def generate_chart(year):
data = get_data(year)
barchart = Bar(data,
values=blend(*SCORED_EVENTS, labels_name='event'),
label=cat(columns='Team', sort=False),
stack=cat(columns='event', sort=False),
color=color(columns='event', palette=Spectral9, sort=False),
xgrid=False, ygrid=False, legend='top_right',
plot_width=1000, plot_height=625,
tools="pan,wheel_zoom,box_zoom,reset,resize")
barchart.title = "Formula SAE Michigan " + str(year) + " Total Scores by Place"
barchart._xaxis.axis_label = "Teams"
barchart._xaxis.axis_line_color = None
barchart._xaxis.major_tick_line_color = None
barchart._xaxis.minor_tick_line_color = None
barchart._xaxis.major_label_text_font_size = '0.6em'
barchart._yaxis.axis_label = "Total Score"
barchart._yaxis.axis_line_color = None
barchart._yaxis.major_tick_line_color = None
barchart._yaxis.minor_tick_line_color = None
barchart.outline_line_color = None
barchart.toolbar_location = 'right'
barchart.logo = None
return barchart
def plotAverage(self):
bar = Bar(\
self.__table,
values = blend('average', name = 'average', labels_name = 'average'),\
label = cat(columns = 'country', sort = False),\
stack = cat(columns = 'average'),\
agg = 'mean',\
title = 'Average of CO2 emissions in European Union',\
legend = False,\
tooltips = [('Average', '@average{1.11}' + ' g/km')])
return bar
def plotAverage(self):
bar = Bar(\
self.__table,
values = blend('average', name = 'average', labels_name = 'average'),\
label = cat(columns = 'fuel'),\
stack = cat(columns = 'average'),\
agg = 'mean',\
title = 'Average of CO2 emissions (by fuel type) in ' + self.__title,\
legend = False,\
tooltips = [('Average', '@average{1.11}' + ' g/km')])
return bar
def plot(self):
bar = Bar(\
self.__fuel_table,
values = blend('percentage', name = 'percentage', labels_name = 'percentage'),\
label = cat(columns = 'fuel'),\
stack = cat(columns = 'percentage'),\
agg = 'mean',\
title = self.__title,\
legend = False,\
tooltips = [('Percentage', '@percentage{0.00%}')])
bar._yaxis.formatter = NumeralTickFormatter(format = '0%')
return bar
def plotTotal(self):
bar = Bar(\
self.__table,
values = blend('total', name = 'total', labels_name = 'total'),\
label = cat(columns = 'fuel'),\
stack = cat(columns = 'total'),\
agg = 'mean',\
title = 'Total of CO2 emissions (by fuel type) in ' + self.__title,\
legend = False,\
tooltips = [('Total', '@total{1,1}' + ' g/km')])
bar._yaxis.formatter = NumeralTickFormatter(format = '0,0' + ' g/km')
return bar
def plot(self):
bar = Bar(\
self.__table,
values = blend('registrations', name = 'registrations', labels_name = 'registrations'),\
label = cat(columns = 'country', sort = False),\
stack = cat(columns = 'registrations'),\
agg = 'mean',\
title = 'Total of new registrations in European Union',\
legend = False,\
tooltips = [('Registrations', '@registrations{1,1}')])
bar._yaxis.formatter = NumeralTickFormatter(format='0,0')
return bar
def generate_chart(team):
data = generate_data(team)
selectable_years = list(map(str, data.index.unique()))
