Skip to content

Latest commit

 

History

History
290 lines (215 loc) · 7.59 KB

distplot.md

File metadata and controls

290 lines (215 loc) · 7.59 KB
jupyter
jupytext kernelspec language_info plotly
notebook_metadata_filter text_representation
all
extension format_name format_version jupytext_version
.md
markdown
1.1
1.1.1
display_name language name
Python 3
python
python3
codemirror_mode file_extension mimetype name nbconvert_exporter pygments_lexer version
name version
ipython
3
.py
text/x-python
python
python
ipython3
3.6.7
description display_as language layout name order page_type permalink thumbnail
How to make interactive Distplots in Python with Plotly.
statistical
python
base
Distplots
4
example_index
python/distplot/
thumbnail/distplot.jpg

Combined statistical representations with px.histogram

Several representations of statistical distributions are available in plotly, such as histograms, violin plots, box plots (see the complete list here). It is also possible to combine several representations in the same plot.

For example, the plotly.express function px.histogram can add a subplot with a different statistical representation than the histogram, given by the parameter marginal. Plotly Express is the easy-to-use, high-level interface to Plotly, which operates on a variety of types of data and produces easy-to-style figures.

import plotly.express as px
df = px.data.tips()
fig = px.histogram(df, x="total_bill", y="tip", color="sex", marginal="rug",
                   hover_data=df.columns)
fig.show()
import plotly.express as px
df = px.data.tips()
fig = px.histogram(df, x="total_bill", y="tip", color="sex",
                   marginal="box", # or violin, rug
                   hover_data=df.columns)
fig.show()

Combined statistical representations with distplot figure factory

The distplot figure factory displays a combination of statistical representations of numerical data, such as histogram, kernel density estimation or normal curve, and rug plot.

Basic Distplot

A histogram, a kde plot and a rug plot are displayed.

import plotly.figure_factory as ff
import numpy as np
np.random.seed(1)

x = np.random.randn(1000)
hist_data = [x]
group_labels = ['distplot'] # name of the dataset

fig = ff.create_distplot(hist_data, group_labels)
fig.show()

Plot Multiple Datasets

import plotly.figure_factory as ff
import numpy as np

# Add histogram data
x1 = np.random.randn(200) - 2
x2 = np.random.randn(200)
x3 = np.random.randn(200) + 2
x4 = np.random.randn(200) + 4

# Group data together
hist_data = [x1, x2, x3, x4]

group_labels = ['Group 1', 'Group 2', 'Group 3', 'Group 4']

# Create distplot with custom bin_size
fig = ff.create_distplot(hist_data, group_labels, bin_size=.2)
fig.show()

Use Multiple Bin Sizes

Different bin sizes are used for the different datasets with the bin_size argument.

import plotly.figure_factory as ff
import numpy as np

# Add histogram data
x1 = np.random.randn(200)-2
x2 = np.random.randn(200)
x3 = np.random.randn(200)+2
x4 = np.random.randn(200)+4

# Group data together
hist_data = [x1, x2, x3, x4]

group_labels = ['Group 1', 'Group 2', 'Group 3', 'Group 4']

# Create distplot with custom bin_size
fig = ff.create_distplot(hist_data, group_labels, bin_size=[.1, .25, .5, 1])
fig.show()

Customize Rug Text, Colors & Title

import plotly.figure_factory as ff
import numpy as np

x1 = np.random.randn(26)
x2 = np.random.randn(26) + .5

group_labels = ['2014', '2015']

rug_text_one = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j',
                'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't',
                'u', 'v', 'w', 'x', 'y', 'z']

rug_text_two = ['aa', 'bb', 'cc', 'dd', 'ee', 'ff', 'gg', 'hh', 'ii', 'jj',
                'kk', 'll', 'mm', 'nn', 'oo', 'pp', 'qq', 'rr', 'ss', 'tt',
                'uu', 'vv', 'ww', 'xx', 'yy', 'zz']

rug_text = [rug_text_one, rug_text_two] # for hover in rug plot
colors = ['rgb(0, 0, 100)', 'rgb(0, 200, 200)']

