def plot_Scatterplot():
plotname = inspect.stack()[0][3][5:]
pandas_bokeh.output_file(os.path.join(PLOT_DIR, f"{plotname}.html"))
df = df_iris()
df = df.sample(frac=1)
#Create Bokeh-Table with DataFrame:
from bokeh.models.widgets import DataTable, TableColumn
from bokeh.models import ColumnDataSource
data_table = DataTable(
columns=[TableColumn(field=Ci, title=Ci) for Ci in df.columns],
source=ColumnDataSource(df.head(10)),
)
#Create Scatterplot:
p_scatter = df.plot_bokeh.scatter(
x="petal length (cm)",
y="sepal width (cm)",
category="species",
title="Iris DataSet Visualization",
show_figure=False)
#Combine Div and Scatterplot via grid layout:
pandas_bokeh.plot_grid([[data_table, p_scatter]], plot_width=400, plot_height=350)
def gen_template(dataframe, outputfile, w, h):
output_file(outputfile)
df_table = DataTable(
columns=[TableColumn(field=Ci, title=Ci) for Ci in dataframe.columns],
source=ColumnDataSource(dataframe),
width=1500,
height=200,
)
x = dataframe[['Country', 'TotalCases']]
i = x.sort_values("TotalCases", axis=0, ascending=False)
i = pd.DataFrame(i).set_index("Country")
i_bar = i.plot_bokeh(kind="bar",
ylabel="Total Cases",
title="",
show_figure=False,
color='orange')
y = dataframe[['Country', 'TotalDeaths']]
j = y.sort_values("TotalDeaths", axis=0, ascending=False)
j = pd.DataFrame(j).set_index("Country")
j_bar = j.plot_bokeh(kind="bar",
ylabel="Total Deaths",
title="",
show_figure=False,
color='red')
pandas_bokeh.plot_grid([[df_table], [i_bar], [j_bar]],
plot_width=w,
plot_height=h)
def graph_AllVariables(self, show_plot = True):
'''
Returns a HTML graph of the variables that the sensor measures.
If the database is Flux, it also gives a graph of the flows
'''
if self.database == 'Raw':
fig_ux_uy = self.graph_TimeSerie(self.data, ['Ux','Uy'],ylabel = 'm/s',name_graph = 'Time Serie - Horizontal Velocity'
,show_figure = False)
fig_uz = self.graph_TimeSerie(self.data, ['Uz'],ylabel = 'm/s',name_graph = 'Time Serie - Vertical Velocity'
, show_figure = False)
fig_temp = self.graph_TimeSerie(self.data, ['T_SONIC'],ylabel = '°C',name_graph = 'Time Serie - Temperature'
,show_figure = False)
fig_c02 = self.graph_TimeSerie(self.data, ['CO2_density'],ylabel = 'mg/m³',name_graph = 'Time Serie - CO2 Density'
,show_figure = False)
fig_h20 = self.graph_TimeSerie(self.data, ['H2O_density'],ylabel = 'g/m³',name_graph = 'Time Serie - H2O Density'
,show_figure = False)
fig_p = self.graph_TimeSerie(self.data, ['PA'], ylabel = 'kPa',name_graph = 'Time Serie - Pressure'
,show_figure = False)
tab1 = Panel(child = fig_ux_uy, title = 'Horizontal velocity')
tab2 = Panel(child = fig_uz, title = 'Vertical velocity')
tab3 = Panel(child = fig_temp, title = 'Sonic temperature')
tab4 = Panel(child = fig_c02, title = 'CO₂ density')
tab5 = Panel(child = fig_h20, title = 'H₂O density')
tab6 = Panel(child = fig_p, title = 'Atmospheric pressure')
fig = pandas_bokeh.plot_grid([[Tabs(tabs = [tab1, tab2, tab3, tab4, tab5, tab6])]],
merge_tools = True,toolbar_location = 'left', show_plot=show_plot)
elif self.database == 'Flux':
fig_ux_uy = self.graph_TimeSerie(self.data, ['Ux','Uy'],ylabel = 'm/s', show_figure = False)
fig_uz = self.graph_TimeSerie(self.data, ['Uz'],ylabel = 'm/s', show_figure = False)
fig_temp = self.graph_TimeSerie(self.data, ['T_SONIC'],ylabel = '°C', show_figure = False)
fig_c02 = self.graph_TimeSerie(self.data, ['CO2_density'],ylabel = 'mg/m³', show_figure = False)
fig_h20 = self.graph_TimeSerie(self.data, ['H2O_density'],ylabel = 'g/m³', show_figure = False)
fig_p = self.graph_TimeSerie(self.data, ['PA'], ylabel = 'kPa', show_figure = False)
tab1 = Panel(child = fig_ux_uy, title = 'Horizontal velocity')
