In [2]:

import pandas as pd

In [3]:

cases = pd.read_csv('./data/WHO-COVID-19-global-data.csv')

In [4]:

cases

Out[4]:

	Date_reported	Country_code	Country	WHO_region	New_cases	Cumulative_cases	New_deaths	Cumulative_deaths
0	2020-01-03	AF	Afghanistan	EMRO	0	0	0	0
1	2020-01-04	AF	Afghanistan	EMRO	0	0	0	0
2	2020-01-05	AF	Afghanistan	EMRO	0	0	0	0
3	2020-01-06	AF	Afghanistan	EMRO	0	0	0	0
4	2020-01-07	AF	Afghanistan	EMRO	0	0	0	0
...	...	...	...	...	...	...	...	...
164473	2021-11-22	ZW	Zimbabwe	AFRO	9	133647	0	4699
164474	2021-11-23	ZW	Zimbabwe	AFRO	27	133674	0	4699
164475	2021-11-24	ZW	Zimbabwe	AFRO	33	133707	4	4703
164476	2021-11-25	ZW	Zimbabwe	AFRO	40	133747	0	4703
164477	2021-11-26	ZW	Zimbabwe	AFRO	27	133774	1	4704

164478 rows × 8 columns

In [5]:

cases.WHO_region.unique()

Out[5]:

array(['EMRO', 'EURO', 'AFRO', 'WPRO', 'AMRO', 'SEARO', 'Other'],
      dtype=object)

In [6]:

cases.loc[cases.WHO_region == 'AMRO'].Country.unique()

Out[6]:

array(['Anguilla', 'Antigua and Barbuda', 'Argentina', 'Aruba', 'Bahamas',
       'Barbados', 'Belize', 'Bermuda',
       'Bolivia (Plurinational State of)', 'Bonaire', 'Brazil',
       'British Virgin Islands', 'Canada', 'Cayman Islands', 'Chile',
       'Colombia', 'Costa Rica', 'Cuba', 'Curaçao', 'Dominica',
       'Dominican Republic', 'Ecuador', 'El Salvador',
       'Falkland Islands (Malvinas)', 'French Guiana', 'Grenada',
       'Guadeloupe', 'Guatemala', 'Guyana', 'Haiti', 'Honduras',
       'Jamaica', 'Martinique', 'Mexico', 'Montserrat', 'Nicaragua',
       'Panama', 'Paraguay', 'Peru', 'Puerto Rico', 'Saba',
       'Saint Barthélemy', 'Saint Kitts and Nevis', 'Saint Lucia',
       'Saint Martin', 'Saint Pierre and Miquelon',
       'Saint Vincent and the Grenadines', 'Sint Eustatius',
       'Sint Maarten', 'Suriname', 'Trinidad and Tobago',
       'Turks and Caicos Islands', 'United States of America',
       'United States Virgin Islands', 'Uruguay',
       'Venezuela (Bolivarian Republic of)'], dtype=object)

In [7]:

cases.loc[cases.Country == 'United States of America']

Out[7]:

	Date_reported	Country_code	Country	WHO_region	New_cases	Cumulative_cases	New_deaths	Cumulative_deaths
156844	2020-01-03	US	United States of America	AMRO	0	0	0	0
156845	2020-01-04	US	United States of America	AMRO	0	0	0	0
156846	2020-01-05	US	United States of America	AMRO	0	0	0	0
156847	2020-01-06	US	United States of America	AMRO	0	0	0	0
156848	2020-01-07	US	United States of America	AMRO	0	0	0	0
...	...	...	...	...	...	...	...	...
157533	2021-11-22	US	United States of America	AMRO	32331	47405130	269	767185
157534	2021-11-23	US	United States of America	AMRO	32036	47437166	111	767296
157535	2021-11-24	US	United States of America	AMRO	162130	47599296	1269	768565
157536	2021-11-25	US	United States of America	AMRO	102708	47702004	1597	770162
157537	2021-11-26	US	United States of America	AMRO	100455	47802459	1367	771529

694 rows × 8 columns

In [8]:

us = cases.loc[cases.Country == 'United States of America']
us.Date_reported = pd.to_datetime(us.Date_reported, format = '%Y-%m-%d')

/home/alexkeeney/anaconda3/envs/bs/lib/python3.8/site-packages/pandas/core/frame.py:3607: 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
  self._set_item(key, value)

In [9]:

us

Out[9]:

	Date_reported	Country_code	Country	WHO_region	New_cases	Cumulative_cases	New_deaths	Cumulative_deaths
156844	2020-01-03	US	United States of America	AMRO	0	0	0	0
156845	2020-01-04	US	United States of America	AMRO	0	0	0	0
156846	2020-01-05	US	United States of America	AMRO	0	0	0	0
156847	2020-01-06	US	United States of America	AMRO	0	0	0	0
156848	2020-01-07	US	United States of America	AMRO	0	0	0	0
...	...	...	...	...	...	...	...	...
157533	2021-11-22	US	United States of America	AMRO	32331	47405130	269	767185
157534	2021-11-23	US	United States of America	AMRO	32036	47437166	111	767296
157535	2021-11-24	US	United States of America	AMRO	162130	47599296	1269	768565
157536	2021-11-25	US	United States of America	AMRO	102708	47702004	1597	770162
157537	2021-11-26	US	United States of America	AMRO	100455	47802459	1367	771529

694 rows × 8 columns

In [10]:

import altair as alt

In [11]:

alt.Chart(us).mark_line().encode(
    x = 'Date_reported:T', 
    y = 'New_cases'
)

Out[11]:

In [12]:

alt.Chart(us).mark_line().encode(
    x = 'Date_reported:T', 
    y = 'New_deaths'
)

Out[12]:

In [13]:

alt.Chart(us).mark_line().encode(
    x = 'Date_reported:T', 
    y = 'Cumulative_cases'
)

Out[13]:

In [14]:

alt.Chart(us).mark_line().encode(
    x = 'Date_reported:T', 
    y = 'Cumulative_deaths'
)

Out[14]:

In [16]:

alt.Chart(
    us.loc[us.Date_reported > pd.Timestamp('07-15-2021')]
).mark_line().encode(
    x = 'Date_reported:T', 
    y = 'New_cases'
)

Out[16]:

In [17]:

alt.Chart(
    us.loc[us.Date_reported > pd.Timestamp('07-15-2021')]
).mark_line().encode(
    x = 'Date_reported:T', 
    y = 'Cumulative_cases'
)

Out[17]:

In [22]:

us_delta = us.loc[us.Date_reported > pd.Timestamp('07-15-2021')].copy()

In [23]:

us_delta.Cumulative_cases \
- us_delta.Cumulative_cases.min()

Out[23]:

157404           0
157405       40447
157406       82632
157407      113953
157408      142189
            ...   
157533    13592445
157534    13624481
157535    13786611
157536    13889319
157537    13989774
Name: Cumulative_cases, Length: 134, dtype: int64

In [24]:

us_delta['new_cumulative_cases'] = us_delta.Cumulative_cases - us_delta.Cumulative_cases.min()

In [25]:

alt.Chart(
    us_delta
).mark_line().encode(
    x = 'Date_reported:T', 
    y = 'new_cumulative_cases'
)

Out[25]:

In [26]:

us_delta.to_csv('./data/us_july_15-present.csv')

In [29]:

max_cases = us_delta.New_cases.max()
us_delta.loc[us_delta.New_cases == max_cases]

Out[29]:

	Date_reported	Country_code	Country	WHO_region	New_cases	Cumulative_cases	New_deaths	Cumulative_deaths	new_cumulative_cases
157453	2021-09-03	US	United States of America	AMRO	198453	39317981	1994	646132	5505296

In [ ]: