def dist_compare_grid(
df1,
df2,
columns=None,
max_bar_categories: int = 40,
grid_size: Tuple[int, int] = (900, 900),
):
if columns is None:
columns = [c for c in df1.columns if c in df2.columns]
else:
for c in columns:
if c not in df1.columns:
raise ValueError("%s is not in df1.columns" % str(c))
if c not in df2.columns:
raise ValueError("%s is not in df2.columns" % str(c))
grid_cols = int(np.ceil(np.sqrt(len(columns))))
grid_rows = int(np.ceil(len(columns) / grid_cols))
plots = [
dist_compare_plot(df1[c], df2[c], max_bar_categories).opts(title=c)
for c in columns
]
grid = hv.Layout(plots).opts(shared_axes=False, normalize=False)
grid.cols(grid_cols)
# set sizes
subplot_size = (int(grid_size[0] / grid_cols),
int(grid_size[1] / grid_rows))
grid.opts(
opts.Histogram(width=subplot_size[0], height=subplot_size[1]),
opts.Bars(width=subplot_size[0], height=subplot_size[1]),
)
return grid
def get_pbars(Week):
abbrev_labels = ['GBM', 'LR', 'NB', 'RF']
mean = round(np.mean([week_probs[i][Week] for i in range(4)])*100,2)
res = hv.Bars([(abbrev_labels[i], week_probs[i][Week]) for i in range(4)],
label='Rain Probability: '+ str(mean)+'%').opts(width=500, height=500)
res.opts(xlabel='Models', ylabel='Probability', \
legend_position='top_right').redim(x=hv.Dimension('x', range=(0.0, 1)), \
y=hv.Dimension('y', range=(0.0, 1)))
res = res.opts(opts.Bars(alpha=0.5))
return res
def __init__(self, path, ping_file_path, speed_test_file_path):
self.path = path
self.ping_file_path = ping_file_path
self.speed_test_file_name = speed_test_file_path
# Define default layout of graphs
hv.extension('bokeh')
opts.defaults(
opts.Bars(xrotation=45, tools=['hover']),
opts.BoxWhisker(width=700, xrotation=30, box_fill_color=Palette('Category20')),
opts.Curve(width=700, tools=['hover']),
opts.GridSpace(shared_yaxis=True),
opts.Scatter(width=700, height=500, color=Palette('Category20'), size=dim('growth')+5, tools=['hover'],alpha=0.5, cmap='Set1'),
opts.NdOverlay(legend_position='left'))
if os.path.isdir(os.path.join(self.path, "webpage","figures")) is False:
os.mkdir(os.path.join(self.path, "webpage","figures"))
print("Path 'figures' created successfully")
else:
print("Path 'figures' initialized")
# Load basic configurations
config = configparser.ConfigParser()
try:
config.read('./modules/config_a.ini')
# Get values from configuration file
self.upper_acceptable_ping_bound = float(config['DEFAULT']['upper_acceptable_ping_bound'])
self.upper_ping_issue_bound = float(config['DEFAULT']['upper_ping_issue_bound'])
self.acceptable_network_speed = float(config['DEFAULT']['acceptable_network_speed'])
except:
# In case no config-file is found or another reading error occured
print("Configuration file not found/readable.")
print("Creating a new configuration file.")
# Creating new file with standard values
config['DEFAULT'] = {'upper_acceptable_ping_bound': '10',
'upper_ping_issue_bound': '99999',
'acceptable_network_speed': '16'}
with open('config_a.ini', 'w') as configfile:
config.write(configfile)
print("New configuration file was created. Running on default parameters, please restart for changes.")