# Generate the chart UNFORTUNATELY using the high level plots. Streaming
# a bunch of quads resulted in lots of graphics corruption when switching
# teams. I would rather have the plots work all the time but really slow
# then have the plot show the wrong information.
barchart = Bar(data,
values=blend(*SCORED_EVENTS, labels_name='event'),
label=cat(columns='Year', sort=False),
stack=cat(columns='event', sort=False),
color=color(columns='event', palette=Spectral9, sort=False),
xgrid=False, ygrid=False,
plot_width=1000, plot_height=625,
tools="pan,wheel_zoom,box_zoom,reset,resize")
barchart.title = "Formula SAE Michigan - " + team
barchart._xaxis.axis_label = "Teams"
barchart._xaxis.axis_line_color = None
barchart._xaxis.major_tick_line_color = None
barchart._xaxis.minor_tick_line_color = None
barchart._yaxis.axis_label = "Total Score"
barchart._yaxis.axis_line_color = None
barchart._yaxis.major_tick_line_color = None
barchart._yaxis.minor_tick_line_color = None
barchart.outline_line_color = None
barchart.toolbar_location = 'right'
barchart.logo = None
# Hacky tooltips
for renderer in barchart.select(GlyphRenderer):
if renderer.data_source.data['height'] != [0]:
year = renderer.data_source.data['Year']
place = data['Place'].loc[data['Year'] == year]
score = data['Total Score'].loc[data['Year'] == year]
hover = HoverTool(renderers=[renderer],
tooltips=[("Year", '@Year'),
("Selection", '@event'),
("Event Score", '@height'),
("Total Score", '%.2f' % score.values[0]),
("Overall Place", '%d' % place.values[0])])
barchart.add_tools(hover)
return barchart
def aggregate(transaction_history):
net = dict()
buy = dict()
sell = dict()
interest = dict()
dividend = dict()
historical = dict()
for t in transaction_history:
quarter = "%s-Q%i" % (t.date.year, (t.date.month-1)//3+1)
net[quarter] = float(handleNull(net.get(quarter))) + float(t.cashflow)
if t.kind == Transaction.BUY:
buy[quarter] = float(handleNull(buy.get(quarter))) + float(t.cashflow)
elif t.kind == Transaction.SELL:
sell[quarter] = float(handleNull(sell.get(quarter))) + float(t.cashflow)
elif t.kind == Transaction.INTEREST:
interest[quarter] = float(handleNull(interest.get(quarter))) + float(t.cashflow)
elif t.kind == Transaction.DIVIDEND:
dividend[quarter] = float(handleNull(dividend.get(quarter))) + float(t.cashflow)
elif t.kind == Transaction.HISTORICAL or t.kind == Transaction.CURRENT:
historical[quarter] = float(handleNull(historical.get(quarter))) + float(t.cashflow)
net = addMissingQuarters(net)
buy = addMissingQuarters(buy)
sell = addMissingQuarters(sell)
interest = addMissingQuarters(interest)
dividend = addMissingQuarters(dividend)
historical = addMissingQuarters(historical)
d = {'net': pd.Series(net),
'buy': pd.Series(buy),
'sell': pd.Series(sell),
'interest':pd.Series(interest),
'dividend':pd.Series(dividend),
'historical':pd.Series(historical)}
df = pd.DataFrame(d)
df['label']=df.index
p1 = Bar(df,
values = blend('buy','sell','interest','dividend','historical',name='cashflow', labels_name='cf'),
label=cat(columns='label',sort=False),
stack=cat(columns='cf',sort=False))
p2 = Bar(df,
values = blend('net'),
label='label')
output_file("test.html")
show(vplot(p1, p2))
def box_riga_price_mean_by_district():
form = NoOutliersForm(request.args, csrf_enabled=False)
outliers = not ('submit' in request.args and form.validate() and form.no_outliers.data)
ds = g.ds[g.ds.city == u'Rīga']
stats = _base_stats(ds)
df = odo(ds, pd.DataFrame)
ordered = {v: k for k, v in list(enumerate(stats.sort_values(by='avg_price_m2')['district']))}
df['pos_mean'] = pd.Series(ordered[d] for d in df['district'])
df['price_m2'] = df['price'] / df['area']
df = _fix_unicode_names(df, 'district')
df.sort(['pos_mean'], ascending=[True], inplace=True)
p = BoxPlot(df,
values='price_m2',
label=cat(columns=['district'], sort=False),
title="Price by m2 vs District (ordered by mean price of m2)",
xlabel="District",
ylabel="m2 price (EUR)",
outliers=outliers,
legend=False
)
return render(p, dict(form=form))
def create_figure_overall_ranks(srcDF, season_num):
overallRanksDF = get_overall_ranks_df(season_num, srcDF)
