import matplotlib.pyplot as plt
import pandas as pd

"""
#===========================================================================================================
# Copyright (c) 2006-2020 Paseman & Associates (www.paseman.com).  All rights reserved.
#===========================================================================================================
Written in Python 3

source activate base
idle3 &


Sources:
https://www.arcgis.com/apps/opsdashboard/index.html#/bda7594740fd40299423467b48e9ecf6
https://www.worldometers.info/coronavirus/
# https://www.kaggle.com/datasets
'/kaggle/input/novel-corona-virus-2019-dataset/2019_nCoV_data.csv'
# https://stackoverflow.com/questions/43121584/matplotlib-scatterplot-x-axis-labels
  #plt.semilogy(df2[[columnLabel]],label=region)

Excel format of the COVID-19 data from Johns Hopkins University (https://lnkd.in/e-eBqNJ).
https://lnkd.in/er34ByJ <-covid-19-data.xlsx

April 15th peak
http://www.healthdata.org/
"""

#===========================================================================================================
def extractTimeSeries(targetRow,columnLabel,title,path="20200402/"):
  dateIndex=4
  dates = targetRow.columns[dateIndex:]
  data = targetRow[dates].values[0]
  df = pd.DataFrame(data,index=dates,columns=[columnLabel])
  # https://pandas.pydata.org/pandas-docs/version/0.24.2/reference/api/pandas.Series.plot.html
  t= title+" "+columnLabel
  ax=df[[columnLabel]].plot(title=t,logy=True)
  ax.set_ylabel("People")
  ax.set_xlabel("Date")
  ax.get_figure().savefig(path+t)

  df["velocity"] = df[columnLabel] - df[columnLabel].shift(1)
  df["acceleration"] = df["velocity"] - df["velocity"].shift(1)
  ax=df[["velocity","acceleration"]].plot(title=t,logy=True)
  ax.set_ylabel("People")
  ax.set_xlabel("Date")
  ax.get_figure().savefig(path+t+"velacc")
  print(t,"\n",df)

  
#===========================================================================================================
# https://www.interviewqs.com/ddi_code_snippets/rows_cols_python
predicate1 = lambda df,region: df.loc[(df[(u'Country/Region')] == region)]
predicate2 = lambda df,region,state: df.loc[(df[(u'Country/Region')] == region)  & (df[(u'Province/State')] == state)]
def processJHU():
  # https://coronavirus.jhu.edu/map.html
  # https://data.humdata.org/dataset/novel-coronavirus-2019-ncov-cases
  for columnLabel,src in [
    ("deaths","https://data.humdata.org/hxlproxy/api/data-preview.csv?url=https%3A%2F%2Fraw.githubusercontent.com%2FCSSEGISandData%2FCOVID-19%2Fmaster%2Fcsse_covid_19_data%2Fcsse_covid_19_time_series%2Ftime_series_covid19_deaths_global.csv&filename=time_series_covid19_deaths_global.csv"),
    ("recovered","https://data.humdata.org/hxlproxy/api/data-preview.csv?url=https%3A%2F%2Fraw.githubusercontent.com%2FCSSEGISandData%2FCOVID-19%2Fmaster%2Fcsse_covid_19_data%2Fcsse_covid_19_time_series%2Ftime_series_covid19_recovered_global.csv&filename=time_series_covid19_recovered_global.csv"),
    ("confirmed","https://data.humdata.org/hxlproxy/api/data-preview.csv?url=https%3A%2F%2Fraw.githubusercontent.com%2FCSSEGISandData%2FCOVID-19%2Fmaster%2Fcsse_covid_19_data%2Fcsse_covid_19_time_series%2Ftime_series_covid19_confirmed_global.csv&filename=time_series_covid19_confirmed_global.csv")]:
    #src= "time_series_covid19_confirmed_global.csv"
    #src= "time_series_covid19_deaths_global.csv"; columnLabel="deaths"
    df = pd.read_csv(src)
    extractTimeSeries(predicate1(df,'US'),columnLabel,title='US')
    extractTimeSeries(predicate1(df,'Italy'),columnLabel,title='Italy')
    extractTimeSeries(predicate2(df,'China','Hubei'),columnLabel,title='China Hubei')
  plt.show()


#===========================================================================================================
if __name__ == '__main__':
  processJHU()