tab2 = Panel(child = fig_uz, title = 'Vertical velocity')
tab3 = Panel(child = fig_temp, title = 'Sonic temperature')
tab4 = Panel(child = fig_c02, title = 'CO₂')
tab5 = Panel(child = fig_h20, title = 'H₂O')
tab6 = Panel(child = fig_p, title = 'Atmospheric pressure')
fig_LE = self.graph_TimeSerie(self.data, ['LE'], ylabel = 'W/m²', show_figure = False)
fig_H = self.graph_TimeSerie(self.data, ['H'], ylabel = 'W/m2', show_figure = False)
fig_TAU = self.graph_TimeSerie(self.data, ['TAU'], ylabel = 'kg/ms²', show_figure = False)
tab7 = Panel(child = fig_LE, title = 'Latent Heat Flux ')
tab8 = Panel(child = fig_H, title = 'Sensible Heat Flux')
tab9 = Panel(child = fig_TAU, title = 'Momentum Flux')
fig = pandas_bokeh.plot_grid([[Tabs(tabs = [tab1, tab2, tab3, tab4, tab5, tab6])],
[Tabs(tabs = [tab7, tab8, tab9])]],
merge_tools = True,toolbar_location = 'left', show_plot=show_plot)
return fig
def plot_Barplot3():
plotname = inspect.stack()[0][3][5:]
pandas_bokeh.output_file(os.path.join(PLOT_DIR, f"{plotname}.html"))
df = df_fruits()
p_bar = df.plot_bokeh.bar(
ylabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
show_figure=False,
)
p_stacked_bar = df.plot_bokeh.bar(
ylabel="Price per Unit [€]",
title="Fruit prices per Year",
stacked=True,
alpha=0.6,
show_figure=False,
)
# Reset index, such that "fruits" is now a column of the DataFrame:
df.reset_index(inplace=True)
# Create horizontal bar (via kind keyword):
p_hbar = df.plot_bokeh(
kind="barh",
x="fruits",
xlabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
legend="bottom_right",
show_figure=False,
)
# Create stacked horizontal bar (via barh accessor):
p_stacked_hbar = df.plot_bokeh.barh(
x="fruits",
stacked=True,
xlabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
legend="bottom_right",
show_figure=False,
)
pandas_bokeh.plot_grid([[p_bar, p_stacked_bar], [p_hbar, p_stacked_hbar]],
plot_width=450)
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 plot_Scatterplot():
df = df_iris()
df = df.sample(frac=1)
# Create Bokeh-Table with DataFrame:
from bokeh.models import ColumnDataSource
from bokeh.models.widgets import DataTable, TableColumn
data_table = DataTable(
columns=[TableColumn(field=Ci, title=Ci) for Ci in df.columns],
source=ColumnDataSource(df.head(10)),
)
# Create Scatterplot:
p_scatter = df.plot_bokeh.scatter(
x="petal length (cm)",
y="sepal width (cm)",
category="species",
title="Iris DataSet Visualization",
show_figure=False,
)
# Combine Div and Scatterplot via grid layout:
return pandas_bokeh.plot_grid([[data_table, p_scatter]],
plot_width=400,
plot_height=350,
show_plot=False)
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_scatterplot():
"Test for scatterplot"
# Load Iris Dataset:
df = pd.read_csv(os.path.join(test_sets_directory, "iris", "iris.csv"))
# Create Div with DataFrame:
from bokeh.models import Div
div_df = Div(text=df.head(10).to_html(index=False), width=550)
div_df_accessor = Div(text=df.head(10).to_html(index=False), width=550)
# Create Scatterplot:
arguments = dict(
x="petal length (cm)",
y="sepal width (cm)",
category="species",
title="Iris DataSet Visualization",
show_figure=False,
)
p_scatter = df.plot_bokeh(kind="scatter", **arguments)
p_scatter_accessor = df.plot_bokeh.scatter(**arguments)
# Combine Div and Scatterplot via grid layout:
output = pandas_bokeh.plot_grid(
[[div_df, p_scatter], [div_df_accessor, p_scatter_accessor]],
show_plot=False,
return_html=True,
)
with open(os.path.join(directory, "Plots", "Scatterplot.html"), "w") as f:
f.write(output)
assert True
def gen_template_1(outputfile):
df = corona_df[0]
#df = df[['Country,Other','TotalCases']]
df = df.head(21)
