def _brief(self):
'''
Return a one-line description of a sim -- used internally and by repr();
see sim.brief() for the user version.
'''
# Try to get a detailed description of the sim...
try:
if self.results_ready:
infections = self.summary['cum_infections']
deaths = self.summary['cum_deaths']
results = f'{infections:n}⚙, {deaths:n}☠'
else:
results = 'not run'
# Set label string
labelstr = f'"{self.label}"' if self.label else '<no label>'
start = sc.date(self['start_day'], as_date=False)
if self['end_day']:
end = sc.date(self['end_day'], as_date=False)
else:
end = sc.date(self['n_days'], start_date=start)
pop_size = self['pop_size']
pop_type = self['pop_type']
string = f'Sim({labelstr}; {start} to {end}; pop: {pop_size:n} {pop_type}; epi: {results})'
# ...but if anything goes wrong, return the default with a warning
except Exception as E:
string = sc.objectid(self)
string += f'Warning, sim appears to be malformed:\n{str(E)}'
return string
def date(self, ind, *args, dateformat=None, as_date=False):
'''
Convert one or more integer days of simulation time to a date/list of dates --
by default returns a string, or returns a datetime Date object if as_date is True.
See also cv.date(), which provides a partly overlapping set of date conversion
features.
Args:
ind (int, list, or array): the index day(s) in simulation time (NB: strings and date objects are accepted, and will be passed unchanged)
args (list): additional day(s)
dateformat (str): the format to return the date in
as_date (bool): whether to return as a datetime date instead of a string
Returns:
dates (str, Date, or list): the date(s) corresponding to the simulation day(s)
**Examples**::
sim = cv.Sim()
sim.date(34) # Returns '2020-04-04'
sim.date([34, 54]) # Returns ['2020-04-04', '2020-04-24']
sim.date([34, '2020-04-24']) # Returns ['2020-04-04', '2020-04-24']
sim.date(34, 54, as_date=True) # Returns [datetime.date(2020, 4, 4), datetime.date(2020, 4, 24)]
'''
# Handle inputs
if not isinstance(ind, list): # If it's a number, string, or dateobj, convert it to a list
ind = sc.promotetolist(ind)
ind.extend(args)
if dateformat is None:
dateformat = '%Y-%m-%d'
# Do the conversion
dates = []
for raw in ind:
if sc.isnumber(raw):
date_obj = sc.date(self['start_day'], as_date=True) + dt.timedelta(days=int(raw))
else:
date_obj = sc.date(raw, as_date=True)
if as_date:
dates.append(date_obj)
else:
dates.append(date_obj.strftime(dateformat))
# Return a string rather than a list if only one provided
if len(ind)==1:
dates = dates[0]
return dates
def load_data(datafile, calculate=True, check_date=True, verbose=True, start_day=None, **kwargs):
'''
Load data for comparing to the model output, either from file or from a dataframe.
Args:
datafile (str or df): if a string, the name of the file to load (either Excel or CSV); if a dataframe, use directly
calculate (bool): whether to calculate cumulative values from daily counts
check_date (bool): whether to check that a 'date' column is present
start_day (date): if the 'date' column is provided as integer number of days, consider them relative to this
kwargs (dict): passed to pd.read_excel()
Returns:
data (dataframe): pandas dataframe of the loaded data
'''
# Load data
if isinstance(datafile, Path): # Convert to a string
datafile = str(datafile)
if isinstance(datafile, str):
df_lower = datafile.lower()
if df_lower.endswith('csv'):
data = pd.read_csv(datafile, **kwargs)
elif df_lower.endswith('xlsx') or df_lower.endswith('xls'):
data = pd.read_excel(datafile, **kwargs)
elif df_lower.endswith('json'):
data = pd.read_json(datafile, **kwargs)
else:
errormsg = f'Currently loading is only supported from .csv, .xls/.xlsx, and .json files, not "{datafile}"'
raise NotImplementedError(errormsg)
elif isinstance(datafile, pd.DataFrame):
data = datafile
else: # pragma: no cover
errormsg = f'Could not interpret data {type(datafile)}: must be a string or a dataframe'
raise TypeError(errormsg)
# Calculate any cumulative columns that are missing
if calculate:
columns = data.columns
for col in columns:
if col.startswith('new'):
cum_col = col.replace('new_', 'cum_')
if cum_col not in columns:
data[cum_col] = np.cumsum(data[col])
if verbose:
print(f' Automatically adding cumulative column {cum_col} from {col}')
# Ensure required columns are present and reset the index
if check_date:
if 'date' not in data.columns:
errormsg = f'Required column "date" not found; columns are {data.columns}'
raise ValueError(errormsg)
else:
if data['date'].dtype == np.int64: # If it's integers, treat it as days from the start day
data['date'] = sc.date(data['date'].values, start_date=start_day)
else: # Otherwise, use Pandas to convert it
data['date'] = pd.to_datetime(data['date']).dt.date
data.set_index('date', inplace=True, drop=False) # Don't drop so sim.data['date'] can still be accessed
return data
def date_formatter(start_day=None, dateformat=None, ax=None):
'''
Create an automatic date formatter based on a number of days and a start day.
