNR7dQBAZcQesn/Tm1o3+MjlmOsfzAifIFJWD+tADkHulCfQfd2+rbmQ/ZG/ZdbWgZZLldtzCWmkzApKhxCuAczfnU5ONo4SCyW5JwY6oFxuLRtCn7WI3A6O8WxSfMla/RiMY0Rg2ldVzm6cHCmazwwjHxwsdAezi5up81cs0YEIXI1Cm4bs4W7NqZh11ZRZgWRcsiqwJVMek3vGbj3iu5JBLkeUzpGc0JnG0f+rrZ0Sp2Vnl60dBUg9qKgziUqUfD/3ZC84v/wuJJwQiyq+PfmrDLeQnuT2NFIt3YYvHsFOWSM2qvs05QmdqFS9onlX8qnQO08NK662DH9ECOztC4usHdQsFcdlTmnJXXyQZPQDP1MZNAcxUOVBWh6P23UNHair6u67BsHusXtxZzQHFAcFgy7p6fhkhLJVhm/3RiOTpl3B1xU5Tw5v34kKm1Pt3DROgDrti1/mW4HWvf5BSNibPm4do740f8+Zi/HPX9wpKA7a3oYqQmF3RpsOdyfA/z2xot/fSllTl+BuZekY+y9my8eZgTNFMGfKpLUFrThw7/RFx55yKkc+JkGT/jURCju0hTdw8fhsoyIHPJcqnSPGEaxU9V28XUjvKd6/Dlu6vx4tYCODAF2mqOe4qfq+Iu4+Ieiil3PIhZHAcsfYXOfU5cMqWLTXNlEcorM/HvvzmiqeEG3HrddFwR4oL2nAPICZmN+BmzMC85wMqynUtyToyppGmU14ndeqn8uDBf5DGCTlq48bOGny/8OXHi4JZ5Y+xAU14Z667nYJe2Et9rbMEfHrsdk2m5MJWXoaVLD4dHbkEGrd+u5r5hmWYv6ihKHlddDBbcOAtr6xnwVMrVwcw8FM8Lhm9ZMcr7tfBJT8WsRVM42bYZ0qed8gBaSvPBolto5AQqySZXF04TWT6OiYDD09zG9IvR7NxRjAOb8pBb5oSkW67CdL9jiZZH89sx7mNHZcpZq4GPN5cN++jPVMEycKXZyC4uR16HDjEzr8e9N01DYoAb8wGqfaPxwdDdjDb6otRVliHzQBHa+jvQwCX/Xi5zODq6wjE4CbMTWGZP9WANWoWNjTi8cjUyq/XoDGJE/WwqVbGeYyQ89t3tFBuaoR1FRUWoLypDdUUVK+40cBLAwAFnAwO6/BGdMgnTp0QjxBpWAibMH+ypxf53XsY/392EfYUVqGqoRllxEQoKh16FegY6JaTiuqsTEXRRfr+j5DXQw1rwh/H6K+9h/eYt2HKggJZWlgql6ungqEdJoZ6Jv7XwZgJq7Qlz5CiPPeJunDAxL6aOue50DqzfXVPOc89G5q5CVHS7I3jaTCxZNhcZLEOn6jOUqVD6WAbz0L//g/c2bca6HSyFWcck0PQ9Mxjod81AB73WExp3Ny5bqn2/ng6qHy3Zm7Dm40+w8sud2FfFsaS8hNkWjveTJtS1e2DWfStwRbAWGktNmE4XY8TP9NdjzXojLa1HWQu8kBHU1XXVqGlqQBFXd3SDAxgIT0N6eiJSw+mXq+pFHFHAMXzJrCMVh5GXdQhrjtAwkHwdvnHlBIQzLmBURo0xtHThuxrQU1eL5voaVJQX42BRDfst3asYN9Dba4SDux8C01KY8YKljS1yf164pCd+qVi87TVwc6dBQzE09HWhu7aEZX4LcXBfOdp9WPFnyQIsXsA8qXTBsO6k6YSU537DpfWCL75Abq8bnFJnYFmir3V9388tnfzVAgTUUTrbK1BQNIB2B5aSuzYZIRftS3mOM6VFSePhi4CERKT4OKAtKwtFxWUoppXPZepSPHbftZgRzqTxaspwQjwug/sEwNdDB1+N0Rw1jvY6NDt4wdWb0fTRcZg5JdRsjVR/nFJcEboZuZ+PFo0PvCZOwuRpGZgVdszP9YTMKryxp8+tuy8fIrSEMtBroI9BNR2tKKci5Z9K39ZpU5E6MQoRyuBojc3Yyxq+ddj5zmc4POgGbWAoIsLDT3mFTZmF6bPTcOWkELirf3FgGmDN6fqD+MvfPsDhGj16nD0QHM6AsFAt9FW0PtYzxRjLxsYnBFoueMWObga+Shk/+n3p8/DG6u2s9+6HqDnzseSmeVgY73fWFQXLXaYeZp8px54XXsZ7eU1odXCDR0gIQv15j3bVobi4C27xCeQQgCCrZ43vRdPBLdh6tBqFeu0p/cPcXyLiERc3FUuXz0G8B1cerKptcMXC0QVuzALhY9/D1FYMZOxq5QS3DUU97kifPJNVzxiwGMIgQasqwxfSMxid3FqHFpbBrO5nQOjURbh5ejjzFnPZ+kIOp8ZvWGXPO8yf5S5pgaWyP8DI8Ha6cjkwJZ93ZDyzkcQzS4mFXIMsJr8ycDHoJoAV+SYEI0LLlQNG2O/Yn4dSQzKuuvMm3LAoHRkRzBRgsTYtfCAqnRX7imBSAk/TJiPF96R93MItyeHGiYAdI1mHO0qOkxjSrBAQAkJACAgBISAEhMClTMDa61eXMks5NyEgBISAEBACQkAICIGzEBCl8yxg5GshIASEgBAQAkJACAgByxEQpdNyLOVIQkAICAEhIASEgBAQAmchIErnWcDI10JACAgBISAEhIAQEAKWIyBKp+VYypGEgBAQAkJACAgBISAEzkJAlM6zgJGvhYAQEAJCQAgIASEgBCxHQJROy7GUIwkBISAEhIAQEAJCQAichYAonWcBI18LASEgBISAEBACQkAIWI6Ao+SGtxxMOZIQEAJCQAgIASEgBITAyATE0jkyF/lWCAgBISAEhIAQEAJCwIIEROm0IEw5lBAQAkJACAgBISAEhMDIBETpHJmLfCsELk0CRUXAn/8KxGcApaVAf/+leZ5yVkJACAgBIWBzBETptLlLIgIJARUJKEpmaytQ1AAMDAAmk4qNyaGFgBAQAkJACJwkIErnSRbyTggIASEgBISAEBACQkAlAqJ0qgRWDisEhIAQEAJCQAgIASFwkoAonSdZyDshIASEgBAQAkJACAgBlQhInk6VwMphhYBNElB8OI+7cZrfK5+Pf2GTEotQQkAICAEhcIkQEEvnJXIh5TSEgBAQAkJACAgBIWDLBETptOWrI7IJASEgBISAEBACQuASISBK5yVyIeU0hIAQEAJCQAgIASFgywRE6bTlqyOyCQEhIASEgBAQAkLgEiEggUSXyIWU0xACYyYggURjRiY/EAJCQAgIgQsnIJbOC2cnvxQCQkAICAEhIASEgBAYJQFROkcJSnYTAkJACAgBISAEhIAQuHACsrx+4ezkl0Lg60fg+JL6cclP/3z8e/lfCAgBISAEhICFCYil08JA5XBCQAgIASEgBISAEBACZxIQpfNMJvKNEBACQkAICAEhIASEgIUJyPK6hYHK4YSATRM4UfLyWPlLWV636cslwgkBISAELiUCYum8lK6mnIsQEAJCQAgIASEgBGyUgFg6bfTCiFhCQBUCbm5AQjxwy1xApwPs7IAT1k9VWpSDCgEhIASEgBAwE7Dr6+vjOptsQkAICAEhIASEgBAQAkJAPQJi6VSPrRxZCAgBISAEhIAQEAJC4BgB8emUriAEhIAQEAJCQAgIASGgOgGxdKqOWBoQAkJACAgBISAEhIAQEEun9AEhIASEgBAQAkJACAgB1QmIpVN1xNKAEBACQkAICAEhIASEgFg6pQ8IASEgBISAEBACQkAIqE5ALJ2qI5YGhIAQEAJCQAgIASEgBP4/h6BGHsS9Y8QAAAAASUVORK5CYII=" } }, "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "## Point 2 - Prevision jusq'à 2025\n", "\n", "\n", "Dans ce paragraphe on va développer un modèle pour prévoir l'évolution de la concentration de CO2 jusqu’au 2025, avec les informations hystériques qu'on a à disposition. \n", "\n", "On peut utiliser la méthode des moindres carrés pour identifier l’évolution linéaire de la tendance montrée en rouge dans le graphique précèdent. La méthode des moindres carrés permet d'identifier la ligne droite qui s'approche le mieux aux différentes points de l'étude. Cette ligne droit présente la forme suivante:\n", "\n", "\n", "\\begin{align}\n", "y=ax+b\n", "\\end{align}\n", "\n", "La théorie de la méthode des moindres carrées, nous permet de définir la forme des coefficients a et b.\n", "\n", "\\begin{equation}\n", "a=\\frac{N\\sum(xy)+\\sum(x)\\sum(y)}{N\\sum(x^2)-(\\sum x)^2}\n", "\\end{equation}\n", "\n", "et\n", "\n", "\\begin{equation}\n", "b=\\frac{\\sum(y)- a\\sum(x)}{N}\n", "\\end{equation}\n", "\n", "Le lien suivant nous montre ça dans le détail.(https://www.mathsisfun.com/data/least-squares-regression.html)\n", "\n", "\n", "Il est intéressant de simplifier cette équation. Pour ce faire on peut rendre 'barycentrique' la série historique, comme montré dans l'image suivante:\n", "\n", "\n", "![Screenshot%202020-07-19%20at%2009.15.53.png](attachment:Screenshot%202020-07-19%20at%2009.15.53.png)\n", "\n", "Cette opération nous permet de réduire la complexité des termes 'a' et 'b' car les sommes\n", "\n", "\\begin{equation}\n", "\\sum x\n", "\\end{equation}\n", "\n", "et\n", "\n", "\\begin{equation}\n", "(\\sum x)^2\n", "\\end{equation}\n", "\n", "deviennent nulle. Donc on peut calculer a et b avec les formes