def paral(selected_cluster, selected_ciudad, choose):
clean = get_views.get_view_by_name('canal_edad_tipo_ciudad_cluster')
df = clean[clean['ciudad_tienda'] == selected_ciudad]
df10 = df['cluster_id'].unique()
if selected_cluster is None:
dff = get_views.get_view_by_name('paralell_plot_cluster')
grupos = dff[(dff['ciudad_tienda'] == selected_ciudad)]
fig2 = px.parallel_categories(
grupos,
dimensions=choose,
color="valor_neto",
color_continuous_scale=px.colors.sequential.Inferno,
title='Parallel Categories Sales Category Diagram')
else:
if selected_cluster in list(df10):
dff = get_views.get_view_by_name('paralell_plot_cluster')
grupos = dff[(dff['ciudad_tienda'] == selected_ciudad)
& dff['cluster_id'].isin([selected_cluster])]
fig2 = px.parallel_categories(
grupos,
dimensions=choose,
color="valor_neto",
color_continuous_scale=px.colors.sequential.Inferno,
title='Parallel Categories Sales Category Diagram')
else:
dff = get_views.get_view_by_name('paralell_plot_cluster')
grupos = dff[(dff['ciudad_tienda'] == selected_ciudad)]
fig2 = px.parallel_categories(
grupos,
dimensions=choose,
color="valor_neto",
color_continuous_scale=px.colors.sequential.Inferno,
title='Parallel Categories Sales Category Diagram')
return fig2
def test_parcats_dimensions_max():
df = px.data.tips()
# default behaviour
fig = px.parallel_categories(df)
assert [d.label for d in fig.data[0].dimensions] == [
"sex",
"smoker",
"day",
"time",
"size",
]
# explicit subset of default
fig = px.parallel_categories(df, dimensions=["sex", "smoker", "day"])
assert [d.label
for d in fig.data[0].dimensions] == ["sex", "smoker", "day"]
# shrinking max
fig = px.parallel_categories(df, dimensions_max_cardinality=4)
assert [d.label for d in fig.data[0].dimensions] == [
"sex",
"smoker",
"day",
"time",
]
# explicit superset of default, violating the max
fig = px.parallel_categories(df,
dimensions=["sex", "smoker", "day", "size"],
dimensions_max_cardinality=4)
assert [d.label for d in fig.data[0].dimensions
] == ["sex", "smoker", "day", "size"]
def get_parallel_categories(dataframe, target_feature):
try:
fig = px.parallel_categories(
dataframe,
color=target_feature,
color_continuous_scale=px.colors.sequential.Inferno)
except:
fig = px.parallel_categories(dataframe)
graphJSON = json.dumps(fig, cls=plotly.utils.PlotlyJSONEncoder)
return graphJSON
def visualize(
self, object: PipelineView, *args: Any, **kwargs: Any
) -> Figure:
"""Creates a pipeline lineage diagram using plotly."""
logger.warning(
"This integration is not completed yet. Results might be unexpected."
)
category_dict = {}
dimensions = ["run"]
for run in object.runs:
category_dict[run.name] = {"run": run.name}
for step in run.steps:
category_dict[run.name].update(
{
step.name: str(step.id),
}
)
if step.name not in dimensions:
dimensions.append(f"{step.name}")
category_df = pd.DataFrame.from_dict(category_dict, orient="index")
category_df = category_df.reset_index()
fig = px.parallel_categories(
category_df,
dimensions,
color=None,
labels="status",
)
fig.show()
return fig
def get_cat_plot(df, columns):
df = df.copy()
df_1 = df[columns]
df_1 = df_1.groupby(columns).size().reset_index(name='count')
fig = px.parallel_categories(
df_1,
dimensions=columns,
color="count",
color_continuous_scale=px.colors.sequential.Pinkyl,
)
fig.update_layout(
autosize=False,
margin=dict(l=150, r=100, t=40, b=40),
paper_bgcolor="#ffffff",
font=dict(
family="Courier New",
size=15,
color="#7f7f7f"
),
title_text='',
legend_orientation="h"
)
return fig
def parallel_categories():
"""Parallel Categories Plot."""
