{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# France" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\pol\\AppData\\Roaming\\Python\\Python37\\site-packages\\statsmodels\\tools\\_testing.py:19: FutureWarning: pandas.util.testing is deprecated. Use the functions in the public API at pandas.testing instead.\n", " import pandas.util.testing as tm\n" ] }, { "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", "
dateRepdaymonthyearcasesdeathscountriesAndTerritoriesgeoIdcountryterritoryCodepopData2019continentExpCumulative_number_for_14_days_of_COVID-19_cases_per_100000
012/10/20201012202020216AfghanistanAFAFG38041757.0Asia6.968658
112/9/2020912202013513AfghanistanAFAFG38041757.0Asia6.963401
212/8/202081220202006AfghanistanAFAFG38041757.0Asia7.094835
312/7/2020712202021026AfghanistanAFAFG38041757.0Asia7.215755
412/6/2020612202023410AfghanistanAFAFG38041757.0Asia7.326160
\n", "
" ], "text/plain": [ " dateRep day month year cases deaths countriesAndTerritories geoId \\\n", "0 12/10/2020 10 12 2020 202 16 Afghanistan AF \n", "1 12/9/2020 9 12 2020 135 13 Afghanistan AF \n", "2 12/8/2020 8 12 2020 200 6 Afghanistan AF \n", "3 12/7/2020 7 12 2020 210 26 Afghanistan AF \n", "4 12/6/2020 6 12 2020 234 10 Afghanistan AF \n", "\n", " countryterritoryCode popData2019 continentExp \\\n", "0 AFG 38041757.0 Asia \n", "1 AFG 38041757.0 Asia \n", "2 AFG 38041757.0 Asia \n", "3 AFG 38041757.0 Asia \n", "4 AFG 38041757.0 Asia \n", "\n", " Cumulative_number_for_14_days_of_COVID-19_cases_per_100000 \n", "0 6.968658 \n", "1 6.963401 \n", "2 7.094835 \n", "3 7.215755 \n", "4 7.326160 " ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "import matplotlib.dates as mdates\n", "from matplotlib.dates import DateFormatter\n", "from matplotlib.ticker import (MultipleLocator, FormatStrFormatter,\n", " AutoMinorLocator) #gia ta ticks\n", "import numpy as np\n", "import seaborn as sns\n", "# Use white grid plot background from seaborn\n", "#sns.set(font_scale=1.5, style=\"whitegrid\")\n", "#sns.set_style('darkgrid')\n", "#sns.set_context(\"poster\")\n", "from scipy.optimize import curve_fit\n", "from lmfit import Model\n", "import scipy.optimize as scopt\n", "\n", "#years = mdates.YearLocator() # every year\n", "months = mdates.MonthLocator() # every month\n", "days = mdates.DayLocator() #every day\n", "#yearsFmt = mdates.DateFormatter('%Y')\n", "\n", "# Handle date time conversions between pandas and matplotlib\n", "from pandas.plotting import register_matplotlib_converters\n", "register_matplotlib_converters()\n", "\n", "from datetime import datetime\n", "\n", "\n", "df = pd.read_csv('COVID-19-geographic-disbtribution-worldwide-2020-12-10.csv')#,index_col='dateRep',parse_dates=True)\n", "#df.describe()\n", "df.head()\n", "#df.columns\n" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "FRA=df.loc[df['countriesAndTerritories'] == 'France'] #country selection" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "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", "
dateRepdaymonthyearcasesdeathscountriesAndTerritoriesgeoIdcountryterritoryCodepopData2019continentExpCumulative_number_for_14_days_of_COVID-19_cases_per_100000
2008812/10/20201012202014595296FranceFRFRA67012883.0Europe229.984136
2008912/9/2020912202013713831FranceFRFRA67012883.0Europe232.501562
2009012/8/202081220203411366FranceFRFRA67012883.0Europe225.699885
2009112/7/2020712202011022174FranceFRFRA67012883.0Europe227.253318
2009212/6/2020612202012923214FranceFRFRA67012883.0Europe230.439272
.......................................
204291/4/202041202000FranceFRFRA67012883.0EuropeNaN
204301/3/202031202000FranceFRFRA67012883.0EuropeNaN
204311/2/202021202000FranceFRFRA67012883.0EuropeNaN
204321/1/202011202000FranceFRFRA67012883.0EuropeNaN
2043312/31/20193112201900FranceFRFRA67012883.0EuropeNaN
\n", "

346 rows × 12 columns

\n", "
" ], "text/plain": [ " dateRep day month year cases deaths countriesAndTerritories \\\n", "20088 12/10/2020 10 12 2020 14595 296 France \n", "20089 12/9/2020 9 12 2020 13713 831 France \n", "20090 12/8/2020 8 12 2020 3411 366 France \n", "20091 12/7/2020 7 12 2020 11022 174 France \n", "20092 12/6/2020 6 12 2020 12923 214 France \n", "... ... ... ... ... ... ... ... \n", "20429 1/4/2020 4 1 2020 0 0 France \n", "20430 1/3/2020 3 1 2020 0 0 France \n", "20431 1/2/2020 2 1 2020 0 0 France \n", "20432 1/1/2020 1 1 2020 0 0 France \n", "20433 12/31/2019 31 12 2019 0 0 France \n", "\n", " geoId countryterritoryCode popData2019 continentExp \\\n", "20088 FR FRA 67012883.0 Europe \n", "20089 FR FRA 67012883.0 Europe \n", "20090 FR FRA 67012883.0 Europe \n", "20091 FR FRA 67012883.0 Europe \n", "20092 FR FRA 67012883.0 Europe \n", "... ... ... ... ... \n", "20429 FR FRA 67012883.0 Europe \n", "20430 FR FRA 67012883.0 Europe \n", "20431 FR FRA 67012883.0 Europe \n", "20432 FR FRA 67012883.0 Europe \n", "20433 FR FRA 67012883.0 Europe \n", "\n", " Cumulative_number_for_14_days_of_COVID-19_cases_per_100000 \n", "20088 229.984136 \n", "20089 232.501562 \n", "20090 225.699885 \n", "20091 227.253318 \n", "20092 230.439272 \n", "... ... \n", "20429 NaN \n", "20430 NaN \n", "20431 NaN \n", "20432 NaN \n", "20433 NaN \n", "\n", "[346 rows x 12 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "FRA" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "5.969001512738976e-08" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "4/67012883" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "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", "
dateRepdaymonthyearcasesdeathscountriesAndTerritoriesgeoIdcountryterritoryCodepopData2019continentExpCumulative_number_for_14_days_of_COVID-19_cases_per_100000
2008812/10/20201012202014595296FranceFRFRA67012883.0Europe229.984136
2008912/9/2020912202013713831FranceFRFRA67012883.0Europe232.501562
2009012/8/202081220203411366FranceFRFRA67012883.0Europe225.699885
2009112/7/2020712202011022174FranceFRFRA67012883.0Europe227.253318
2009212/6/2020612202012923214FranceFRFRA67012883.0Europe230.439272
\n", "