# Create distplot with custom bin_size
fig = ff.create_distplot(
    [x1, x2], group_labels, bin_size=.2,
    rug_text=rug_text, colors=colors)

fig.update_layout(title_text='Customized Distplot')
fig.show()

Plot Normal Curve

import plotly.figure_factory as ff
import numpy as np

x1 = np.random.randn(200)
x2 = np.random.randn(200) + 2

group_labels = ['Group 1', 'Group 2']

colors = ['slategray', 'magenta']

# Create distplot with curve_type set to 'normal'
fig = ff.create_distplot([x1, x2], group_labels, bin_size=.5,
                         curve_type='normal', # override default 'kde'
                         colors=colors)

# Add title
fig.update_layout(title_text='Distplot with Normal Distribution')
fig.show()

Plot Only Curve and Rug

import plotly.figure_factory as ff
import numpy as np

x1 = np.random.randn(200) - 1
x2 = np.random.randn(200)
x3 = np.random.randn(200) + 1

hist_data = [x1, x2, x3]

group_labels = ['Group 1', 'Group 2', 'Group 3']
colors = ['#333F44', '#37AA9C', '#94F3E4']

# Create distplot with curve_type set to 'normal'
fig = ff.create_distplot(hist_data, group_labels, show_hist=False, colors=colors)

# Add title
fig.update_layout(title_text='Curve and Rug Plot')
fig.show()

Plot Only Hist and Rug

import plotly.figure_factory as ff
import numpy as np

x1 = np.random.randn(200) - 1
x2 = np.random.randn(200)
x3 = np.random.randn(200) + 1

hist_data = [x1, x2, x3]

group_labels = ['Group 1', 'Group 2', 'Group 3']
colors = ['#835AF1', '#7FA6EE', '#B8F7D4']

# Create distplot with curve_type set to 'normal'
fig = ff.create_distplot(hist_data, group_labels, colors=colors, bin_size=.25,
                         show_curve=False)

# Add title
fig.update_layout(title_text='Hist and Rug Plot')
fig.show()

Plot Hist and Rug with Different Bin Sizes

import plotly.figure_factory as ff
import numpy as np

x1 = np.random.randn(200) - 2
x2 = np.random.randn(200)
x3 = np.random.randn(200) + 2

hist_data = [x1, x2, x3]

group_labels = ['Group 1', 'Group 2', 'Group 3']
colors = ['#393E46', '#2BCDC1', '#F66095']

fig = ff.create_distplot(hist_data, group_labels, colors=colors,
                         bin_size=[0.3, 0.2, 0.1], show_curve=False)

# Add title
fig.update(layout_title_text='Hist and Rug Plot')
fig.show()

Plot Only Hist and Curve

import plotly.figure_factory as ff
import numpy as np

x1 = np.random.randn(200) - 2
x2 = np.random.randn(200)
x3 = np.random.randn(200) + 2

hist_data = [x1, x2, x3]

group_labels = ['Group 1', 'Group 2', 'Group 3']
colors = ['#A56CC1', '#A6ACEC', '#63F5EF']

# Create distplot with curve_type set to 'normal'
fig = ff.create_distplot(hist_data, group_labels, colors=colors,
                         bin_size=.2, show_rug=False)

# Add title
fig.update_layout(title_text='Hist and Curve Plot')
fig.show()

Distplot with Pandas

import plotly.figure_factory as ff
import numpy as np
import pandas as pd

df = pd.DataFrame({'2012': np.random.randn(200),
                   '2013': np.random.randn(200)+1})
fig = ff.create_distplot([df[c] for c in df.columns], df.columns, bin_size=.25)
fig.show()

Reference

For more info on ff.create_distplot(), see the full function reference