Plotly Tutorial

What is Plotly?

Plotly allows you to create over 40 beautiful interactive web-based visualizations that can be displayed in Jupyter notebooks or saved to HTML files. It is widely used to plot scientific, statistical and financial data. Plotly is free to use unless you want them to host your data for you.

Installation

You can install using Anaconda under the environment tab by searching for Plotly. You'll also need Cufflinks and a few other packages that you can install by running : conda install -c conda-forge cufflinks-py in your command line or terminal. Also you can use the commands pip install plotly and pip install cufflinks. Cufflinks connects Plotly to Pandas.

Import

import pandas as pd
import numpy as np
import chart_studio.plotly as py
import cufflinks as cf
import seaborn as sns
import plotly.express as px
%matplotlib inline

# Make Plotly work in your Jupyter Notebook
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
init_notebook_mode(connected=True)
# Use Plotly locally
cf.go_offline()

Basics

# Create a dataframe using a NumPy array that is 50 by 4
arr_1 = np.random.randn(50, 4)
df_1 = pd.DataFrame(arr_1, columns=['A','B','C','D'])
df_1.head()

	A	B	C	D
0	-0.629896	-1.029932	1.978985	0.735458
1	-1.603906	-0.544156	0.253062	1.342460
2	0.605409	1.266526	-0.795807	-0.784913
3	1.049247	-0.147862	-0.086077	0.611336
4	-0.650904	-1.613309	-0.635976	-1.069726

# Compare old plots to a Plotly interactive plot
# You can save as PNG, Zoom, Pan, Turn off & on Data and more
df_1.plot()

<AxesSubplot:>

df_1.iplot()

Line Plots

# Allows us to create graph objects for making more customized plots
import plotly.graph_objects as go

# Use included Google price data to make one plot
df_stocks = px.data.stocks()
df_stocks.head()

	date	GOOG	AAPL	AMZN	FB	NFLX	MSFT
0	2018-01-01	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
1	2018-01-08	1.018172	1.011943	1.061881	0.959968	1.053526	1.015988
2	2018-01-15	1.032008	1.019771	1.053240	0.970243	1.049860	1.020524
3	2018-01-22	1.066783	0.980057	1.140676	1.016858	1.307681	1.066561
4	2018-01-29	1.008773	0.917143	1.163374	1.018357	1.273537	1.040708

px.line(df_stocks, x='date', y='GOOG', labels={'x':'Date', 'y':'Price'})

# Make multiple line plots
px.line(df_stocks, x='date', y=['GOOG','AAPL'], labels={'x':'Date', 'y':'Price'},
       title='Apple Vs. Google')

# Create a figure to which I'll add plots
fig = go.Figure()
# You can pull individual columns of data from the dataset and use markers or not
fig.add_trace(go.Scatter(x=df_stocks.date, y=df_stocks.AAPL, 
                        mode='lines', name='Apple'))
fig.add_trace(go.Scatter(x=df_stocks.date, y=df_stocks.AMZN, 
                        mode='lines+markers', name='Amazon'))
# You can create custom lines (Dashes : dash, dot, dashdot)
fig.add_trace(go.Scatter(x=df_stocks.date, y=df_stocks.GOOG, 
                        mode='lines+markers', name='Google',
                        line=dict(color='firebrick', width=2, dash='dashdot')))
# Further style the figure
# fig.update_layout(title='Stock Price Data 2018 - 2020',
#                    xaxis_title='Price', yaxis_title='Date')

# Go crazy styling the figure
fig.update_layout(
    # Shows gray line without grid, styling fonts, linewidths and more
    xaxis=dict(
        showline=True,
        showgrid=False,
        showticklabels=True,
        linecolor='rgb(204, 204, 204)',
        linewidth=2,
        ticks='outside',
        tickfont=dict(
            family='Arial',
            size=12,
            color='rgb(82, 82, 82)',
        ),
    ),
    # Turn off everything on y axis
    yaxis=dict(
        showgrid=False,
        zeroline=False,
        showline=False,
        showticklabels=False,
    ),
    autosize=False,
    margin=dict(
        autoexpand=False,
        l=100,
        r=20,
        t=110,
    ),
    showlegend=False,
    plot_bgcolor='white'
)

