
import pandas as pd
import matplotlib.pyplot as plt
import datetime as dt
import matplotlib.dates as mdates


df = pd.read_csv("COVID-19.csv")
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 61900 entries, 0 to 61899
Data columns (total 12 columns):
 #   Column                                                      Non-Null Count  Dtype  
---  ------                                                      --------------  -----  
 0   dateRep                                                     61900 non-null  object 
 1   day                                                         61900 non-null  int64  
 2   month                                                       61900 non-null  int64  
 3   year                                                        61900 non-null  int64  
 4   cases                                                       61900 non-null  int64  
 5   deaths                                                      61900 non-null  int64  
 6   countriesAndTerritories                                     61900 non-null  object 
 7   geoId                                                       61625 non-null  object 
 8   countryterritoryCode                                        61777 non-null  object 
 9   popData2019                                                 61777 non-null  float64
 10  continentExp                                                61900 non-null  object 
 11  Cumulative_number_for_14_days_of_COVID-19_cases_per_100000  59021 non-null  float64
dtypes: float64(2), int64(5), object(5)
memory usage: 5.7+ MB


df.head()


df.isna().sum()

dateRep                                                          0
day                                                              0
month                                                            0
year                                                             0
cases                                                            0
deaths                                                           0
countriesAndTerritories                                          0
geoId                                                          275
countryterritoryCode                                           123
popData2019                                                    123
continentExp                                                     0
Cumulative_number_for_14_days_of_COVID-19_cases_per_100000    2879
dtype: int64


df = df.dropna(axis=0, how='any', thresh=None, subset=None, inplace=False)


df.head()


df.isna().sum()

dateRep                                                       0
day                                                           0
month                                                         0
year                                                          0
cases                                                         0
deaths                                                        0
countriesAndTerritories                                       0
geoId                                                         0
countryterritoryCode                                          0
popData2019                                                   0
continentExp                                                  0
Cumulative_number_for_14_days_of_COVID-19_cases_per_100000    0
dtype: int64


df.loc[:, "case_death_ratio"] = df.cases / df.deaths
df.head()


areas = df.countriesAndTerritories.unique()


def recursive_countries(list, n):
    #base case to start
    if n == 0:
        print("\nThese are all the countries you can choose from:")
    #base case to escape
    if n == len(list):
        print("No more countries to show!")
    #recursive case
    else:
        print("•", list[n])
        return recursive_countries(list, n + 1)


country = ""

while True:
    print("Enter in a country name: (Type areas for list of areas)")
    user_in = input()
    if user_in == 'areas':
        recursive_countries(list=areas, n=0)
    elif user_in in areas:
        country = user_in
    #user input is acceptable
    if country == user_in:
        print("You have chosen", country + ", nice choice! Lets see the data.")
        country_df = df[df.countriesAndTerritories == country]

        #fix the order of the data
        country_df = country_df.iloc[::-1]

        print("This is the head of the data for " + country)
        print(country_df.head())

        country_df.loc[:,"dateRep"] = pd.to_datetime(country_df['dateRep'], format="%m/%d/%Y").dt.strftime("%Y-%m-%d")

        fig, ax = plt.subplots(nrows=2, ncols=1)
        fig.suptitle("Cases and Deaths for Data Date Range for " + country)
        plt.setp(ax[0].xaxis.get_majorticklabels(), rotation=25)

        ax[0].plot(country_df.dateRep, country_df.cases)
        ax[0].set_xlabel("Date since data collection in " + country + "(interval: 20 days)")
        ax[0].set_ylabel("Cases in " + country)

        plt.setp(ax[1].xaxis.get_majorticklabels(), rotation=25)
        ax[1].plot(country_df.dateRep, country_df.deaths)

        ax[1].set_xlabel("Date since data collection in " + country + "(interval: 20 days)")
        ax[1].set_ylabel("Deaths in " + country)

        days = mdates.DayLocator(interval=20)
        ax[0].xaxis.set_major_locator(days)
        ax[1].xaxis.set_major_locator(days)
        fig.tight_layout()

        plt.show(block=True)

    elif country != user_in and user_in != "areas":
        print("Error: Incorrect country spelling. Type areas for list of countries and try again.")

