def test_pieplot():
"Test Pieplot"
p_pie = df_pie = pd.read_csv(
os.path.join(test_sets_directory, "Bundestagswahl", "Bundestagswahl.csv")
)
p_pie = df_pie.plot_bokeh.pie(
x="Partei",
y="2017",
colormap=["blue", "red", "yellow", "green", "purple", "orange", "grey"],
title="Results of German Bundestag Election 2017",
show_figure=False,
)
p_pie_multiple = df_pie.plot_bokeh(
kind="pie",
x="Partei",
colormap=["blue", "red", "yellow", "green", "purple", "orange", "grey"],
title="Results of German Bundestag Elections [2002-2017]",
line_color="grey",
show_figure=False,
)
layout = pandas_bokeh.plot_grid(
[[p_pie, p_pie_multiple]], plot_width=450, plot_height=300, show_plot=False
)
pandas_bokeh.output_file(os.path.join(directory, "Plots", "Pieplot.html"))
pandas_bokeh.save(layout)
def test_mapplot(df_mapplot):
"Mapplot test"
kwargs = dict(
x="longitude",
y="latitude",
hovertool_string="""<h2> @{name} </h2>
<h3> Population: @{pop_max} </h3>""",
tile_provider="STAMEN_TERRAIN_RETINA",
size="size",
figsize=(900, 600),
title="World cities with more than 1.000.000 inhabitants",
show_figure=False,
)
p_map = df_mapplot.plot_bokeh(kind="map", **kwargs)
p_map_accessor = df_mapplot.plot_bokeh.map(**kwargs)
p_map_pandas_backend = df_mapplot.plot(kind="map", **kwargs)
p_map_accessor_pandas_backend = df_mapplot.plot.map(**kwargs)
layout = pandas_bokeh.plot_grid([[p_map, p_map_accessor]],
plot_width=450,
plot_height=300,
show_plot=False)
pandas_bokeh.output_file(os.path.join(DIRECTORY, "Plots", "Mapplot.html"))
pandas_bokeh.save(layout)
def test_pieplot(df_election):
"Test Pieplot"
p_pie = df_election.plot_bokeh.pie(
x="Partei",
y="2017",
colormap=[
"blue", "red", "yellow", "green", "purple", "orange", "grey"
],
title="Results of German Bundestag Election 2017",
show_figure=False,
)
p_pie_multiple = df_election.plot_bokeh(
kind="pie",
x="Partei",
colormap=[
"blue", "red", "yellow", "green", "purple", "orange", "grey"
],
title="Results of German Bundestag Elections [2002-2017]",
line_color="grey",
show_figure=False,
)
p_pie_pandas_backend = df_election.plot.pie(
x="Partei",
y="2017",
colormap=[
"blue", "red", "yellow", "green", "purple", "orange", "grey"
],
title="Results of German Bundestag Election 2017",
show_figure=False,
)
p_pie_multiple_pandas_backend = df_election.plot(
kind="pie",
x="Partei",
colormap=[
"blue", "red", "yellow", "green", "purple", "orange", "grey"
],
title="Results of German Bundestag Elections [2002-2017]",
line_color="grey",
show_figure=False,
)
layout = pandas_bokeh.plot_grid(
[
[p_pie, p_pie_multiple],
[p_pie_pandas_backend, p_pie_multiple_pandas_backend],
],
plot_width=450,
plot_height=300,
show_plot=False,
)
pandas_bokeh.output_file(os.path.join(DIRECTORY, "Plots", "Pieplot.html"))
pandas_bokeh.save(layout)
def test_area_plots(df_energy):
"Test area plots"
p_area = df_energy.plot_bokeh.area(
x="Year",
stacked=True,
legend="top_left",
colormap=["brown", "orange", "black", "grey", "blue", "green"],
title="Worldwide energy consumption split by energy source",
ylabel="Million tonnes oil equivalent",
ylim=(0, 16000),
show_figure=False,
)
p_area_normed = df_energy.plot_bokeh(
kind="area",
x="Year",
stacked=True,
normed=100,
legend="bottom_left",
colormap=["brown", "orange", "black", "grey", "blue", "green"],
title="Worldwide energy consumption split by energy source",
ylabel="Million tonnes oil equivalent",
show_figure=False,
)
p_area_pandas_backend = df_energy.plot.area(
x="Year",
stacked=True,
legend="top_left",
colormap=["brown", "orange", "black", "grey", "blue", "green"],
title="Worldwide energy consumption split by energy source",
ylabel="Million tonnes oil equivalent",
ylim=(0, 16000),
show_figure=False,
)
p_area_normed_pandas_backend = df_energy.plot(
kind="area",
x="Year",
stacked=True,
normed=100,
legend="bottom_left",
colormap=["brown", "orange", "black", "grey", "blue", "green"],
title="Worldwide energy consumption split by energy source",
ylabel="Million tonnes oil equivalent",
show_figure=False,
)
layout = pandas_bokeh.plot_grid([[p_area, p_area_normed]],
plot_width=450,
plot_height=300,
show_plot=False)
pandas_bokeh.output_file(os.path.join(DIRECTORY, "Plots", "Areaplot.html"))
pandas_bokeh.save(layout)
def test_basic_lineplot_rangetool(df_stock):
"""Test for basic lineplot above with a rangetool extension"""
p_basic_lineplot_accessor_pandas_backend = df_stock.plot.line(
show_figure=False, rangetool=True)
# Output plot as HTML:
pandas_bokeh.output_file(
os.path.join(DIRECTORY, "Plots", "Basic_lineplot_rangetool.html"))
pandas_bokeh.save(p_basic_lineplot_accessor_pandas_backend)
assert True
def test_histogram():
"Test for histograms"
import numpy as np
df_hist = pd.DataFrame(
{
"a": np.random.randn(1000) + 1,
"b": np.random.randn(1000),
"c": np.random.randn(1000) - 1,
},
columns=["a", "b", "c"],
)
# Top-on-Top Histogram (Default):
p_tt = df_hist.plot_bokeh.hist(
bins=np.linspace(-5, 5, 41),
vertical_xlabel=True,
hovertool=False,
title="Normal distributions (Top-on-Top)",
line_color="black",
show_figure=False,
)
# Side-by-Side Histogram (multiple bars share bin side-by-side) also accessible via
# kind="hist":
p_ss = df_hist.plot_bokeh(
kind="hist",
bins=np.linspace(-5, 5, 41),
histogram_type="sidebyside",
vertical_xlabel=True,
hovertool=False,
title="Normal distributions (Side-by-Side)",
line_color="black",
show_figure=False,
)
# Stacked histogram:
p_stack = df_hist.plot_bokeh.hist(
bins=np.linspace(-5, 5, 41),
histogram_type="stacked",
vertical_xlabel=True,
hovertool=False,
title="Normal distributions (Stacked)",
line_color="black",
show_figure=False,
)
layout = pandas_bokeh.column([p_tt, p_ss, p_stack])
pandas_bokeh.output_file(os.path.join(directory, "Plots", "Histogram.html"))
pandas_bokeh.save(layout)
def test_histogram_average_diplay(df_hist):
"Test average & cumulative function of histogram"
p_hist = df_hist.plot_bokeh.hist(
y=["a", "b"],
bins=np.arange(-4, 6.5, 0.5),
normed=100,
vertical_xlabel=True,
ylabel="Share[%]",
title="Normal distributions (normed)",
show_average=True,
xlim=(-4, 6),
ylim=(0, 30),
show_figure=False,
)
p_hist_cum = df_hist.plot_bokeh.hist(
y=["a", "b"],
bins=np.arange(-4, 6.5, 0.5),
normed=100,
cumulative=True,
vertical_xlabel=True,
ylabel="Share[%]",
title="Normal distributions (normed & cumulative)",
show_figure=False,
)
p_hist_cum_pandas_backend = df_hist.plot.hist(
by=["a", "b"],
bins=np.arange(-4, 6.5, 0.5),
normed=100,
cumulative=True,
vertical_xlabel=True,
ylabel="Share[%]",
title="Normal distributions (normed & cumulative)",
show_figure=False,
)
p_average = pandas_bokeh.plot_grid(
[[p_hist, p_hist_cum, p_hist_cum_pandas_backend]],
plot_width=450,
plot_height=300,
show_plot=False,
)
pandas_bokeh.output_file(
os.path.join(DIRECTORY, "Plots",
"Histogram_average_and_cumulative.html"))
pandas_bokeh.save(p_average)
def test_autosizing(df_fruits):
"""
Autoscaling test
"""
kwargs = dict(figsize=(500, 200),
sizing_mode="scale_width",
show_figure=False)
p_autoscale = df_fruits.plot_bokeh(kind="bar", **kwargs)
pandas_bokeh.output_file(os.path.join(DIRECTORY, "Plots",
"AutoScale.html"))
pandas_bokeh.save(p_autoscale)
assert True
def test_histogram_average_diplay():
"Test average & cumulative function of histogram"
import numpy as np
df_hist = pd.DataFrame(
{
"a": np.random.randn(1000) + 1,
"b": np.random.randn(1000),
"c": np.random.randn(1000) - 1,
},
columns=["a", "b", "c"],
)
p_hist = df_hist.plot_bokeh.hist(
y=["a", "b"],
bins=np.arange(-4, 6.5, 0.5),
normed=100,
vertical_xlabel=True,
ylabel="Share[%]",
title="Normal distributions (normed)",
show_average=True,
xlim=(-4, 6),
ylim=(0, 30),
show_figure=False,
)
p_hist_cum = df_hist.plot_bokeh.hist(
y=["a", "b"],
bins=np.arange(-4, 6.5, 0.5),
normed=100,
cumulative=True,
vertical_xlabel=True,
ylabel="Share[%]",
title="Normal distributions (normed & cumulative)",
show_figure=False,
)
p_average = pandas_bokeh.plot_grid(
[[p_hist, p_hist_cum]], plot_width=450, plot_height=300, show_plot=False
)
pandas_bokeh.output_file(
os.path.join(directory, "Plots", "Histogram_average_and_cumulative.html")
)
pandas_bokeh.save(p_average)
def draw_graph(df, key_selected):
plots = []
result_type_name = key_selected.replace("_", " ").capitalize()
for alg in set(sorted(df[k0_algorithm].values)):
alg_name = alg
alg_type = "scheduling"
if "heuristic" in alg:
alg_name = "OGSA"
elif "optimal" in alg:
alg_name = "Optimisation model"
if "fw" in alg:
alg_name += " with FW"
alg_type = "pricing"
df_selected = df.loc[lambda df2: df[k0_algorithm] == alg,
lambda df2: [k0_households_no, key_selected]]
df_selected = df_selected.set_index(k0_households_no)
y_label = ""
if "time" in key_selected:
y_label = "Run time (seconds)"
elif "iteration" in key_selected:
y_label = "Iteration"
elif "reduction" in key_selected:
y_label = key_selected.replace("_", " ").capitalize()
p_line = df_selected.plot_bokeh(
kind="line",
title="{} of {}, {}".format(result_type_name, alg_type,
alg_name),
xlabel="Number of Households",
ylabel=y_label,
show_figure=False,
sizing_mode="scale_width",
)
if "reduction" in key_selected:
p_line.yaxis.formatter = NumeralTickFormatter(format='0 %')
p_line.legend.location = "top_left"
p_line.y_range.start = 0
plots.append(p_line)
pandas_bokeh.output_file("{}{}.html".format(dt_folder,
result_type_name))
grid = pandas_bokeh.plot_grid(plots, ncols=2, show_plot=False)
pandas_bokeh.save(grid)
def test_mapplot():
"Mapplot test"
df_mapplot = pd.read_csv(os.path.join(test_sets_directory, "populated places","populated_places.csv"))
df_mapplot["size"] = df_mapplot["pop_max"] / 1000000
p_map = df_mapplot.plot_bokeh.map(
x="longitude",
y="latitude",
hovertool_string="""<h2> @{name} </h2>
<h3> Population: @{pop_max} </h3>""",
tile_provider="STAMEN_TERRAIN_RETINA",
size="size",
figsize=(900, 600),
title="World cities with more than 1.000.000 inhabitants",
show_figure=False)
pandas_bokeh.output_file(os.path.join(directory, "Plots", "Mapplot.html"))
pandas_bokeh.save(p_map)
def lineplot(x: str,
y: list,
data,
title="Line Plot",
output_file="",
**lineplot_kwargs):
"""
Plots a line plot.