overallRankspDF = overallRanksDF.toPandas()
clr = get_color_list('Viridis', overallRanksDF.count()) # Brewing color hex values for each tuple('team')
figureOverallRanks = Bar(overallRankspDF, values="Wins", color="Team",\
palette=clr, label=cat(columns="Team", sort=False),\
xgrid=True, xlabel="Team", ylabel="Wins",\
title="Overall Standings " + str(season_num),\
legend='top_right', plot_width=950, bar_width=0.6) # generating bar chart
return figureOverallRanks
def plot_stacked_bar_chart(df):
bar = Bar(df,
values=blend('Murder',
'Rape',
'Robbery',
'Aggravated Assault',
'Burglary',
'Larceny Theft',
'Motor Vehicle Theft',
name='Crime',
labels_name='crime'),
label=cat(columns='State', sort=False),
stack=cat(columns='crime', sort=False),
legend='top_right',
title="Crime per state",
width=1000,
height=500,
tooltips=[('crime', '@crime'), ('state', '@State')])
#output_file("stacked_bar.html", title="stacked_bar.py example")
show(bar)
def stack_bokeh(infile):
with open(infile, "r") as file:
data = pd.read_csv(file)
print(data)
p = Bar(data,
values=blend('locus dropout',
'allelic dropout',
'biallelic coverage',
name='samp',
labels_name="samps"),
label=cat(columns='Sample', sort=False),
stack=cat(columns='samps', sort=False),
color=color(columns="samps",
palette=["green", "red", "black"],
sort=False),
legend='top_right',
title="sam")
output_file("stacked_bar.html")
curdoc().add_root(p)
show(p)
def generate_chart(year):
data = get_data(year)
barchart = Bar(data,
values=blend(*SCORED_EVENTS, labels_name='event'),
label=cat(columns='Team', sort=False),
stack=cat(columns='event', sort=False),
color=color(columns='event', palette=Spectral9, sort=False),
xgrid=False,
ygrid=False,
legend='top_right',
plot_width=1000,
plot_height=625,
tools="pan,wheel_zoom,box_zoom,reset,resize")
barchart.title = "Formula SAE Michigan " + str(
year) + " Total Scores by Place"
barchart._xaxis.axis_label = "Teams"
barchart._xaxis.axis_line_color = None
barchart._xaxis.major_tick_line_color = None
barchart._xaxis.minor_tick_line_color = None
barchart._xaxis.major_label_text_font_size = '0.6em'
barchart._yaxis.axis_label = "Total Score"
barchart._yaxis.axis_line_color = None
barchart._yaxis.major_tick_line_color = None
barchart._yaxis.minor_tick_line_color = None
barchart.outline_line_color = None
barchart.toolbar_location = 'right'
barchart.logo = None
return barchart
def get_concentration_bar_chart(df):
"""Creates bar chart visualizing portfolio concentration by position"""
df = df[["Symbol", "Concentration"]].sort_values("Concentration",
ascending=False)
chart = Bar(df,
label=cat(columns='Symbol', sort=False),
values='Concentration',
title='Portfolio Concentration By Position',
ylabel='Concentration (%)',
plot_width=1200,
plot_height=400,
legend=False,
color='#4285f4')
return file_html(chart, INLINE)
def bar(self, hot_users, top=5, width=800, height=300, plot=False):
hot_users = hot_users.sort_values("hotness", ascending=False)
bar = Bar(data=hot_users.head(top),
values='hotness',
label=cat(columns='user', sort=False),
color="blue",
width=width,
height=height,
legend=False)
if plot:
show(bar)
output_file("temp/bar.html")
script, div = components(bar)
return {"script": script, "div": div}
def generate_chart():
data = get_data()
# Bokeh doesn't let me control the order of the grouping! This is
# frustrating since it will be different on every server launch
barchart = Bar(data,
label='year',
values='count',
group=cat(columns='size', ascending=True, sort=True),
color=color(columns='size', palette=Spectral4),
legend='top_left',
xgrid=False,
ygrid=False,
plot_width=800,
plot_height=500,
tools="pan,wheel_zoom,box_zoom,reset,resize")
barchart.title = "Formula SAE Michigan Engine Cylinders"
barchart._xaxis.axis_label = "Year"
barchart._xaxis.axis_line_color = None
barchart._xaxis.major_tick_line_color = None
barchart._xaxis.minor_tick_line_color = None
barchart._yaxis.axis_label = "Frequency"
barchart._yaxis.axis_line_color = None
barchart._yaxis.major_tick_line_color = None
barchart._yaxis.minor_tick_line_color = None
barchart.outline_line_color = None