fig

Bar Charts

# Get population change in US by querying for US data
df_us = px.data.gapminder().query("country == 'United States'")
df_us.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
1608	United States	Americas	1952	68.44	157553000	13990.48208	USA	840
1609	United States	Americas	1957	69.49	171984000	14847.12712	USA	840
1610	United States	Americas	1962	70.21	186538000	16173.14586	USA	840
1611	United States	Americas	1967	70.76	198712000	19530.36557	USA	840
1612	United States	Americas	1972	71.34	209896000	21806.03594	USA	840

px.bar(df_us, x='year', y='pop')

# Create a stacked bar with more customization
df_tips = px.data.tips()
px.bar(df_tips, x='day', y='tip', color='sex', title='Tips by Sex on Each Day',
      labels={'tip': 'Tip Amount', 'day': 'Day of the Week'})

# Place bars next to each other
px.bar(df_tips, x="sex", y="total_bill",
             color='smoker', barmode='group')

# Display pop data for countries in Europe in 2007 greater than 2000000
df_europe = px.data.gapminder().query("continent == 'Europe' and year == 2007 and pop > 2.e6")
fig = px.bar(df_europe, y='pop', x='country', text='pop', color='country')
# Put bar total value above bars with 2 values of precision

fig.update_traces(texttemplate='%{text:.2s}', textposition='outside')
# Set fontsize and uniformtext_mode='hide' says to hide the text if it won't fit
fig.update_layout(uniformtext_minsize=8)
# Rotate labels 45 degrees
fig.update_layout(xaxis_tickangle=-45)

Scatter Plot

# Use included Iris data set
df_iris = px.data.iris()
df_iris.head()

	sepal_length	sepal_width	petal_length	petal_width	species	species_id
0	5.1	3.5	1.4	0.2	setosa	1
1	4.9	3.0	1.4	0.2	setosa	1
2	4.7	3.2	1.3	0.2	setosa	1
3	4.6	3.1	1.5	0.2	setosa	1
4	5.0	3.6	1.4	0.2	setosa	1

# Create a scatter plot by defining x, y, different color for count of provided
# column, size based on supplied column and additional data to display on hover
px.scatter(df_iris, x="sepal_width", y="sepal_length", color="species",
                 size='petal_length', hover_data=['petal_width'])

# Create a customized scatter with black marker edges with line width 2, opaque
# and colored based on width. Also show a scale on the right
fig = go.Figure()
fig.add_trace(go.Scatter(
    x=df_iris.sepal_width, y=df_iris.sepal_length,
    mode='markers',
    marker_color=df_iris.sepal_width,
    text=df_iris.species,
    marker=dict(showscale=True)
))
fig.update_traces(marker_line_width=2, marker_size=10)

# Working with a lot of data use Scattergl
fig = go.Figure(data=go.Scattergl(
    x = np.random.randn(100000),
    y = np.random.randn(100000),
    mode='markers',
    marker=dict(
        color=np.random.randn(100000),
        colorscale='Viridis',
        line_width=1
    )
))

fig

Pie Charts

# Create Pie chart of the largest nations in Asia
# Color maps here plotly.com/python/builtin-colorscales/
df_samer = px.data.gapminder().query("year == 2007").query("continent == 'Asia'")
df_samer.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
11	Afghanistan	Asia	2007	43.828	31889923	974.580338	AFG	4
95	Bahrain	Asia	2007	75.635	708573	29796.048340	BHR	48
107	Bangladesh	Asia	2007	64.062	150448339	1391.253792	BGD	50
227	Cambodia	Asia	2007	59.723	14131858	1713.778686	KHM	116
299	China	Asia	2007	72.961	1318683096	4959.114854	CHN	156

px.pie(df_samer, values='pop', names='country', 
       title='Population of Asian continent', 
       color_discrete_sequence=px.colors.sequential.RdBu)

# Customize pie chart
colors = ['blue', 'green', 'black', 'purple', 'red', 'brown']
fig = go.Figure(data=[go.Pie(labels=['Water','Grass','Normal','Psychic', 'Fire', 'Ground'], 
                       values=[110,90,80,80,70,60])])