#set default values to continue with program
self.upper_acceptable_ping_bound = float(config['DEFAULT']['upper_acceptable_ping_bound'])
self.upper_ping_issue_bound = float(config['DEFAULT']['upper_ping_issue_bound'])
self.acceptable_network_speed = float(config['DEFAULT']['acceptable_network_speed'])
def get_split(complete_df):
# preprocessing
df = complete_df.copy()
df['Leves'] = abs(df['Casos'] - (df['Hospitalizados'] + df['UCI']))
df = df[[
'Comunidad Autónoma', 'Fecha', 'Leves', 'Hospitalizados', 'UCI',
'Fallecidos'
]]
df = pd.melt(df,
id_vars=df.columns[:2],
var_name='Estado',
value_name='Número')
# plot
key_dimensions = ['Fecha', 'Estado']
value_dimensions = ['Número']
# for better date representation
df.Fecha = df.loc[:, 'Fecha'].dt.strftime('%d-%m')
macro = hv.Table(df, key_dimensions, value_dimensions)
bars = macro.to.bars(key_dimensions, value_dimensions,
'Comunidad Autónoma')
# color_cycle = hv.Cycle(['#FEE5AD', '#F7A541', '#F45D4C', '#2E2633'])
color_cycle = hv.Palette('Inferno', reverse=True)
bars.opts(
opts.Bars(color=color_cycle,
show_legend=True,
stacked=True,
width=900,
height=450,
shared_axes=False,
ylabel='',
xlabel='Fecha',
responsive=True,
tools=['hover'],
title='Desglose por estado',
legend_position='top_left',
xrotation=90,
active_tools=['pan', 'wheel_zoom']), )
return bars
def plot_segregation(adata, save=False, filename=None):
"""Plot gabaergic and glutamaterig cell populations"""
import holoviews as hv
from holoviews import opts
import pandas as pd
hv.extension("matplotlib")
df = pd.DataFrame(adata.uns["ligands"]).loc[["GABA", "L-glutamic acid"
]].stack().reset_index()
df.columns = ["ligand", "cluster", "value"]
df = df.sort_values(by="cluster", axis=0)
opts.defaults(
opts.Bars(stacked=True,
xrotation=90,
legend_position="right",
ylabel="Ligand score"))
bars = hv.Bars(df, kdims=["cluster", "ligand"])
if save is True:
hv.save(bars, filename)
return bars
def get_sens_spec(thingers):
abbrev_labels = ['GBM', 'LR', 'NB', 'RF']
tp = [thingers[i][0,0] for i in range(4)]
fp = [thingers[i][0,1] for i in range(4)]
tn = [thingers[i][1,1] for i in range(4)]
fn = [thingers[i][1,0] for i in range(4)]
sens = np.array([tp[i]/(tp[i]+fn[i]) for i in range(4)])
spec = np.array([tn[i]/(tn[i]+fp[i]) for i in range(4)])
hist1 = hv.Bars([(abbrev_labels[i], sens[i]) for i in range(4)], \
label='Sensitivity').opts(width=500, height=500)
hist2 = hv.Bars([(abbrev_labels[i], spec[i]) for i in range(4)], \
label='Specificity').opts(width=500, height=500)
both = (hist1*hist2).opts(xlabel='Models', ylabel='Rates', \
legend_position='top_right').redim(x=hv.Dimension('x', range=(0.0, 1)), \
y=hv.Dimension('y', range=(0.0, 1)))
both = both.opts(opts.Bars(alpha=0.5)).redim(x=hv.Dimension('x', range=(0.0, 1)), \
y=hv.Dimension('y', range=(0.0, 1)))
return sens, spec, both
def config_layout(PlotItem, **kwargs):
"""Configs the layout of the output"""
for key, value in kwargs.items():
try:
getattr(PlotItem, key)(value)
except AttributeError as err:
log.warning(
"Option '{}' for plot not possible with error: {}".format(