barchart.toolbar_location = 'right'
barchart.logo = None
hover = HoverTool(tooltips=[("Engine", '@size'), ("# Teams", '@height')])
barchart.add_tools(hover)
return barchart
def plot_opt(name):
with open('{}.txt'.format(name), 'r') as f:
data = f.read()
N = int(re.findall('\[I(\d*) \d*\]\n.* .* .*', data)[0])
B = int(re.findall('\[I\d* (\d*)\]\n.* .* .*', data)[0])
TP = ['with', 'without']
T1 = [float(x) for x in re.findall('\[I\d* \d*\]\n(.*) .* .*', data)]
T2 = [float(x) for x in re.findall('\[I\d* \d*\]\n.* (.*) .*', data)]
T3 = [float(x) for x in re.findall('\[I\d* \d*\]\n.* .* (.*)', data)]
T1 += [
float(x)
for x in re.findall('\[I\d* \d*\]\n.* .* .*\n(.*) .* .*', data)
]
T2 += [
float(x)
for x in re.findall('\[I\d* \d*\]\n.* .* .*\n.* (.*) .*', data)
]
T3 += [
float(x)
for x in re.findall('\[I\d* \d*\]\n.* .* .*\n.* .* (.*)', data)
]
df = pd.DataFrame({
'type': TP,
'computation': T1,
'communication': T2,
'memcpy': T3
})
bar = Bar(df,
label=['type'],
values=blend('computation',
'communication',
'memcpy',
name='times',
labels_name='time'),
xlabel='comparison',
ylabel='total time(s)',
stack=cat(columns=['time'], sort=False),
title='{}'.format(name))
output_file('{}.html'.format(name), title='N={}, B={}'.format(N, B))
save(bar)
def generate_chart():
data = get_data()
# Bokeh doesn't let me control the order of the grouping! This is
# frustrating since it will be different on every server launch
barchart = Bar(data,
label='year',
values='count',
group=cat(columns='size', ascending=True, sort=True),
color=color(columns='size', palette=Spectral4),
legend='top_left',
xgrid=False, ygrid=False,
plot_width=800, plot_height=500,
tools="pan,wheel_zoom,box_zoom,reset,resize")
barchart.title = "Formula SAE Michigan Engine Cylinders"
barchart._xaxis.axis_label = "Year"
barchart._xaxis.axis_line_color = None
barchart._xaxis.major_tick_line_color = None
barchart._xaxis.minor_tick_line_color = None
barchart._yaxis.axis_label = "Frequency"
barchart._yaxis.axis_line_color = None
barchart._yaxis.major_tick_line_color = None
barchart._yaxis.minor_tick_line_color = None
barchart.outline_line_color = None
barchart.toolbar_location = 'right'
barchart.logo = None
hover = HoverTool(tooltips=[("Engine", '@size'),
("# Teams", '@height')])
barchart.add_tools(hover)
return barchart
def _render_bar_riga_any_by_district(key, **kwargs):
ds = g.ds[(g.ds.city == u'Rīga')]
form = FlatsNoNewProjectsForm(request.args, csrf_enabled=False)
if 'submit' in request.args and form.validate() and form.no_new.data:
ds = ds[ds.project != u'Jaun.']
df = _base_stats(ds)
df = _fix_unicode_names(df, 'district')
df.sort([key, 'district'], ascending=[True, False], inplace=True)
p = Bar(df,
values=key,
label=cat(columns=['district'], sort=False),
xlabel="District",
legend=False,
**kwargs)
set_numerical_axis(p)
return render(p, dict(form=form))
def plot_weak(name):
with open('{}.tot'.format(name), 'r') as f:
data = f.read()
Ns = [int(x) for x in re.findall('\[I(\d*) \d*\]\n.* .* .*', data)]
Bs = [int(x) for x in re.findall('\[I\d* (\d*)\]\n.* .* .*', data)]
T1s = [float(x) for x in re.findall('\[I\d* \d*\]\n(.*) .* .*', data)]
T2s = [float(x) for x in re.findall('\[I\d* \d*\]\n.* (.*) .*', data)]
T3s = [float(x) for x in re.findall('\[I\d* \d*\]\n.* .* (.*)', data)]
"""
if 'cuda' not in name:
Ns += Ns
Bs += Bs
T1s += [float(x) for x in re.findall('\[I\d* \d*\]\n.* .* .*\n(.*) .* .*', data)]
T2s += [float(x) for x in re.findall('\[I\d* \d*\]\n.* .* .*\n.* (.*) .*', data)]
T3s += [float(x) for x in re.findall('\[I\d* \d*\]\n.* .* .*\n.* .* (.*)', data)]
"""
df = pd.DataFrame({
'N': Ns,
'B': Bs,
'computation': T1s,
'communication': T2s,
'memcpy': T3s
})
bar = Bar(df,
label=['N', 'B'],
values=blend('computation',
'communication',
'memcpy',
name='times',
labels_name='time'),
xlabel='#node',
ylabel='total time(s)',
stack=cat(columns=['time'], sort=False),
title='Weak Scalability')
output_file('weak_{}.html'.format(name))
save(bar)
def plot_read_dist(rinfo):
df = pd.read_table(rinfo)
data = df[['length', 'mapper', 'count']].groupby(['length',
'mapper']).count()
data = data.apply(lambda s: s / data.sum() * 100, axis=1).reset_index()
p = Bar(data,
plot_width=500,
plot_height=400,
label='length',
values='count',
agg='sum',
stack=cat(columns='mapper', sort=False),
legend='top_right',
color=color(columns='mapper',
palette=["#f98283", "#a4a4a4"],
sort=False),
xlabel='read length (nt)',
ylabel='proportion (%)',
ygrid=False,
tooltips=[('length', '@length'), ('mapper', '@mapper'),
('percent', '@height')])
p.toolbar.logo = None
p.outline_line_color = None
return p
from bokeh.charts import Bar, output_file, show
from bokeh.charts.operations import blend
from bokeh.charts.attributes import cat, color
from bokeh.charts.utils import df_from_json
from bokeh.sampledata.olympics2014 import data
# utilize utility to make it easy to get json/dict data converted to a dataframe
df = df_from_json(data)
# filter by countries with at least one medal and sort by total medals
df = df[df['total'] > 0]
df = df.sort("total", ascending=False)
bar = Bar(df,
values=blend('bronze',
'silver',
'gold',
name='medals',
labels_name='medal'),
label=cat(columns='abbr', sort=False),
stack=cat(columns='medal', sort=False),
color=color(columns='medal',
palette=['SaddleBrown', 'Silver', 'Goldenrod'],
sort=False),
legend='top_right',
title="Medals per Country, Sorted by Total Medals",
tooltips=[('medal', '@medal'), ('country', '@abbr')])
output_file("stacked_bar.html")
show(bar)
from bokeh.charts import Bar, output_file, show
from bokeh.charts.attributes import cat, color
from bokeh.charts.operations import blend
from bokeh.charts.utils import df_from_json
from bokeh.sampledata.olympics2014 import data
# utilize utility to make it easy to get json/dict data converted to a dataframe
df = df_from_json(data)
# filter by countries with at least one medal and sort by total medals
df = df[df['total'] > 0]
df = df.sort_values(by="total", ascending=False)
bar = Bar(df,
values=blend('bronze', 'silver', 'gold', name='medals', labels_name='medal'),
label=cat(columns='abbr', sort=False),
stack=cat(columns='medal', sort=False),
color=color(columns='medal', palette=['SaddleBrown', 'Silver', 'Goldenrod'],
sort=False),
legend='top_right',
title="Medals per Country, Sorted by Total Medals",
tooltips=[('medal', '@medal'), ('country', '@abbr')])
output_file("stacked_bar.html", title="stacked_bar.py example")
show(bar)
from bokeh.charts import Bar, output_file, show
from bokeh.charts.attributes import cat, color
from bokeh.charts.operations import blend
from bokeh.charts.utils import df_from_json
from bokeh.sampledata.olympics2014 import data
# utilize utility to make it easy to get json/dict data converted to a dataframe
df = df_from_json(data)
# filter by countries with at least one medal and sort by total medals
df = df[df["total"] > 0]
df = df.sort("total", ascending=False)
bar = Bar(
df,
values=blend("bronze", "silver", "gold", name="medals", labels_name="medal"),
label=cat(columns="abbr", sort=False),
stack=cat(columns="medal", sort=False),
color=color(columns="medal", palette=["SaddleBrown", "Silver", "Goldenrod"], sort=False),
legend="top_right",
title="Medals per Country, Sorted by Total Medals",
tooltips=[("medal", "@medal"), ("country", "@abbr")],
)
output_file("stacked_bar.html")
show(bar)
def portalDynamicity(df):
def getWeekString(yearweek):
if yearweek is None or len(str(yearweek)) == 0:
return ''
year = "'" + str(yearweek)[:2]
week = int(str(yearweek)[2:])
# d = d - timedelta(d.weekday())
# dd=(week)*7
# dlt = timedelta(days = dd)
# first= d + dlt
# dlt = timedelta(days = (week)*7)
# last= d + dlt + timedelta(days=6)
return 'W' + str(week) + '-' + str(year)
bp = figure(plot_width=600, plot_height=300, y_axis_type="datetime", responsive=True,
tools='') # ,toolbar_location=None
bp.toolbar.logo = None
bp.toolbar_location = None
label_dict={}
for i, s in enumerate(df['snapshot']):
label_dict[i] = getWeekString1(s)
bp.yaxis[0].formatter = NumeralTickFormatter(format="0.0%")
bp.xaxis[0].axis_label = 'Snapshots'
bp.yaxis[0].axis_label = '% of portals'
li = bp.line(df.index.values.tolist(), df['dyratio'], line_width=2, line_color='red', legend="dyratio")
c = bp.circle(df.index.values.tolist(), df['dyratio'], line_width=2, line_color='red', legend="dyratio")
li1 = bp.line(df.index.values.tolist(), df['adddelratio'], line_width=2, line_color='blue', legend="adddelratio")
c = bp.circle(df.index.values.tolist(), df['adddelratio'], line_width=2, line_color='blue', legend="adddelratio")
legend = bp.legend[0].legends
bp.legend[0].legends = []
l = Legend(location=(0, -30))
l.items = legend
bp.add_layout(l, 'right')
labels=["staticRatio","updatedRatio","addRatio","delRatio"]
#for l in labels:
# df[l]= df[l]*100
print brewer.keys()
colors = brewer["Pastel2"][len(labels)]
bar = Bar(df,
values=blend("staticRatio","updatedRatio","addRatio","delRatio", name='medals', labels_name='medal'),
label=cat(columns='snapshot', sort=False),
stack=cat(columns='medal', sort=False),
color=color(columns='medal', palette=colors,
sort=False),
legend='top_right',
bar_width=0.5, responsive=True,
tooltips=[('ratio', '@medal'), ('snapshot', '@snapshot'),('Value of Total',' @height{0.00%}')])
legend = bar.legend[0].legends
bar.legend[0].legends = []
l = Legend(location=(0, -30))
l.items = legend
bar.add_layout(l, 'right')
bar.xaxis[0].axis_label = 'Snapshots'
bar.yaxis[0].axis_label = '% of datasets'
bar.width=600
bar.height=300
bar.xaxis[0].formatter = FuncTickFormatter.from_py_func(getWeekStringTick)
bar.toolbar.logo = None
bar.toolbar_location = None
bar.yaxis[0].formatter = NumeralTickFormatter(format="0.0%")
return {'bar':bar,'lines':bp}
for hashtag in t
]
trump_most_common_hashtags = Counter(trump_all_hashtags).most_common(15)
trump_all_mentions = [
hashtag
for t in tweet_df[tweet_df.handle == 'realDonaldTrump']['user_mentions']
for hashtag in t
]
trump_most_common_mentions = Counter(trump_all_mentions).most_common(15)
#put them on a plot
labels, freq = zip(*trump_most_common_hashtags)
data = {'data': freq, 'x': labels}
bar = Bar(data, values='data',\
label=cat(columns='x', sort=False),\
title="Top Hashtags Used By Trump", \
legend = False,
xlabel="Hashtags", ylabel="Number of Occurance")
labels_2, freq_2 = zip(*trump_most_common_mentions)
data_2 = {'data_2': freq_2, 'x_2': labels_2}
bar_2 = Bar(data_2, values='data_2',\
label=cat(columns='x_2', sort=False),\
title="Top User Mentions By Trump", \
legend = False,
xlabel="User Mentions", ylabel="Number of Occurance")
output_file("trump_top_mentions.png.html")
show(row(bar, bar_2))
for m in range(len(stat)):
data['ACCEPTABLE'].append(stat[m][0])
data['UNACCEPTABLE'].append(stat[m][1] + stat[m][2])
data['Date'].append(unique_dates[m])
data['Total'] = [
data['ACCEPTABLE'][k] + data['UNACCEPTABLE'][k]
for k in range(len(data['Date']))
]
df = pd.DataFrame(data)
bar = Bar(df,
values=blend('ACCEPTABLE',
'UNACCEPTABLE',
name='Hours',
labels_name='medal'),
label=cat(columns='Date', sort=False),
stack=cat(columns='medal', sort=False),
color=color(columns='medal',
palette=['Green', 'Red'],
sort=False),
legend='top_left',
title="Respiration data quality of participant id " +
str(ids[i]),
width=800)
output_file('Respiration_DataQuality_of_' + str(ids[i]) + ".html",
title="RIP_BAR_Plot")
source = ColumnDataSource(data)
columns = [
def output_components(prefix, order, maxaln):
rinfo = "{0}.rinfo".format(prefix)
comp = "{0}.comp".format(prefix)
def plot_read_dist(rinfo):
df = pd.read_table(rinfo)
data = df[['length', 'mapper', 'count']].groupby(['length',
'mapper']).count()
data = data.apply(lambda s: s / data.sum() * 100, axis=1).reset_index()
p = Bar(data,
plot_width=500,
plot_height=400,
label='length',
values='count',
agg='sum',
stack=cat(columns='mapper', sort=False),
legend='top_right',
color=color(columns='mapper',
palette=["#f98283", "#a4a4a4"],
sort=False),
xlabel='read length (nt)',
ylabel='proportion (%)',
ygrid=False,
tooltips=[('length', '@length'), ('mapper', '@mapper'),
('percent', '@height')])
p.toolbar.logo = None
p.outline_line_color = None
return p
rdist = plot_read_dist(rinfo)
df = pd.read_table(comp, index_col=0)
total = df.sum()
total = total * 100 / total.sum()
df = df.apply(lambda s: s * 100 / s.sum(), axis=1)
df = df.reset_index()
#ftypes = df.columns[1:].tolist()
ftypes = order
colors = sns.color_palette("hls", len(ftypes)).as_hex()
bar = Bar(df,
values=blend(*ftypes, name="ftypes", labels_name="ftype"),
x_range=rdist.x_range,
y_range=(0, 100),
label=cat(columns='rlen', sort=False),
stack=cat(columns='ftype', sort=False),
xlabel='read length (nt)',
ylabel='proportion (%)',
legend="top_right",
ygrid=False,
width=500,
height=400,
color=color(columns='ftype', palette=colors, sort=False),
fill_alpha=1,
tooltips=[("length", "@rlen"), ("feature", "@ftype"),
("percent", "@height")])
bar.toolbar.logo = None
bar.outline_line_color = None
start_angles = {}
end_angles = {}
start = 0
for ftype in ftypes:
end = 2 * pi * total[ftype] / 100
start_angles[ftype] = start
end_angles[ftype] = start + end
start += end
colors = dict(zip(ftypes, colors))
df = pd.DataFrame(total).reset_index()
df.columns = ["ftype", "percent"]
df["start"] = df.apply(lambda s: start_angles[s["ftype"]], axis=1)
df["end"] = df.apply(lambda s: end_angles[s["ftype"]], axis=1)
df["color"] = df.apply(lambda s: colors[s["ftype"]], axis=1)
df["x"] = df.apply(lambda s: 1.2 * cos(
(start_angles[s["ftype"]] + end_angles[s["ftype"]]) / 2),
axis=1)
df["y"] = df.apply(lambda s: 1.2 * sin(
(start_angles[s["ftype"]] + end_angles[s["ftype"]]) / 2),
axis=1)
df["text"] = df.apply(lambda s: "{0:.3f}%".format(s["percent"]), axis=1)
source = ColumnDataSource(data=df)
pie = figure(width=400,
height=400,
x_range=(-1.4, 1.4),
y_range=(-1.4, 1.4))
pie.toolbar.logo = None
wr = pie.annular_wedge(x=0,
y=0,
inner_radius=0.5,
outer_radius=1,
start_angle="start",
end_angle="end",
fill_color="color",
line_color="#ffffff",
line_width=0.5,
source=source)
pie.axis.visible = False
pie.grid.grid_line_color = None
pie.outline_line_color = None
hover = HoverTool(tooltips=[("feature", "@ftype"),
("percent", "@percent")],
renderers=[wr])
pie.add_tools(hover)
text_props = {
"source": source,
"angle": 0,
"color": "black",
"text_align": "center",
"text_baseline": "middle",
"text_font_size": "8pt",
"text_font_style": "normal"
}
pie.text(x="x", y="y", text="text", **text_props)
empty = figure(width=400,
height=400,
x_range=(-1.1, 1.1),
y_range=(-1.1, 1.1))
empty.toolbar.logo = None
empty.axis.visible = False
empty.grid.grid_line_color = None
empty.outline_line_color = None
empty.toolbar_location = None
stat = get_stat(prefix, maxaln)
source = ColumnDataSource(data=stat)
columns = [
TableColumn(field="Statistics", title="Statistics", width=200),
TableColumn(field="Number of reads",
title="Number of reads",
formatter=NumberFormatter(format="0,0"),
width=150),
TableColumn(field="Proportion",
title="Proportion",
formatter=NumberFormatter(format="0.000%"),
width=100),
]
data_table = DataTable(source=source,
columns=columns,
width=450,
row_headers=False)
script, div = components(
layout([[data_table, rdist], [pie, bar]], sizing_mode="scale_width"))
return script, div
def stack_bar(data_dict):
"""
Creates a stacked bar graph showing percentages of participation for each member for each day/week (hover doesn't work)
:param data_dict: Dictionary for stacked bar chart input. Maps each chart attribute to a list (with all lists being same length):
{'labels': [Day1, Day2, ..., Day1, Day2, ...],
'members': [Member1, Member1, ..., Member2, Member2, ...],
'turns': [...],
'speak': [...] }
:return: bokeh plot
"""
# Percentage of turns graph
# Removed percentages from hover tool because didn't show correct percentages (y values accumulated)
hover_turns = HoverTool(
tooltips="""
<div>
<div>
<span style="font-size: 17px; font-weight: bold;">@member</span>
</div>
<div>
<span style="font-size: 17px;">@labels</span>
</div>
</div>
"""
)
# turns = Bar(data=data_dict, values='turns', label='week_num', stack='member',
turns = Bar(data=data_dict, values='turns', label=cat(columns='labels', sort=False), stack='member',
title='Member Participation by Speaking Turns', legend='top_right',
plot_width=800,
plot_height=600,
tools=[hover_turns])
# tools=[BoxZoomTool(), WheelZoomTool(), ResetTool()])
label_font_style = 'normal' # 'italic', 'bold'
turns.below[0].axis_label = 'Dates'
turns.below[0].major_label_orientation = 'horizontal'
turns.below[0].axis_label_text_font_style = label_font_style
turns.left[0].axis_label = 'Your Percentage of Participation (Based on Number of Speaking Turns)'
turns.left[0].axis_label_text_font_style = label_font_style
# Percentage of speaking time graph
hover_speak = HoverTool(
tooltips="""
<div>
<div>
<span style="font-size: 17px; font-weight: bold;">@member</span>
</div>
<div>
<span style="font-size: 17px;">@labels</span>
</div>
</div>
"""
)
speak = Bar(data=data_dict, values='speak', label=cat(columns='labels', sort=False), stack='member',
title='Member Participation by Speaking Time', legend='top_right',
plot_width=800,
plot_height=600,
tools=[hover_speak])
# tools=[BoxZoomTool(), WheelZoomTool(), ResetTool()])
speak.below[0].axis_label = 'Dates'
speak.below[0].major_label_orientation = 'horizontal'
speak.below[0].axis_label_text_font_style = label_font_style
speak.left[0].axis_label = 'Your Percentage of Participation (Based on Amount of Speaking Time)'
speak.left[0].axis_label_text_font_style = label_font_style
tab_turns = Panel(child=turns, title='Participation by Speaking Turns')
tab_speak = Panel(child=speak, title='Participation by Speaking Time')
bars = Tabs(tabs=[tab_speak, tab_turns])
return bars
def make_stacked_bar_chart(buckets,
stack,
data,
palette,
width=500,
height=500):
cp = data
if buckets == "day":
cp[buckets] = cp.apply(lambda row: row['pickup_datetime'].weekday(),
axis=1)
elif buckets == "month":
cp[buckets] = cp.apply(lambda row: row['pickup_datetime'].month,
axis=1)
TOOLS = "pan,reset,hover,save"
stacked_bar = Bar(cp,
label=buckets,
values=buckets,
agg='count',
stack=cat(stack, sort=True),
tools=TOOLS,
title="{0} Stacked Bar for {1}".format(
("Daily" if buckets == "day" else "Monthly"),
stack.replace("_", " ").title()),
palette=palette,
plot_width=width,
plot_height=height,
toolbar_location="above",
toolbar_sticky=False,
legend_sort_field='color',
legend_sort_direction='ascending',
responsive=True)
hover = stacked_bar.select_one(HoverTool)
hover.point_policy = "follow_mouse"
hover.tooltips = [("Frequency", "@height"),
("{0}".format(stack.replace("_", " ").title()),
"@{0}".format(stack))]
def day_ticker():
days = [
"Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday",
"Sunday"
]
if abs(int(round(tick)) - tick) < .05:
return days[int(round(tick))]
else:
return ""
def month_ticker():
months = [
"January", "February", "March", "April", "May", "June", "July"
]
if abs(int(round(tick)) - tick) < .05:
return months[int(round(tick))]
else:
return ""
if buckets == "day":
stacked_bar.xaxis.formatter = FuncTickFormatter.from_py_func(
day_ticker)
else:
stacked_bar.xaxis.formatter = FuncTickFormatter.from_py_func(
month_ticker)
stacked_bar.grid.grid_line_color = "SlateGray"
stacked_bar.grid.grid_line_alpha = .5
stacked_bar.grid.minor_grid_line_color = "SlateGray"
stacked_bar.grid.minor_grid_line_alpha = .2
return stacked_bar
# Put data into dataframe broken into min, mean, and max values each for month
ts = Series(vals, index=days[0])
firstmerge = pd.merge(ts.resample('M').min().to_frame(name="min"),
ts.resample('M').mean().to_frame(name="mean"),
left_index=True, right_index=True)
frame = pd.merge(firstmerge, ts.resample('M').max().to_frame(name="max"),
left_index=True, right_index=True)
# You can use DataFrame index for bokeh x values but it doesn't like timestamp
frame['Month'] = frame.index.strftime('%m-%Y')
# Main object to render with stacking
bar = Bar(frame,
values=blend('min', 'mean', 'max',
name='values', labels_name='stats'),
label=cat(columns='Month', sort=False),
stack=cat(columns='values', sort=False),
color=color(columns='values',
palette=['SaddleBrown', 'Silver', 'Goldenrod'],
sort=True),
legend=None,
title="Statistical Values Grouped by Month",
tooltips=[('Value', '@values')]
)
# Legend info (if legend attribute is used it gets ugly with large dataset)
factors = ["min", "mean", "max"]
x = [0] * len(factors)
y = factors
pal = ['SaddleBrown', 'Silver', 'Goldenrod']
p = figure(width=100, toolbar_location=None, y_range=factors)