df = df.fillna(method='ffill')
data_table = DataTable(
columns=[TableColumn(field=Ci, title=Ci) for Ci in df.columns],
source=ColumnDataSource(df),
width=800,
)
df = pd.DataFrame(df).set_index("Country,Other")
bar_graph = df.plot_bokeh.barh(xlabel='TotalCases Count',
ylabel='Country',
show_figure=False)
pandas_bokeh.plot_grid([[data_table, bar_graph]],
plot_width=800,
plot_height=350)
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 plot_Histogram():
plotname = inspect.stack()[0][3][5:]
pandas_bokeh.output_file(os.path.join(PLOT_DIR, f"{plotname}.html"))
df = df_hist()
# Top-on-Top Histogram (Default):
p1 = df.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":
p2 = df.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:
p3 = df.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,
)
pandas_bokeh.plot_grid([[p1], [p2], [p3]])
def get_plot():
nu_df = getdata()
mac_df = nu_df[[
'Food items', 'Protein (g)', 'Total Fat(g)', 'Total Carbs(g)',
'Fiber, total dietary(g)'
]]
min_df = nu_df[[
'Food items', 'Vitamin C(mg)', 'Vitamin E(mg)', 'Vitamin B6(mg)',
'Calcium, Ca(mg)', 'Iron, Fe(mg)', 'Magnesium, Mg(mg)',
'Phosphorus, P(mg)', 'Zinc, Zn(mg)', 'Sodium, Na(mg)',
'Potassium, K(mg)'
]]
pw = nu_df.plot_bokeh.scatter(x='Food items',
y='Calories (kcal)',
show_figure=False)
px = nu_df.plot_bokeh.scatter(x='Calories (kcal)',
y='Protein (g)',
category='Food items',
show_figure=False)
py = nu_df.plot_bokeh.scatter(x='Calories (kcal)',
y='Total Fat(g)',
category='Food items',
show_figure=False)
pz = nu_df.plot_bokeh.scatter(x='Calories (kcal)',
y='Total Carbs(g)',
category='Food items',
show_figure=False)
pm = mac_df.plot_bokeh.bar(x='Food items',
ylabel="grams (g)",
show_figure=False)
pn = min_df.plot_bokeh.bar(x='Food items',
ylabel="milligrams (mg)",
show_figure=False)
a_plot = pandas_bokeh.plot_grid([[pw, px], [py, pz]])
b_plot = pandas_bokeh.plot_grid([[pm, pn]])
return (a_plot, b_plot)
def test_scatterplot(df_iris):
"Test for scatterplot"
# Create Bokeh-Table with DataFrame:
from bokeh.models import ColumnDataSource
from bokeh.models.widgets import DataTable, TableColumn
data_table = DataTable(
columns=[TableColumn(field=Ci, title=Ci) for Ci in df_iris.columns],
source=ColumnDataSource(df_iris.head(10)),
)
data_table_accessor = DataTable(
columns=[TableColumn(field=Ci, title=Ci) for Ci in df_iris.columns],
source=ColumnDataSource(df_iris.head(10)),
)
# Create Scatterplot:
arguments = dict(
x="petal length (cm)",
y="sepal width (cm)",
category="species",
title="Iris DataSet Visualization",
show_figure=False,
)
p_scatter = df_iris.plot_bokeh(kind="scatter", **arguments)
p_scatter_accessor = df_iris.plot_bokeh.scatter(**arguments)
p_scatter_pandas_backend = df_iris.plot(kind="scatter", **arguments)
p_scatter_accessor_pandas_backend = df_iris.plot.scatter(**arguments)
# Combine Div and Scatterplot via grid layout:
output = pandas_bokeh.plot_grid(
[
[data_table, p_scatter],
[
data_table_accessor,
p_scatter_accessor,
p_scatter_pandas_backend,
p_scatter_accessor_pandas_backend,
],
],
show_plot=False,
return_html=True,
)
with open(os.path.join(DIRECTORY, "Plots", "Scatterplot.html"), "w") as f:
f.write(output)
assert True
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 plot_lines_dashboard_ita(cases_df, figures_path, geo_name,
plot_dashboard_flag):
for save_flag in [False]:
p1 = plot_df_lines_bokeh(cases_df, "data", [
"totale_tamponi",
"totale_casi",
], figures_path, "tamponi", save_flag)
p2 = plot_df_lines_bokeh(cases_df, "data", [
"totale_attualmente_positivi", "totale_deceduti",
"totale_dimessi_guariti"
], figures_path, "totali_principali", save_flag)
p3 = plot_df_lines_bokeh(cases_df, "data", [