suivantes:\n", "\n", "\\begin{equation}\n", "a=\\frac{\\sum(xy)}{\\sum(x^2)}\n", "\\end{equation}\n", "\n", "et\n", "\n", "\\begin{equation}\n", "b=\\frac{\\sum(y)}{N}\n", "\\end{equation}\n", "\n", "On commence par calculer le terme 'a'. Pour ce faire on réalise un tableau en normalisant les périodes prises dans l'étude: chaque mois représente une période normalisé, on aura donc 744 (12*62 ) périodes, équivalentes à la longueur des vecteurs de 'raw_data_new'. \n", "\n", "On va donc définir tous les opérateurs nécessaires pour calculer a." ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "text/plain": [ "0.1511674880564176" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "x=np.zeros((len(raw_data_new),1))\n", "\n", "\n", "for i in range(len(raw_data_new)):\n", " x[0]=-368\n", " x[i]=x[i-1]+1\n", " \n", "sumx =len(raw_data_new)\n", " \n", "y=np.zeros((len(raw_data_new),1))\n", " \n", "for j in range(len(raw_data_new)):\n", " y[j]=raw_data_new.seasonally_adjusted_filled[j]\n", " \n", " \n", "xy=np.multiply(x,y)\n", "sumxy=np.sum(xy)\n", "\n", "x2=np.multiply(x,x)# c'est le vecteur des x^2\n", "sumx2=np.sum(x2)\n", "\n", "N=len(raw_data_new)\n", "\n", "#on passe a calculer a\n", "\n", "a=(sumxy)/(sumx2)\n", "a\n", "\n" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "La valeure de a est:0.1511674880564176 et ça représente le coefficient angulaire de la ligne droite qu'on cherche à calculer. On passe à calculer b." ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "ename": "NameError", "evalue": "name 'sumy' is not defined", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mb\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msumy\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m/\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mN\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mb\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;31mNameError\u001b[0m: name 'sumy' is not defined" ] } ], "source": [ "b=((sumy))/(N)\n", "b" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "On définit donc la ligne droite calculée comme :\n", "\n", "\\begin{equation}\n", " y=0.1511674880564176*x+355.3829380053908\n", "\\end{equation}\n", "\n", "Avec x qui représente une unité temporelle d'un mois. Les 742 mois donnent l'information jusqu’au 2020. Donc pour chercher l'évolution de la concentration de CO2 au 2025, il faut considérer qu'il nous font 5*12 mois, soit 60unité temporelles normalisées. Ces 60 unités temporelles normalisées il faut les sommer aux 371 qui donnent la quantité de CO2 au 2020, en arrivant à 431 unités de temps normalisé. A la fin du 2025, la concentration de CO2 sera:\n", "\n", "\\begin{equation}\n", " y=0.1511674880564176*431+355.3829380053908\n", "\\end{equation}\n", "\n", "Soit, " ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "text/plain": [ "420.53612535770685" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y2025=(0.1511674880564176*431)+355.3829380053908\n", "\n", "y2025" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "text/plain": [ "[]" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAD8CAYAAAB5Pm/hAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvIxREBQAAIABJREFUeJzt3Xl4VOXdxvHvL3vCGlaBEPZdEHBEwQXEjaJCa9VibcWWSlWU1lZR1NbWvta11rVVtCp1owiuKCKoCCKICQiEPewBhAAGiJB1nvePOYawJmCSM5ncn+vKxZxnzmRuhsmdw3POnGPOOUREJHJF+R1AREQql4peRCTCqehFRCKcil5EJMKp6EVEIpyKXkQkwqnoRUQinIpeRCTCqehFRCJcjN8BABo1auRat27tdwwRkWolPT19h3OucVnrhUXRt27dmrS0NL9jiIhUK2a2oTzraepGRCTCqehFRCKcil5EJMKp6EVEIpyKXkQkwqnoRUQiXLmL3syizWyhmU3xlh82sxVmttjM3jKz+qXWHWtmmWa20swuqozgIiLV3ty5cP/9oT8r0fEcR/87YDlQ11ueDox1zhWZ2YPAWOB2M+sKDAO6Ac2BGWbW0TlXXIG5RUSqteI5X+DOO4+owkKi4uPg44+hb99Kea5ybdGbWQpwMfD892POuY+cc0Xe4jwgxbs9FJjgnMt3zq0DMoE+FRdZRKR6m7tmJ/+9fzwUFBAVLIaCApg5s9Ker7xTN48BY4DgUe7/NTDVu90C2FTqvixv7CBmNtLM0swsLTs7u5wxRESqr40793H9y+lc9dw85rY8GYuLw0VHQ1wcDBhQac9b5tSNmV0CbHfOpZvZYUnM7C6gCHj1+6EjfBt32IBz44BxAIFA4LD7RUQixd68Qp76NJMXP19PdJTxxws6ct05g4i+JhDakh8woNKmbaB8c/RnAkPMbDCQANQ1s1ecc78ws+HAJcB5zrnvyzoLaFnq8SnAlooMLSJSHRQHHZPSN/HwtFXsyM3nst4tuH1QZ5rWTQit0LdvpRb898oseufcWEI7WvG26G/1Sn4QcDvQ3zm3r9RD3gVeM7NHCe2M7QDMr+jgIiLhbN7anfxtyjKWbtnDqa2S+c/wAKe0rF/2AyvBDzl75VNAPDDdzADmOeeud84tNbOJwDJCUzqjdMSNiNQUm3bt4+8fLGdqxjc0r5fAE1f14tIezfB60hd2YMbFP4FAwOk0xSJSneXmF/H0p5n8Z/Y6oqOMGwa047qz25IYF11pz2lm6c65QFnrhcX56EVEqqtg0DEpPYuHpq0MzcP3asFtgzrRrF6i39FKqOhFRE7Q/HW7uHfKUjI276F3an2eHx6gp0/z8MeiohcROU6bdu3jgakreH/JVprVS+DxYT0ZckpzX+fhj0VFLyJSTt/lF/GvmZk8N3sdUQa3nN+RkedU7jx8RVDRi4iUIRh0TF4QmofP3pvPT3q1YEyYzcMfi4peROQY9uYV8tuX0/lizU56tqzPs788ld6pyX7HOi4qehGRo3hl3gbufjsDgLsGd2HEWW2IigrPefhj0YVHRESOYPf+Qv49cw0AbRvXqrYlD9qiFxE5jHOOES99xeac/bw8og+ntW5QbUseVPQiIgfZuDN0CoO0Dd9ydodGnN2hsd+RfjAVvYiIZ8L8jfzf+8vJzQ9dU+mZX5zqc6KKoaIXEQHGf7Gee95dWrL80E97UCs+MioyMv4WIiI/QH5RcUnJB1ol88+f9aRlgySfU1UcFb2I1HifrghdzvSOH3Xm+v7tfE5T8XR4pYjUeO98vZlGteP4zVlt/I5SKVT0IlIjOefYX1DMy3PXMzXjGy7p0ZyY6MisRE3diEiN45zjuv+mM2P5tpKxy09N8TFR5YrMX18iIsfw6PRVB5X85Bv6cXKLej4mqlzaoheRGmNLzn7ufjuDT1Zs55IezXjwpz3Yk1dYbc5CeaJU9CIS8Xbk5jNzZTZ//2A5u74rIC46ilsv7ESt+JiIOVb+WCL/bygiNVphcZDA/80oWR7etxU3DexA4zrxPqaqWip6EYlIxUFHYXGQhRtzSsZaNUzijxd1om5CrI/Jqp6KXkQi0t1vZ/D6/I30Sq1PbLSx4E8XUKeGFfz3dNSNiESk1+dvBGDhxhxOb9OwxpY8qOhFJALtzM0/aHlw92Y+JQkPmroRkYgSDDquem4eALde2JHT2zYk0Kp6XeO1oqnoRSSiTErPYtW2XOKioxh1bnvMqu+VoSqKpm5EJKJMSs8iJsr48Pdnq+Q95S56M4s2s4VmNsVbbmBm081stfdncql1x5pZppmtNLOLKiO4iMih9hcUs2Djt1x3TlvaNq7td5ywcTxb9L8DlpdavgP42DnXAfjYW8bMugLDgG7AIOBfZhZdMXFFRA5XHHQ89clquvz5Q4qCrsbPyR+qXEVvZinAxcDzpYaHAuO92+OBH5can+Ccy3fOrQMygT4VE1dE5HCzVmXzyEerSpbPbN/IxzThp7xb9I8BY4BgqbGmzrmtAN6fTbzxFsCmUutleWMiIhVuwvyN/