Wrapper for Matplotlib's date formatter. Note, start_day is not required if the
axis uses dates already. To be used in conjunction with setting the x-axis
tick label formatter.
Args:
start_day (str/date): the start day, either as a string or date object
dateformat (str): the date format
ax (axes): if supplied, automatically set the x-axis formatter for this axis
**Example**::
formatter = date_formatter(start_day='2020-04-04', dateformat='%Y-%m-%d')
ax.xaxis.set_major_formatter(formatter)
'''
# Set the default -- "Mar-01"
if dateformat is None:
dateformat = '%b-%d'
# Convert to a date object
start_day = sc.date(start_day)
@ticker.FuncFormatter
def mpl_formatter(x, pos):
if sc.isnumber(x):
return (start_day + dt.timedelta(days=x)).strftime(dateformat)
else:
return x.strftime(dateformat)
if ax is not None:
ax.xaxis.set_major_formatter(mpl_formatter)
return mpl_formatter
def date_formatter(start_day=None,
dateformat=None,
interval=None,
start=None,
end=None,
ax=None,
sim=None):
'''
Create an automatic date formatter based on a number of days and a start day.
Wrapper for Matplotlib's date formatter. Note, start_day is not required if the
axis uses dates already. To be used in conjunction with setting the x-axis
tick label formatter.
Args:
start_day (str/date): the start day, either as a string or date object
dateformat (str): the date format (default '%b-%d')
interval (int): if supplied, the interval between ticks (must supply an axis also to take effect)
start (str/int): if supplied, the lower limit of the axis
end (str/int): if supplied, the upper limit of the axis
ax (axes): if supplied, automatically set the x-axis formatter for this axis
sim (Sim): if supplied, get the start day from this
**Examples**::
# Automatically configure the axis with default option
cv.date_formatter(sim=sim, ax=ax)
# Manually configure
ax = pl.subplot(111)
ax.plot(np.arange(60), np.random.random(60))
formatter = cv.date_formatter(start_day='2020-04-04', interval=7, start='2020-05-01', end=50, dateformat='%Y-%m-%d', ax=ax)
ax.xaxis.set_major_formatter(formatter)
'''
# Set the default -- "Mar-01"
if dateformat is None:
dateformat = '%b-%d'
# Convert to a date object
if start_day is None and sim is not None:
start_day = sim['start_day']
if start_day is None:
errormsg = 'If not supplying a start day, you must supply a sim object'
raise ValueError(errormsg)
start_day = sc.date(start_day)
@ticker.FuncFormatter
def mpl_formatter(x, pos):
return (start_day + dt.timedelta(days=int(x))).strftime(dateformat)
# Set initial tick marks (intervals and limits)
if ax is not None:
# Handle limits
xmin, xmax = ax.get_xlim()
if start:
xmin = sc.day(start, start_day=start_day)
if end:
xmax = sc.day(end, start_day=start_day)
ax.set_xlim((xmin, xmax))
# Set the x-axis intervals
if interval:
ax.set_xticks(np.arange(xmin, xmax + 1, interval))
# Set the formatter
ax.xaxis.set_major_formatter(mpl_formatter)
return mpl_formatter