sfo_avg_price_by_neighborhood = sfo_data.groupby(['year', 'neighborhood'
]).mean().reset_index()
top10_neighborhoods = sfo_data.groupby(['neighborhood']).mean()
top10_neighborhoods.sort_values(['sale_price_sqr_foot'],
ascending=False,
inplace=True)
top10_neighborhoods = top10_neighborhoods.reset_index().head(10)
df_expensive_neighborhoods_per_year = sfo_avg_price_by_neighborhood[
sfo_avg_price_by_neighborhood["neighborhood"].isin(
top10_neighborhoods["neighborhood"])]
cat_plot = px.parallel_categories(
top10_neighborhoods,
dimensions=[
'neighborhood', 'sale_price_sqr_foot', 'housing_units',
'gross_rent'
],
color='sale_price_sqr_foot',
color_continuous_scale=px.colors.sequential.Inferno,
labels={
'neighborhood': 'neighborhood',
'sale_price_sqr_foot': 'sale_price_sqr_foot',
'housing_units': 'housing_units',
'gross_rent': 'gross_rent'
},
)
return cat_plot
def plot_categorical_categorical(df, feature_1, feature_2):
fig = px.parallel_categories(
df,
dimensions=[feature_1, feature_2],
)
fig.update_layout(title="Plot of {} vs. {}".format(feature_1, feature_2))
st.plotly_chart(fig)
def update_figure(year2):
newdata = data[data['ReportPeriod'].str.slice(start=6, stop=10) == (
str(year2))][[
'ReportPeriod', 'Terminal', 'Domestic_International',
'Arrival_Departure'
]]
figure = px.parallel_categories(newdata)
return figure
def g5(batch_id, color, colorset):
input_model = models.BatchInput(batch_id)
df = input_model.as_pandas_dataframe()
fig = px.parallel_categories(df, color=color,
color_continuous_scale=get_colorset(colorset))
div = opy.plot(fig, auto_open=False, output_type='div')
return div
def parallel_categories_plotly(*args,
plotly_width=1200,
plotly_height=600,
**kwargs):
fig = px.parallel_categories(*args,
**kwargs,
color_continuous_scale=color_scale)
fig.update_layout(autosize=False, width=plotly_width, height=plotly_height)
return fig
def parallel_categories_index():
parallel_categories_index = px.parallel_categories(data_csv,
dimensions=["Name","Population Size","Income Range","Poverty Level"],
color="Year",
color_continuous_scale=px.colors.sequential.Blues,
labels={"Name": "Borough"},
width=970)
return parallel_categories_index
def get_parallel_categories():
parallel_categories = px.parallel_categories(
top10_df_plot,
dimensions=[
"neighborhood", "sale_price_sqr_foot", "housing_units",
"gross_rent"
],
color="sale_price_sqr_foot",
title="Parallel Categories Plot.")
return parallel_categories
def update_graph(selectedData):
if selectedData:
indices = [point['pointIndex'] for point in selectedData['points']]
dff = df.iloc[indices, :]
else:
dff = df
fig = px.parallel_categories(dff, dimensions=['Type_1', 'Color', 'Body_Style'],
labels={'Type': 'Type_1', 'Color': 'Color',
'Body Style': 'Body_Style'}
)
return fig
def updateParallelCategoriesPlot(productCategory, product, company):
print("Running updateParallelCategoriesPlot callback")
dff = getDataFrameFilteredBy(productCategory, product, company)
dff = dff.drop_duplicates(subset=[
"Company", "Product Category", "Product", "Purchase Type", "Age"
])
fig = px.parallel_categories(
dff,
dimensions=["Product Category", "Product", "Purchase Type", "Age"],
color="Age",
color_continuous_scale=px.colors.sequential.Rainbow,
title="Product, Purchase Type, and Age Information",
)
return fig
def update_parralel(value):
# New dataframe to make the map out of
df = pd.read_csv(
os.path.join('..', 'datasets',
'Police_Department_Incidents_-_Previous_Year__2016_.csv'))
df['color'] = df.apply(lambda row: get_color(row), axis=1)
df['Time of Day'] = df.apply(lambda row: get_time_of_day(row), axis=1)
df = df[df.Category.isin(value)]
fig = px.parallel_categories(
df,
color='color',
dimensions=['DayOfWeek', 'PdDistrict', 'Time of Day'])
fig.update_layout(showlegend=True)
return fig
def parallel_categories():
"""Parallel Categories Plot."""