Parameters
----------
x : str
X axis column
y : list
Y axis column
data : Dataframe
Dataframe
title : str, optional
Title of the plot, by default 'Line Plot'
output_file : str, optional
If a name is provided save the plot to an html file, by default ''
"""
data_copy = data[[x] + y].copy()
data_copy = data_copy.set_index(x)
xlabel = lineplot_kwargs.pop("xlabel", x)
p_line = data_copy.plot_bokeh.line(title=title,
xlabel=xlabel,
**lineplot_kwargs)
if output_file:
pandas_bokeh.output_file(output_file)
pandas_bokeh.save(p_line)
def test_histogram(df_hist):
"Test for histograms"
# Top-on-Top Histogram (Default):
p_tt = df_hist.plot_bokeh.hist(
bins=np.linspace(-5, 5, 41),
vertical_xlabel=True,
hovertool=False,
title="Normal distributions (Top-on-Top)",
line_color="black",
show_figure=False,
)
# Side-by-Side Histogram (multiple bars share bin side-by-side) also accessible via
# kind="hist":
p_ss = df_hist.plot_bokeh(
kind="hist",
bins=np.linspace(-5, 5, 41),
histogram_type="sidebyside",
vertical_xlabel=True,
hovertool=False,
title="Normal distributions (Side-by-Side)",
line_color="black",
show_figure=False,
)
# Stacked histogram:
p_stack = df_hist.plot_bokeh.hist(
bins=np.linspace(-5, 5, 41),
histogram_type="stacked",
vertical_xlabel=True,
hovertool=False,
title="Normal distributions (Stacked)",
line_color="black",
show_figure=False,
)
# Top-on-Top Histogram (Default):
p_tt_pandas_backend = df_hist.plot.hist(
bins=np.linspace(-5, 5, 41),
vertical_xlabel=True,
hovertool=False,
title="Normal distributions (Top-on-Top)",
line_color="black",
show_figure=False,
)
# Side-by-Side Histogram (multiple bars share bin side-by-side) also accessible via
# kind="hist":
p_ss_pandas_backend = df_hist.plot(
kind="hist",
bins=np.linspace(-5, 5, 41),
histogram_type="sidebyside",
vertical_xlabel=True,
hovertool=False,
title="Normal distributions (Side-by-Side)",
line_color="black",
show_figure=False,
)
# Stacked histogram:
p_stack_pandas_backend = df_hist.plot.hist(
bins=np.linspace(-5, 5, 41),
histogram_type="stacked",
vertical_xlabel=True,
hovertool=False,
title="Normal distributions (Stacked)",
line_color="black",
show_figure=False,
)
layout = pandas_bokeh.column([p_tt, p_ss, p_stack])
pandas_bokeh.output_file(os.path.join(DIRECTORY, "Plots",
"Histogram.html"))
pandas_bokeh.save(layout)
def draw_graphs(df_summary, df_demands_dt, df_prices_dt, df_others_dt,
exp_folder):
df_summary.index.names = [k0_algorithm]
df_summary = df_summary.reset_index()
data_table_summary = DataTable(
columns=[TableColumn(field=Ci, title=Ci) for Ci in df_summary.columns],
source=ColumnDataSource(df_summary),
height=50,
sizing_mode="scale_both",
# height_policy='auto',
)
def place_legend(pl):
legend = pl.legend[0]
legend.items[0].label['value'] = "Preferred"
legend.items[-1].label['value'] = "Optimised"
for item in legend.items[1:-1]:
item.label['value'] = "Itr {}".format(item.label['value'])
legend.click_policy = "mute"
pl.add_layout(legend, 'right')
return pl
rows = [[data_table_summary]]
x_ticks = [i for i in range(48) if i % 4 == 0]
p_height = 250
for alg in df_demands_dt:
alg_name = alg
if "heuristic" in alg:
alg_name = "OGSA and FW"
elif "optimal" in alg:
alg_name = "Optimisation model and FW"
if 'fw' in alg:
df_cost = df_others_dt[alg].T[k0_cost].div(100)
p_line_cost = df_cost.plot_bokeh(
kind="line",
title="Costs, {}".format(alg_name),
xlabel="Iteration",
ylabel="Costs",
show_figure=False,
marker="circle",
)
p_line_cost.plot_height = p_height