key, err))
try:
TOOLTIPS = [("File", "@Name"), ("index", "$index"),
("(x,y)", "($x, $y)")]
hover = HoverTool(tooltips=TOOLTIPS)
PlotItem.opts(
opts.Curve(tools=[hover], toolbar="disable"),
opts.Scatter(tools=[hover], toolbar="disable"),
opts.Histogram(tools=[hover], toolbar="disable"),
opts.Points(tools=[hover], toolbar="disable"),
opts.BoxWhisker(tools=[hover], toolbar="disable"),
opts.Bars(tools=[
HoverTool(tooltips=[('Value of ID:', ' $x'), ('Value:', '$y')])
],
toolbar="disable"),
opts.Violin(tools=[hover], toolbar="disable"))
except AttributeError as err:
log.error(
"Nonetype object encountered while configuring final plots layout. This should not happen! Error: {}"
.format(err))
except ValueError as err:
if "unexpected option 'tools'" in str(err).lower(
) or "unexpected option 'toolbar'" in str(err).lower():
pass
else:
raise
return PlotItem
for i in open(base_dir + 'kyoto-train.en', 'r').readlines()
]
df = pd.DataFrame({"ja": ja, "en": en}).iloc[0:3000, :]
# Japanese PreProcessing
df['ja_preprocessed'] = df['ja'].apply(lambda x: ja_preprocess(x))
# English PreProcessing
df['en_preprocessed'] = df['en'].apply(lambda x: en_preprocess(x))
# English tfidf / bow features
en_bow = bow_features(df['en_preprocessed'],
_max_features=10,
_max_ngrams=1)
en_tfidf = tfidf_features(df['en_preprocessed'],
_max_features=10,
_max_ngrams=1)
# English Ngram Count
en_ngram = ngram_count(df['en_preprocessed'], ngram=1, common_num=30)
# Ngram Count Bar Plot
en_ngram_graph = hv.Bars(en_ngram[::-1]) \
.opts(opts.Bars(title="Ngram Count", color="red", xlabel="Unigrams", ylabel="Count", width=400, height=600, show_grid=True, invert_axes=True))
hv.save(en_ngram_graph, 'en_graph.html')
# Japanese WordCloud
wordCloud(df['ja_preprocessed'],
_font_path='NotoSansCJKjp-Regular.otf',
_output_file='wordCloud_ja.png')
# English WordCloud
wordCloud(df['en_preprocessed'], _output_file='wordCloud_en.png')
def bars_defaults(cls, **kwargs):
"""
Set defaults for holoviews Points class. Use kwargs to overwrite elvis defaults
and set user-specific defaults
"""
return opts.defaults(opts.Bars(**_dict_merge(kwargs, cls.DEFAULT_BARS_OPTS)))
from bokeh.models import HoverTool
from .average_water_thread import AverageWaterThread
from .plot_average_data import PlotAverageData
from .bokeh_plot_manager import BokehPlotManager
import math
from . import average_water_view
from rti_python.Post_Process.Average.AverageWaterColumn import AverageWaterColumn
import pandas as pd
import holoviews as hv
from holoviews import opts, dim, Palette
hv.extension('bokeh')
import panel as pn
pn.extension()
from bokeh.plotting import figure, ColumnDataSource
opts.defaults(
opts.Bars(xrotation=45, tools=['hover']),
opts.BoxWhisker(width=800, xrotation=30, box_fill_color=Palette('Category20')),
opts.Curve(width=600, tools=['hover']),
opts.GridSpace(shared_yaxis=True),
opts.Scatter(width=800, height=400, color=Palette('Category20'), size=dim('growth')+5, tools=['hover']),
opts.NdOverlay(legend_position='left'))
class AverageWaterVM(average_water_view.Ui_AvgWater, QWidget):
increment_ens_sig = pyqtSignal(int)
reset_avg_sig = pyqtSignal()
avg_taken_sig = pyqtSignal()
def __init__(self, parent, rti_config):
average_water_view.Ui_AvgWater.__init__(self)
def seriesToHistogram(data,
fileName='histogram',
graphTitle='Distribution',
sortedAscending=True,
logScale=False,
xlbl='Value',
ylbl='Frequency'):
data2 = data.replace(' ', np.nan)
data2.dropna(inplace=True)
# data2.sort_values(inplace=True)
try:
histData = pd.to_numeric(data2, errors='raise')
numericData = True
except:
histData = data2
numericData = False
if numericData:
# frequencies, edges = np.histogram(gpas, int((highest - lowest) / 0.1), (lowest, highest))
dataList = histData.tolist()
frequencies, edges = np.histogram(dataList,
(int(math.sqrt(len(dataList))) if
(len(dataList) > 30) else
(max(len(dataList) // 3, 1))),
(min(dataList), max(dataList)))
#print('Values: %s, Edges: %s' % (frequencies.shape[0], edges.shape[0]))
if logScale:
frequencies = [
math.log10(freq) if freq > 0 else freq for freq in frequencies
]
ylbl += ' (log 10 scale)'
histo = hv.Histogram((edges, frequencies))
histo.opts(
opts.Histogram(xlabel=xlbl,
ylabel=ylbl,
title=graphTitle,
fontsize={
'title': 40,
'labels': 20,
'xticks': 20,
'yticks': 20
}))
subtitle = 'mean: ' + str(round(sum(dataList) / len(dataList),
3)) + ', n = ' + str(len(dataList))
hv.output(size=250)
graph = hv.render(histo)
graph.add_layout(
Title(text=subtitle,
text_font_style="italic",
text_font_size="30pt"), 'above')
output_file(outDir + fileName + '.html', mode='inline')
save(graph)
show(graph)
# JH: Adds some specific display components when not in a graphical program.
# JH: Consider a separate function for the two cases.
if not edmApplication:
hv.output(size=300)
histo.opts(toolbar=None)
graph = hv.render(histo)
graph.add_layout(
Title(text=subtitle,
text_font_style="italic",
text_font_size="30pt"), 'above')
export_png(graph, filename=outDir + fileName + '.png')
else:
barData = histData.value_counts(dropna=False)
dictList = sorted(zip(barData.index, barData.values),
key=lambda x: x[sortedAscending])
# print(dictList)
bar = hv.Bars(dictList)
bar.opts(opts.Bars(xlabel=xlbl, ylabel=ylbl, title=graphTitle))
subtitle = 'n = ' + str(len(dictList))
hv.output(size=250)
graph = hv.render(bar)
graph.add_layout(
Title(text=subtitle,
text_font_style="italic",
text_font_size="30pt"), 'above')
output_file(outDir + fileName + '.html', mode='inline')
save(graph)
show(graph)
# JH: Consider a bool exportPng=True when calling from outside edmAppliation
if not edmApplication:
hv.output(size=300)
bar.opts(toolbar=None)
graph2 = hv.render(bar)
graph2.add_layout(
Title(text=subtitle,
text_font_style="italic",
text_font_size="30pt"), 'above')
export_png(graph2, filename=outDir + fileName + '.png')
hv.output(size=125)
def plot_countries(df,
col,
round_val=1,
col_tooltip='',
nr_countries=10,
reverse=False):
'''
Plot the overview for the top x (default 10) countries and for the overall countries as well.
Returns a HoloViews plot layout.
Arguments:
df - Dataframe to process, must have the columns 'Country' and 'Year' within.
col - Column in Dataframe where values are evaluated for the plotting process
round_val (optional) - single numeric value to set the y axis limit on max found within col
col_tooltip (optional) - tooltip to be set in the plots for the col values
nr_countries (int) (optional) - number of countries to plot in the top views
reverse (bool) (optional) - if True the bottom countries are listed
'''
max_y = np.ceil(np.nanmax(df[col].values))
max_y = max_y - max_y % round_val + 2 * round_val
if col_tooltip == '':
col_tooltip = '@{' + col.replace(
" ", "_"
) + '}{0,0.000}' # Holoviews auto-replaces spaces with underscores
years_list = list(df['Year'].unique())
if reverse == True:
label = 'Bottom' + str(nr_countries)
plot_df = df[-nr_countries * len(years_list):]
else:
label = 'Top' + str(nr_countries)
plot_df = df[:nr_countries * len(years_list)][::-1]
plot_df_invert = plot_df[::-1].copy()
df_invert = df[::-1].copy()
# Plot settings and parameters
top_hover = HoverTool(tooltips=[('Country',
'@Country'), ('Year',
'@Year'), (col,
col_tooltip)])
country_hover = HoverTool(tooltips=[("Year", "@Year"), (col, col_tooltip)])
year_hover = HoverTool(tooltips=[("Country", "@Country"), (col,
col_tooltip)])
top_plot_arguments = dict(x='Year', y=col, by='Country', tools=[top_hover])
options_shared = dict(height=700,
ylim=(0, max_y),
hooks=[set_bokeh_plot],
active_tools=['wheel_zoom'],
padding=(0.1, 0.1))
options = [
opts.Bars(width=700, show_grid=True, **options_shared),
opts.Scatter(xticks=years_list, marker='o', size=10, **options_shared),
opts.NdOverlay(width=650, xticks=years_list, **options_shared),
opts.Layout(tabs=True)
]
# Create the multiplot
layout = (
plot_df_invert.hvplot(
kind='barh', label=label + 'BarPlot', **top_plot_arguments) +
plot_df.hvplot(
kind='line', label=label + 'LinePlot', **top_plot_arguments) *
plot_df.hvplot(
kind='scatter', label=label + 'LinePlot', **top_plot_arguments) +
df.hvplot(kind='bar',
x='Year',
y=col,
groupby='Country',
label='SingleCountryDropdown',
tools=[country_hover]) +
df_invert.hvplot(kind='barh',
x='Country',
y=col,
groupby='Year',
label='AllCountriesYearSlider',
tools=[year_hover])).opts(options)
return layout
def holoviews_bar_small(self):
"""
holoviews_bar_small :-
Plot the Categorical Cols.
Plot Cat Cols with Max and Min Categories.
"""
try:
import pandas as pd
import holoviews as hv
from holoviews import opts
from bokeh.plotting import figure, show, output_file
from bokeh.embed import components
from bokeh.resources import CDN
from holoviews.core.options import Store
df_for_bokeh = pd.read_pickle("./df_holoviewPlots.pkl")
col_names_fromPSQL = list(df_for_bokeh)
ls_SeriesName = []
ls_SeriesUnqCnts = []
for k in range(len(col_names_fromPSQL)):
series_name = str(col_names_fromPSQL[k])
ls_SeriesName.append(series_name)
unq_values_list = df_for_bokeh[series_name].unique()
ls_SeriesUnqCnts.append(len(unq_values_list))
df_calcUnq = pd.DataFrame({
'ls_SeriesName': ls_SeriesName,
'ls_SeriesUnqCnts': ls_SeriesUnqCnts
})
# ls_SeriesUnqCnts -- is COUNT of SUB_CATEGORIES within the CATEGORY = ls_SeriesName
min_valIndex = df_calcUnq['ls_SeriesUnqCnts'].idxmin()
# min_valIndex -- is INDEX of SERIES with LEAST NUMBER of UNIQUE VALUES
max_valIndex = df_calcUnq['ls_SeriesUnqCnts'].idxmax()
# max_valIndex -- is INDEX of SERIES with MAX NUMBER of UNIQUE VALUES
colA_with_CategoricalValues = df_calcUnq.iloc[min_valIndex][
'ls_SeriesName']
unq_values_listA = df_for_bokeh[
colA_with_CategoricalValues].unique()
#print("----------unq_values_listA-------------",unq_values_listA)
#key_dimensions = [('businesstravel', 'BUSINESS_TRAVEL'), ('dailyrate', 'DAILY_RATE')]