# YOUR CODE HERE!
avg = df.groupby([df['neighborhood']]).mean()
avg2 = avg.sort_values(by='sale_price_sqr_foot', ascending=False).head(10)
parallel_cat = px.parallel_categories(
avg2.reset_index().round(1),
dimensions=[
'neighborhood', 'sale_price_sqr_foot', 'housing_units',
'gross_rent'
],
color="sale_price_sqr_foot",
color_continuous_scale=px.colors.sequential.Inferno)
return parallel_cat
def parallel_categories(self,
parameters,
scores,
score_name_to_plot='mean_test_score',
message=''):
parameters_local = parameters.copy()
scores_local = scores[score_name_to_plot].copy()
temp_df = parameters_local.join(scores_local, how='outer')
temp_df = temp_df.sort_values('mean_test_score', ascending=False)
fig = px.parallel_categories(
temp_df,
color='mean_test_score',
color_continuous_scale=px.colors.sequential.Inferno)
filename = os.path.join(self.current_directory,
message + '_parallel_categories_plot.html')
plotly.offline.plot(fig, show_link=True, filename=filename)
def para_coord(df=para_df()):
fig = px.parallel_categories(
df,
dimensions=['freeshippingflag', 'PRODUCTGROUPNAME', 'channel'],
color='log_totalprice',
color_continuous_scale=px.colors.sequential.Inferno,
labels={
'PRODUCTGROUPNAME': 'Product groupname',
'freeshippingflag': 'Free shipping',
'channel': 'Campaign channel',
'log_totalprice': 'Log(TotalRevenue)'
},
height=500)
fig = fig.update_layout(showlegend=False,
margin=dict(l=30, r=30, t=20, b=20))
return fig
def results(request, pk):
reading = Reading.objects.get(pk=pk)
query = str(reading.cards.all().query)
df = pandas.read_sql_query(query, connection)
fig_elements = px.pie(df,
names='card_element',
color_discrete_sequence=px.colors.sequential.RdBu)
graph_elements = fig_elements.to_html(full_html=False,
default_height=350,
default_width=350)
fig_arcana_rank = px.pie(df,
names='card_arcana_rank',
color_discrete_sequence=px.colors.sequential.RdBu)
graph_arcana_rank = fig_arcana_rank.to_html(full_html=False,
default_height=350,
default_width=350)
fig_categories = px.parallel_categories(
df,
dimensions=['card_element', 'card_astro_sign', 'card_astro_planet'])
graph_categories = fig_categories.to_html(full_html=False,
default_height=350,
default_width=850)
context = {
"question": reading.question,
"reading_id": reading.id,
"reading_num_cards": reading.num_of_cards,
"cards": reading.cards.all(),
"plot_elements_div": graph_elements,
"plot_arcana_rank_div": graph_arcana_rank,
"plot_categories_div": graph_categories
}
return render(request, "results.html", context)
def generate_parallel_categories(dataset,
group,
filter=None,
filter_value=None,
year=None):
df = dataset.copy()
group = ['Rango de edad', 'Sexo', 'Año', 'Total']
year = 2015
filter = 'Tipo de delito'
filter_value = 'Homicidio'
if filter_value != None:
df = df[df[filter] == filter_value]
if year != None:
df = df[df['Año'] == year]
df = df.groupby(group).sum().reset_index()
fig = px.parallel_categories(df,
color="Total",
color_continuous_scale='Bluered')
fig.show()
def update_histogram(numeric1, numeric2, selected_data, var1, var2, var3,
var4):
if selected_data == None:
selected_data = {
"points":
list(map(lambda x: {"pointNumber": x}, list(range(len(df)))))
}
selected_indices = list(
map(lambda x: x['pointNumber'], selected_data['points']))
scatter = px.scatter(df, x=numeric1, y=numeric2)
scatter.update_traces(selectedpoints=selected_indices)
scatter.update_layout(dragmode='lasso')
pc_df = df.iloc[selected_indices, :]
parallel_categories = px.parallel_categories(
pc_df,
dimensions=[var1, var2, var3, var4],
color="will_readmit_for_sepsis",
labels={
var1: var1.split('_')[0].title(),
var2: var2.split('_')[0].title(),
var3: var3.split('_')[0].title(),
var4: var4.split('_')[0].title(),
})
parallel_categories.update_traces(
dimensions=([{
"categoryorder": "array",
"ticktext": ["Wasn't Diagnosed", "Was Diagnosed"]
}] * 4))
return [scatter, parallel_categories]
# -*- coding: utf-8 -*-
"""
Created on Mon Nov 23 22:37:17 2020
@author: 54963
"""
import numpy as np
import pandas as pd
import plotly as py
import plotly.express as px
import plotly.graph_objects as go
import matplotlib.pyplot as plt
#from plotly.offline import iplot, plot, init_notebook_mode
# 加载数据
flight = pd.read_csv('Flights dataset.csv')
# timesData相关信息
#flight.info()
flight.head()
fig = px.parallel_categories(flight)
fig.show()
labels={
"species_id": "Species",
"sepal_width": "Sepal Width",
"sepal_length": "Sepal Length",
"petal_width": "Petal Width",
"petal_length": "Petal Length",
},
color_continuous_scale=px.colors.diverging.Tealrose,
color_continuous_midpoint=2,
)
fig.write_html(os.path.join(dir_name, "parallel_coordinates.html"))
import plotly.express as px
tips = px.data.tips()
fig = px.parallel_categories(
tips, color="size", color_continuous_scale=px.colors.sequential.Inferno)
fig.write_html(os.path.join(dir_name, "parallel_categories.html"))
import plotly.express as px
tips = px.data.tips()
fig = px.scatter(
tips,
x="total_bill",
y="tip",
color="size",
facet_col="sex",
color_continuous_scale=px.colors.sequential.Viridis,
render_mode="webgl",
)
fig.write_html(os.path.join(dir_name, "scatter_webgl.html"))
def parallel_categories():
"""Parallel Categories Plot."""
