Plotly's Python library is free and open source! Get started by dowloading the client and reading the primer.
You can set up Plotly to work in online or offline mode, or in jupyter notebooks.
We also have a quick-reference cheatsheet (new!) to help you get started!
import plotly.plotly as py
import plotly.graph_objs as go
from plotly.tools import FigureFactory as FF
import numpy as np
import pandas as pd
import scipy
We will import a dataset to perform our discrete frequency analysis on. We will look at the consumption of alcohol by country in 2010.
data = pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/2010_alcohol_consumption_by_country.csv')
df = data[0:10]
table = FF.create_table(df)
py.iplot(table, filename='alcohol-data-sample')
We can produce a histogram plot of the data with the y-axis representing the probability distribution of the data.
x = data['alcohol'].values.tolist()
trace = go.Histogram(x=x, histnorm='probability',
xbins=dict(start=np.min(x),
size=0.25,
end=np.max(x)),
marker=dict(color='rgb(25, 25, 100)'))
layout = go.Layout(
title="Histogram with Probability Distribution"
)
fig = go.Figure(data=go.Data([trace]), layout=layout)
py.iplot(fig, filename='histogram-prob-dist')
trace = go.Histogram(x=x,
xbins=dict(start=np.min(x),
size=0.25,
end=np.max(x)),
marker=dict(color='rgb(25, 25, 100)'))
layout = go.Layout(
title="Histogram with Frequency Count"
)
fig = go.Figure(data=go.Data([trace]), layout=layout)
py.iplot(fig, filename='histogram-discrete-freq-count')
trace = go.Histogram(x=x, histnorm='percent',
xbins=dict(start=np.min(x),
size=0.25,
end=np.max(x)),
marker=dict(color='rgb(50, 50, 125)'))
layout = go.Layout(
title="Histogram with Frequency Count"
)
fig = go.Figure(data=go.Data([trace]), layout=layout)
py.iplot(fig, filename='histogram-percentage')
We can also take the cumulatve sum of our dataset and then plot the cumulative density function, or CDF
, as a scatter plot
cumsum = np.cumsum(x)
trace = go.Scatter(x=[i for i in range(len(cumsum))], y=10*cumsum/np.linalg.norm(cumsum),
marker=dict(color='rgb(150, 25, 120)'))
layout = go.Layout(
title="Cumulative Distribution Function"
)
fig = go.Figure(data=go.Data([trace]), layout=layout)
py.iplot(fig, filename='cdf-dataset')
from IPython.display import display, HTML
display(HTML('<link href="//fonts.googleapis.com/css?family=Open+Sans:600,400,300,200|Inconsolata|Ubuntu+Mono:400,700" rel="stylesheet" type="text/css" />'))
display(HTML('<link rel="stylesheet" type="text/css" href="http://help.plot.ly/documentation/all_static/css/ipython-notebook-custom.css">'))
! pip install git+https://github.com/plotly/publisher.git --upgrade
import publisher
publisher.publish(
'python-Discrete-Frequency.ipynb', 'python/discrete-frequency/', 'Discrete Frequency | plotly',
'Learn how to perform discrete frequency analysis using Python.',
title='Discrete Frequency in Python. | plotly',
name='Discrete Frequency',
language='python',
page_type='example_index', has_thumbnail='false', display_as='statistics', order=3,
ipynb= '~notebook_demo/110')
Collecting git+https://github.com/plotly/publisher.git Cloning https://github.com/plotly/publisher.git to /var/folders/ld/6cl3s_l50wd40tdjq2b03jxh0000gp/T/pip-54mgFf-build Installing collected packages: publisher Found existing installation: publisher 0.10 Uninstalling publisher-0.10: Successfully uninstalled publisher-0.10 Running setup.py install for publisher ... - \ done Successfully installed publisher-0.10
/Users/brandendunbar/Desktop/test/venv/lib/python2.7/site-packages/IPython/nbconvert.py:13: ShimWarning: The `IPython.nbconvert` package has been deprecated. You should import from nbconvert instead. "You should import from nbconvert instead.", ShimWarning) /Users/brandendunbar/Desktop/test/venv/lib/python2.7/site-packages/publisher/publisher.py:53: UserWarning: Did you "Save" this notebook before running this command? Remember to save, always save. warnings.warn('Did you "Save" this notebook before running this command? '