OqlrwC4qk8qs8ecS0KsJhFKK7PozewSYLtzLr2c3/NIez/cEb7vSDNLM7O07Ozscn5rEZEDPlmxjTveXALA6IHtuf+y7hF1rdeKUp7DK88EhpjZYCABqGtmrwDbzKyZc26rmTUDtnvrZwEtSz0+Bdhy6Dd1zo0DxgEEAoHDfhGIiBzNjGXbuP6VdIqCjg5NavPOTWeSFKejxY+mzC1659xY51yKc641oZ2snzjnfgG8Cwz3VhsOvOPdfhcYZmbxZtYG6ADMr/DkIlIjbdq1j5tfX0hRMLR9+NTPe6vky/BDXp0HgIlmNgLYCFwB4JxbamYTgWVAETDKOVf8g5OKSI03c+V2rn0xNB8/emB7eqUm0+mkOj6nCn/mnP+zJoFAwKWlpfkdQ0TC2Dtfb+Z3E74uWc7460XUrgEXDTkWM0t3zgXKWq9mv0oiUi0MemwWK77ZC8CMP5xDclJcjS/546FXSkTC1u79hZz5wCfk5hcB8MHos2nfRFM1x0vnuhGRsPXinHUlJT/xt33p2ryuz4mqJ23Ri0hYmrFsG4/NWE2PlHrcPLADp7XWaQ1OlIpeRMLOt98V8Jv/phEXE8Urvzm9xl3jtaKp6EUkrCzc+C1Pf7oGgIcv76GSrwAqehEJG1ty9vOTf30BwNCezRnaU6fJqggqehHxXTDomJSexZjJiwHo2LQ2dw3u4nOqyKGiFxHfPflJJv+cETrNcOuGSUy+oR91NGVTYVT0IuKrJVm7+eeMVbRpVIu3buxHvcRYXQKwgqnoRaTKFRUH+dM7GaRv+JbGdeIB+OuQbtRPivM5WWRS0YtIlbvzrSVMTMsCYNW2XH5zVhvO6djY51SRS0UvIlUmc3suM5Zv4430LBrWiuOeId1YkpXDrRd18jtaRFPRi0iV+GLNDq4bn8Z3BcXExUTxya0DqJcYy5BTmvsdLeKp6EWkStz9dgZN6yZwVodG9GvXiHqJOqqmqqjoRaTSzVy5nbXZ33Hn4M6MPKed33FqHBW9iFSq295YxBvpWbRrXEufdPWJil5EKoVzjqVb9vBGeujompdHnE7Tugk+p6qZVPQiUqGCQce2vXlc+Ogs9uYX0aROPO+PPrvkeHmpeip6EakwS7fs5spn5vJdQTEA8TFRTPxtX5W8z1T0IlIh9hUUcf8HK0pK/qS6CXx++7nEROtCdn5T0YvID1IcdLy5IIv3Fm/l88wdnNoqmb8O6UbXZnWJitI5a8KBil5ETlgw6Ljx1XSmLd0GQIcmtXnpV6fpzJNhRv+nEpET9sc3FpWUPMAlPZqr5MOQil5EjtuczB2MenUBby3czAVdmzLp+r40rRtP/046MVk40tSNiByXTbv2cfXzX5YsX9arBYHWDfjyzvN9TCXHoqIXkXIpKg5y8+sLmZrxDQANa8XxjytP4ZwO2ooPdyp6ESnTvoIiXpyzvqTkxwzqxA392+lKUNVEmUVvZgnALCDeW3+Sc+4eM+sJPAMkAEXAjc65+d5jxgIjgGJgtHNuWiXlF5FKtDM3nz+/u5T3F28FYGDnJjw+rKd2uFYz5dmizwcGOudyzSwW+NzMpgL3An91zk01s8HAQ8AAM+sKDAO6Ac2BGWbW0TlXXEl/BxGpJH+bsqyk5C/o2pS7L+6ikq+Gyix655wDcr3FWO/LeV91vfF6wBbv9lBggnMuH1hnZplAH2BuBeYWkUrknGNqxje8u2gLgVbJ3P6jzpzWuoHfseQElWuO3syigXSgPfC0c+5LM/s9MM3MHiF0mGY/b/UWwLxSD8/yxkSkmvjzO0t5ed4GAMZdE6BBLV20uzor13H0zrli51xPIAXoY2YnAzcAtzjnWgK3AP/xVj/S3hl36ICZjTSzNDNLy87OPrH0IlLhhr8wv6TkH7niFJV8BDiuD0w553KAmcAgYDjwpnfXG4SmZyC0Bd+y1MNSODCtU/p7jXPOBZxzgcaNdXiWSDh4fMZqPlsV2vD68s7zuPzUFJ8TSUUos+jNrLGZ1fduJwLnAysIlXd/b7WBwGrv9rvAMDOLN7M2QAdgfkUHF5GK9enK7fxzxioAbh/UWRcJiSDlmaNvBoz35umjgInOuSlmlgM8bmYxQB4wEsA5t9TMJgLLCB12OUpH3IiEp9mrs3nmszU8dPkp3PbGYmKjjdeuO0M7XiOMhQ6q8VcgEHBpaWl+xxCpcYY89TmLs3YDEBNlvHvTWXRtXreMR0m4MLN051ygrPX0yViRGihj825emLOupOTjoqN48ue9VPIRSkUvUsNkbN7NT/41B+egY9PaPP3z3rRqWIu4GJ3MNlKp6EVqkMzte7ny2bnUTYhl6u/Ppkkd7XCtCfQrXKSG+HLtTn727DyKih1vjzpTJV+DaItepAZ46pPVPPJR6NDJWy/sSMsGST4nkqqkoheJcE9/mskjH60iJsr40yVduaZvK78jSRVT0YtEsNz8Ih6ethKAl0ecTt92DX1OJH7QHL1IBBvx0lcAnNG2gUq+BtMWvUgEenT6KqYs3sLa7O8A+PtPuvucSPykoheJMFMWb+GJj0OnnoqPieKjW86hVcNaPqcSP6noRSLIxp37GDt5Cb1S63PvkJNpkZyo0wyLil6kutuTV8h9U5YzeUEWRUFHnYQYnhjWS4dQSgkVvUg1NnfNTq567sAF3ZrXS+DZXwZU8nIQFb1INfXtdwWMnrCQ+kmxnNGmIQXFQf5yaTdSG6rk5WAqepFqJL+omOdnr2Pump18nrmDuOgoJt/Qj+4p9fyOJmFMRS8S5nL2FfDy3A0kxkXz8rwNbNi5r+S+uy/popKXMqnoRcLYx8u3MWL8wRfl+cUZqaQkJ7F6Wy5XBloe5ZEiB6joRcKQc46/vreMl75YT8sGiWzatR+AlOREbruwM/WSYn1OKNWJil4kDL0ybwMvfbGe2Ghj0vX9MKBWfAy14vUjK8dP7xqRMLMnr5BHp6+iWb0Eptx8Fg1rx/sdSao5Fb1IGNn1XQG/eukrcvYX8t6I01XyUiF09kqRMJFfVMyf3s5gSVYOjw/rxcktdDSNVAwVvUiYeHHOet5fspU/XNCRIac09zuORBAVvUgYKCgKMmH+RgKtkrlpYAe/40iE0Ry9iI9WbdvL4zNW8/6SrQCMGdTZ50QSiVT0IlUsN7+ITbv28e+Za3h30ZaD7ju3UxOfUkkkU9GLVJGlW3Yzd81OXpyzns05+0vGG9WO47LeKVwZSCExLtrHhBKpVPQiVSC/qJhLn/ycoAstn5JSj/O6NOWmc9sTFWX+hpOIV2bRm1kCMAuI99af5Jy7x7vvZuAmoAh43zk3xhsfC4wAioHRzrlplRNfJPzlFxUz8JHPSkr+zsGdGXlOO39DSY1Sni36fGCgcy7XzGKBz81sKpAIDAV6OOfyzawJgJl1BYYB3YDmwAwz6+icK66cv4JIeMrNL2JS2ib+8t4yAOolxrLwTxdoC16qXJlF75xzQK63GOt9OeAG4AHnXL633nZvnaHABG98nZllAn2AuRWcXSRsBYOOi5+YXXJK4aS4aOaOHaiSF1+U6zh6M4s2s6+B7cB059yXQEfgbDP70sw+M7PTvNVbAJtKPTzLGxOpEQqKgox6bUFJyc8ecy7L7h1EUpx2iYk/yvXO86ZdeppZfeAtMzvZe2wycAZwGjDRzNoCR9pkcYcOmNlIYCRAamrqiaUXCUP3vb+MqRnf0K5xLd64vh8NasX5HUlquOPaxHDO5ZjZTGAQoS31N72pnflmFgQaeeOlr4aQAmw5wvcaB4wDCAQCh/0iEKlOnHNkbs9l2tJvGD93A9f2a81fhnTzO5YIUL6jbhoDhV7JJwLnAw8SmrcfCMw0s45AHLADeBd4zcweJbQztgMwv5Lyi/hu9/5CBj8+u+TY+EHdTuKui7v4nErkgPJs0TcDxptZNKE5/YnOuSlmFge8YGYZQAEw3Nu6X2pmE4FlhA67HKUjbiSSTZi/kc05+2ndMIkbBrTjilNbaqerhBULdbO/AoGAS0tLK3tFkTCxv6CYiWmbSIqL5t73ltEiOZEPRp+tgpcqZWbpzrlAWevpMACRMhQHHfe+t5TlW/cyvF9r1u/8joenrSy5v0mdeJ795akqeQlbKnqRQ8xds5Ov1u/ipnPbA3DbpEW8uWAzAPPX7ypZ76z2jWhRP5Grz0ilVcNavmQVKQ8VvUgpm3P2c9Vz8wDYuGsfn63KJntvPkN7Nmf3/kJmrsymfZPa3DGoM+d3bepzWpHyUdGLeHbk5vOb8aF9RfExUUxKz6J+UiyPD+vJpT2aa2pGqi0VvQiwr6CIYePmkbk9l+SkWKbdcg5zMndwZrtGNKmb4Hc8kR9ERS81Vl5hMeNmrWXmyu0s2JgDQNO68bxw7Wk0qZPAT3ql+JxQpGKo6KVG2pmbz9+mLOPtrw98aPu3/dtyx6DOmGmKRiKLil5qjD15hcxfu4t/TF/F8q17AAi0SuasDo24tl9r6ifpnDQSmVT0UiPMXp3NL/9z4EwcteKieXxYL87r0kRb8BLxVPQS0QqLg9z3/nJe+mJ9ydh1Z7fhzsFdVPBSY6joJWI55xj9+kKmZnxDn9YNGDu4M6kNkmhYO97vaCJVSkUvEemLNTv4+XNfAnDrhR25aWAHnxOJ+KdcV5gSqW5emrMegBsHtOPGAe39DSPiM23RS0TJKyzm3zPX8NGybfz89FTGDOrsdyQR36noJaLc/XYGk9KzaFwnnmv7tfY7jkhYUNFLxPj7B8uZlJ7F+V2a8tw1p+qoGhGPil6qtWVb9pAUF83s1dmMm7WW5KRY/nBBR5W8SCkqeqm2gkHH4CdmlywnxEbx2ZhzqZsQ62MqkfCjo26kWpq5cjv9H/m0ZLlXan3eHnWmSl7kCLRFL9XKnrxCFm7M4Q8TF1ErPprRA9sz4qy21EtSwYscjYpewt6HGd/w2apsVn6zp+R0wgAP/TSgqzyJlIOKXsLe9a+kl9yOjjJGnduevm0b0rddQx9TiVQfKnoJS7n5Razatpdb/vc1AKMHtueKQEtSkhN1RI3IcVLRS9i59Y1FTErPKlnu06YB1w9oR1Kc3q4iJ0I/ORIW5q7ZSe34GB74cDlzMneWjF/VJ5X7L+vuYzKR6k9FL77bvjePq56bV7LctlEtJow8g/iYaGon6C0q8kPpp0h8FQw6xk5eUrLcrXld3ryxH/Ex0T6mEoksKnrx1ZsLN/Pxiu2MPKctvVPrc0HXk4iO0s5WkYqkohffbM7Zz61vLKJR7TjG/qizjqYRqSRlFr2ZJQCzgHhv/UnOuXtK3X8r8DDQ2Dm3wxsbC4wAioHRzrlplZBdqpnpy7bxj49W8l1BEc3rJZK+4VsARpzVViUvUonKs0WfDwx0zuWaWSzwuZlNdc7NM7OWwAXAxu9XNrOuwDCgG9AcmGFmHZ1zxZWQX6qJtdm53Pz6AvIKgwBs2rWf7i3q8cszWnHlaS19TicS2coseuecA3K9xVjvy3nL/wTGAO+UeshQYIJzLh9YZ2aZQB9gbkWFlvDnnOP9JVvZ/O1+Op1Uh1v+9zVRZnzyx/40r59IQqx2topUlXLN0ZtZNJAOtAeeds59aWZDgM3OuUWH/Le7BTCv1HKWN3bo9xwJjARITU09sfQSlpxzTFu6jZteW1gylhQXzf9G9qVt49o+JhOpmcpV9N60S08zqw+8ZWY9gLuAC4+w+pEmW91hA86NA8YBBAKBw+6X6mdvXiGvfrmRV+ZtIOvb/TSqHc8jV/Qgc3suZ7RtyMkt6vkdUaRGOq6jbpxzOWY2k9D0TBvg+635FGCBmfUhtAVfetI1BdhSIWklbL0ybwN3v50BQHxMFK0aJjHmos4M6NSEAZ2a+JxOpGYrz1E3jYFCr+QTgfOBB51zTUqtsx4IOOd2mNm7wGtm9iihnbEdgPmVkl7Cwva9eSUlf07Hxrx47Wk6Fl4kjJRni74ZMN6bp48CJjrnphxtZefcUjObCCwDioBROuImMu3eX8hDH65gxTd7AWjbuBYvDA+o5EXCTHmOulkM9CpjndaHLN8H3PeDkklYyyssZvDjs9mcsx+Awd1P4v9+3J2YaF2dUiTc6JOxUm7FQUeUwcyV2fzqpa8AiIky7rq4C9f2a60PPYmEKRW9lEv23nyueWE+y7fuKRkb3P0kHvtZL+JitBUvEs5U9FKmDzO2cv0rCw4ae/KqXlx6SnOfEonI8VDRy1G9vXAz6Ru+5eV5GwA4v0sTnh9+ms+pROR4qejliJ74eDWPTl9Vsvy3H5/MpT2a+ZhIRE6Uil4O89ystSUlf/Xpqdw5uAu14vVWEamu9NMrB/l4+Tbu+2A5g7qdxBNXaUerSCRQ0QvOOZZu2cOe/YWMGJ8GwD+uPEUlLxIhVPQ1WFFxkPunruA/n687aPzeod00VSMSQfTTXMMEg443F25mcnoWe/IKWboldFz8KS3r07h2HKPObU+v1GSfU4pIRVLR1wA5+wqolxjLnrwiHpuxihfnrAegRf1EHrisO0N6NicpTm8FkUiln+4I8/cPlvP+4q386+retG5Ui7lrdnDz6wtJToojOzcf56BeYiyTb+hL+yZ1/I4rIlVARR9BNu3axwufr6Mo6Bj69Byio4ziYOiaLolx0USbcV3/ttx2YSeidIZJkRpDRR9BHpq2ktjoKP4ypAt3v51BcdDx6zPbcGb7hpzXpanf8UTEJyr6COCc47ZJi3lv0RZuOrc9VwRSmL5sG60aJvHnS7v6HU9EfKair+aWZO3mty+nsWV3Hr88oxU3n9ee+Jhoxv+6j9/RRCRMqOirsfyiYv70TgZbdufx6zPbcOfgzrrwh4gcRkVfDTnneHbWWh6YugKAx4f1ZGjPFj6nEpFwpaKvJvIKi7l3yjImp2eRXxQsGQ+0SlbJi8gxqejDVF5hMc/NWsuKb/bSskESu/cX8vr8jQet07Fpbf71i94+JRSR6kJFHyYKioLsySsE4A8TFzFrVfZh65zfpSlXn57KgE6Nmbt2J71Tk0mIja7qqCJSzajow8CGnd/R/+GZAPRKrc/CjTkAXNuvNVf1SWXK4i08+UkmI85qQ992DQHo166RX3FFpJpR0fvsm9153FDqeqwLN+Zw+akpNKgVx+2DOhMdZXRs2pHB3ZvRpVldH5OKSHWlovfRok05DH16DgCX9W7B8L6tSYiNptNJB5+DxsxU8iJywlT0Pnj2szVkfbu/5KLbNw5ox5hBnX1OJSKRSkVfRXbk5rPruwK278nnfu/4d4AHf9qdKwMtfUwmIpFORV9JMjbvpijo6HxSHeav28XoCQvJ2VdIlEHDWnF88Luzyc0vol3j2n5HFZEIp6KvQM450jZ8C8AVz8w96L6kuGguPaU5LZMT+empKTStm4DOJykiVaHMojezBGAWEO+tP8k5d4+ZPQxcChQAa4BfOedyvMeMBUYAxcBo59y0SsofNnL2FTDwH5+x67uCg8aTk2Jp36Q2//7FqTSqHe9TOhGpycqzRZ8PDHTO5ZpZLPC5mU0FpgNjnXNFZvYgMBa43cy6AsOAbkBzYIaZdXTOFVfS38E3hcVBXvtyI//7ahNrd+SSVxikd2p9lm3dw+CTm/HQ5T2IjjLMdJEPEfFPmUXvnHNArrcY630559xHpVabB1zu3R4KTHDO5QPrzCwT6AMcPJdRDeXmFxFllFxf9fbJi3lzweaS+5+8qhcXd29GQXGQmCjTmSRFJCyUa47ezKKBdKA98LRz7stDVvk18D/vdgtCxf+9LG+s2iksDhIbHUUw6Pj3Z2t4eNpKAHqn1mdxVmhn6/cu6dGMS3o0w8xIiNJpCUQkfJSr6L1pl55mVh94y8xOds5lAJjZXUAR8Kq3+pHmKdyhA2Y2EhgJkJqaegLRK96SrN18uHQrt5zfkenLtjHqtQWc36UpQeeYsXx7yXoLvFMUANw7tBvX9G3tQ1oRkfI5rqNunHM5ZjYTGARkmNlw4BLgPG+KB0Jb8KUPDE8Bthzhe40DxgEEAoHDfhFUlWDQkVdUzMKNOVz9fOg/Kk9/uqbk/o+WbQMgPiaKT28dQJM68cxanU3t+Fg+z9zBz07TMfAiEt7Kc9RNY6DQK/lE4HzgQTMbBNwO9HfO7Sv1kHeB18zsUUI7YzsA8ys++g+zJWc/Zz34CY1qx5MQG83GXfsOW+f5awKc0a4h2/fkkdogqWTOfWDn0IGRfdo0qNLMIiInojxb9M2A8d48fRQw0Tk3xdvJGg9M944qmeecu945t9TMJgLLCE3pjPL7iJuMzbuZvmwb1/dvR2JcNC/P28Cf3