plelcategplot=px.parallel_categories(top,color='sale_price_sqr_foot',)
return plelcategplot
# Creating Appellate results to use in visuals if requested
df["Appellate"] = np.random.randint(1, 3, size=len(df))
df.loc[df['Outcome'] == 'Granted', 'Appellate'] = 'N/A'
df.loc[df['Outcome'] == 'Denied', 'Appellate'] = 'N/A'
df.loc[df['Appellate'] == 1, 'Appellate'] = 'Appeal Granted'
df.loc[df['Appellate'] == 2, 'Appellate'] = 'Appeal Denied'
number = LabelEncoder()
df['Outcome_enc'] = number.fit_transform(df['Outcome'])
external_stylesheets = ['https://codepen.io/chriddyp/pen/bWLwgP.css']
app = dash.Dash(__name__, external_stylesheets=external_stylesheets)
fig = px.parallel_categories(
df,
dimensions=["Outcome", "Protected Ground", "Country"],
color="Outcome_enc",
color_continuous_scale=px.colors.sequential.Viridis)
app.layout = html.Div(children=[
html.H1(children='Hello Dash'),
html.Div(children='''
Dash: A web application framework for Python.
'''),
dcc.Graph(id='example-graph', figure=fig)
])
if __name__ == '__main__':
app.run_server(debug=True)
def build_sankey():
sankey_df = df[['Type_1', 'Body_Style']]
fig = px.parallel_categories(sankey_df)
return fig
# Fetch the data from all expensive neighborhoods per year.
df_expensive_neighborhoods_per_year = sfo_avg_price_by_neighborhood[
sfo_avg_price_by_neighborhood["neighborhood"].isin(
top10_neighborhoods["neighborhood"])]
df_expensive_neighborhoods_per_year.head(10)
# In[189]:
plot = px.parallel_categories(
top10_neighborhoods,
dimensions=[
'neighborhood', 'sale_price_sqr_foot', 'housing_units', 'gross_rent'
],
color='sale_price_sqr_foot',
color_continuous_scale=px.colors.sequential.Inferno,
labels={
'neighborhood': 'neighborhood',
'sale_price_sqr_foot': 'sale_price_sqr_foot',
'housing_units': 'housing_units',
'gross_rent': 'gross_rent'
},
width=1000,
)
plot.show()
# In[ ]:
# In[190]:
# Parallel Categories Plot
px.parallel_coordinates(
app.layout = html.Div([
html.Div([
html.H1(
children='Análisis Personas en Ciencia y técnica',
className='twelve columns',
style={
'textAlign': 'center',
})
]),
html.Div([dcc.Graph(id = "paralel", figure = px.parallel_categories(path))]),
html.Div([
html.Div([
dcc.Graph(
id='fig_scatter_3d',
figure = fig_scatter_3d ),
],
className="six columns",
style = {"margin-top": "5px", "margin-bottom": "10px"}
),
],
labels={
"total_enrollment": "Enrollment",
"male_num": "Male",
"female_num": "Female",
"asian_num": "Asian",
"white_num": "White",
"hispanic_num": "Hispanic",
"black_num": "Black"
},
title="7 Axes Parallel Coordinate Display for Numerical Data")),
dcc.Graph(figure=px.parallel_categories(
dataset3,
dimensions=['DBN', 'name', 'year'],
labels={
"DBN": "District Borough Number",
"name": "Name",
"year": "Year"
},
title="3 Axes Parallel Coordinate Display for Categorical Data")),
html.Br(),
dcc.Link('Go back', href='/advanced-displays')
])
pca_plot_layout = html.Div([
html.H1('PCA & Scree Plot Page', style={'text-align': 'center'}),
html.Br(),
dcc.Graph(figure=px.scatter(
components,
x=0,
y=1,
)
income_distribution = pd.read_csv(
'https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-09/income_distribution.csv'
)
income_mean = pd.read_csv(
'https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-02-09/income_mean.csv'
)
####################### parallel categories plot ###########################
import plotly.express as px
fig = px.parallel_categories(
lifetime_earn,
color="lifetime_earn",
color_continuous_scale=px.colors.sequential.Inferno,
labels={
'gender': 'Gender',
'race': 'Race',
'lifetime_earn': 'Lifetime Earnings (US$)'
})
fig.update_layout(
#autosize=False,
#width=950,
#height=1100,
#showlegend=False,
#legend_title="Legend Title",
title="Average lifetime earning by race/gender",
#title_text='Your title',
title_x=0.5,
#xaxis_title="Year",
#yaxis_title="Percent of population (persons age 25 and over)",