key_dimensions = [('businesstravel', 'BUSINESS_TRAVEL')]
value_dimensions = [('dailyrate', 'DAILY_RATE')]
macro = hv.Table(df_for_bokeh, key_dimensions, value_dimensions)
bars = macro.to.bars(['businesstravel', 'dailyrate'], 'department',
[])
print("---------type(bars)----1----",
type(bars)) ## <class 'holoviews.element.chart.Bars'>
##### Below line Commented for TESTING
bars.opts(
opts.Bars(color=hv.Cycle('Category20'),
show_legend=False,
stacked=True,
tools=['hover'],
width=600,
xrotation=90))
#### ERROR == AttributeError: type object 'opts' has no attribute 'Bars'
# /dc_dash/dc_holoviews.py", line 65, in holoviews_bar_small
# bokeh_renderer = Store.renderers['bokeh']
# KeyError: 'bokeh'
# bokeh_renderer = Store.renderers['bokeh']
# bokeh_plot = bokeh_renderer.get_plot(bars).state
# hv.renderer('bokeh').get_plot(bars).state
print("---------type(bars)----2----",
type(bars)) ## <class 'holoviews.element.chart.Bars'>
#print("---------type(bokeh_plot)-------",type(bokeh_plot))
#bars.toolbar.logo = None
#bars.toolbar_location = None
# FOO_Issue = https://github.com/pyviz/holoviews/issues/1975
js_holo_bar, div_holo_bar = components(bokeh_plot)
cdn_js_holo_bar = CDN.js_files[0] # NOT REQD ??
cdn_css_holo_bar = CDN.css_files[0] # NOT REQD ??
return js_holo_bar, div_holo_bar, cdn_js_holo_bar, cdn_css_holo_bar
except Exception as e:
print(
"--Exception as e:---File=>>-dc_holoviews.py-=--def holoviews_bar_small(self)------",
e)
def run(self):
"""Runs the script"""
from forge.tools import plainPlot # some elusive error in debugger it works while running it does not, but only here
# Do some grouping and sanatizing
groupedcountries = self.data["All"].groupby(
self.data["All"]["Country/Region"]) # Data grouped by country
self.countries = list(groupedcountries.groups)
self.PlotDict["All"] = None
prekeys = self.data["keys"]
for items in self.config["COVID19"]["Countries"]:
countryName = list(items.keys())[0]
inhabitants = list(items.values())[0]
countrycasegrouped = groupedcountries.get_group(
countryName).groupby(
"Name") # Grouped for death, confirmed, recovered
seldata = {
} # a dict containing all data from one country grouped by death, confirmed, recovered
for i, key in enumerate(
prekeys): # The three groups: death, confirmed, recovered
rawdata = countrycasegrouped.get_group(key).sum(
) # Some countries have region information (I combine them to a single one)
seldata[self.keys_basenames[i]] = rawdata[
self.measurements].reindex(self.measurements)
# Now do the anlysis
growth = {}
relgrowth = {}
for key, dat in seldata.items():
growth[key] = dat.diff()
# Calculate the relative growth
gr = growth[key].reindex(self.measurements)
absc = dat.reindex(self.measurements)
relgrowth[key] = gr.shift(
periods=-1, fill_value=np.nan).divide(
absc.replace(0, np.nan)).shift(
periods=1, fill_value=np.nan
) * self.config["COVID19"]["GrowingRateMulti"]
# Replace the data in the data structure
newkeys = [
"Accumulated", "Growth", "RelativeGrowth*{}".format(
self.config["COVID19"]["GrowingRateMulti"])
]
self.data["keys"] = newkeys
self.data["columns"] = self.keys_basenames
units = ["#" for i in self.keys_basenames]
for key, dat in zip(newkeys, [seldata, growth, relgrowth]):
self.data[key] = {
"analysed": False,
"plots": False,
"header": ""
}
self.data[key]["measurements"] = self.keys_basenames
self.data[key]["units"] = units
#self.data[key]["units"][-2] = "%" # The last one is percent
dat["Date"] = pd.to_datetime(pd.Series(self.measurements,
name="Date",
index=pd.Index(
self.measurements)),
infer_datetime_format=True)
dat["Date"] = dat["Date"].dt.to_period('d')
dat["Name"] = pd.Series([key for i in self.measurements],
name="Name",