"nuovi_positivi", "nuovi_attualmente_positivi", "nuovi_deceduti",
"nuovi_dimessi_guariti"
], figures_path, "nuovi_principali", save_flag)
p4 = plot_df_lines_bokeh(cases_df, "data", [
"tasso_positivi_tamponi", "tasso_nuovi_positivi",
"tasso_mortalita", "tasso_guarigione"
], figures_path, "tassi_principali", save_flag)
p5 = plot_df_lines_bokeh(cases_df, "data", [
"attualmente_isolamento_domiciliare",
"attualmente_ricoverati",
"attualmente_terapia_intensiva",
], figures_path, "dettaglio_pazienti_attuali", save_flag)
p6 = plot_df_lines_bokeh(cases_df, "data", [
"tasso_ricoverati_con_sintomi",
"tasso_terapia_intensiva",
"tasso_terapia_intensiva_ricoverati",
], figures_path, "tassi_condizioni_cliniche", save_flag)
if plot_dashboard_flag:
outfp = os.path.join(figures_path, geo_name + ".html")
output_file(outfp)
pandas_bokeh.output_file(outfp)
plot_grid = pandas_bokeh.plot_grid([
[p1, p2],
[p3, p4],
[p5, p6],
],
toolbar_location="left")
# pandas_bokeh.save(plot_grid)
save(plot_grid)
def plot_Barplot3():
df = df_fruits()
p_bar = df.plot_bokeh.bar(
ylabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
show_figure=False,
)
p_stacked_bar = df.plot_bokeh.bar(
ylabel="Price per Unit [€]",
title="Fruit prices per Year",
stacked=True,
alpha=0.6,
show_figure=False,
)
# Reset index, such that "fruits" is now a column of the DataFrame:
df.reset_index(inplace=True)
# Create horizontal bar (via kind keyword):
p_hbar = df.plot_bokeh(
kind="barh",
x="fruits",
xlabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
legend="bottom_right",
show_figure=False,
)
# Create stacked horizontal bar (via barh accessor):
p_stacked_hbar = df.plot_bokeh.barh(
x="fruits",
stacked=True,
xlabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
legend="bottom_right",
show_figure=False,
)
return pandas_bokeh.plot_grid(
[[p_bar, p_stacked_bar], [p_hbar, p_stacked_hbar]],
plot_width=450,
show_plot=False,
)
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 plot_lines_dashboard(cases_df, figures_path, geo_name,
plot_dashboard_flag):
if plot_dashboard_flag:
save_flag = False
outfp = os.path.join(figures_path, geo_name + ".html")
output_file(outfp)
pandas_bokeh.output_file(outfp)
else:
save_flag = True
p1 = plot_df_lines_bokeh(cases_df, "datetime", [
"total_cases",
], figures_path, "cases", save_flag)
p2 = plot_df_lines_bokeh(cases_df, "datetime",
["total_deaths", "total_recovered"], figures_path,
"main_totals", save_flag)
p3 = plot_df_lines_bokeh(cases_df, "datetime", [
"new_positives", "new_currently_positives", "new_deaths",
"new_recovered"
], figures_path, "main_new", save_flag)
p4 = plot_df_lines_bokeh(
cases_df, "datetime",
["rate_new_positives", "rate_deaths", "rate_recovered"], figures_path,
"main_rate", save_flag)
if plot_dashboard_flag:
plot_grid = pandas_bokeh.plot_grid([
[p1, p2],
[p3, p4],
],
toolbar_location="left")
# pandas_bokeh.save(plot_grid)
save(plot_grid)
def plot_Histogram():
df = df_hist()
# Top-on-Top Histogram (Default):
p1 = df.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":
p2 = df.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:
p3 = df.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,
)
return pandas_bokeh.plot_grid([[p1], [p2], [p3]], show_plot=False)
def test_barplot_layout(df_fruits):
"Test for Barplot layout"
p_bar = df_fruits.plot_bokeh.bar(
ylabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
show_figure=False,
)
p_stacked_bar = df_fruits.plot_bokeh.bar(
ylabel="Price per Unit [€]",
title="Fruit prices per Year",
stacked=True,
alpha=0.6,
show_figure=False,
)
p_bar_pandas_backend = df_fruits.plot.bar(
ylabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