" ], "text/plain": [ " dateRep day month year cases deaths countriesAndTerritories \\\n", "20088 12/10/2020 10 12 2020 14595 296 France \n", "20089 12/9/2020 9 12 2020 13713 831 France \n", "20090 12/8/2020 8 12 2020 3411 366 France \n", "20091 12/7/2020 7 12 2020 11022 174 France \n", "20092 12/6/2020 6 12 2020 12923 214 France \n", "\n", " geoId countryterritoryCode popData2019 continentExp \\\n", "20088 FR FRA 67012883.0 Europe \n", "20089 FR FRA 67012883.0 Europe \n", "20090 FR FRA 67012883.0 Europe \n", "20091 FR FRA 67012883.0 Europe \n", "20092 FR FRA 67012883.0 Europe \n", "\n", " Cumulative_number_for_14_days_of_COVID-19_cases_per_100000 \n", "20088 229.984136 \n", "20089 232.501562 \n", "20090 225.699885 \n", "20091 227.253318 \n", "20092 230.439272 " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "FRA.head() #decide which columns to select " ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "67012883.0\n" ] } ], "source": [ "population=df['popData2019'][20088]\n", "print(population)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "FRA=FRA[['dateRep','cases']] #select columns" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "FRA = FRA.rename(index = lambda x: x - 20087).sort_index(axis=0 ,ascending=False) #concise indexing" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [], "source": [ "FRA= FRA.rename({'dateRep': 'Date'}, axis=1) # change the name of the column of dates" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "FRA.index=range(346) #reverse the numbering of indexes beginning from last day of 2019" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "FRA['Date'] = pd.to_datetime(FRA['Date'],format=\"%m/%d/%Y\")" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "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", "
Datecases
02019-12-310
12020-01-010
22020-01-020
32020-01-030
42020-01-040
52020-01-050
62020-01-060
72020-01-070
82020-01-080
92020-01-090
102020-01-100
112020-01-110
122020-01-120
132020-01-130
142020-01-140
152020-01-150
162020-01-160
172020-01-170
182020-01-180
192020-01-190
202020-01-200
212020-01-210
222020-01-220
232020-01-230
242020-01-240
252020-01-253
262020-01-260
272020-01-270
282020-01-280
292020-01-291
302020-01-301
312020-01-311
322020-02-010
332020-02-020
342020-02-030
352020-02-040
362020-02-050
372020-02-060
382020-02-070
392020-02-085
402020-02-090
412020-02-100
422020-02-110
432020-02-120
442020-02-130
452020-02-140
462020-02-150
472020-02-160
482020-02-171
492020-02-180
502020-02-190
512020-02-200
522020-02-210
532020-02-220
542020-02-230
552020-02-240
562020-02-250
572020-02-262
582020-02-273
592020-02-2821
\n", "
" ], "text/plain": [ " Date cases\n", "0 2019-12-31 0\n", "1 2020-01-01 0\n", "2 2020-01-02 0\n", "3 2020-01-03 0\n", "4 2020-01-04 0\n", "5 2020-01-05 0\n", "6 2020-01-06 0\n", "7 2020-01-07 0\n", "8 2020-01-08 0\n", "9 2020-01-09 0\n", "10 2020-01-10 0\n", "11 2020-01-11 0\n", "12 2020-01-12 0\n", "13 2020-01-13 0\n", "14 2020-01-14 0\n", "15 2020-01-15 0\n", "16 2020-01-16 0\n", "17 2020-01-17 0\n", "18 2020-01-18 0\n", "19 2020-01-19 0\n", "20 2020-01-20 0\n", "21 2020-01-21 0\n", "22 2020-01-22 0\n", "23 2020-01-23 0\n", "24 2020-01-24 0\n", "25 2020-01-25 3\n", "26 2020-01-26 0\n", "27 2020-01-27 0\n", "28 2020-01-28 0\n", "29 2020-01-29 1\n", "30 2020-01-30 1\n", "31 2020-01-31 1\n", "32 2020-02-01 0\n", "33 2020-02-02 0\n", "34 2020-02-03 0\n", "35 2020-02-04 0\n", "36 2020-02-05 0\n", "37 2020-02-06 0\n", "38 2020-02-07 0\n", "39 2020-02-08 5\n", "40 2020-02-09 0\n", "41 2020-02-10 0\n", "42 2020-02-11 0\n", "43 2020-02-12 0\n", "44 2020-02-13 0\n", "45 2020-02-14 0\n", "46 2020-02-15 0\n", "47 2020-02-16 0\n", "48 2020-02-17 1\n", "49 2020-02-18 0\n", "50 2020-02-19 0\n", "51 2020-02-20 0\n", "52 2020-02-21 0\n", "53 2020-02-22 0\n", "54 2020-02-23 0\n", "55 2020-02-24 0\n", "56 2020-02-25 0\n", "57 2020-02-26 2\n", "58 2020-02-27 3\n", "59 2020-02-28 21" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "FRA.head(60)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "#create a distinct column of cumulative cases begining from reported case number 1\n", "FRA['cumulative_cases']=FRA['cases']\n", "for i in range(1,346):\n", " FRA.loc[i, 'cumulative_cases'] = FRA.loc[i, 'cases'] + FRA.loc[i-1, 'cumulative_cases'] #create df column of cumulative cases\n" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": [ "# convert the Date column to a datetime type\n", "FRA.Date = pd.to_datetime(FRA.Date)\n", "\n", "# set the column of Date as the index\n", "FRA.set_index('Date', inplace=True)" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "FRA.plot(style='o',markersize=3,figsize=(10,7),x_compat=True)" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "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", "
casescumulative_cases
Date
2020-10-1216101734974
2020-10-138505743479
2020-10-1412993756472
2020-10-1522591779063
2020-10-1630621809684
2020-10-1725086834770
2020-10-1832427867197
2020-10-1929837897034
2020-10-2013243910277
2020-10-2120468930745
2020-10-2226676957421
2020-10-2341622999043
2020-10-24420321041075
2020-10-25454221086497
2020-10-26520101138507
2020-10-27267711165278
2020-10-28334171198695
2020-10-29364371235132
2020-10-30476371282769
2020-10-31492151331984
2020-11-01326411364625
2020-11-02492901413915
2020-11-03525181466433
2020-11-04363301502763
2020-11-05405581543321
2020-11-06580461601367
2020-11-07604861661853
2020-11-08868521748705
2020-11-09386191787324
2020-11-10201551807479
2020-11-11221801829659
2020-11-12358791865538
2020-11-13331721898710
2020-11-14237941922504
2020-11-15320951954599
2020-11-16272281981827
2020-11-1794061991233
2020-11-18455222036755
2020-11-19283832065138
2020-11-20211502086288
2020-11-21228822109170
2020-11-22178812127051
2020-11-23131572140208
2020-11-2444522144660
2020-11-2591552153815
2020-11-26162822170097
2020-11-27135632183660
2020-11-28125392196199
2020-11-29125002208699
2020-11-3097842218483
2020-12-0140052222488
2020-12-0280832230571
2020-12-03140642244635
2020-12-04126962257331
2020-12-05112212268552
2020-12-06129232281475
2020-12-07110222292497
2020-12-0834112295908
2020-12-09137132309621
2020-12-10145952324216
\n", "
" ], "text/plain": [ " cases cumulative_cases\n", "Date \n", "2020-10-12 16101 734974\n", "2020-10-13 8505 743479\n", "2020-10-14 12993 756472\n", "2020-10-15 22591 779063\n", "2020-10-16 30621 809684\n", "2020-10-17 25086 834770\n", "2020-10-18 32427 867197\n", "2020-10-19 29837 897034\n", "2020-10-20 13243 910277\n", "2020-10-21 20468 930745\n", "2020-10-22 26676 957421\n", "2020-10-23 41622 999043\n", "2020-10-24 42032 1041075\n", "2020-10-25 45422 1086497\n", "2020-10-26 52010 1138507\n", "2020-10-27 26771 1165278\n", "2020-10-28 33417 1198695\n", "2020-10-29 36437 1235132\n", "2020-10-30 47637 1282769\n", "2020-10-31 49215 1331984\n", "2020-11-01 32641 1364625\n", "2020-11-02 49290 1413915\n", "2020-11-03 52518 1466433\n", "2020-11-04 36330 1502763\n", "2020-11-05 40558 1543321\n", "2020-11-06 58046 1601367\n", "2020-11-07 60486 1661853\n", "2020-11-08 86852 1748705\n", "2020-11-09 38619 1787324\n", "2020-11-10 20155 1807479\n", "2020-11-11 22180 1829659\n", "2020-11-12 35879 1865538\n", "2020-11-13 33172 1898710\n", "2020-11-14 23794 