index=pd.Index(self.measurements))
self.data[key]["measurements"].append("Date")
self.data[key]["units"].append("")
self.data[key]["data"] = pd.DataFrame(dat)
# Start plotting
# All individual
donts = ["Date"]
individual = plot_all_measurements(
self.data,
self.config,
"Date",
"COVID19",
keys=[
"Accumulated", "Growth", "RelativeGrowth*{}".format(
self.config["COVID19"]["GrowingRateMulti"])
],
do_not_plot=donts,
PlotLabel="{}".format(countryName))
if self.Plots:
self.Plots += individual
else:
self.Plots = individual
self.relgrowth_all_countries(countryName)
if self.config["COVID19"]["Normalize"] == True:
self.accumulated_all_countries_normalizes(
countryName, inhabitants)
elif self.config["COVID19"]["Normalize"] == False:
self.accumulated_all_countries(countryName)
# Cases vs growth
if not self.GrowthvsCases:
self.GrowthvsCases = plainPlot(
"Curve",
self.data["Accumulated"]["data"]["confirmed"],
self.data["Growth"]["data"]["confirmed"],
label=countryName,
ylabel="New Cases",
**self.config['COVID19']['General'],
**self.config['COVID19']['GvC']["PlotOptions"])
else:
self.GrowthvsCases *= plainPlot(
"Curve",
self.data["Accumulated"]["data"]["confirmed"],
self.data["Growth"]["data"]["confirmed"],
label=countryName,
ylabel="New Cases",
**self.config['COVID19']['General'],
**self.config['COVID19']['GvC']["PlotOptions"])
# Death vs growth
if not self.DeathvsCases:
self.DeathvsCases = plainPlot(
"Curve",
self.data["Accumulated"]["data"]["confirmed"],
self.data["Accumulated"]["data"]["deaths"],
label=countryName,
ylabel="Total Deaths",
**self.config['COVID19']['General'],
**self.config['COVID19']['GvC']["PlotOptions"])
else:
self.DeathvsCases *= plainPlot(
"Curve",
self.data["Accumulated"]["data"]["confirmed"],
self.data["Accumulated"]["data"]["deaths"],
label=countryName,
ylabel="Total Deaths",
**self.config['COVID19']['General'],
**self.config['COVID19']['GvC']["PlotOptions"])
# Relabel the plots
self.GrowthvsCases = relabelPlot(
self.GrowthvsCases.opts(xlim=(1, None), ylim=(1, None)),
"New Cases vs. Total Cases")
self.DeathvsCases = relabelPlot(
self.DeathvsCases.opts(xlim=(1, None), ylim=(1, None)),
"Total Death vs. Total Cases")
if not self.config["COVID19"]["Normalize"]:
self.cases = relabelPlot(self.cases,
"Confirmed Cases not normalized")
self.recovered = relabelPlot(self.recovered,
"Recovered Cases not normalized")
self.deaths = relabelPlot(self.deaths, "Deaths not normalized")
self.casesrelgrowth = relabelPlot(self.casesrelgrowth,
"Confirmed Cases relative growth")
self.recoveredrelgrowth = relabelPlot(
self.recoveredrelgrowth, "Recovered Cases relative growth")
self.deathsrelgrowth = relabelPlot(self.deathsrelgrowth,
"Deaths relative growth")
if self.config["COVID19"]["Normalize"]:
self.casesNorm = relabelPlot(self.casesNorm,
"Confirmed Cases normalized")
self.recoveredNorm = relabelPlot(self.recoveredNorm,
"Recovered Cases normalized")
self.deathsNorm = relabelPlot(self.deathsNorm, "Deaths normalized")
# Define Plotting order
self.plottingOrder = [
self.GrowthvsCases, self.DeathvsCases, self.casesNorm,
self.recoveredNorm, self.deathsNorm, self.casesrelgrowth,
self.recoveredrelgrowth, self.deathsrelgrowth, self.cases,
self.recovered, self.deaths, self.Plots
]
for plot in self.plottingOrder:
if plot:
if self.PlotDict["All"]:
self.PlotDict["All"] += plot
else:
self.PlotDict["All"] = plot
# Reconfig the plots to be sure
self.PlotDict["All"].opts(opts.Bars(stacked=True))
self.PlotDict["All"] = config_layout(
self.PlotDict["All"],
**self.config.get(self.analysisname, {}).get("Layout", {}))
return self.PlotDict
def plot_sankey(G, notebook=False):
"""
render an interactive sankey plot of the graph.