show_figure=False,
)
p_stacked_bar_pandas_backend = df_fruits.plot.bar(
ylabel="Price per Unit [€]",
title="Fruit prices per Year",
stacked=True,
alpha=0.6,
show_figure=False,
)
# Reset index, such that "fruits" is now a column of the DataFrame:
df_fruits.reset_index(inplace=True)
p_hbar = df_fruits.plot_bokeh(
kind="barh",
x="fruits",
xlabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
legend="bottom_right",
show_figure=False,
)
p_stacked_hbar = df_fruits.plot_bokeh.barh(
x="fruits",
stacked=True,
xlabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
legend="bottom_right",
show_figure=False,
)
p_hbar_pandas_backend = df_fruits.plot(
kind="barh",
x="fruits",
xlabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
legend="bottom_right",
show_figure=False,
)
p_stacked_hbar_pandas_backend = df_fruits.plot.barh(
x="fruits",
stacked=True,
xlabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
legend="bottom_right",
show_figure=False,
)
# Plot all barplot examples in a grid:
output = pandas_bokeh.plot_grid(
[[p_bar, p_stacked_bar], [p_hbar, p_stacked_hbar]],
plot_width=450,
show_plot=False,
return_html=True,
)
# Output plot as HTML:
with open(os.path.join(DIRECTORY, "Plots", "Barplot_layout.html"),
"w") as f:
f.write(output)
assert True
gdp_df = gdp[['Country', 'GDP_nominal_2017', 'GDP_abbrev']]
data = gdp_df.rename(columns={'index': 'Country'})
l = data['GDP_nominal_2017'].to_list()
l = [sub.replace('$', '').replace(',', '') for sub in l]
l = [int(i) for i in l]
l = pd.Series(l)
data['angle'] = l / l.sum() * 2 * pi
data['color'] = Category20c[len(gdp)]
p = figure(plot_height=350,
title="World GDP Distribution",
toolbar_location='above',
tooltips="@Country:" + "@GDP_abbrev",
x_range=(-0.5, 1.0))
p.wedge(x=0,
y=1,
radius=0.4,
start_angle=cumsum('angle', include_zero=True),
end_angle=cumsum('angle'),
line_color="white",
fill_color='color',
legend_field='Country',
source=data)
p.axis.axis_label = None
p.axis.visible = False
p.grid.grid_line_color = None
pandas_bokeh.plot_grid([[gdp_table, p]])
def plot_Startimage():
plotname = inspect.stack()[0][3][5:]
pandas_bokeh.output_file(os.path.join(PLOT_DIR, f"{plotname}.html"))
# Barplot:
data = {
"fruits": ["Apples", "Pears", "Nectarines", "Plums", "Grapes", "Strawberries"],
"2015": [2, 1, 4, 3, 2, 4],
"2016": [5, 3, 3, 2, 4, 6],
"2017": [3, 2, 4, 4, 5, 3],
}
df = pd.DataFrame(data).set_index("fruits")
p_bar = df.plot_bokeh(
kind="bar",
ylabel="Price per Unit [€]",
title="Fruit prices per Year",
show_figure=False,
)
# Lineplot:
np.random.seed(42)
df = pd.DataFrame(
{"Google": np.random.randn(1000) + 0.2, "Apple": np.random.randn(1000) + 0.17},
index=pd.date_range("1/1/2000", periods=1000),
)
df = df.cumsum()
df = df + 50
p_line = df.plot_bokeh(
kind="line",
title="Apple vs Google",
xlabel="Date",
ylabel="Stock price [$]",
yticks=[0, 100, 200, 300, 400],
ylim=(0, 400),
colormap=["red", "blue"],
show_figure=False,
)
# Scatterplot:
df = df_iris()
p_scatter = df.plot_bokeh(
kind="scatter",
x="petal length (cm)",
y="sepal width (cm)",
category="species",
title="Iris DataSet Visualization",
show_figure=False,
)
# Histogram:
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(
kind="hist",
bins=np.arange(-6, 6.5, 0.5),
vertical_xlabel=True,
normed=100,
hovertool=False,
title="Normal distributions",
show_figure=False,
)
# Make Dashboard with Grid Layout:
plot = pandas_bokeh.plot_grid(
[[p_line, p_bar], [p_scatter, p_hist]], plot_width=450
)
def plot_top_words_conditional(texts,
labels,
vectorizer=default_vectorizer,
topk=20,
interactive=False,
save_path='../visualizations/'):
if type(texts[0]) == list:
texts = [" ".join(LemmaTokenizer()(" ".join(i))) for i in texts]
else:
texts = [" ".join(LemmaTokenizer()(i)) for i in texts]
vectorized_corpus = vectorizer.fit_transform(texts)
top_words = vectorizer.get_feature_names()
top_words_df = pd.DataFrame(vectorized_corpus.toarray(), columns=top_words)
top_words_df['label'] = labels
top_words_df = top_words_df.groupby(['label'
]).mean().reset_index(drop=False)
#print (top_words_df.head(5))
#top_words_df = pd.melt(top_words_df, id_vars=['label'],value_vars=list(top_words))
top_words_df = pd.melt(top_words_df,
col_level=0,
id_vars=['label'],
value_vars=top_words_df.columns[1:])
top_words_df.columns = ['label', 'top_word', 'word_weight']
top_words_df = top_words_df.sort_values(
by=['label', 'word_weight'], ascending=[True,
True]).reset_index(drop=True)
top_words_df = top_words_df.groupby(['label'
]).tail(topk).reset_index(drop=True)
if interactive:
pd.set_option('plotting.backend', 'pandas_bokeh')
html_plots = []
for lb in top_words_df.label.unique():
html_plots.append(top_words_df[top_words_df['label'] == lb][[
'top_word', 'word_weight'
]].set_index('top_word').plot_bokeh(
kind="barh",
title="Top Words: Label = {}".format(lb),
legend=False,
show_figure=False,
xlabel="Weight",
ylabel="Word"))
html_plot = pandas_bokeh.plot_grid([html_plots],
plot_width=450,
return_html=True,
show_plot=False)
#Export the HTML string to an external HTML file and show it:
with open(os.path.join(save_path, "top_words_conditional.html"),
"w") as f:
f.write(html_plot)
else:
pd.set_option('plotting.backend', 'matplotlib')
fig, ax = plt.subplots(1,
top_words_df.label.nunique(),
figsize=(15, 6))
fig.tight_layout()
for i, lb in enumerate(top_words_df.label.unique()):
top_words_df[top_words_df['label'] == lb][[
'top_word', 'word_weight'
]].set_index('top_word').plot.barh(legend=False, ax=ax[i])
ax[i].set_xlabel("Weight")
if i == 0:
ax[i].set_ylabel("Word")
else:
ax[i].set_ylabel(None)
ax[i].set_title("Top Words: Label = {}".format(lb))
#plt.title("Top Words")
plt.savefig(os.path.join(save_path, "top_words_conditional.png"),
dpi=200,
bbox_inches='tight')
plt.close()
def visualize_polytrend_polygon(result):
""" Create maps for polygons
Args:
result: list
contains what comes out of PolyTrend R package
Returns:
render_template with graphics
"""
## get staticstics for all points
result_to_display = get_PT_statistics(result)
trend_stats = {
"concealed": result_to_display["count_concealed"],
"linear": result_to_display["count_linear"],
"no trend": result_to_display["count_no_trend"],
"quadratic": result_to_display["count_quadratic"],
"cubic": result_to_display["count_cubic"],
}
# get pie plots for summary statistics
trend_data = (pd.Series(trend_stats).reset_index(name="value").rename(
columns={"index": "trend"}))
trend_data["angle"] = trend_data["value"] / trend_data["value"].sum(
) * 2 * pi
trend_data["color"] = ["gray", "forestgreen", "yellow", "blue", "red"]
trend_pie = figure(
plot_height=350,
title="Trend type (share in total number of pixels)",
toolbar_location=None,
tools="hover",
tooltips="@trend: @value",
x_range=(-0.5, 1.0),
sizing_mode="scale_both",
)
trend_pie.wedge(
x=0,
y=1,
radius=0.4,
start_angle=cumsum("angle", include_zero=True),
end_angle=cumsum("angle"),
line_color="white",
fill_color="color",
legend="trend",
source=trend_data,
)
trend_pie.axis.axis_label = None
trend_pie.axis.visible = False
trend_pie.grid.grid_line_color = None
direction_stats = {
"negative": result_to_display["count_negative"],
"positive": result_to_display["count_positive"],
}
dir_data = (pd.Series(direction_stats).reset_index(name="value").rename(
columns={"index": "direction"}))
dir_data["angle"] = dir_data["value"] / dir_data["value"].sum() * 2 * pi
dir_data["color"] = ["gray", "forestgreen"]
direction_pie = figure(
plot_height=350,
title="Change direction (share in total number of pixels)",
toolbar_location=None,
tools="hover",
x_range=(-0.5, 1.0),
sizing_mode="scale_both",
tooltips="@direction: @value",
)
direction_pie.wedge(
x=0,
y=1,
radius=0.4,
start_angle=cumsum("angle", include_zero=True),
end_angle=cumsum("angle"),
line_color="white",
fill_color="color",
legend="direction",
source=dir_data,
)
direction_pie.axis.axis_label = None
direction_pie.axis.visible = False
direction_pie.grid.grid_line_color = None
pie_layout = row([trend_pie, direction_pie], sizing_mode="stretch_both")
script, div = components(pie_layout)
### get maps
gpd_coordinates = result["geometry"].apply(Point)
gpd_df = gpd.GeoDataFrame(result, geometry=gpd_coordinates)
gpd_df.crs = {"init": "epsg:4326"}
pointA = result["geometry"][0]
pointB = result["geometry"][1]
buffer_size = pointA.distance(pointB) / 2
gpd_df.geometry = gpd_df.geometry.buffer(buffer_size).envelope
colormap_trend = ["grey", "yellow", "green", "blue", "red"]
trend_map = gpd_df.plot_bokeh(
category="trend_type",
colormap=colormap_trend,
line_color=None,
title="Map of trend types",
legend="Trend type",
show_figure=False,
show_colorbar=True,
hovertool_columns="all",
)
colormap_dir = ["yellow", "green"]
direction_map = gpd_df.plot_bokeh(
category="direction",
colormap=colormap_dir,
line_color=None,
title="Map of direction",
legend="Direction",
show_figure=False,
show_colorbar=True,
hovertool_columns="all",
)
slope_map = gpd_df.plot_bokeh(
category="slope",
fill_color=palette,
legend="Slope",
title="Slope map",
show_figure=False,
line_color=None,
hovertool_columns="all",
)
plot_grid = pandas_bokeh.plot_grid(
[[trend_map, direction_map], [slope_map]],
show_plot=False,
return_html=True)
return render_template(
"results_polytrend.html",
result=result_to_display,
pt_map=plot_grid,
script=script,
div=div,
is_point=False,
)
def dbest_visualize_polygon(result, algorithm, data_type):
""" Create maps for polygons
Args:
result: dataframe
contains what comes out of DBEST package
algorithm: string
'generalization' or 'change detection' depending on user's choice
Returns:
render_template with graphics
"""
result_to_display = {}
if data_type == "cyclical":
gpd_coordinates = result["geometry"].apply(Point)
gpd_df = gpd.GeoDataFrame(result, geometry=gpd_coordinates)
gpd_df.crs = {"init": "epsg:4326"}
pointA = result["geometry"][0]
pointB = result["geometry"][1]
buffer_size = pointA.distance(pointB) / 2
gpd_df.geometry = gpd_df.geometry.buffer(buffer_size).envelope
mapper = LinearColorMapper(palette=palette)
colormap = ["grey", "yellow"]
start_map = gpd_df.plot_bokeh(
category="start",
colormap=palette,
title="Start time",
legend="Start time",
line_color=None,
show_figure=False,
show_colorbar=True,
)
duration_map = gpd_df.plot_bokeh(
category="duration",
colormap=palette,
title="Duration (months)",
legend="Duration",
line_color=None,
show_figure=False,
)
change_map = gpd_df.plot_bokeh(
category="change",
colormap=palette,
title="Change map",
legend="Change value",
line_color=None,
show_figure=False,
)
change_type_map = gpd_df.plot_bokeh(
category="change_type",
colormap=colormap,
title="Change type map - abrupt (1), non-abrupt (0)",
legend="Change type",
line_color=None,
show_figure=False,
)
plot_grid = pandas_bokeh.plot_grid(
[[change_map, duration_map], [start_map, change_type_map]],
return_html=True,
show_plot=False,
)
script = ""
div = ""
generalization = ""
change_detection = ""
elif data_type == "non-cyclical":
plot_grid = ""
script = ""
div = ""
generalization = "No result for non-cyclical data yet..."