p_line_cost.y_range.start = 0
p_line_demand = df_demands_dt[alg].T.plot_bokeh(
kind="line",
title="Demand Profiles, {}".format(alg_name),
xlabel="Time Period",
ylabel="Demand (kWh)",
xticks=x_ticks,
show_figure=False,
muted_alpha=0,
muted=True,
sizing_mode="scale_width",
toolbar_location="above",
)
p_line_demand.plot_height = p_height
p_line_demand.y_range.start = 0
p_line_demand = place_legend(p_line_demand)
p_line_demand.renderers[0].muted = False
p_line_demand.renderers[-1].muted = False
p_line_price = df_prices_dt[alg].T.plot_bokeh(
kind="line",
title="Prices, {}".format(alg_name),
xlabel="Time Period",
ylabel="Price (Dollar)",
xticks=x_ticks,
show_figure=False,
muted_alpha=0,
muted=True,
sizing_mode="scale_width",
toolbar_location="above",
)
p_line_price.plot_height = p_height
p_line_price.y_range.start = 0
p_line_price = place_legend(p_line_price)
p_line_price.renderers[0].muted = False
p_line_price.renderers[-1].muted = False
rows.append([p_line_demand, p_line_price])
pandas_bokeh.output_file("{}plots.html".format(exp_folder))
layout = pandas_bokeh.layout(rows, sizing_mode='scale_width')
pandas_bokeh.save(layout)
def barplot(
x,
y,
data,
groupby=None,
method=None,
orient="v",
stacked=False,
output_file="",
**barplot_kwargs,
):
"""
Visualizes a bar plot.
Kwargs are bokeh plot, vbar, and hbar bokeh plots.
Parameters
----------
x : str
Column name for the x axis.
y : list
Columns for the y axis
data : Dataframe
Dataset
groupby : str
Data to groupby - xaxis, optional, by default None
method : str
Method to aggregate groupy data
Examples: min, max, mean, etc., optional
by default None
orient : str, optional
Orientation of graph, 'h' for horizontal
'v' for vertical, by default 'v'
stacked : bool
Whether to stack the different columns resulting in a stacked bar chart,
by default False
"""
alpha = barplot_kwargs.pop("alpha", 0.6)
data_copy = data[[x] + y].copy()
data_copy = data_copy.set_index(x)
if groupby:
data_copy = data_copy.groupby(groupby, as_index=False)
data_copy = getattr(data_copy, method)()
if orient == "v":
p_bar = data_copy.plot_bokeh.bar(
figsize=(1500, 500), # For now until auto scale is implemented
stacked=stacked,
alpha=alpha,
**barplot_kwargs,
)
else:
p_bar = data_copy.plot_bokeh.barh(figsize=(1500, 500),
stacked=stacked,
alpha=alpha,
**barplot_kwargs)
if output_file:
pandas_bokeh.output_file(output_file)
pandas_bokeh.save(p_bar)
def scatterplot(
x: str,
y: str,
z=None,
data=None,
category=None,
title="Scatter Plot",
size=8,
output_file="",
**scatterplot_kwargs,
):
"""
Plots a scatter plot.
Parameters
----------
x : str
X axis column
y : str
Y axis column
z: str
Z axis column
data : Dataframe
Dataframe
category : str, optional
Category to group your data, by default None
title : str, optional
Title of the plot, by default 'Scatterplot'
size : int or str, optional
Size of the circle, can either be a number
or a column name to scale the size, by default 8
output_file : str, optional
If a name is provided save the plot to an html file, by default ''
"""
if z is None:
fill_alpha = scatterplot_kwargs.pop("fill_alpha", 0.6)
data[[x, y]] = data[[x, y]].apply(pd.to_numeric)
p_scatter = data.plot_bokeh.scatter(
x=x,
y=y,
category=category,
title=title,
size=size,
fill_alpha=fill_alpha,
**scatterplot_kwargs,
)
if output_file:
pandas_bokeh.output_file(output_file)
pandas_bokeh.save(p_scatter)
else:
fig = px.scatter_3d(data, x=x, y=y, z=z, **scatterplot_kwargs)
fig.show()
