Skip to content

Instantly share code, notes, and snippets.

@avances123
Last active April 12, 2020 17:54
Show Gist options
  • Save avances123/41111ffe62e8854df54e3cc6e44dd029 to your computer and use it in GitHub Desktop.
Save avances123/41111ffe62e8854df54e3cc6e44dd029 to your computer and use it in GitHub Desktop.
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"%matplotlib inline\n",
"plt.rcParams['figure.figsize'] = [15, 8]\n"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"pais = 'Spain'"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv('/home/fabio/repos/COVID-19/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_deaths_global.csv')\n",
"df = df.loc[df['Country/Region'].isin([pais])]\n",
"df = df[~df['Province/State'].notna()]\n",
"df = df.drop(['Lat','Long','Province/State', 'Country/Region'], axis=1)\n",
"df = df.T.reset_index()\n",
"df.columns = ['fecha', 'muertes']\n",
"df['fecha'] = pd.to_datetime(df['fecha'])\n",
"# empezamos el dia con mas de 10 muertes\n",
"df = df[ df['fecha'] > '2020-04-01']\n",
"X = df.index.to_numpy()\n",
"y = df['muertes'].to_numpy()\n"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"# Meto el cero para ajustar siempre a 0 muertes\n",
"#y = np.insert(y,0,0)\n",
"#X = np.insert(X,0,0)\n",
"#print(y)\n",
"#print(X)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"DatetimeIndex(['2020-04-02', '2020-04-03', '2020-04-04', '2020-04-05',\n",
" '2020-04-06', '2020-04-07', '2020-04-08', '2020-04-09',\n",
" '2020-04-10', '2020-04-11'],\n",
" dtype='datetime64[ns]', freq='D')\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/usr/lib/python3.8/site-packages/scipy/optimize/minpack.py:807: OptimizeWarning: Covariance of the parameters could not be estimated\n",
" warnings.warn('Covariance of the parameters could not be estimated',\n"
]
},
{
"data": {
"text/plain": [
"Text(0.5, 0.01, '@avances123')"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1080x576 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"from scipy import optimize\n",
"from datetime import datetime\n",
"from matplotlib.offsetbox import AnchoredText\n",
"\n",
"# DAtos\n",
"ydata = y\n",
"xdata = X\n",
"periodos = 200\n",
"\n",
"# Funcion a optimizar \n",
"def sigmoid(x, L ,x0, k, b):\n",
" y = L / (1 + np.exp(-k*(x-x0)))+b\n",
" return (y)\n",
"\n",
" \n",
"# Curva de hoy\n",
"p0 = [max(ydata), np.median(xdata),1,min(ydata)] # this is an mandatory initial gues\n",
"popt, pcov = optimize.curve_fit(sigmoid,xdata,ydata,p0,maxfev=15000)\n",
"xfit = np.arange(df.index[0], periodos)\n",
"yfit = sigmoid(xfit, *popt)\n",
"x_axis_fit = pd.date_range(start=df['fecha'].iloc[0], periods=periodos - df.index[0])\n",
"plt.plot(x_axis_fit,yfit,'c-',label='curva ajustada')\n",
"\n",
"# Asintota\n",
"asintota = sigmoid(100000, *popt)\n",
"plt.axhline(asintota, color='g')\n",
"at = AnchoredText(\"Asintota actual: \" + str(round(asintota)),\n",
" prop=dict(size=12), frameon=True,\n",
" loc='upper left',\n",
" )\n",
"at.patch.set_boxstyle(\"round,pad=0.,rounding_size=0.2\")\n",
"ax = plt.gca()\n",
"ax.add_artist(at)\n",
"\n",
"\n",
"# Puntos naranjas\n",
"x_axis_data = pd.date_range(start=df['fecha'].iloc[0], periods=len(df.index))\n",
"plt.plot(x_axis_data,y[0:], 'ro', label='muertes acumuladas')\n",
"print(x_axis_data)\n",
"\n",
"\n",
"# Curvas anteriores\n",
"for dia in range(4, len(X)):\n",
" # DAtos\n",
" ydata_anterior = y[:dia]\n",
" xdata_anterior = X[:dia]\n",
" p0 = [max(ydata_anterior), np.median(xdata_anterior),1,min(ydata_anterior)] # this is an mandatory initial gues\n",
" popt, pcov = optimize.curve_fit(sigmoid,xdata_anterior,ydata_anterior,p0,maxfev=15000)\n",
" xfit = np.arange(df.index[0], periodos)\n",
" yfit = sigmoid(xfit, *popt)\n",
" x_axis_fit = pd.date_range(start=df['fecha'].iloc[0], periods=periodos - df.index[0])\n",
" plt.plot(x_axis_fit,yfit, 'k-', alpha=0.1)\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"# Leyenda y titulo\n",
"plt.xlabel('Fecha')\n",
"plt.ylabel('Numero de muertes')\n",
"plt.legend(loc='lower right')\n",
"plt.title(pais)\n",
"\n",
"plt.figtext(0.5, 0.01, \"Prediccion actual junto con las de anteriores dias en gris\\nFecha de comienzo segun el supuesto pico de la enfermedad\\n\", \n",
" wrap=True, horizontalalignment='center', fontsize=11, fontstyle='italic')\n",
"\n",
"plt.figtext(0.5, 0.01, \"@avances123\", \n",
" wrap=True, horizontalalignment='center', fontsize=9)\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.8.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Display the source blob
Display the rendered blob
Raw
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment