def plt_barchart_grupped(data, param_dict, mode='object', output_path=None):
'''
data: rows = list of dicts(): keywords with neat naming straight to put in charts
param_dict: dictionary with settings as follows:
{'x':'name of column to put on x axis',
'y':'name of column to put in y axis',
'agg':'name of aggregate function: 'sum'/'count' /etc',
'color':'name of name of column to create siloses by/to apply aggr funct',
'tooltips':['list() of strings with column names to put in tooltip cloud']}
mode: 'object'/'save'/'show'/'embed' - either returns plot object / saves to path + returns True / saves to path and shows plot
output_path: string with html ext to save chart to. If None then emmbed is returned
returns: True(saved to file) or emmbed data code
'''
# tooltips=[
# ("Date", "$x"),
# ("version", "@HVAC_version")]
# p = Bar(data, label='Date', values='HVAC_version', agg='count', group='HVAC_version',
# title="Median MPG by YR, grouped by ORIGIN", legend='bottom_right', bar_width=3.0,
# plot_width=1000, plot_height=400, tooltips = tooltips)
# p.legend.background_fill_alpha = 0.8
# output_file("bar.html")
# show(p)
#to_date(data,'%Y-%m-01')
tooltips = create_tooltips(param_dict)
title = "{} of {} by {}, grouped by {}".format(param_dict['agg'],
param_dict['y'].upper(),
param_dict['x'].upper(),
param_dict['color'].upper())
p = Bar(data=data,
label=param_dict['x'],
values=param_dict['y'],
agg=param_dict['agg'],
group=param_dict['color'],
title=title,
legend='bottom_right',
bar_width=3.0,
plot_width=1000,
plot_height=600,
tooltips=tooltips)
#legend_sort_field = param_dict['group'])
p.legend.background_fill_alpha = 0.8
if type(data[0][param_dict['x']]) == str:
x_rng = sort_axis(data, param_dict['x'], False, True)
p.x_range = x_rng
if type(data[0][param_dict['y']]) == str:
y_rng = sort_axis(data, param_dict['y'], False, True)
p.y_range = y_rng
return do_output(p, mode, output_path)
def bar_plot_table(table, **kwargs):
"""Plot a tabular DataFrame with an index and multiple columns representing
categories using a Bokeh bar chart.
In addition to the keyword parameters accepted by bokeh.charts.Bar, this
function accepts the following additional keyword arguments:
number_of_categories: integer
The number of categories ranked by total value to use.
xaxis_formatter: TickFormatter
The formatter to use for x axis values.
yaxis_formatter: TickFormatter
The formatter to use for y axis values.
x_range: Range1d
A range to use for the X-axis.
y_range: Range1d
A range to use for the Y-axis.
"""
if kwargs.has_key('number_of_categories'):
revenue_table = analysis.select_top_n_columns(
table, kwargs['number_of_categories'])
else:
revenue_table = table
revenue_stacked = revenue_table.stack().reset_index()
revenue_stacked.columns = ['year', 'commodity_desc', 'value']
revenue_plot = Bar(
revenue_stacked,
label='year',
stack='commodity_desc',
values='value',
**_remove_custom_keys(kwargs)
)
if kwargs.has_key('x_range'):
revenue_plot.x_range = kwargs['x_range']
if kwargs.has_key('y_range'):
revenue_plot.y_range = kwargs['y_range']
else:
revenue_plot.y_range = Range1d(0, revenue_table.max().sum())
if kwargs.has_key('xaxis_formatter'):
revenue_plot._xaxis.formatter = kwargs['xaxis_formatter']
if kwargs.has_key('yaxis_formatter'):
revenue_plot._yaxis.formatter = kwargs['yaxis_formatter']
return revenue_plot
def bar_plot_table(table, **kwargs):
"""Plot a tabular DataFrame with an index and multiple columns representing
categories using a Bokeh bar chart.
In addition to the keyword parameters accepted by bokeh.charts.Bar, this
function accepts the following additional keyword arguments:
number_of_categories: integer
The number of categories ranked by total value to use.
xaxis_formatter: TickFormatter
The formatter to use for x axis values.
yaxis_formatter: TickFormatter
The formatter to use for y axis values.
x_range: Range1d
A range to use for the X-axis.
y_range: Range1d
A range to use for the Y-axis.
"""
if kwargs.has_key('number_of_categories'):
revenue_table = analysis.select_top_n_columns(
table, kwargs['number_of_categories'])
else:
revenue_table = table
revenue_stacked = revenue_table.stack().reset_index()
revenue_stacked.columns = ['year', 'commodity_desc', 'value']
revenue_plot = Bar(revenue_stacked,
label='year',
stack='commodity_desc',
values='value',
**_remove_custom_keys(kwargs))
if kwargs.has_key('x_range'):
revenue_plot.x_range = kwargs['x_range']
if kwargs.has_key('y_range'):
revenue_plot.y_range = kwargs['y_range']
else:
revenue_plot.y_range = Range1d(0, revenue_table.max().sum())
if kwargs.has_key('xaxis_formatter'):
revenue_plot._xaxis.formatter = kwargs['xaxis_formatter']
if kwargs.has_key('yaxis_formatter'):
revenue_plot._yaxis.formatter = kwargs['yaxis_formatter']
return revenue_plot
def make_bar_plot(labels, values):
data = {'labels': labels, 'values': values}
bar = Bar(data,
values='values',
label=CatAttr(columns=['labels'], sort=False),
legend=False,
agg='mean',
bar_width=0.6,
plot_width=500,
plot_height=350)
bar.y_range = Range1d(0.0, 1.0)
script, div = components(bar)
return script, div
def generate_chart(event):
data = get_data(TIMED_EVENTS[event])
# 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,
values='percentage_dnf',
label='year',
color="FireBrick",
xgrid=False,
ygrid=False,
plot_width=800,
plot_height=500,
tools="pan,wheel_zoom,box_zoom,reset,resize")
barchart.title = "Formula SAE Michigan DNFs - " + event
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 = "Percentage DNF"
barchart._yaxis.axis_line_color = None
barchart._yaxis.major_tick_line_color = None
barchart._yaxis.minor_tick_line_color = None
barchart._yaxis.formatter = NumeralTickFormatter(format="0%")
barchart.y_range = Range1d(0, 1)
barchart.outline_line_color = None
barchart.toolbar_location = 'right'
barchart.logo = None
for renderer in barchart.select(GlyphRenderer):
if renderer.data_source.data['height'] != [0]:
year = renderer.data_source.data['year']
num_dnf = data['dnfs'].loc[data['year'] == year]
num_entries = data['entries'].loc[data['year'] == year]
percent_dnf = data['percentage_dnf'].loc[data['year'] == year]
hover = HoverTool(renderers=[renderer],
tooltips=[
("# DNFs", '%d' % num_dnf.values[0]),
("# Entries", '%d' % num_entries.values[0]),
("% DNF",
'%.2f%%' % (100 * percent_dnf.values[0]))
])
barchart.add_tools(hover)
return barchart
def generate_chart(event):
data = get_data(TIMED_EVENTS[event])
# 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,
values='percentage_dnf',
label='year',
color="FireBrick",
xgrid=False, ygrid=False,
plot_width=800, plot_height=500,
tools="pan,wheel_zoom,box_zoom,reset,resize")
barchart.title = "Formula SAE Michigan DNFs - " + event
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 = "Percentage DNF"
barchart._yaxis.axis_line_color = None
barchart._yaxis.major_tick_line_color = None
barchart._yaxis.minor_tick_line_color = None
barchart._yaxis.formatter = NumeralTickFormatter(format="0%")
barchart.y_range = Range1d(0, 1)
barchart.outline_line_color = None
barchart.toolbar_location = 'right'
barchart.logo = None
for renderer in barchart.select(GlyphRenderer):
if renderer.data_source.data['height'] != [0]:
year = renderer.data_source.data['year']
num_dnf = data['dnfs'].loc[data['year'] == year]
num_entries = data['entries'].loc[data['year'] == year]
percent_dnf = data['percentage_dnf'].loc[data['year'] == year]
hover = HoverTool(renderers=[renderer],
tooltips=[("# DNFs", '%d' % num_dnf.values[0]),
("# Entries", '%d' % num_entries.values[0]),
("% DNF", '%.2f%%' % (100 * percent_dnf.values[0]))])
barchart.add_tools(hover)
return barchart
hover.tooltips = [(c, '@' + c) for c in cols]
hover.tooltips.append(('index', '$index'))
# Finally add/enable the tool
fig.add_tools(hover)
return fig
p2 = scatter_with_hover(test2, 'abs_third_less_adv_simple', 'abs_third_less_adv', marker='circle', fig_width=800, fig_height=800, cols=['bea_code', 'date', 'abs_third_less_adv_simple', 'abs_third_less_adv'], size=20)
p2.title ="Offsetting revisions"
p2.xaxis.axis_label="Absolute (third less adv)"
p2.yaxis.axis_label="Aggregate absolute (third less adv)"
p2.x_range= Range1d(0,test2['abs_third_less_adv_simple'].max()*1.1)
p2.y_range= Range1d(0,test2['abs_third_less_adv'].max()*1.1)
sum_rev = test2['abs_third_less_adv']
simple = test2['abs_third_less_adv_simple']
regression = np.polyfit(simple, sum_rev, 1)
r_x, r_y = zip(*((i, i*regression[0] + regression[1]) for i in range(len(test2['abs_third_less_adv']))))
p2.line(r_x, r_y, color="red", line_width=6)
output_file("regression.html")
show(p2)
# Make the chart
TOOLS = ''
plt2 = Bar(portions_df,
label="Name",
values="Portion",
stack="SaleStatus",
legend="bottom_right",
color=['Green', 'Red'],
xlabel="Listing feature",
ylabel="Portion sold or unsold",
title="Impact of listing features on likelihood of sale",
tools=TOOLS)
plt2.logo = None
plt2.toolbar_location = None
plt2.y_range = Range1d(start=0, end=1)
# Save the plot
output_file("./templates/plot3_new.html")
# show(plt2)
#######################################################
# Look at dependence of sale outcome on seller feedback score
#######################################################
# hist = Histogram(data_sold, values='feedbackScore', color='listingType',
# title="Distribution of feedback scores for sold items", legend='top_left')
#
# # Save the plot
# output_file("./templates/data_exploration.html")
# show(hist)
# Make the chart
TOOLS = ''
plt2 = Bar(portions_df,
label="Name",
values="Portion",
stack = "SaleStatus",
legend="bottom_right",
color=['Green','Red'],
xlabel="Listing feature",
ylabel="Portion sold or unsold",
title="Impact of listing features on likelihood of sale",
tools=TOOLS)
plt2.logo = None
plt2.toolbar_location = None
plt2.y_range = Range1d(start=0,end=1)
# Save the plot
output_file("./templates/plot3_new.html")
# show(plt2)
#######################################################
# Look at dependence of sale outcome on seller feedback score
#######################################################
# hist = Histogram(data_sold, values='feedbackScore', color='listingType',
# title="Distribution of feedback scores for sold items", legend='top_left')
#
# # Save the plot
# output_file("./templates/data_exploration.html")
def make_bar_plot(labels, values):
data = {'labels': labels, 'values': values}
bar = Bar(data, values='values', label=CatAttr(columns=['labels'], sort=False), legend=False, agg='mean', bar_width=0.6, plot_width=500, plot_height=350)
bar.y_range = Range1d(0.0, 1.0)
script, div = components(bar)
return script, div
