def get_place_comparison_df(place, place2, level='countries', priority='now'):
# df_orig = pd.read_csv(data_dir + 'total_cases_{}_normalized.csv'.format(level))
df_orig = Country.all_countries_as_df()
# to force place order
df_orig_c1 = df_orig[df_orig['Name'] == place]
df_orig_c2 = df_orig[df_orig['Name'] == place2]
len_c1 = len(df_orig_c1[df_orig_c1['TotalDeaths'] > 0])
len_c2 = len(df_orig_c2[df_orig_c2['TotalDeaths'] > 0])
# place has to be the one with smallest number of values for Deaths
if (len_c1 > len_c2):
place, place2 = place2, place
df_orig = pd.concat([df_orig_c2, df_orig_c1])
else:
df_orig = pd.concat([df_orig_c1, df_orig_c2])
df_countries_gap = get_places_gap_df(df_orig, place, place2, priority)
df_total_cases_top = get_total_cases_df_adjusted(df_orig, df_countries_gap,
place, place2)
place_start_cases = (
df_orig.set_index('Name').loc[place, ].set_index('Day')['Total'] >
0).idxmax()
df_total_cases_top = df_total_cases_top[
df_total_cases_top['DayAdj'] >= place_start_cases]
return df_total_cases_top.reset_index()
def get_timeline_list(place, place2, level='countries'):
# df_orig = pd.read_csv(data_dir + 'total_cases_{}_normalized.csv'.format(level))
df_orig = Country.all_countries_as_df()
# to force place order
df_orig_c1 = df_orig[df_orig['Name'] == place]
df_orig_c2 = df_orig[df_orig['Name'] == place2]
len_c1 = len(df_orig_c1[df_orig_c1['TotalDeaths'] > 0])
len_c2 = len(df_orig_c2[df_orig_c2['TotalDeaths'] > 0])
# place has to be the one with smallest number of values for Deaths
if (len_c1 > len_c2):
place, place2 = place2, place
df_orig = pd.concat([df_orig_c2, df_orig_c1])
else:
df_orig = pd.concat([df_orig_c1, df_orig_c2])
df_places_gap = get_places_gap_df(df_orig, place, place2)
df_total_cases_top = get_total_cases_df_adjusted(df_orig, df_places_gap,
place, place2)
places = [place, place2]
df_places_to_show = df_total_cases_top.loc[places, :]
places_to_show = list(df_places_to_show.index.unique())
df_events_owd = pd.DataFrame({
'Date': [],
'Name': [],
'Desc': [],
'FullText': [],
'Highlight': []
})
today = df_places_to_show['Date'].max()
for c in places_to_show:
df_place = df_places_to_show.loc[c, ]
# df_events_owd = df_events_owd.append(pd.DataFrame({'Date':['2019-12-31'], 'Name': [c], 'Desc':['Begining of epidemic'], 'FullText':['First day of data tracking.']}))
df_events_owd = df_events_owd.append(pd.Series(
[(df_place.set_index('Date')['Total'] > 0).idxmax(), c,
'1st Confirmed Case', '', 1],
index=df_events_owd.columns),
ignore_index=True)
df_events_owd = df_events_owd.append(pd.Series(
[(df_place.set_index('Date')['TotalDeaths'] > 0).idxmax(), c,
'1st Death', '', 5],
index=df_events_owd.columns),
ignore_index=True)
msg = """{} is approximately {} days behind {}'s epidemic progression.
This is an estimate based on matching their death growth curves.""".format(
place, abs(df_places_gap.loc[place2, 'gap']), place2)
df_events_owd = df_events_owd.append(pd.Series(
[today, c, 'Today', msg, 1], index=df_events_owd.columns),
ignore_index=True)
df_events_owd['Source'] = 'Our World in Data'
# Adding data from Situation Reports
if level == 'countries':
df_events_sr = pd.read_csv(data_dir +
'situation_reports_countries_highlight.csv')
else:
df_events_sr = pd.DataFrame({'Name': []})
df_events_sr = df_events_sr[df_events_sr['Name'].isin([place, place2])]
df_events = pd.concat([df_events_owd, df_events_sr], sort=True)
# Groups events that happen on the same day
df_events_grouped = pd.DataFrame(
df_events.groupby(['Date',
'Name'])['Desc'].apply(lambda x: "\n".join(x)))
df_events_grouped['FullText'] = df_events.groupby(
['Date', 'Name'])['FullText'].apply(lambda x: "\n".join(x))
df_events_grouped['Source'] = df_events.groupby(
['Date', 'Name'])['Source'].apply(lambda x: "\n".join(x))
df_events_grouped['Highlight'] = df_events.groupby(['Date', 'Name'
])['Highlight'].max()
df_events_adj = pd.merge(df_events_grouped,
df_places_to_show[['Date',
'DayAdj']].reset_index(),
how='left',
on=['Date', 'Name'])
df_events_adj['Highlight'] = df_events_adj['Highlight'].astype(int)
df_places_events = pd.merge(df_events_adj[[
'Name', 'DayAdj', 'Desc', 'FullText', 'Highlight', 'Source'
]],
df_places_to_show.reset_index(),
how='outer',
on=['DayAdj', 'Name'])
df_places_events = df_places_events.set_index('Name')
df_places_events_merged = pd.merge(
df_places_events.loc[place, :].reset_index(),
df_places_events.loc[place2, :].reset_index(),
on='DayAdj',
how='outer',
suffixes=('', '2'))