# Define hover info, text size, pull amount for each pie slice, and stroke
fig.update_traces(hoverinfo='label+percent', textfont_size=20,
                  textinfo='label+percent', pull=[0.1, 0, 0.2, 0, 0, 0],
                  marker=dict(colors=colors, line=dict(color='#FFFFFF', width=2)))

Histograms

# Plot histogram based on rolling 2 dice
dice_1 = np.random.randint(1,7,5000)
dice_2 = np.random.randint(1,7,5000)
dice_sum = dice_1 + dice_2

# bins represent the number of bars to make
# Can define x label, color, title
# marginal creates another plot (violin, box, rug)
fig = px.histogram(dice_sum, nbins=11, labels={'value':'Dice Roll'},
             title='5000 Dice Roll Histogram', marginal='violin',
            color_discrete_sequence=['green'])

fig.update_layout(
    xaxis_title_text='Dice Roll',
    yaxis_title_text='Dice Sum',
    bargap=0.2, showlegend=False
)

# Stack histograms based on different column data
df_tips = px.data.tips()
df_tips.head()

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4

px.histogram(df_tips, x="total_bill", color="sex")

Box Plots

# A box plot allows you to compare different variables
# The box shows the quartiles of the data. The bar in the middle is the median 
# The whiskers extend to all the other data aside from the points that are considered
# to be outliers
df_tips = px.data.tips()
df_tips.head()

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4

# We can see which sex tips the most, points displays all the data points
px.box(df_tips, x='sex', y='tip', points='all')

# Display tip sex data by day
px.box(df_tips, x='day', y='tip', color='sex')

# Adding standard deviation and mean
fig = go.Figure()
fig.add_trace(go.Box(x=df_tips.sex, y=df_tips.tip, marker_color='blue',
                    boxmean='sd'))

# Complex Styling
df_stocks = px.data.stocks()
df_stocks.head()

	date	GOOG	AAPL	AMZN	FB	NFLX	MSFT
0	2018-01-01	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
1	2018-01-08	1.018172	1.011943	1.061881	0.959968	1.053526	1.015988
2	2018-01-15	1.032008	1.019771	1.053240	0.970243	1.049860	1.020524
3	2018-01-22	1.066783	0.980057	1.140676	1.016858	1.307681	1.066561
4	2018-01-29	1.008773	0.917143	1.163374	1.018357	1.273537	1.040708

fig = go.Figure()
# Show all points, spread them so they don't overlap and change whisker width
fig.add_trace(go.Box(y=df_stocks.GOOG, boxpoints='all', name='Google',
                    fillcolor='blue', jitter=0.5, whiskerwidth=0.2))
fig.add_trace(go.Box(y=df_stocks.AAPL, boxpoints='all', name='Apple',
                    fillcolor='red', jitter=0.5, whiskerwidth=0.2))
# Change background / grid colors
fig.update_layout(title='Google vs. Apple', 
                  yaxis=dict(gridcolor='rgb(255, 255, 255)',
                 gridwidth=3),
                 paper_bgcolor='rgb(243, 243, 243)',
                 plot_bgcolor='rgb(243, 243, 243)')

Violin Plot

# Violin Plot is a combination of the boxplot and KDE
# While a box plot corresponds to data points, the violin plot uses the KDE estimation
# of the data points
df_tips = px.data.tips()
df_tips.head()

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4

px.violin(df_tips, y="total_bill", box=True, points='all')

# Multiple plots
px.violin(df_tips, y="tip", x="smoker", color="sex", box=True, points="all",
          hover_data=df_tips.columns)

# Morph left and right sides based on if the customer smokes
fig = go.Figure()
fig.add_trace(go.Violin(x=df_tips['day'][ df_tips['smoker'] == 'Yes' ],
                        y=df_tips['total_bill'][ df_tips['smoker'] == 'Yes' ],
                        legendgroup='Yes', scalegroup='Yes', name='Yes',
                        side='negative',
                        line_color='blue'))
fig.add_trace(go.Violin(x=df_tips['day'][ df_tips['smoker'] == 'No' ],
                        y=df_tips['total_bill'][ df_tips['smoker'] == 'No' ],
                        legendgroup='Yes', scalegroup='Yes', name='No',
                        side='positive',
                        line_color='red'))