Enter in a country name: (Type areas for list of areas)
 CanadaYou have chosen Canada, nice choice! Lets see the data.
This is the head of the data for Canada
         dateRep  day  month  year  cases  deaths countriesAndTerritories  \
10652  1/13/2020   13      1  2020      0       0                  Canada   
10651  1/14/2020   14      1  2020      0       0                  Canada   
10650  1/15/2020   15      1  2020      0       0                  Canada   
10649  1/16/2020   16      1  2020      0       0                  Canada   
10648  1/17/2020   17      1  2020      0       0                  Canada   

      geoId countryterritoryCode  popData2019 continentExp  \
10652    CA                  CAN   37411038.0      America   
10651    CA                  CAN   37411038.0      America   
10650    CA                  CAN   37411038.0      America   
10649    CA                  CAN   37411038.0      America   
10648    CA                  CAN   37411038.0      America   

       Cumulative_number_for_14_days_of_COVID-19_cases_per_100000  \
10652                                                0.0            
10651                                                0.0            
10650                                                0.0            
10649                                                0.0            
10648                                                0.0            

       case_death_ratio  
10652               NaN  
10651               NaN  
10650               NaN  
10649               NaN  
10648               NaN

Enter in a country name: (Type areas for list of areas)

	dateRep	day	month	year	cases	deaths	countriesAndTerritories	geoId	countryterritoryCode	popData2019	continentExp	Cumulative_number_for_14_days_of_COVID-19_cases_per_100000
0	12/14/2020	14	12	2020	746	6	Afghanistan	AF	AFG	38041757.0	Asia	9.013779
1	12/13/2020	13	12	2020	298	9	Afghanistan	AF	AFG	38041757.0	Asia	7.052776
2	12/12/2020	12	12	2020	113	11	Afghanistan	AF	AFG	38041757.0	Asia	6.868768
3	12/11/2020	11	12	2020	63	10	Afghanistan	AF	AFG	38041757.0	Asia	7.134266
4	12/10/2020	10	12	2020	202	16	Afghanistan	AF	AFG	38041757.0	Asia	6.968658

	dateRep	day	month	year	cases	deaths	countriesAndTerritories	geoId	countryterritoryCode	popData2019	continentExp	Cumulative_number_for_14_days_of_COVID-19_cases_per_100000
0	12/14/2020	14	12	2020	746	6	Afghanistan	AF	AFG	38041757.0	Asia	9.013779
1	12/13/2020	13	12	2020	298	9	Afghanistan	AF	AFG	38041757.0	Asia	7.052776
2	12/12/2020	12	12	2020	113	11	Afghanistan	AF	AFG	38041757.0	Asia	6.868768
3	12/11/2020	11	12	2020	63	10	Afghanistan	AF	AFG	38041757.0	Asia	7.134266
4	12/10/2020	10	12	2020	202	16	Afghanistan	AF	AFG	38041757.0	Asia	6.968658

	dateRep	day	month	year	cases	deaths	countriesAndTerritories	geoId	countryterritoryCode	popData2019	continentExp	Cumulative_number_for_14_days_of_COVID-19_cases_per_100000	case_death_ratio
0	12/14/2020	14	12	2020	746	6	Afghanistan	AF	AFG	38041757.0	Asia	9.013779	124.333333
1	12/13/2020	13	12	2020	298	9	Afghanistan	AF	AFG	38041757.0	Asia	7.052776	33.111111
2	12/12/2020	12	12	2020	113	11	Afghanistan	AF	AFG	38041757.0	Asia	6.868768	10.272727
3	12/11/2020	11	12	2020	63	10	Afghanistan	AF	AFG	38041757.0	Asia	7.134266	6.300000
4	12/10/2020	10	12	2020	202	16	Afghanistan	AF	AFG	38041757.0	Asia	6.968658	12.625000