# Libraries
import datetime
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from dateutil.parser import parse
from pandas import Series

Data from contralacorrupcion.mx

# Reading the dataset
covid19 = pd.read_csv("actas-defuncion-covid-19-cdmx1.csv",parse_dates=['FECHA'], index_col = "FECHA")
covid19.head()

number_by_date = covid19.drop(['EDAD', 'SEMANA', 'MES', 'RAZON', 'ACTA'], axis=1)
number_by_date

number_by_date['MUERTES'] = 0

number_by_date

number_by_date.drop(number_by_date.head(2).index, inplace=True)

number_by_date = number_by_date.groupby('FECHA').count()
number_by_date.head()

Data from gob.mx

covid19_oficial = pd.read_csv("200521COVID19MEXICO.csv", sep = ",",parse_dates = ["FECHA_DEF"], encoding ='latin1')
covid19_oficial.head(10)

temp = covid19_oficial[['FECHA_DEF', 'ENTIDAD_RES']]

temp = temp.set_index('FECHA_DEF')

temp

from_cdmx = temp.loc[(temp['ENTIDAD_RES'] == 9)] #Number nine corresponds to CDMX as stated in the data dictionary

from_cdmx

from_cdmx.drop(['ENTIDAD_RES'], axis=1, inplace=True, errors='ignore')

C:\Users\User\Anaconda3\lib\site-packages\pandas\core\frame.py:3997: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  errors=errors,

from_cdmx

from_cdmx['MUERTES'] = 0

C:\Users\User\Anaconda3\lib\site-packages\ipykernel_launcher.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  """Entry point for launching an IPython kernel.

from_cdmx = from_cdmx.groupby('FECHA_DEF').count()

from_cdmx.head()

from_cdmx.drop(from_cdmx.tail(1).index, inplace=True) #9999-99-99 date is dropped

from_cdmx = from_cdmx.reset_index()

from_cdmx = from_cdmx.loc[(from_cdmx['FECHA_DEF'] >= '2020-03-26') &  (from_cdmx['FECHA_DEF'] <= '2020-05-12')]

from_cdmx = from_cdmx.set_index('FECHA_DEF')

print(from_cdmx.head(1))
print(from_cdmx.tail(1))

            MUERTES
FECHA_DEF          
2020-03-26        3
            MUERTES
FECHA_DEF          
2020-05-12       60

from_cdmx = from_cdmx.reset_index()
from_cdmx['FECHA_DEF'] = pd.to_datetime(from_cdmx['FECHA_DEF'])

from_cdmx = from_cdmx.set_index('FECHA_DEF')

Visualization

sns.set(rc={'figure.figsize':(14, 7)})

start, end = '2020-03', '2020-05'

fig, ax = plt.subplots()
ax.plot(from_cdmx.loc[start:end],
marker='o', markersize=8, linestyle='-', label='gob.mx')
ax.plot(number_by_date.loc[start:end],
marker='o', markersize=8, linestyle='-', label='contralacorrupcion.mx')
ax.set_xlabel('Date')
ax.set_ylabel('Number of Deaths')
ax.set_title('COVID-19 death comparison in CDMX')
ax.legend()

<matplotlib.legend.Legend at 0x1946b7e5a58>