Density Heatmap

# Create a heatmap using Seaborn data
flights = sns.load_dataset("flights")
flights.head()

	year	month	passengers
0	1949	Jan	112
1	1949	Feb	118
2	1949	Mar	132
3	1949	Apr	129
4	1949	May	121

# You can set bins with nbinsx and nbinsy
fig = px.density_heatmap(flights, x='year', y='month', z='passengers', 
                         color_continuous_scale="Viridis")
fig

# You can add histograms
fig = px.density_heatmap(flights, x='year', y='month', z='passengers', 
                         marginal_x="histogram", marginal_y="histogram")
fig

3D Scatter Plots

# Create a 3D scatter plot using flight data
fig = px.scatter_3d(flights, x='year', y='month', z='passengers', color='year',
                   opacity=0.7, width=800, height=400)
fig

3D Line Plots

fig = px.line_3d(flights, x='year', y='month', z='passengers', color='year')
fig

Scatter Matrix

# With a scatter matrix we can compare changes when comparing column data
fig = px.scatter_matrix(flights, color='month')
fig

Map Scatter Plots

# There are many interesting ways of working with maps
# plotly.com/python-api-reference/generated/plotly.express.scatter_geo.html
df = px.data.gapminder().query("year == 2007")
fig = px.scatter_geo(df, locations="iso_alpha",
                     color="continent", # which column to use to set the color of markers
                     hover_name="country", # column added to hover information
                     size="pop", # size of markers
                     projection="orthographic")

fig

Choropleth Maps

# You can color complex maps like we do here representing unemployment data

# Allows us to grab data from a supplied URL
from urllib.request import urlopen
# Used to decode JSON data
import json
# Grab US county geometry data
with urlopen('https://raw.githubusercontent.com/plotly/datasets/master/geojson-counties-fips.json') as response:
    counties = json.load(response)

# Grab unemployment data based on each counties Federal Information Processing number
df = pd.read_csv("https://raw.githubusercontent.com/plotly/datasets/master/fips-unemp-16.csv",
                   dtype={"fips": str})
df.head()

---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
D:\software_install\anaconda\lib\urllib\request.py in do_open(self, http_class, req, **http_conn_args)
   1349             try:
-> 1350                 h.request(req.get_method(), req.selector, req.data, headers,
   1351                           encode_chunked=req.has_header('Transfer-encoding'))

D:\software_install\anaconda\lib\http\client.py in request(self, method, url, body, headers, encode_chunked)
   1254         """Send a complete request to the server."""
-> 1255         self._send_request(method, url, body, headers, encode_chunked)
   1256 

D:\software_install\anaconda\lib\http\client.py in _send_request(self, method, url, body, headers, encode_chunked)
   1300             body = _encode(body, 'body')
-> 1301         self.endheaders(body, encode_chunked=encode_chunked)
   1302 

D:\software_install\anaconda\lib\http\client.py in endheaders(self, message_body, encode_chunked)
   1249             raise CannotSendHeader()
-> 1250         self._send_output(message_body, encode_chunked=encode_chunked)
   1251 

D:\software_install\anaconda\lib\http\client.py in _send_output(self, message_body, encode_chunked)
   1009         del self._buffer[:]
-> 1010         self.send(msg)
   1011 

D:\software_install\anaconda\lib\http\client.py in send(self, data)
    949             if self.auto_open:
--> 950                 self.connect()
    951             else:

D:\software_install\anaconda\lib\http\client.py in connect(self)
   1423 
-> 1424             self.sock = self._context.wrap_socket(self.sock,
   1425                                                   server_hostname=server_hostname)

D:\software_install\anaconda\lib\ssl.py in wrap_socket(self, sock, server_side, do_handshake_on_connect, suppress_ragged_eofs, server_hostname, session)
    499         # ctx._wrap_socket()
--> 500         return self.sslsocket_class._create(
    501             sock=sock,