df_places_events_merged = df_places_events_merged.set_index(
'DayAdj').sort_index()
start_events = min(df_places_events_merged['Desc'].first_valid_index(),
df_places_events_merged['Desc2'].first_valid_index())
end_events = max(
df_places_events_merged['TotalDeaths'].last_valid_index(),
df_places_events_merged['TotalDeaths2'].last_valid_index())
df_places_events_trimed = df_places_events_merged.loc[
start_events:end_events]
df_places_events_trimed = df_places_events_trimed[[
'Name',
'Date',
'Desc',
'FullText',
'Highlight',
'Source',
'Total',
'TotalDeaths',
'GrowthRate',
'GrowthRateDeaths',
'DaysToDouble',
'DaysToDoubleDeaths',
'Date2',
'Name2',
'Desc2',
'FullText2',
'Highlight2',
'Source2',
'Total2',
'TotalDeaths2',
'GrowthRate2',
'GrowthRateDeaths2',
'DaysToDouble2',
'DaysToDoubleDeaths2',
]]
# Fill place name for 1st place
df_places_events_trimed['Name'] = df_places_events_trimed['Name'].ffill()
# Fill place name for 2nd place
df_places_events_trimed['Name2'] = df_places_events_trimed['Name2'].ffill()
# Fill TotalDeath
# df_places_events_trimed['TotalDeaths'] = df_places_events_trimed['TotalDeaths'].ffill()
# df_places_events_trimed['TotalDeaths2'] = df_places_events_trimed['TotalDeaths2'].ffill()
# Fill dates for 1st place
# sr_days = pd.to_datetime(df_places_events_trimed['Date'].ffill())
# sr_adj_days = df_places_events_trimed.groupby(df_places_events_trimed['Date'].notnull().cumsum()).cumcount()
# df_places_events_trimed['Date'] = (sr_days + pd.to_timedelta(sr_adj_days, unit='d')).dt.strftime('%Y-%m-%d')
# Fill dates for 2nd place
# sr_days = pd.to_datetime(df_places_events_trimed['Date2'].ffill())
# sr_adj_days = df_places_events_trimed.groupby(df_places_events_trimed['Date2'].notnull().cumsum()).cumcount()
# df_places_events_trimed['Date2'] = (sr_days + pd.to_timedelta(sr_adj_days, unit='d')).dt.strftime('%Y-%m-%d')
df_places_events_trimed = df_places_events_trimed.fillna('').replace(
{'NaT': ''})
return df_places_events_trimed.to_dict('records')
def get_df_similar_places(place, level='countries'):
# if level == 'cities':
# df_sim = pd.read_csv(data_dir + 'all_{}_similarity.csv'.format(level))
# df_sim = df_sim[df_sim['CityBase'] == place]
# df_sim = df_sim[['Name', 'gap', 'dist', 'Similarity']].set_index('Name')
# return df_sim
# df_orig = pd.read_csv(data_dir + 'total_cases_{}_normalized.csv'.format(level))
df_orig = Country.all_countries_as_df()
df_orig_piv_day = df_orig.pivot(index='Name',
columns='Day',
values='TotalDeaths')
df_orig_piv_day = df_orig_piv_day.fillna(0)
sr_place = df_orig_piv_day.loc[place, ]
place_start = (sr_place > 0).idxmax()
# place_start_cases = (df_orig.set_index('Name').loc[place,].set_index('Day')['Total'] > 0).idxmax()
days_ahead = 14 #if level == 'countries' else 5
df_places_ahead = df_orig_piv_day[
df_orig_piv_day.loc[:, max(place_start - days_ahead, 0)] > 0.0]
df_places_rate_norm = df_orig_piv_day.loc[df_places_ahead.index, :]
# df_places_rate_norm = df_orig_piv_day.loc[['France', 'Italy'], :]
df_places_rate_norm = df_places_rate_norm.append(
df_orig_piv_day.loc[place, ])
# reverse order to keep base place on top
df_places_rate_norm = df_places_rate_norm.iloc[::-1]
sr_place = df_orig_piv_day.loc[place, ]
# place_start = (sr_place > 0).idxmax()
# sr_place_compare = sr_place.loc[place_start:].dropna()
sr_place = df_orig_piv_day.loc[place, ]
place_start = (sr_place > 0).idxmax()
sr_place_compare = sr_place.loc[place_start:].dropna()
df_places_gap = pd.DataFrame({'Name': [], 'gap': [], 'dist': []})
df_places_gap = df_places_gap.append(pd.Series(
[place, 0.0, -1], index=df_places_gap.columns),
ignore_index=True)
for other_place in df_places_rate_norm.index[1:]:
sr_other_place = df_places_rate_norm.loc[other_place, ].fillna(0)
min_dist = np.inf
min_pos = 0
for i in range(0, 1 + len(sr_other_place) - len(sr_place_compare)):
sr_other_place_compare = sr_other_place[i:i +
len(sr_place_compare)]
dist = euclidean(sr_place_compare, sr_other_place_compare)
if (dist < min_dist):
min_dist = dist
min_pos = i
day_place2 = sr_other_place.index[min_pos]
gap = day_place2 - place_start
df_places_gap = df_places_gap.append(pd.Series(
[other_place, gap, min_dist], index=df_places_gap.columns),
ignore_index=True)
df_places_gap = df_places_gap.set_index('Name')
similar_places = df_places_gap.sort_values('dist')
dist_max = euclidean(sr_place_compare, np.zeros(len(sr_place_compare)))
similar_places['Similarity'] = similar_places['dist'].apply(
lambda x: (1.0 - x / dist_max) if x >= 0 else 1)
return similar_places