1922504\n", "2020-11-15 32095 1954599\n", "2020-11-16 27228 1981827\n", "2020-11-17 9406 1991233\n", "2020-11-18 45522 2036755\n", "2020-11-19 28383 2065138\n", "2020-11-20 21150 2086288\n", "2020-11-21 22882 2109170\n", "2020-11-22 17881 2127051\n", "2020-11-23 13157 2140208\n", "2020-11-24 4452 2144660\n", "2020-11-25 9155 2153815\n", "2020-11-26 16282 2170097\n", "2020-11-27 13563 2183660\n", "2020-11-28 12539 2196199\n", "2020-11-29 12500 2208699\n", "2020-11-30 9784 2218483\n", "2020-12-01 4005 2222488\n", "2020-12-02 8083 2230571\n", "2020-12-03 14064 2244635\n", "2020-12-04 12696 2257331\n", "2020-12-05 11221 2268552\n", "2020-12-06 12923 2281475\n", "2020-12-07 11022 2292497\n", "2020-12-08 3411 2295908\n", "2020-12-09 13713 2309621\n", "2020-12-10 14595 2324216" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "FRA.tail(60)" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# Create figure and plot space\n", "fig, ax = plt.subplots(figsize=(8,6))\n", "\n", "# Add x-axis and y-axis\n", "ax.plot(FRA['cases'],'o',FRA['cumulative_cases'],'o',markersize=3) \n", "\n", "\n", "\n", "# Set title and labels for axes\n", "ax.set(xlabel=\"Datetime\",\n", " ylabel=\"Infections\",\n", " title=\"January - December 2020 for France\")\n", "\n", "\n", "# Define the date format\n", "date_form = DateFormatter(\"%d/%m\")#/%Y\")\n", "ax.xaxis.set_major_formatter(date_form)\n", "#set ticks every week\n", "ax.xaxis.set_major_locator(mdates.WeekdayLocator(interval=1))\n", "\n", "# format the ticks\n", "ax.xaxis.set_major_locator(months)\n", "\n", "ax.xaxis.set_minor_locator(days)\n", "#ax.set_xticklabels(labels, rotation=45)\n", "\n", "# rotates and right aligns the x labels, and moves the bottom of the\n", "# axes up to make room for them\n", "fig.autofmt_xdate()\n", "ax.legend(['cases','cumulative cases'])\n", "\n", "ax.grid(True)\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Define Function and start lmfit" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [], "source": [ "def fkin1(t1,b1,c1):\n", "\n", " TotalInfected1=1/(1+c1*t1**(b1))\n", " return TotalInfected1\n", "\n", "\n", "def fkin2(t2, a2, c2, h2):\n", " \n", " f=((a2*t2)**(1-h2))/(h2-1)\n", " \n", " TotalInfected2=1/(1+c2*np.exp(f))\n", " return TotalInfected2 \n", "\n", "def fkin3(t3,b3,c3):\n", "\n", " TotalInfected3=1/(1+c3*t3**(b3))\n", " return TotalInfected3\n", "\n", "\n", "def fkin4(t4, a4, c4, h4):\n", " \n", " f=((a4*t4)**(1-h4))/(h4-1)\n", " \n", " TotalInfected4=1/(1+c4*np.exp(f))\n", " return TotalInfected4 " ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "['b1', 'c1']\n", "['a2', 'c2', 'h2']\n", "['b3', 'c3']\n", "['a4', 'c4', 'h4']\n" ] } ], "source": [ "fkmod1= Model(fkin1)\n", "print(fkmod1.param_names)\n", "\n", "fkmod2 = Model(fkin2)\n", "print(fkmod2.param_names)\n", "\n", "fkmod3 = Model(fkin3)\n", "print(fkmod3.param_names)\n", "\n", "fkmod4 = Model(fkin4)\n", "print(fkmod4.param_names)\n" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "['t1']\n", "['t2']\n", "['t3']\n" ] } ], "source": [ "print(fkmod1.independent_vars)\n", "print(fkmod2.independent_vars)\n", "print(fkmod3.independent_vars)" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [], "source": [ "params1 = fkmod1.make_params(b1=0,c1=400000)\n", "params2 = fkmod2.make_params(a2=0.010147118061103244,c2=387.64, h2=4.74)\n", "params3 = fkmod3.make_params(b3=0,c3=30000000.5)\n", "params4 = fkmod4.make_params(a4=0.0031571424140701687,c4=27.18, h4=22.84)" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [], "source": [ "params1['b1'].min=-100\n", "params1['c1'].min=0\n", "\n", "params2['a2'].min=0\n", "params2['c2'].min=0\n", "params2['h2'].min=0\n", "\n", "params3['b3'].min=-100\n", "params3['c3'].min=0\n", "\n", "params4['a4'].min=0\n", "params4['c4'].min=0\n", "params4['h4'].min=0" ] }, { "cell_type": "code", "execution_count": 47, "metadata": {}, "outputs": [], "source": [ "Y1=FRA.loc['2020-01-25':'2020-12-10','cumulative_cases'].values[0:51] # up to 17 March 1st lockdown +2\n", "y1=Y1/population\n", "\n", "\n", "Y2=FRA.loc['2020-01-25':'2020-12-10','cumulative_cases'].values[52:184] # up to 20 July ease of measures and begin of rise days +1\n", "y2=Y2/population\n", "\n", "Y3=FRA.loc['2020-01-25':'2020-12-10','cumulative_cases'].values[185:268] #up to 28 October 2nd lockdown \n", "y3=Y3/population\n", "\n", "Y4=FRA.loc['2020-01-25':'2020-12-10','cumulative_cases'].values[269::]\n", "y4=Y4/population\n", "\n" ] }, { "cell_type": "code", "execution_count": 48, "metadata": {}, "outputs": [], "source": [ "T1=np.arange(1,len(y1)+1)\n", "T2=np. arange(len(y1),len(y1)+len(y2))\n", "T3=np.arange(len(y1)+len(y2),len(y1)+len(y2)+len(y3))\n", "T4=np.arange(len(y1)+len(y2)+len((y3)-1),len(y1)+len(y2)+len(y3)+len(y4)) " ] }, { "cell_type": "code", "execution_count": 61, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(array([4.47675113e-08, 4.47675113e-08, 4.47675113e-08, 4.47675113e-08,\n", " 5.96900151e-08, 7.46125189e-08, 8.95350227e-08, 8.95350227e-08,\n", " 8.95350227e-08, 8.95350227e-08, 8.95350227e-08, 8.95350227e-08,\n", " 8.95350227e-08, 8.95350227e-08, 1.64147542e-07, 1.64147542e-07,\n", " 1.64147542e-07, 1.64147542e-07, 1.64147542e-07, 1.64147542e-07,\n", " 1.64147542e-07, 1.64147542e-07, 1.64147542e-07, 1.79070045e-07,\n", " 1.79070045e-07, 1.79070045e-07, 1.79070045e-07, 1.79070045e-07,\n", " 1.79070045e-07, 1.79070045e-07, 1.79070045e-07, 1.79070045e-07,\n", " 2.08915053e-07, 2.53682564e-07, 5.67055144e-07, 8.50582716e-07,\n", " 1.49225038e-06, 1.93992549e-06, 2.65620567e-06, 3.16357080e-06,\n", " 4.25291358e-06, 6.31221910e-06, 9.14749482e-06, 1.06845127e-05,\n", " 1.68027393e-05, 2.10705753e-05, 2.66217467e-05, 3.40382311e-05,\n", " 4.29171209e-05, 5.46312863e-05, 6.71363445e-05]),\n", " array([9.89809676e-05, 1.15350954e-04, 1.36302150e-04, 1.64072929e-04,\n", " 1.88202618e-04, 2.15764482e-04, 2.39028666e-04, 2.96301235e-04,\n", " 3.32801679e-04, 3.76539538e-04, 4.35065598e-04, 4.91905415e-04,\n", " 5.60713080e-04, 5.99496667e-04, 6.64797543e-04, 7.77880277e-04,\n", " 8.50418568e-04, 8.81994586e-04, 9.60084048e-04, 1.02375837e-03,\n", " 1.05170822e-03, 1.11008506e-03, 1.16644735e-03, 1.22436159e-03,\n", " 1.28831944e-03, 1.35311295e-03, 1.39958163e-03, 1.42365163e-03,\n", " 1.46353948e-03, 1.54556848e-03, 1.58485944e-03, 1.62426977e-03,\n", " 1.63031338e-03, 1.66864930e-03, 1.68036346e-03, 1.71096952e-03,\n", " 1.75076783e-03, 1.77803125e-03, 1.80269815e-03, 1.82915575e-03,\n", " 1.85209163e-03, 1.85897091e-03, 1.87680330e-03, 1.89269577e-03,\n", " 1.91667623e-03, 1.93367296e-03, 1.94268615e-03, 1.95453462e-03,\n", " 1.95913075e-03, 1.96772612e-03, 1.98420056e-03, 2.04662139e-03,\n", " 2.05600765e-03, 2.06558790e-03, 2.07204934e-03, 2.07516814e-03,\n", " 2.08197281e-03, 2.09253794e-03, 2.10010365e-03, 2.10938544e-03,\n", " 2.11778681e-03, 2.12333799e-03, 2.12512869e-03, 2.13247056e-03,\n", " 2.14028995e-03, 2.14652756e-03, 2.15127291e-03, 2.15728668e-03,\n", " 2.16086808e-03, 2.16258417e-03, 2.16792643e-03, 2.17204504e-03,\n", " 2.17489524e-03, 2.22451256e-03, 2.23342130e-03, 2.26069963e-03,\n", " 2.26453472e-03, 2.26957852e-03, 2.25814788e-03, 2.26340061e-03,\n", " 2.27484617e-03, 2.28396382e-03, 2.29260395e-03, 2.29772236e-03,\n", " 2.30087101e-03, 2.30688478e-03, 2.31501755e-03, 2.32135961e-03,\n", " 2.33219335e-03, 2.34004259e-03, 2.34611604e-03, 2.34838427e-03,\n", " 2.35351761e-03, 2.36035211e-03, 2.36732092e-03, 2.37942307e-03,\n", " 2.38898840e-03, 2.39322639e-03, 2.39879248e-03, 2.40650742e-03,\n", " 2.40771614e-03, 2.40771614e-03, 2.43141308e-03, 2.43141308e-03,\n", " 2.43141308e-03, 2.45117047e-03, 2.45924355e-03, 2.47294240e-03,\n", " 2.48277633e-03, 2.49146123e-03, 2.49146123e-03, 2.49146123e-03,\n", " 2.51197967e-03, 2.51906786e-03, 2.52896148e-03, 2.53822836e-03,\n", " 2.54804737e-03, 2.54804737e-03, 2.54804737e-03, 2.57229643e-03,\n", " 2.57229643e-03, 2.58612960e-03, 2.59409821e-03, 2.60657343e-03,\n", " 2.60657343e-03, 2.60657343e-03, 2.63761223e-03, 2.64632698e-03,\n", " 2.66121963e-03, 2.67706733e-03, 2.69392976e-03, 2.69392976e-03]),\n", " array([0.002732 , 0.00274282, 0.00276359, 0.00278414, 0.00280422,\n", " 0.00280422, 0.00280422, 0.0028546 , 0.0028701 , 0.0028954 ,\n", " 0.00291933, 0.00295348, 0.00295348, 0.00295348, 0.00302591,\n", " 0.00304676, 0.00308442, 0.00312425, 0.00316672, 0.00321611,\n", " 0.0032611 , 0.00326846, 0.00330186, 0.00335821, 0.0034294 ,\n", " 0.00349783, 0.00355159, 0.00362466, 0.00365383, 0.00370314,\n", " 0.00378415, 0.00387534, 0.00398546, 0.00406683, 0.00414761,\n", " 0.0041936 , 0.00426794, 0.00437265, 0.00447945, 0.00461338,\n", " 0.00474097, 0.00484649, 0.00490921, 0.00500686, 0.00513485,\n", " 0.00528173, 0.00542209, 0.00557969, 0.00568688, 0.00577877,\n", " 0.00589594, 0.00604194, 0.00620002, 0.00639722, 0.00659864,\n", " 0.00677128, 0.00683542, 0.00698476, 0.00717983, 0.00742002,\n", " 0.00765575, 0.00787081, 0.0080368 , 0.00809753, 0.00821767,\n", " 0.00840935, 0.00861782, 0.0087991 , 0.00905236, 0.00923957,\n", " 0.00931573, 0.00947225, 0.00975199, 0.01002252, 0.01032603,\n", " 0.01072739, 0.01096765, 0.01109457, 0.01128846, 0.01162557,\n", " 0.01208251, 0.01245686, 0.01294075]),\n", " array([0.01358361, 0.01388905, 0.01428712, 0.01490822, 0.01553545,\n", " 0.01621326, 0.01698938, 0.01738887, 0.01788753, 0.01843126,\n", " 0.01914213, 0.01987654, 0.02036362, 0.02109915, 0.02188285,\n", " 0.02242499, 0.02303021, 0.02389641, 0.02479901, 0.02609506,\n", " 0.02667135, 0.02697211, 0.02730309, 0.0278385 , 0.02833351,\n", " 0.02868857, 0.02916751, 0.02957382, 0.02971418, 0.03039348,\n", " 0.03081703, 0.03113264, 0.0314741 , 0.03174093, 0.03193726,\n", " 0.0320037 , 0.03214031, 0.03238328, 0.03258567, 0.03277279,\n", " 0.03295932, 0.03310532, 0.03316509, 0.0332857 , 0.03349557,\n", " 0.03368503, 0.03385248, 0.03404532, 0.0342098 , 0.0342607 ,\n", " 0.03446533, 0.03468312]))" ] }, "execution_count": 61, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y1,y2,y3,y4" ] }, { "cell_type": "code", "execution_count": 50, "metadata": {}, "outputs": [], "source": [ "result1 = fkmod1.fit(y1, params1, t1=T1)\n", "result2 = fkmod2.fit(y2, params2, t2=T2)\n", "result3 = fkmod3.fit(y3, params3, t3=T3)\n", "result4 = fkmod4.fit(y4, params4, t4=T4)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# R square score" ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(0.9991609423978772,\n", " 0.9901739394079395,\n", " 0.9835755768902418,\n", " 0.9945984944146592)" ] }, "execution_count": 51, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#r2 sxore for heard\n", "from sklearn.metrics import r2_score\n", "y_pred1=result1.best_fit\n", "y_true1=y1\n", "\n", "r2_score(y_true1, y_pred1)\n", "\n", "#r2 sCore for fractal\n", "y_pred2=result2.best_fit\n", "y_true2=y2\n", "\n", "r2_score(y_true2,y_pred2)\n", "\n", "#r2 sCore for HEARD again\n", "y_pred3=result3.best_fit\n", "y_true3=y3\n", "\n", "r2_score(y_true3,y_pred3)\n", "\n", "\n", "#r2 sCore for fractal AGAIN\n", "y_pred4=result4.best_fit\n", "y_true4=y4\n", "\n", "r2_score(y_true1, y_pred1), r2_score(y_true2,y_pred2) ,r2_score(y_true3,y_pred3),r2_score(y_true4,y_pred4)\n", "\n" ] }, { "cell_type": "code", "execution_count": 52, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "({'b1': -11.694639073625012, 'c1': 1.368163811780042e+24},\n", " {'a2': 0.010131109706548624,\n", " 'c2': 386.51670622704995,\n", " 'h2': 4.717542750868408},\n", " {'b3': -5.0831936422608095, 'c3': 171456303931019.4},\n", " {'a4': 0.003111964242595633,\n", " 'c4': 25.501973448787428,\n", " 'h4': 16.105520568573073})" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" } ], "source": [ "result1.best_values,result2.best_values,result3.best_values ,result4.best_values" ] }, { "cell_type": "code", "execution_count": 53, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "The PostScript backend does not support transparency; partially transparent artists will be rendered opaque.\n", "The PostScript backend does not support transparency; partially transparent artists will be rendered opaque.\n" ] }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAESCAYAAAAMifkAAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAA8TklEQVR4nO3dd3hUZfbA8e9JI6EGEBHQBRRFpKrxJ4hgQJTFgiiuBdC1rIV1kXXtC2JDQXHVVVcXsCIWVIpYUYSRqoB0VEAEEdAV0RACCZnMnN8f9yZMJpNkBjKZSXI+z5Mnc/uZlzBn3nLfK6qKMcYYU5aEWAdgjDEm/lmyMMYYUy5LFsYYY8plycIYY0y5LFkYY4wplyULY4wx5bJkUc2IiE9EVgb8tIpBDJ6Dua6IDBaR1e7PIhHpHOHxrURkbaTXLeVcz4vICSHWXyUiz0TzGvFARMaLSPcYxzCgrPIRkRtF5MoytrcSkUEHcd2XReTiSI+r7pJiHYCpcLmq2iXUBhERQFTVX7khhW0zcIaq/i4i/YAJwKmxCERV/1IdrnEITgX+WpEnFJFEVfVFcMgA4H3g6xDnSlLV/5ZzfCtgEPB6BNc0pbCaRTXnfrv6RkSeBZYDR4nIcyKyTETWicj9AftuEZH7RWS5iKwRkePd9XVF5CV33WoRGeiuP1tEFrv7vy0idd1T/Qb4RCTR/Za21j32lrJiVdVFqvq7u/gFcGTQe5joxvyJiKS5204WkVUishi4qYxyuF1Elrrx3x9w3m9F5BV3/TsiUtvd5hGRDPf11SKyQUQ+B7oHnLOJiEx1z7u08Ju4iNznnvMTt0wvEpFH3TL4WESSQ1zjj245rhKRz0LE/6GIdHJfrxCRUe7rB0XkL+6/0WcB/3YXuNsfEZG/BpznPhG5tbQycde3AzYEf7AHf+MWkRz3d6b7Xt5xy/M194tJ4d/UKBFZAPyptL8ZERkrIl+7sTwmIqcB/YFx4tSQj3Gv8bD77zDcfS+3uce3EZHZbvktF5FjgLFAD/f4W9y/x3EB7/kG91gRkWfc638AHF7a31GNpqr2U41+AB+w0v2ZjvPtyg90Ddinkfs7EfAAndzlLcAw9/Vfgefd148ATwYc3xA4DJgH1HHX3QmMCorlZODTgOX0CN7HbQHXbwUUAF3c5beAIe7r1Ti1EYBxwNoQ5zobp5YiOF+Q3gd6uudVoLu734vAbe5rD5ABNAO2Ak2AFGAh8Iy7z+vA6e7rPwDfuK/vAxYAyUBnYB/Qz902HRgQdI0mwI9A68B/n6D3cBdOMqwPLAVmuevnAm1xWgnqu+sOA75z3++JwOcB5/najTVkmbj7/AO4JkQMLwMXByznuL8zgd04yT0BWBxQLluAOwLiKvE3AzQC1uPUeov+TkJczwM8G7B8X8C/15fAhe7rVKC2G9f7AftfD4x0X9cClgGtgYuAT3H+PzQHsgKvaz/OjzVDVT/FmqHE6Tv4QVW/CNjnEhG5HucDphlwAs6HLsA09/dXOP+JAPoAlxUerE4z0XnucQvdL5EpOB8Sgb4HjhaRp4EPgE/CeQMi0gu4Fjg9YPVmVV0ZEFsrEWmA88Hyubv+VaBfiFOe7f6scJfrAsfiJIEfVXWhu34ycDPwWMCxpwIeVd3pxjYFOM7d1gc4wX3/APVFpJ77+iNV9YrIGpwPoY/d9WtwklSgrsA8Vd0MoKq/hXgP893YNuOU5VluLaiVqq53aysPi0hPnC8HLYCmqrpCRA4XkeY4Sel3Vd0qIjeXUibzgL7A1SFiKMsSVd0GICIr3fe4wN02JeB9hvqbyQbygOfdb/bvl3GdKcEr3DJvoarTAVQ1z10fvOvZQKeA2lEDnPfcE3hDnZrUDhGZE9Y7rmEsWdQMewtfiEhrnG/tp7gf+i/jfBMrtN/97ePA34fgfAMPJDi1hstLu6h7/s44Hz43AZcA15QVqNvU8jzON/FdIeIqjC2tlLhCnhYYo6rjg67VKsTxoc5X2jUSgG6qmht03qJ4VdUvIl51v87ifJAH/78L530sxamFfI/zLfgw4DqcxAkwGCcZnOwmqS0c+Hd9B7gYOAJ4M+CaocqkNk4C3hEihgL3PRf2f6UEbAv+9wl8j4V/f6X+zYjI/wFn4nwp+RvQO8T1A89V7PBS9g213zBVnRV07XMI7++oRrM+i5qnPs5/uN0i0pTQ38SDfYLzHxgAEWmI06fQXUTauOtqi8hxgQeJyGFAgqpOBe4BTirrIiLyB5yazRWquqG8oFQ1y30fhTWQwaXsOgu4JqB9vIWIFLZL/0FEurmvL+fAt+FCXwKZItLY/fb+p4BtweXSpbyYS7EYOMNN5IhIo+AdVDUfp6nqEpyyn4+T9Oe7uzQAfnETRS+gZcDhb+J8CF+Mkzig9DLphdO0FcoWnKZFgAtwmtkiEfJvxo2hgap+CPwd6OLuvweoF+pEgVQ1G9gmIgPc89Zyk17w8bOAoXKgz+g4EamDU5u6zO3TaIZTBiaI1SxqGFVdJSIrgHU431IXlnMIwGjgP+IMS/UB96vqNBG5CnhDRGq5+40EAj/kWwAviUjhl5K7y7nOKKAx8Kz77bxAVTPKOeZq4EUR2YfzYVCCqn4iTqftYve8OcAQ9718A/xZRMYDG4Hngo79SUTuw/lA/wlnkECiu/lmnHJZjfN/aR5wYznxhopvp9ssOM0tq1+As0LsOh84U1X3ich8nD6CwmTxGvCeiCzD6a/6NuD869ymmu2q+lM5ZdKPAwkl2ETgXRFZAnxG6G/55b3Pqyj5N7PHPW8qzrf/woEQbwIT3Saz8oayXgGMF5EHAC9OUl8NFIjIKpz+j3/jNI8td2tGO3FGXE3Hqcmswfn7/RxTghyoHRtTs7jNUO+raodYxxIvRGQ5cKqqemMdi4kvVrMwxhRR1TKbCk3NZTULY4wx5bIObmOMMeWyZGGMMaZc1bbP4rDDDtNWrVoVLe/du5c6derELqAqwsopPFZO4bFyCl+8lNVXX331q6o2CV5fbZNFq1atWLZsWdGyx+MhMzMzdgFVEVZO4bFyCo+VU/jipaxE5IdQ660ZyhhjTLksWRhjjCmXJQtjjDHlqrZ9FqF4vV62bdtGXl5erEOJK6mpqRx55JEkJ0c61Y8xpqaoUcli27Zt1KtXj1atWoWavrhGUlV27drFtm3baN26dazDMcbEqRqVLPLy8ixRBBERGjduzM6dO2MdijHmEMxYsZ1xs9azIyuX5ulp3N63LQNObFFh569RyQJCPhClxrMyMaZqm7FiO3dPW0Ou13kS7vasXO6etgagwhKGdXAbY0wVN27W+qJEUSjX62PcrPUVdg1LFjF033338dhjj5W6fcaMGXz99deVGJExpirakZUb0fqDYcmiDDNWbKf72Dm0vusDuo+dw4wV2yv3+pYsjDFhaJ6eFtH6g2HJohSFbYDbs3JRDrQBHmrCeOihh2jbti19+vRh/Xqnijhx4kROOeUUOnfuzMCBA9m3bx+LFi1i5syZ3H777XTp0oVNmzaF3M8YY27v25a05MRi69KSE7m9b9sKu4Yli1JEow3wq6++4s0332TFihVMmzaNpUuXAnDRRRexdOlSVq1aRbt27XjhhRc47bTT6N+/P+PGjWPlypUcc8wxIfczxpgBJ7ZgzEUdaZGehgAt0tMYc1FHGw1VGaLRBjh//nwuvPBCateuDUD//v0BWLt2LSNHjiQrK4ucnBz69u0b8vhw9zPG1DwDTmxRockhmNUsShGtNsBQw1SvuuoqnnnmGdasWcO9995b6h3m4e5njDEVzZJFKaLRBtizZ0+mT59Obm4ue/bs4b333gNgz549NGvWDK/Xy2uvvVa0f7169dizZ0/Rcmn7GWNqpsochGPNUKUorM5V5B2RJ510EpdeeildunShZcuW9OjRA4AHH3yQU089lZYtW9KxY8eiBHHZZZdx3XXX8dRTT/HOO++Uup8xpuapjBvxAlmyKEM02gBHjBjBiBEjSqwfOnRoiXXdu3cvNnR26NChIfczxtQ8ZQ3CiUaysGYoY4ypgirjRrxAliyMMaYKqowb8QJZsjDGmCqoMm7EC2R9FsYYUwVFYxBOWSxZGGNMFRHqmRUL7+pdKdeulGYoEXlCROaLyL+D1jcXkTkiskhE+rjr+onItyKyIGC/80XkCxFZLCK3VkbMxhgTT6I1X124op4sROQkoI6q9gBSROSUgM13ASOBs93fAF8AnYNOswroDpwG9BeRBtGNOnq2bNlChw4dDukcHo+HRYsWlbr97bffpl27dvTq1Ytly5Zx8803h3WcMSZ+VcYzK8pSGc1Q3YDZ7uvZQFdgqbvcCRiuqioie0Sknqr+DsWnxVDVrYWvRcQH+Csh7rjl8XioW7cup512WsjtL7zwAs8++yy9evUCICMjI6zjjDHxK6yhsjm/wLcfQMbVFX79ykgW6cAm9/VuoH3AtkRV1YBtDYFSb0sWkX7Ad6oach8RuR64HqBp06Z4PJ6ibTk5OTRo0CDmdz3n5OSQn5/PoEGDWL16NW3atGH8+PGsX7+ef/7zn+zdu5dGjRrx3//+lyOOOILnnnuOF198kaSkJNq2bcv999/Pc889R2JiIpMmTWLcuHHFPvzHjh3LggUL2LRpE+eccw59+/blqaee4rHHHivzuLy8PDweDzk5OcXKzYRm5RQeK6fwlVdWjVKFXXkacr3H4yGxYC9dVo6g9r4dLPm1LvtTm1RofJWRLLKA+u7r+u5yocA6VfC2YkTkaOAO4LzS9lHVCcAEgIyMDM3MzCza5vF4SE1NpV69es6Kj+6Cn9eE+x7Cc0RH6De2zF3q1q3Lxo0beemll+jevTvXXHMNkyZNYvr06bz77rs0adKEKVOmMGbMGF588UWefPJJNm/eTK1atcjKyiI9PZ2hQ4dSt25dbrvtthLnf+ihh1i4cCGPPfYYGRkZeDwekpKS6NChQ5nHpaamcuKJJ+LxeAgsNxOalVN4rJzCV15Z3dOg+PQe4AyVveeCjmS2bwiTB8K+bTDoTbq16VPh8VVGslgM3AC8BfQBXg7YtlpEugGrgfqqmh3qBCJSzz3uKlXdG9VoK8FRRx1F9+7dARgyZAgPP/wwa9eu5ayzzgLA5/PRrFkzADp16sTgwYMZMGAAAwYMiFXIxpgYK3WobKfD4c3BsHUxXPwCRCFRQCUkC1VdLiJ5IjIfWKWqS0TkaVUdBjwKTALSgHsBRCQDGAt0EJHZODWJvwGtgRfdvoyrVXXzIQVWTg0gmoKnKa9Xrx7t27dn8eLFJfb94IMPmDdvHjNnzuTBBx9k3bp1xbb7fD5OPvlkwHk+xgMPPBC9wI0xMVVivjq/H2bcCBtnwXlPQIeBUbt2pdxnoarDg5aHub+3Ab2Dti3DqYEEGuP+VAtbt25l8eLFdOvWjTfeeIOuXbsyceLEonVer5cNGzbQrl07fvzxR3r16sXpp5/O66+/Tk5ODvXq1SM726mEJSYmsnLlyrCuG3icMSb+hbqvoihZqMJHd8DqKdB7JGRcE9VYbLqPGGjXrh2vvPIKnTp14rfffmPYsGG888473HnnnXTu3JkuXbqwaNEifD4fQ4YMoWPHjpx44onccsstpKenc/755zN9+nS6dOnC/Pnzw77uwR5njKl85d5XMWc0LJ0Ipw2DHiX7ISua3cFdyVq1alVs2vFCXbp0Yd68eSXWL1iwoMS64447jtWrV5d6jcARFZmZmUWdZuUdZ4yJH2VOQb7vHZj/GJx0JZz1IIR4AmdFs2RhjDFxqLT7Ks7Y8z58+gK0vwjOe7JSEgVYM5QxxsSlUFON909YyOjkF+HYs+HC8ZCQGOLI6KhxyeLAPYCmkJWJMfEneArysxOW8njyc+w67BS4ZBIkpVRqPDWqGSo1NZVdu3bRuHHjEsNXaypVZdeuXaSmpsY6FGNqvODRTwNPbsHcb3fSJvsLnkl5muyGHWly3TRIjs4DjspSo5LFkUceybZt29i5c2esQ4krqampHHnkkbEOw5gabdEOL69+duAO7e1ZuUz9ajsTeu6nx5dPwWHtaPTnd6FWvZjEV6OSRXJyMq1bt451GMYYU8LUDV5yvcWbhI8v+JaTF46Bw/4AQ6ZDWsMYRVcD+yyMMSaezFixne5j55SYJLC9bOaVlEf4xd8ArpwJdSt2YsBIWbIwxpgYCbzxLlBb2crklDFkU5t/pD0I9ZvFKMIDalQzlDHGxFpgJ3aCCL6g0YjHyHYmpzxMHilc7R/FTX88PUaRFmfJwhhjKklhTaKwEzs4URwtO3gj5SFA+EetB7ipX+/iEwfGkCULY4ypJKGm8CjUUn7m9ZSHSMDP8FqjeeOfV1RydGWzPgtjjKkkpU3hcZT8jzdSRpOCl2v89/CnftF5JsWhCLtmISJdgOMBBdar6sooxWSMMdVS8/S0Ep3ZR8pO3kh5iNrs5++1HuSafn+Mm6anQOUmCxG5DegGbAQ2AwJcLiL3AotUdVx0QzTGmKorsEO7QVoyyYmC1+f0VRwpO5mSMpomKfms7vQAL59/bYyjLV04NYtPVPWxUBtEpFMFx2OMMdVGcId2Vq6X5AShYe1k6uTu4O1ao2mcvJ+Uq2eSs2F3jKMtW7l9Fqpa7AEIIjKgtG3GGGMOCNWh7fUrRyf9xoKm/6JZaj4pV8+E5ifGKMLwHUwH96kiUqvCIzHGmGomVIf2kbKTJ/NGQt5uuPLdKpEo4OCGzh4F3C0idQC/qt5ZwTEZY0y1ENyh7Yx6eoj6kgdXvl9lEgWEUbMQkeApDt9W1ftU9XZLFMYYU7rAZ1K0lJ+ZkvIgdcnjqzNerlKJAsKrWbwtIvWBPcC3wDcicgbwjar+EtXojDGmCiscAvvmR3N4Yv9o0sTL8sxJ9M48M8aRRa7cZKGqfwQQkbpAO+AE4BzgH8AFUY3OGGOqoMDhsqfV/5WX5QFS6yTAn2fRu2n7WId3UMK5z6Kzqq5S1RxgqftTbFs0AzTGmKokcLjs8bKVf+9/mD0ksLD3JM6sookCwmuG6uPegPcjsMVd1wqno3sBYMnCGGNchcNl28tmJqeMIY8UBuWPIH+xjzPPiHV0By+cZqh/icjjQGfgWJw7uOcCq1SDpkw0xpgabkdWLifKRl5OeYQ91Oby/BH8qE2RUuaFqirCGjrrJoWV7o8xxphSnFN/E4/sH8Ov2oDB+f9kO84T7pqnp8U4skNjU5QbY8whKuzQbpP9BeNTHmcbhzMo/5/8gvPM7LTkRG7v2zbGUR6aSpmiXESeEJH5IvLvoPXNRWSOiCwSkT7uun4i8q2ILAjYL0lEXhWRBSJyV2XEbIwx4Sjs0G6fPY+JyY+xyd+cwd5ReGsfjgAt0tMYc1HHuJxJNhJhJwsRucr9fYqIfCgiF4d53ElAHVXtAaSIyCkBm+8CRgJnu78BvsDpHwnUH+e+jtOB00XkiHDjNsaYaBo3az19fZ/zbPK/WaetuTx/BP/z16N2ShKbx57Lwrvi52l3hyKSmsUQ9/ffgGtxPujD0Q2Y7b6eDXQN2NYJWOwOy90jIvVU9XdV3V/GOeYCp2CMMXGg156ZPJ78HEv8xzMk/26yqQuU/qCjqiqSPou6ItITyFHVn0Rkb5jHpQOb3Ne7gcCBxokBI6p2Aw1x7hQPdY7soP1KEJHrgesBmjZtisfjKdqWk5NTbNmEZuUUHiun8FT3cjpq61RGJ0/iU99J/M17M/tJKdrWKFUieu/xXlaRJItbgH7AgyKSCkwL87gsoL77ur67XChw7t7gbWWd47tQO6nqBGACQEZGhmZmZhZt83g8BC6b0KycwmPlFJ7qWk4zlm8j+4NRZPqm8hHd+Yf/RvaTWLQ9LTmRey7oSGYEzU/xXlaRNEN9DezDSRpeDtQWyrMYKJwIpQ9On0Sh1SLSzZ3Btr6qZpc4uuQ5ehFwF7kxxlSmGcu3kjdjOFf6pvJawZnclDeUAk2iYe3katWhHSySZDEZ5z6LbqrqA/4ezkGquhzIE5H5OFOaLxGRp93NjwIP4fRHPAwgIhkiMhvoICKz3VrMe+7yApw+jp8iiNsYYypGQT713r+RyxJm85+C/owouAY/CXj9Wu06tINF0gyVpqofi8gd7rKEe6CqDg9aHub+3gb0Dtq2DKcGEmxwBLEaY0zFyt8LU67gTP9CHvIOYqLvvGKbq1uHdrBIksUGEbkTaCQitwDrohSTMcbEl32/wWt/gh3LGZN0ExPzupfYparfoV2esJOFqv5VRM4DXgO+U9UnoheWMcbEid3byJ54PrVyfuTm/OF8Wes0khML8PoOTI1XHe7QLk/YyUJErlLVl0Xkf8D9IlJLVd+JYmzGGBNbO9ez78X+yL7d/Nl7J1/4T4BcL8kJQsPayWTt89I8PY3b+7atlv0UgSJphhoCvMyBm/LeAyxZGGOqpx+XwuuXkJvr54r8e/haWxVtKuzQXjHq7NjFV8kq46Y8Y4ypWjbMomDKlfzsT2fw/jv4QUvOMFTdO7SDRXpT3jlEflOeMcbEvcKZY0/b8xFjkp/nG39Lrs6/g19pEHL/6t6hHSySDu7FIrKTAw9AWhG1qIwxphI5M8eu5mr/NO5Ifot5vo7c6L2FfaSG3L8mdGgHi6SD+xmgAdAdWATUBuZFKS5jjKk0j3/8NSN0IkOSP2Oa73Tu9F6Pt5SPxxY1pEM7WCTNUJ1UtaeIzFXVISJizVDGmKovfy+j9j1Mn6TlPFvQn0cLLqW0e45bpKex8K7eIbdVd5EkiwIRSQCyRORKoE2UYjLGmKibsWI7Ez9ewujc0fRK2MRI79VM9p1V6v41sekpUCTJYjDOXFJDgUHAFVGJyBhjomzGiu2MnzaL52QsR8hv3Oi9hU/9GcX2SU4Q6qYm1ah7KcoSSbJ4XlXPBX4WkSdw7rM4r5xjjDEm7sz6aDqvJ4zBRwKX5d/DSnUaShJF8KtacgghkmRRp/CFqqqI1ItCPMYYE11rp/Lk/vvYro25ynsnW7Vp0Sa/KpvHnhvD4OJXJMlio4iMxhkJ1Q3YGJ2QjDEmClRZ99Z9tP/mSVbrcVyXfytZFP/OW9PunYhEJMnieuACoAOwDJgZlYiMMaai+bz88Mr1tN86jZm+btzuvaHYI1DBOrDLE8lNeQrMiF4oxhgTBblZ8NYVtNw6j6cKBvBEwcVo0HPfauq9E5GIpGZhjDFVyicLvuDYz66lhf8n7vbeyFR/zxL7CNTYeyciYcnCGFMtzZs9k1Pm/xVQrvTe7UwvHoL1U4Qn7Gdwi0gDEblLRB4RkUT3QUjGGBN/Vr5B1wVX85vW5cL8+0tNFNZPEb6wkwUwGVgJdFNVH/D3aARkjDEHze+H2ffDjBtZ6mvLhfn3s0WbldhNcPopxlzU0fopwhRJM1Saqn4sIne4y6EnTzHGmFjYn8NPL11Bs5/n8EZBL+7zXcN+EkvsVpPndzoUkSSLDSJyJ9BIRG4B1kUpJmOMiUzWVna/eDGH797AfQVX8rKvL6G+z1qz08GLJFnMAfYDrwHfqeoT0QnJGGMi8MNimDKEhH37uMp7J/P9nYpttik8KkYkyaIZ8EdgD7BVROqoqj1a1RgTMyumP0mHVQ+yzX8Yf/HezyYtmQhsCo+KEXYHt6o+7U4kOAw4GfgpalEZY0xZfF6+f2UoJ666l0W+E7gg/4GQiQJsaGxFieRJeW2BPwGZwA/ApVGKyRhjSrf3V3j7Ko7eMp8JBecytuBy/KV877U+iooTSTPUrcA7wBh36KwxxlSun1axb9JlJObu5O78G5kW4o5scLq2rY+iYkUyN9T10QzEGGNCmbFiO+Nmrefk7M94JGUCu7UuN+SPYrUeE3J/GxobHeUmCxG5WlVfEpEHAQ3cpqqjwrmI+7CkDGC5qg4PWN8c52a/VGCUqs52n5PxOtAIGK+qk0TkCOBNnC8Mm1T1mvDenjGmKpuxYjsjp63kZn2N61M+4Ev/8dyUP5xfaRByf2t2ip5wOriXu79nA58F/MwO5wIichJQR1V7ACkickrA5ruAkcDZ7m+A64A3gJ7AX0QkBecxri+q6hmAT0Q6h3NtY0zVNvHjJYznIa5P+oBJBWcxJP+fpSYKuyM7usqtWajqKvflSFUtepq5iLwBzAvjGt04kFhmA12Bpe5yJ2C4++S9PW6tohtwk6r6RGQV0Bb4FmjtHlMPyAp1IRG5Hue5GzRt2hSPx1O0LScnp9iyCc3KKTxWTuE5mHJatMPL1A1emu/fxISUJzgsIZtb80PPGFuocarwUNcE2L0Rj6dqPpct3v+mwmmG6gX0Bo4VkQcCjmse5jXSgU3u691A+4Btie5zMgq3NXT3zw5atwx4UET+BixV1R9CXUhVJwATADIyMjQzM7Nom8fjIXDZhGblFB4rp/BEWk4zVmzn1c/WcL5/Dg+mvMxOGjAw/17W6tGlHpOWnMg9F3Qks4rXKOL9byqcDu7vAT9wNE7zE4AXGBvmNbKA+u7r+hSvFQSOqircVrh/XsC6W4Gxqvq2iDwtIj1VNZxajTGmCvn3x6u5T//LpckeFvjaM8w7jN+LPj4cyQlC3dQksvZ5bcRTJQqnGeoHnPsqPheRY3BqFElAF8JrhloM3AC8BfQBXg7YtlpEugGrgfqqmi0ii4EzReQt9xrrcTq2f3OP2QWlNFoaY6qkGSu2M/mjeTyVN5aOSVt4puACHi/4U7H7J2w4bGxFclPeMzgf0t2BRUBtwkgWqrpcRPJEZD6wSlWXiMjTqjoMeBSYBKQB97qHPI8zGmoYMEFV94vIs8ArIjIKJ1k8HPY7NMbEtRkrtvPRtEk8n/A0CaL8Jf9WZvtPLraPDYeNvUhuyuukqj1FZK6qDhGRaeEeGDhc1l0e5v7ehtMfErgtGzgvaN0W4IwIYjXGVAV+H1nvj2J84jt87W/JUO9wftAjiu1iw2HjQyTJokBEEoAsEbkSaBOlmIwxNUHOLzD1Wq7yzePNgkzuLbiK/aQU26WFNTvFjUiSxWCc+zKG4tz3cEVUIjLGVH9bFsA710Lebh5KGsbEvG4ldrGmp/gSztDZEndu4/Q1DQRWlTzCGGNK4ffDgn+hcx5mqzTjhrx7+Tn1GJITC/D6DnzMWNNT/AmnZhHWndrGGFOmvb/CtOtg0xze93fnrvxr2Esa5HpJThAa1k624bBxLJyhs58DiEjpt08aY0xZNs+HqX+B3N95JGkoz+WcTuBjT71+pXZKEitGnR27GE2ZIumz6OX+FqAjTtOU3RhnjCmd+mDuGJj3KDQ6Boa8w3+f3Bpy1x1ZuZUcnIlEJFOU3x+4LCIzKjwaY0z1kb2DzqtGQdZath41gGt+uYRNT24lQQSfBneD2hPt4l0kN+UFTgveHDis4sMxxlQL6z+CGX+l/v69fHXiwwxZdgy5Xmd2n1CJwjq0418kzVCF8zgpsAZ4ssKjMcZUbd48+HQULBkPR3Ri2R9u4B+rm5PrLdnElCiCX9U6tKuISJqhXhGRLjizwArwf8CcKMVljKlqfvnW6cT+3xq+O/pK/rL9PLZsKQBC90X4Vdk89tzKjdEctEiaod4DtgM/uasUSxbGGFVY9gLMGgEpdVl86nNcs6gRud6CMg+zPoqqJZJmqDRVvTFqkRhjqp69u2Dm32D9h3DMmTDgOW77z7qQzU6BrI+i6okkWbzoPkt7Le4d3ar6YlSiMsbEv42z4d2/Qu7v0HcMM2qdz7j/rGN7GUNgbZrxqiuSZDEU+BAou25pjKnevLnw6b2wZDzfy1H8Le9+dnzShr35a4pN2RHM5nqq2iJJFrtUdUzUIjHGxL+fVsHU6+DX9bziP4eH8y9xZorN9ZZ5mDU7VX2RJAsVkekUb4YaFZWojDHxxVcAC58Az1io04S/J9/LjD3hffjbNOPVQyTJ4sloBWGMiWO7NsH0G2HbEmYnnM5tO68ki7phHdo4VazpqZqIqGYRtSiMMfGncEjsJ/eQTxJ3+29mal7XsA9PS05k4HGJUQzQVCabSNAYU9LubfDu3+D7uXB0Ly7ZPoiV+XXKPCQ5QaibmlRsmvH03RsrKWATbTaRoDHmAFVY9SZ8dCf4C+DcxyHjGlbd/WGph5Q1HNbjsWRRXRzsRILNsIkEjalesn+C9/8OGz6GP3SDAc8y44dajHtkbqlt0DYctuY42IkE12Id3sZUD6qwegp8dAcU5EPfMXDqjcxY9RN3T1tTNFtsMBsOW7NEkiwuUdVzAUREgPeA86ISlTGmcmTvgPf/ARs+gqO6woBnofExAIybtb7URGHDYWueSJJFUe+WqqqI1ItCPMaYyqAKKyY7k//58qHvw25t4mfGTZzDjqzcUpueBKzpqQaKJFlsFJHRwCKgG2A9V8ZURVlb4b3hsGkOtDwd+j8FjY9hxortZTY7FbLZYmumSJLF9cAFQAdgGTAzKhEZY6LD74MlE+GzB5zlcx6DjGshIQEou9mpkPVT1FyRDJ1VYEb0QjHGRM0v38LMYbBtCbQ5C857AtKPYsaK7Yybtb7MZiew2WJNZDWLg+ZObZ4BLFfV4QHrmwOTgVRglKrOdvtCXgcaAeNVdZK7753AWW7MvVXVXxmxG1OlFeyH+Y/D/H9BrXpw4QTodAmIhN3sZMNjDYSRLERE3FrFQRGRk4A6qtpDRJ4TkVNUdam7+S5gJLAaeB+YDVwHvAFMAeaKyJtAZ6CuqvY52DiMqXF+WAzv3Qy/boCOlzid2HWbFG22ZicTiYQw9pkLICITDvIa3XCSAO7vwMllOgGLVTUH2OPWKroBs1XVB6wC2gLnA41FZK6I2Ey3xpQl93enA/ulP0JBHgyeCgMnFiWKGSu2033snHIfUtQiPY0xF3W0ZicDhNcMlSMirwO9RSQ1cIOqXhnG8enAJvf1bqB9wLbEgFrLbqChu3920LqmOM/T6CUib4rISaq6PPhCInI9Tkc8TZs2xePxHHgTOTnFlk1oVk7hictyUuXwX+bT5rvnSfbuYduRF7C59SD825NguweARTu8vLw2n/wyGnEbpwr/yqztLOzeeEhTdsRlOcWpeC+rcpOFqp4nIs2AR4E1QDLO0/KmhnmNLKC++7q+u1wosA5cuK1w/7yAdbuBz9395gLtgBLJQlUnABMAMjIyNDMzs2ibx+MhcNmEZuUUnrgrp9++hw9udYbDtjgZznuSo5p14igo1omdIEIZD7MjLTmRey7oSGYF1SbirpziWLyXVVgd3Kr6k4gk4iSKr3A6q0cDl4dx+GLgBuAtoA/wcsC21SLSDafPor6qZovIYuBMEXkL6AKsx7m3oxMwy133ajhxG1PtefNg4b+dDuzEFDjnMWYk9WXcK9+xI+sDGqQlsze/oOhxp74yuh/trmxTlkhGQzVX1UHu61ki4gnnIFVdLiJ5IjIfWKWqS0TkaVUdhlNbmQSkAfe6hzyPMxpqGDBBVfeLyPvARBH5HPhWVRdFELcx1dOmuU5t4rdN0P4i6PswMzb5i41wyirncaeFbMSTKU8kyWKHiIzAaf7JAH4O98DA4bLu8jD39zagd9C2bILmnFLVAuDqCGI1pvravR0+GQHrpkOjY1jY7XnuWNGYHQ8vd5uZIhu8aCOeTDgiSRZXABfiNAd9C4yJSkTGmNAK8uHL58DzCKgPeo1gZp2LufPdDeR6nZFN4SaKRBH8qnajnQlbJHdw+4B3ohiLMaY0m+Y6DyT6dT20PQf+OAYatuKRsXPKvVciWFpyog2JNREL5z4LY0ysZG2FKVfAqwPAtx8unwKXv8GMLcnl3itRKDlBaFg72e6dMIekUqb7MMZEyJsLC5+CBU84y71HQrdhkJwa1jQd1sxkKlokj1WtDZyJc9OcABTO22SMqSCq8PUM+OQe2P0jnDAAzh4N6UcV7VLeNB3WzGSiIZKaxSzgQ2BHlGIxpmb7eQ18fDdsmQ9NO8CA56B1D4CwZ4e1eyVMtESSLH5XVRsBZUxFy9kJcx6E5ZMgLR3O/RecdBUkOv89bXZYEw8iSRZ+EZkOrAXny42q2qR+xhwsbx4sGQ+fj4OCXOg6FM64A9Iahpiio+whsXavhIm2SJLFE1GLwpiaRBXWTYPZ9zmjnY7tC30fgsOOBUrWJMpKFPZQIlNZIkkW84GBQBucWWTDnUjQGFPoxyUwa4TzxLqmHeCKGXBMr2K7hPOcCbBmJ1O5IkkWrwLrODCR4GTCm0jQGLNrE3x2P3z9LtRtCv2fgS6DICGxaJfCpqdw7p2wZidT2SJJFkeq6mD39Sx3Uj9jTFn27oJ5j8LSFyAxGc64C04bBrXqFuuXCJ4dNhS7d8LEUiTJYnvQRII/RSckY6qB/H3wxbPO9OH5OXDiFXzU5BpGf/4bO2Z9XiI5lDc7rN07YWLtYCYS7Ah8AzwclYiMqcp8BbByMswdAzk/Q9tz4cxRzNhe76CmDge7d8LEh3KThYhcraovAffhDJkVoDPO7LM2dNYYcO+8fte5X2LXd3DUqczrMo67l9Vlx+ObDmrqcLBObBM/wqlZFD6+dHbQ+sj/8o2pblThe4/Teb1jBTQ5Hi57nRn7OnP39LURTx0eyDqxTTwJ5xncq9yXI1X1rML1IvIGMC9agRkT935cAp894EzP0eAoZ3qOTpdCQiLjDmLq8OQEoW5qEln7vNaJbeJOOM1QvXCeZnesiDwQcFzzaAZmTNz6eQ0d1owGz1Ko0wT6PQonXwVJtSIa/mrJwVQl4TRDfQ/4gaOBz9x1XmBstIIyJi798g14xsDX79IgqQ6cOQpOvRFS6gDhzeFkw19NVRVOM9QPwA+A3VdhaqZfN8Lnj8CadyClLvS8gy99nTm9x3luTeLLsOZwsuGvpiqL5HkWH6jque5rAd5T1fOiFpkxsfbrd84NdWvehqRU6D7c+andiAKPJ6I5nGz4q6nqIrnPok7hC1VVEakXhXiMib1fv4N542DNW5BYC7rdBKcNh7pN3JqE8zjTRFkV1ignG/5qqoNIksVGERkNLAK6ARujE5IxMbJzPcx7DNa+4ySJrn91ahJ1Dwcimw22kA1/NdVFJMnieuACoAOwDJgZlYiMqWz/W+ckiXXTITkNuv3Nmb8pIEmEO8IJrBPbVE9hJwu36WkNsAvnLu4e2H0WpirbvtxJEus/cDquuw+H04YxY8N+xj2zNuwJ/gJZJ7apriLp4H4GaAB0x2mKqo0lC1PVqMIPC2H+v2DTHEhN55u2N3HLllNZ/1kSDRYtj2iCP7CahKkZImmG6qSqPUVkrqoOEZFpUYvKmIrm98PGT5wksW0Ju0hnovcy3qMfv6xNiSg5BLKahKkpIkkWBSKSAGSJyJU4T8wzJr75vLB2qjNV+C9fsy+tOY/5r+G1/J7sJwV8cLDTnNlwWFOThJUs3PsqngcSgKHAIODKcC8iIk/gPANjuaoOD1jfHOeJe6nAKFWd7Q7JfR1oBIxX1UkB+z8FNFLVIeFe29RQ+3NgxWRY/Azs/pHsem14Mnk4k34/mYKIviOVlJacyBXtEvnnIBsOa2qOsP7XuJ3bl6rq68DPwOPhXkBETgLqqGoPEXlORE5R1aXu5ruAkcBq4H2cmW2vA94ApgBzReRNVc0XkaZAKyA73GubGijnF/hyPCx9HvKy4KiuLD7+bq5d1JB93oOrQYSawyl9t40cNzVLRF+xRORDnCnL/QCqGs7zLLpxYHrz2UBXoDBZdAKGu8loj1ur6AbcpKo+EVkFtAXWALcATwN/LiO+63GG+NK0aVM8Hk/RtpycnGLLJrSqWk61927jyG3vcsTPcxEtYEOdUxjLuczdeCwJG8EfQVNTIpCWDDleaJwqDDwumdOaJwMpzg67N1bZcqpsVk7hi/eyCmfW2XqquocIahNB0oFN7uvdQPuAbYmqRXc27QYauvtnB64TkUZAE8q5EVBVJwATADIyMjQzM7Nom8fjIXDZhFalykkVtixwmpo2fMx+UnizoAdTkvrzdVbTok5rfzmnOZjZX6tUOcWQlVP44r2swqlZvAv0VtXPReQFVb02wmtkAfXd1/Xd5UKB03MWbivcPy9g3XDgmQiva6qrgv2wdhp88R/4eQ37UxoxwX8xL+X34TfqQwGE22ltndTGhCfSnr7WB3GNxcANwFtAH+DlgG2rRaQbTp9FfVXNFpHFwJki8hbQBVjvXncMkIbzXI1LVPWtg4jFVGU5O+Grl5z+iJz/kV2vDc8m/ZWXsv/PGdkUARvyakxkwkkWR7sPPZKA10B4fRaqulxE8kRkPrBKVZeIyNOqOgx4FJiEkwTudQ95Hmc01DBggqruxx15JSKtgNGWKGqGwmk2Guz+hptqz+Zs/wKSNR+PrzNTEq9j9m8nEMnD6OzmOWMOXjjJIrBDOfg53GEJHC7rLg9zf2/DeQpf4LZsIOTU56q6BbBhs9VUYXLYkZVL41ShW8EXPJ4wi1Nrfcu+glq84TuDV3xns0lbOI/fioDVJIw5NOE8/MgeemSiJnCSPgEas5ubEucwWD+jWdJvbPU3YbR3MG/5Msk+MEt+ueyRpcZUrEO7O8mYQ3Bgyu8CTpYNXJn0Kf0SviRFfMzzdWSE7xo8/i74SYjovNZpbUzFs2RhKlVgU1M9yeOihAUMSZlNu4StZGttJvvOYrKvD99r84jPbU1NxkSPJQsTVYHJoXC67zb+LQxNms2AxIXUlTzW+Vtyl/cvvOs7jVxSwz63NTUZU3ksWZgKF9wPoUAaeZydP5dBiXPokryJPE3mPV83XvP1YaUegzPYrrjgZNDr+CbM/XYnO7JyLTkYU8ksWZhyBdYOQn1oBy4HPyzoBNnMZYlzuSBxIfUll43+FtzvvYJpvh7spm6JaxUmF+t3MCa+WLIwIYWqHQBsz8pl8hdbi/YLXs7K9VKfvVyauIjLEufSIWELeZrMh/5Teb2gN8u0LcG1CLv/wZj4Z8nCAMWTQ/rnnxSrHYQzcYbgp2vCN1yS6KFfwhJSxcvX/pbc472Kd33dSx32ap3SxlQNlixqkODOZhHI2uct0XQUydPiWrCTgYnzGZg4j5YJv5CttXnbdwZTfJms1dYE1yKsU9qYqsmSRTUWaiRSqIQQ8aNEyeOPCUu5OHEe3RPXAbDQ154n8i/mI3/JeZqsH8KYqs+SRRVTWu2gvI7mSBNCsMJmpoGJ8+mX8CV1ZD9b/U143HsxU3092E6Ton2t9mBM9WPJIs6UNfKorAQQqqO5IrSRbVyUuIALEhfSQnaRQ22+aXQ2L+Z05ePsljRLr2NDWo2pASxZxEBpCaG8kUcVlQDKczi/MyBpMQOSFnICmykggV+bng6n/5m6x59LRnIaGZUSiTEmXliyOEjl1QDCbR4KTggH95ToQ9coYR/9a31Fn4J5nJb4NQkoND8ROo0lqcNAjqh7eIwiM8bEA0sWAcJNAOV94FdG89DBCOxLaJCWTBp5nLx/CZekfkl3VpDo95Jb5wgSTr0DOl4Ch7WJWazGmPhiycJ1YAZU52k6ZX3Ix/IDPxIhO5o7NIbvZsO6N2H9R6D7oE4zaH89dBzIlxuyyezVK9ahG2PijCUL17hZ64sSRTwLrh2U1txVrKO5YD9smgPr7oePP4L92VC7MXS6FDpcBC27Q0Kic4GNnpi+P2NMfLJk4dqRlRvrEIoE3pdw0CONvHlOgpj2AKz/0EkQqenQrj90uBBanwGJyVF+J8aY6sKShat5ehrbKylhRG021fy9ThPT1zNhw8eQn3MgQbS/EFr3hKSUck9jjDHBLFm4bu/btlifRXnK+sAPu3moIuz7DTbMgm/eg02fQUGe08TUYSCccIGTIKwGYYw5RJYsXIUf3uEOh43pjWe7t8G3H8K378GWhaA+qNccTvoznNAfjuoKifZPa4ypOPaJEmDAiS3i885jVfh5jdP3sP5D+GmVs/6w46D7cDj+POeeiITInlVtjDHhsmQRrwr2w5b5sP5jp/9h94+AwJGnQJ/7oO250OS4WEdpjKkhLFnEkz3/g42fOMnhe4/TQZ2UBsf0gp63Q9t+YHdSG2NiwJJFLPl9sGOFkyA2fuK8BqjfAjr+yUkOrXtCclps4zTG1HiWLCrb3l+d+x82fuqMXtq3CyQBWmRA73vguL7QtAOIlH8uY4ypJJYsos3nhW1LnQTx3WzYsRJQqH0YtOkDx54Nx/SG2o1iHakxxpSqUpKFiDwBZADLVXV4wPrmwGQgFRilqrNFpB7wOtAIGK+qk0TkfGAEzo3N76jqvyoj7oOiCr99D9/PhU1zYfM85+5pSXA6p3uNgDZnQrMuNnrJGFNlRD1ZiMhJQB1V7SEiz4nIKaq61N18FzASWA28D8wGrgPeAKYAc0XkTWAV0B3wAx4ReV5Vd0c79rDt3QVb5jmd0pvmQtYPzvoGf3DunG5zpjO9Rlp6LKM0xpiDVhk1i244SQD3d1egMFl0AoarqorIHrdW0Q24SVV9IrIKaKuqawpPJiI+nKQRO/tzYOsXsNkD33/u3AOBQko9p0P6tGFO01Kjo63vwRhTLVRGskgHNrmvdwPtA7YlqqoGbGvo7p8dtA4AEekHfKeqe0JdSESuB64HaNq0KR6Pp2hbTk5OseVIJPjyqZ/9LelZa0jPWkv97PUkqA+/JJFdvy2/txrE7w07safesWhCIuwD1vwI/HhQ14ulQymnmsTKKTxWTuGL97KqjGSRBdR3X9d3lwsFTsRUuK1w/7zA/UXkaOAO4LzSLqSqE4AJABkZGZqZmVm0zePxELhcJm+u0ym9ZSH8sBB+XAK+/U6/Q7Mu0PFmaN2ThKO6kp5Sm3SgdXhnjnsRlVMNZuUUHiun8MV7WVVGslgM3AC8BfQBXg7YtlpEuuH0WdRX1WwRWQycKSJvAV2A9W7z1MvAVaq6N6rRvnaJ0znty3eSwxEd4f+uc5qX/tAVUhtE9fLGGBOPop4sVHW5iOSJyHxglaouEZGnVXUY8CgwCUgD7nUPeR5nNNQwYIKq7heRf+B8eX9RnD6Aq1V1c1QCbtzGmUajVQ9LDsYY46qUobOBw2Xd5WHu721A76Bt2QQ1NanqGGBMlMN0/PHhSrmMMcZUJTbQ3xhjTLksWRhjjCmXJQtjjDHlsmRhjDGmXJYsjDHGlMuShTHGmHJZsjDGGFMuSxbGGGPKJQfm8ateRGQn8EPAqsOAXyvg1A1wJjisCBV1roqMqaLKCeLz/VXUuaycwhOP5VSR54rH/3uHGlNLVW1SYq2q1ogfYFkFnWdCBcZUIeeq4JgqpJzi+P1VVExWTlW0nOK4zOPuMyrwx5qhIvdeHJ6rImOqSPH4/uKxrKycwhOP76+6l1ORatsMFUxElqlqRqzjiHdWTuGxcgqPlVP44r2salLNYkKsA6girJzCY+UUHiun8MV1WdWYmoUxxpiDV5NqFsYYYw6SJQtjjDHlqlbJQkSai0jhk/mSRCRBRCaLyOciMltEDnP3Gywii0TkfRGpX955qxsROdV9//NF5Al33e0iskBEXhORZHedlVNAOYlIa/f1PBF5XUQS3f2snIL+ntz1A0Xkx4DlGl1OUOr/vbNEZI6IeETkZHdd3JVVtUoWwG/AmcAX7nIXIF9VzwBeAga7H4Q3Aj2BV3GeD17T/AD0VtUewOEi0gPopaqn4zwPfYCVExBUTsCRwPmq2hPYDJxj5QSU/Hvq6K6/GPgRwMqpSKiyugE4S1UzVfWreC2rapUsVDVPVX8PWLUdKOzBTwd2AccBa1S1AJgNdK3UIOOAqv6sqnnuYgHQCfC4y4VlYuVUspx2qWpWwLIPK6dQ5eQTkXOBTwG/u77GlxOELKseOGX0kYi8KiJ1iNOyqlbJIoRfgVoi8g0wFJiGkzSy3e27gYaxCS32RKQTzhQDWZQsk/QQ62qkwnJS1a/d5eZAH+ATrJyKBJXTn4HJAZvTsXIqEvB/73egGdAPWIRTi0gnDsuquieLs4HdqtoOuA+4DeeDsbANsL67XOOISCPgGeBaQpdJqHU1TlA5ISK1gFeA69xvfllYORUrJxHpDSxS1fyAXbKwcgJK/E3tBhaoqg+YA7QjTsuquicLwenHAKeW0QDYAHRwOyf7cKB/o8YQkSScb323q+rPwFLgDHdzYZlYOZUsJ3BunHq2sJaBlVOocuoA9BeRj4H2IjIaKyeg1P977dzNXXD6wuKyrJJiHUBFcjuGPgI6A7OAfwLtRMSDkxivVlWviEwE5uNUAQfFKNxY+hNwCvCIiADcDcwTkQXAVuBJKycgdDldBLQUkeHAv1V1upVTyXJS1acARGSBqo50X9f0coLQf1Ofi8g8YB8wKF7/79kd3MYYY8pV3ZuhjDHGVABLFsYYY8plycIYY0y5LFkYY4wplyULY4wx5bJkYUwFEpFMEflBRD5zJ4a7PNYxGVMRLFkYU/FeVdUzcaZwGCwiJ8U6IGMOlSULY6JEVXOBfwHnuzWNeSIyVUQSReROd7I9RGSAiNwqIheKyBJ3uupzYhu9McVZsjAmunYARwDnuVObfwP0Bl4HLnX3+RMwBRgIXKKqvXFmIjAmblSr6T6MiUMtgJ+AF0SkBdAU2Kiqn4pIIxFpDKSr6jZ3DqWR7vxBDwEbYxe2McVZzcKYKBGRVODvwF5gg/sQrqk4E1wCzAT+C7znLv+gqn/BmazwH5UbrTFls5qFMRXvChHpBiTifPDPA2aKSAbOlNSFNYa3gcdxnrUCcJ+IdAXqArdWbsjGlM0mEjQmRkSkIfC8qg6MdSzGlMeaoYyJARE5Hqf56d+xjsWYcFjNwhhjTLmsZmGMMaZcliyMMcaUy5KFMcaYclmyMMYYUy5LFsYYY8r1/+FdDMLuQoU5AAAAAElFTkSuQmCC\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[[Model]]\n", " Model(fkin3)\n", "[[Fit Statistics]]\n", " # fitting method = leastsq\n", " # function evals = 463\n", " # data points = 83\n", " # variables = 2\n", " chi-square = 1.1309e-05\n", " reduced chi-square = 1.3962e-07\n", " Akaike info crit = -1308.12664\n", " Bayesian info crit = -1303.28896\n", "[[Variables]]\n", " b3: -5.08319364 +/- 0.08369288 (1.65%) (init = 0)\n", " c3: 1.7146e+14 +/- 7.8877e+13 (46.00%) (init = 3e+07)\n", "[[Correlations]] (unreported correlations are < 0.100)\n", " C(b3, c3) = -1.000\n" ] } ], "source": [ "a3, c3 =result3.best_values.values()\n", "#,h\n", "#str_h=\"{:.2f}\".format(h)\n", "\n", "fig,ax=plt.subplots()\n", "result3.plot_fit(ax=ax)\n", "ax.grid(True)\n", "plt.xticks(size = 8)\n", "plt.yticks(size = 8)\n", "ax.xaxis.set_minor_locator(MultipleLocator(5))\n", "ax.set_ylabel(\"Fraction of cumulative cases ($I_T$)\",fontsize=8)\n", "ax.set_xlabel(\"Days\",fontsize=8)\n", "plt.title(\"France's 2nd epidemic wave/ unrestricted\",fontsize=10)\n", "#ax.set_title(country_name+ \" h=\"+str_h)\n", "#fig.savefig(country_name+\".pdf\")\n", "plt.savefig(r'C:\\Users\\pol\\Desktop\\France_second_heard_period.eps', format='eps')\n", "plt.show()\n", "print(result3.fit_report())" ] }, { "cell_type": "code", "execution_count": 54, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "The PostScript backend does not support transparency; partially transparent artists will be rendered opaque.\n", "The PostScript backend does not support transparency; partially transparent artists will be rendered opaque.\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[[Model]]\n", " Model(fkin4)\n", "[[Fit Statistics]]\n", " # fitting method = leastsq\n", " # function evals = 17\n", " # data points = 52\n", " # variables = 3\n", " chi-square = 1.2721e-05\n", " reduced chi-square = 2.5961e-07\n", " Akaike info crit = -785.621994\n", " Bayesian info crit = -779.768263\n", "[[Variables]]\n", " a4: 0.00311196 +/- 1.3484e-05 (0.43%) (init = 0.003157142)\n", " c4: 25.5019734 +/- 0.29981622 (1.18%) (init = 27.18)\n", " h4: 16.1055206 +/- 0.54203334 (3.37%) (init = 22.84)\n", "[[Correlations]] (unreported correlations are < 0.100)\n", " C(a4, h4) = 0.982\n", " C(a4, c4) = 0.969\n", " C(c4, h4) = 0.932\n" ] } ], "source": [ "a4, c4,h4 =result4.best_values.values()\n", "#,h\n", "#str_h=\"{:.2f}\".format(h)\n", "\n", "fig,ax=plt.subplots()\n", "result4.plot_fit(ax=ax)\n", "ax.grid(True)\n", "plt.xticks(size = 8)\n", "plt.yticks(size = 8)\n", "ax.xaxis.set_minor_locator(MultipleLocator(5))\n", "ax.set_ylabel(\"Fraction of cumulative cases ($I_T$)\",fontsize=8)\n", "ax.set_xlabel(\"Days\",fontsize=8)\n", "plt.title(\"France's 2nd epidemic wave/restricted\",fontsize=10)\n", "#ax.set_title(country_name+ \" h=\"+str_h)\n", "#fig.savefig(country_name+\".pdf\")\n", "plt.savefig(r'C:\\Users\\pol\\Desktop\\France_2ndfractal_period.eps', format='eps')\n", "plt.show()\n", "print(result4.fit_report())" ] }, { "cell_type": "code", "execution_count": 55, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "The PostScript backend does not support transparency; partially transparent artists will be rendered opaque.\n", "The PostScript backend does not support transparency; partially transparent artists will be rendered opaque.\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[[Model]]\n", " Model(fkin3)\n", "[[Fit Statistics]]\n", " # fitting method = leastsq\n", " # function evals = 463\n", " # data points = 83\n", " # variables = 2\n", " chi-square = 1.1309e-05\n", " reduced chi-square = 1.3962e-07\n", " Akaike info crit = -1308.12664\n", " Bayesian info crit = -1303.28896\n", "[[Variables]]\n", " b3: -5.08319364 +/- 0.08369288 (1.65%) (init = 0)\n", " c3: 1.7146e+14 +/- 7.8877e+13 (46.00%) (init = 3e+07)\n", "[[Correlations]] (unreported correlations are < 0.100)\n", " C(b3, c3) = -1.000\n" ] } ], "source": [ "\n", "#,h\n", "#str_h=\"{:.2f}\".format(h)\n", "\n", "#fig,ax=plt.subplots()\n", "\n", "#,h\n", "#str_h=\"{:.2f}\".format(h)\n", "\n", "\n", "#ax.set_title(country_name+ \" h=\"+str_h)\n", "#fig.savefig(country_name+\".pdf\")\n", "#plt.savefig(r'C:\\Users\\pol\\Desktop\\France_linear.eps', format='eps')\n", "plt.show()\n", "\n", "\n", "#ax.set_title(country_name+ \" h=\"+str_h)\n", "#fig.savefig(country_name+\".pdf\")\n", "#plt.savefig(r'C:\\Users\\pol\\Desktop\\France_linear.eps', format='eps')\n", "\n", "\n", "\n", "a1, c1 =result1.best_values.values()\n", "a2,c2,h2 =result2.best_values.values()\n", "a3, c3 =result3.best_values.values()\n", "a4,c4,h4 =result4.best_values.values()\n", "#,h\n", "#str_h=\"{:.2f}\".format(h)\n", "\n", "fig,ax=plt.subplots(figsize=(12,5))\n", "result1.plot_fit(ax=ax)\n", "result2.plot_fit(ax=ax)\n", "result3.plot_fit(ax=ax)\n", "result4.plot_fit(ax=ax)\n", "ax.grid(True)\n", "plt.xticks(size = 8)\n", "plt.yticks(size = 8)\n", "ax.xaxis.set_minor_locator(MultipleLocator(5))\n", "ax.set_ylabel(\"Fraction of cumulative cases ($I(t)$)\",fontsize=8)\n", "ax.set_xlabel(\"Days\",fontsize=8)\n", "plt.title(\"France's 4 periods up to 10/12/20\",fontsize=10)\n", "#ax.set_title(country_name+ \" h=\"+str_h)\n", "#fig.savefig(country_name+\".pdf\")\n", "plt.savefig(r'C:\\Users\\pol\\Desktop\\France_4periods_10_12_202.eps', format='eps')\n", "plt.show()\n", "print(result3.fit_report())" ] }, { "cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "The PostScript backend does not support transparency; partially transparent artists will be rendered opaque.\n", "The PostScript backend does not support transparency; partially transparent artists will be rendered opaque.\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "[[Model]]\n", " Model(fkin1)\n", "[[Fit Statistics]]\n", " # fitting method = leastsq\n", " # function evals = 740\n", " # data points = 51\n", " # variables = 2\n", " chi-square = 8.6737e-12\n", " reduced chi-square = 1.7701e-13\n", " Akaike info crit = -1495.53028\n", " Bayesian info crit = -1491.66663\n", "[[Variables]]\n", " b1: -11.6946391 +/- 0.09377878 (0.80%) (init = 0)\n", " c1: 1.3682e+24 +/- 5.0038e+23 (36.57%) (init = 400000)\n", "[[Correlations]] (unreported correlations are < 0.100)\n", " C(b1, c1) = -1.000\n" ] } ], "source": [ "#first herd\n", "\n", "a1, c1 =result1.best_values.values()\n", "\n", "fig,ax=plt.subplots()\n", "result1.plot_fit(ax=ax)\n", "ax.grid(True)\n", "plt.xticks(size = 8)\n", "plt.yticks(size = 8)\n", "ax.xaxis.set_minor_locator(MultipleLocator(5))\n", "ax.set_ylabel(\"Fraction of cumulative cases ($I_T$)\",fontsize=8)\n", "ax.set_xlabel(\"Days\",fontsize=8)\n", "plt.title(\"France's 1st epidemic wave/ unrestricted\",fontsize=10)\n", "#ax.set_title(country_name+ \" h=\"+str_h)\n", "#fig.savefig(country_name+\".pdf\")\n", "plt.savefig(r'C:\\Users\\pol\\Desktop\\France_1stheard_period.eps', format='eps')\n", "plt.show()\n", "print(result1.fit_report())" ] } ], "metadata": { "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": "3.7.9" } }, "nbformat": 4, "nbformat_minor": 2 }