If notebook is False, starts an bokeh app in a browser window,
if True, renders the plot directly in the cell.
"""
import scConnect as cn
import holoviews as hv
from holoviews import opts, dim
import networkx as nx
import pandas as pd
import numpy as np
# instantiate the bokeh renderer
renderer = hv.renderer('bokeh')
hv.extension("bokeh")
hv.output(size=100)
# set visuals
opts.defaults(
opts.Sankey(cmap='Category20',
edge_cmap='Category20',
edge_color=dim("receptorfamily"),
labels='cluster',
node_color=dim('cluster'),
inspection_policy="edges",
selection_policy="edges",
colorbar=True,
toolbar="above"),
opts.Bars(invert_axes=False, xrotation=70, toolbar="above"))
# Create values to be used for filtering of the graph
edges = nx.to_pandas_edgelist(G)
percentiles = [0, 20, 40, 60, 80, 90, 95, 99]
th_values = np.percentile(edges["weighted_score"], percentiles)
nodes_list = list(G.nodes())
node = hv.Dimension(("node", "Focus cluster"), default=nodes_list[0])
th = hv.Dimension(('th', 'Weighted score threshold'), default=th_values[0])
# Filter data on node and threshold, and return a sankey element
def sankey_graph(node, th):
# Find all interactions where node is target or source node
G_s = nx.MultiDiGraph()
for n, nbrs in G.adj.items():
for nbr, edict in nbrs.items():
if n == node:
for e, d in edict.items():
# append dash after the target node
G_s.add_edge(n, nbr + "_", **d)
if nbr == node:
for e, d in edict.items():
# append dash before the source node
G_s.add_edge("_" + n, nbr, **d)
# create the dataset used to build the sankey graph.
# Sort values on weight to get ordered representation on plot.
edges = nx.to_pandas_edgelist(G_s)
links = hv.Dataset(edges, ["source", "target"],
["weighted_score", "interaction", "receptorfamily"
]).sort("weighted_score")
nodes = hv.Dataset(list(G_s.nodes), 'cluster')
sankey = hv.Sankey((links, nodes)).select(weighted_score=(th, None))
# calculate bars
ligands = hv.Dataset(edges, ["ligand", "source"], ["score"]).select(
source=node).aggregate(function=np.mean).sort("score",
reverse=True)
receptors = hv.Dataset(edges, ["receptor", "target"],
["score"]).select(target=node).aggregate(
function=np.mean).sort("score",
reverse=True)
bars = (hv.Bars(ligands, "ligand") +
hv.Bars(receptors, "receptor")).cols(2)
# calculate table
ligands = hv.Dataset((G.node[node]["ligands"]), "ligand",
"score").sort("score", reverse=True)
receptors = hv.Dataset((G.node[node]["receptors"]), "receptor",
"score").sort("score", reverse=True)
table = hv.Layout(hv.Table(ligands) + hv.Table(receptors)).cols(2)
return (bars + table + sankey).cols(2)
sankey = hv.DynamicMap(sankey_graph,
kdims=[node, th]).redim.values(node=nodes_list,
th=th_values)
layout = sankey
# Run the server if not in notebook
if notebook == False:
server = renderer.app(layout, show=True, new_window=True)
if notebook == True:
return layout