s4AYPve/JL1Xrg2QI+U+hQWBykOOlKSkwCorQ81iUg1ZgdmXPwTCARcWlpahX7P/KJi4qKjKCgOctaDn5K9N5+OTWvTtG4Cs1fvAOC5awLUiosmKso4o23DCn1+EZHKZmbpzrlAWetFxCdjg97RL1FRof3A2/bkcfrfPwYgJTmR7L35nNupMZ+uzGbVtlxa1E/kiat6cmorTb2ISOSLiKK/+50M3lu0hYd+GvqA0s2vLyy5L+vb/ZzepgEvXHsaG3ftIy4miiZ1EoiO0oddDiGhAAAFkklEQVSYRKRmqPZFn5tfxGtfhq6lesOrBy7g0b9jY578eS927M2nUZ14zIxWDWv5FVNExDfVvuhPvufg0+gkxkZz83ntuXFAewDqJsT6EUtEJGxU66LP+vbAIZFv3tiPLifVJTFOn0oVESmtWhd9XmExF3RtyvX929E7NdnvOCIiYalaF337JnV47poyjywSEanRdHpFEZEIp6IXEYlwKnoRkQinohcRiXAqehGRCKeiFxGJcCp6EZEIp6IXEYlwYXE+ejPLBjZ4i42AHT7GOZpwzQXhm025jo9yHR/lglbOucZlrRQWRV+amaWV50T6VS1cc0H4ZlOu46Ncx0e5yk9TNyIiEU5FLyIS4cKx6Mf5HeAowjUXhG825To+ynV8lKucwm6OXkREKlY4btGLiEgFCouiN7NbzcyZWaNSY2PNLNPMVprZRaXGTzWzJd59T5hZhV/l28z+ZmaLzexrM/vIzJqHSa6HzWyFl+0tM6sfJrmuMLOlZhY0s8Ah9/mW6wg5B3k5Ms3sjsp+vkOe+wUz225mGaXGGpjZdDNb7f2ZXOq+I75ulZCrpZl9ambLvX/D34VDNjNLMLP5ZrbIy/XXcMhV6rmizWyhmU0Jp1xH5Zzz9QtoCUwjdBx9I2+sK7AIiAfaAGuAaO+++UBfwICpwI8qIVPdUrdHA8+ESa4LgRjv9oPAg2GSqwvQCZgJBEqN+5rrkIzR3vO3BeK8XF2r8H1+DtAbyCg19hBwh3f7jvL8e1ZCrmZAb+92HWCV9/y+ZvPeF7W927HAl8AZfucqle8PwGvAlHD5tzzWVzhs0f8TGAOU3lkwFJjgnMt3zq0DMoE+ZtaMUAnPdaFX8b/Ajys6kHNuT6nFWqWy+Z3rI+dckbc4D0gJk1zLnXMrj3CXr7kO0QfIdM6tdc4VABO8fFXCOTcL2HXI8FBgvHd7PAdegyO+bpWUa6tzboF3ey+wHGjhdzYXkustxnpfzu9cAGaWAlwMPF9q2Pdcx+Jr0ZvZEGCzc27RIXe1ADaVWs7yxlp4tw8dr4xs95nZJuBq4M/hkquUXxPaEg63XKWFU66jZfFTU+fcVggVLtDEG/clq5m1BnoR2nr2PZs3PfI1sB2Y7pwLi1zAY4Q2ToOlxsIh11FV+jVjzWwGcNIR7roLuJPQdMRhDzvCmDvGeIXmcs6945y7C7jLzMYCNwH3hEMub527gCLg1e8fFg65jvSwys51HPx4zhNV5VnNrDYwGfi9c27PMXaZVFk251wx0NPbF/WWmZ18jNWrJJeZXQJsd86lm9mA8jzkCGNV/r6r9KJ3zp1/pHEz605ozmqR96ZKARaYWR9Cv/Vallo9BdjijaccYbzCch3Ba8D7hIre91xmNhy4BDjPm/YgHHIdRaXnqoAsftpmZs2cc1u96azt3niVZjWzWEIl/6pz7s1wygbgnMsxs5nAoDDIdSYwxMwGAwlAXTN7JQxyHVtV7xQ42hewngM7Y7tx8A6MtRzYifcVoZ0y3+/EG1wJWTqUun0zMClMcg0ClgGNDxn3NVepHDM5eGdsWOTyni/Ge/42HNgZ262K3+OtOXhn7MMcvAPvobJet0rIZIT2kTx2yLiv2YDGQH3vdiIwm9AGju+vWamMAziwMzZsch0xa1U/4TFetPV4Re8t30VoD/VKSh2RAQSADO++p/A+9FXBWSZ7z7EYeA9oESa5MgnN933tfT0TJrl+QmjLJR/YBkwLh1xHyDmY0FElawhNOVXl+/t1YCtQ6L1WI4CGwMfAau/PBmW9bpWQ6yxCUwmLS72vBvudDegBLPRyZQB/9sZ9f81KPd8ADhR92OQ60pc+GSsiEuHC4fBKERGpRCp6EZEIp6IXEYlwKnoRkQinohcRiXAqehGRCKeiFxGJcCp6EZEI9/81NQIDYbP7xgAAAABJRU5ErkJggg==\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "xnew=np.append(x,431)\n", "ynew=np.append(y,y2025)\n", "plt.plot(xnew,ynew) \n", "plt.plot(431, y2025, marker='o', markersize=3, color=\"red\")" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Le point en rouge représente le niveau de concentration de CO2 en ppm à la fin du 2025." ] } ], "metadata": { "hide_code_all_hidden": false, "kernelspec": { "display_name": "Python 3", "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": "3.6.4" } }, "nbformat": 4, "nbformat_minor": 2 }