change_detection = ""
return render_template(
"results_DBEST.html",
generalization=generalization,
change_detection=change_detection,
dbest_maps=plot_grid,
result=result_to_display,
is_point=False,
script=script,
div=div,
)
def test_barplot_layout():
"Test for Barplot layout"
data = {
"fruits": ["Apples", "Pears", "Nectarines", "Plums", "Grapes", "Strawberries"],
"2015": [2, 1, 4, 3, 2, 4],
"2016": [5, 3, 3, 2, 4, 6],
"2017": [3, 2, 4, 4, 5, 3],
}
df = pd.DataFrame(data).set_index("fruits")
p_bar = df.plot_bokeh.bar(
ylabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
show_figure=False,
)
p_stacked_bar = df.plot_bokeh.bar(
ylabel="Price per Unit [€]",
title="Fruit prices per Year",
stacked=True,
alpha=0.6,
show_figure=False,
)
# Reset index, such that "fruits" is now a column of the DataFrame:
df.reset_index(inplace=True)
# Create horizontal bar (via kind keyword):
p_hbar = df.plot_bokeh(
kind="barh",
x="fruits",
xlabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
legend="bottom_right",
show_figure=False,
)
# Create stacked horizontal bar (via barh accessor):
p_stacked_hbar = df.plot_bokeh.barh(
x="fruits",
stacked=True,
xlabel="Price per Unit [€]",
title="Fruit prices per Year",
alpha=0.6,
legend="bottom_right",
show_figure=False,
)
# Plot all barplot examples in a grid:
output = pandas_bokeh.plot_grid(
[[p_bar, p_stacked_bar], [p_hbar, p_stacked_hbar]],
plot_width=450,
show_plot=False,
return_html=True,
)
# Output plot as HTML:
with open(os.path.join(directory, "Plots", "Barplot_layout.html"), "w") as f:
f.write(output)
assert True
dataUSEstd[['大区名称', '小区名称', '城市', '经销商代码', '客户来源更新', '车型new', '潜客量']])
dataEsti = dataEsti.groupby(['大区名称', '小区名称', '城市', '经销商代码', '客户来源更新',
'车型new'])['潜客量'].sum().reset_index()
# 添加车型站比
dataEsti['dealer汇总'] = dataEsti.groupby(
['大区名称', '小区名称', '城市', '经销商代码', '客户来源更新'])['潜客量'].transform('sum')
dataEsti['车型占比'] = dataEsti['潜客量'] / dataEsti['dealer汇总']
dataEsti['日均概率'] = dataEsti['潜客量'] / monthDays
dealerUnique = dataCOMPUTed[['大区名称', '小区名称', '经销商代码', '城市',
'客户来源更新']].drop_duplicates()
dealerUnique = dealerUnique.reset_index(drop=True)[['经销商代码', '客户来源更新']]
# 生成数据
start = 0
for idx, row in dealerUnique.iterrows():
print(idx, row['经销商代码'], row['客户来源更新'])
start = genNewData(row['经销商代码'], row['客户来源更新'], start)
print(start)
# 这时再做合并就是类似dataAvailable一样了
newMiss = dataMiss.groupby(
['日期', '大区名称', '小区名称', '经销商代码', '经销商名称', '城市', '客户来源更新',
'车型new']).sum().reset_index()
# 画图，并生成html
pics = []
for pic in graphLVL:
pics.extend(batDraw(pic))
html = pb.plot_grid(pics, plot_width=300, return_html=True)
with open("tt.html", 'w') as f:
f.write(html)
source = ColumnDataSource(dg)
val = dg[group_by][0]
for k in dg:
if k != col:
continue
p.line(x=datecolumn,
y=k,
source=source,
legend_label=f"{k}[{val}]",
name=f"{k}[{val}]",
color=next(colors))
continue
else:
p = df.plot_bokeh(title=title, kind='line', show_figure=False)
plots.append(p)
for p in plots:
p.legend.click_policy = "hide"
grid = []
for i in range(0, len(plots), args.chart_cols):
grid.append(plots[i:i + args.chart_cols])
pandas_bokeh.plot_grid(grid)