D:\software_install\anaconda\lib\ssl.py in _create(cls, sock, server_side, do_handshake_on_connect, suppress_ragged_eofs, server_hostname, context, session)
   1039                         raise ValueError("do_handshake_on_connect should not be specified for non-blocking sockets")
-> 1040                     self.do_handshake()
   1041             except (OSError, ValueError):

D:\software_install\anaconda\lib\ssl.py in do_handshake(self, block)
   1308                 self.settimeout(None)
-> 1309             self._sslobj.do_handshake()
   1310         finally:

FileNotFoundError: [Errno 2] No such file or directory

During handling of the above exception, another exception occurred:

URLError                                  Traceback (most recent call last)
<ipython-input-49-c9555274605d> in <module>
      6 import json
      7 # Grab US county geometry data
----> 8 with urlopen('https://raw.githubusercontent.com/plotly/datasets/master/geojson-counties-fips.json') as response:
      9     counties = json.load(response)
     10 

D:\software_install\anaconda\lib\urllib\request.py in urlopen(url, data, timeout, cafile, capath, cadefault, context)
    220     else:
    221         opener = _opener
--> 222     return opener.open(url, data, timeout)
    223 
    224 def install_opener(opener):

D:\software_install\anaconda\lib\urllib\request.py in open(self, fullurl, data, timeout)
    523 
    524         sys.audit('urllib.Request', req.full_url, req.data, req.headers, req.get_method())
--> 525         response = self._open(req, data)
    526 
    527         # post-process response

D:\software_install\anaconda\lib\urllib\request.py in _open(self, req, data)
    540 
    541         protocol = req.type
--> 542         result = self._call_chain(self.handle_open, protocol, protocol +
    543                                   '_open', req)
    544         if result:

D:\software_install\anaconda\lib\urllib\request.py in _call_chain(self, chain, kind, meth_name, *args)
    500         for handler in handlers:
    501             func = getattr(handler, meth_name)
--> 502             result = func(*args)
    503             if result is not None:
    504                 return result

D:\software_install\anaconda\lib\urllib\request.py in https_open(self, req)
   1391 
   1392         def https_open(self, req):
-> 1393             return self.do_open(http.client.HTTPSConnection, req,
   1394                 context=self._context, check_hostname=self._check_hostname)
   1395 

D:\software_install\anaconda\lib\urllib\request.py in do_open(self, http_class, req, **http_conn_args)
   1351                           encode_chunked=req.has_header('Transfer-encoding'))
   1352             except OSError as err: # timeout error
-> 1353                 raise URLError(err)
   1354             r = h.getresponse()
   1355         except:

URLError: <urlopen error [Errno 2] No such file or directory>

# Draw map using the county JSON data, color using unemployment values on a range of 12
fig = px.choropleth(df, geojson=counties, locations='fips', color='unemp',
                           color_continuous_scale="Viridis",
                           range_color=(0, 12),
                           scope="usa",
                           labels={'unemp':'unemployment rate'}
                          )
fig

Polar Chart

# Polar charts display data radially 
# Let's plot wind data based on direction and frequency
# You can change size and auto-generate different symbols as well
df_wind = px.data.wind()
df_wind.head()

	direction	strength	frequency
0	N	0-1	0.5
1	NNE	0-1	0.6
2	NE	0-1	0.5
3	ENE	0-1	0.4
4	E	0-1	0.4

px.scatter_polar(df_wind, r="frequency", theta="direction", color="strength",
                size="frequency", symbol="strength")

# Data can also be plotted using lines radially
# A template makes the data easier to see
px.line_polar(df_wind, r="frequency", theta="direction", color="strength",
                line_close=True, template="plotly_dark", width=800, height=400)

Ternary Plot

# Used to represent ratios of 3 variables
df_exp = px.data.experiment()
df_exp.head()

	experiment_1	experiment_2	experiment_3	gender	group
0	96.876065	93.417942	73.033193	male	control
1	87.301336	129.603395	66.056554	female	control
2	97.691312	106.187916	103.422709	male	treatment
3	102.978152	93.814682	56.995870	female	treatment
4	87.106993	107.019985	72.140292	male	control

px.scatter_ternary(df_exp, a="experiment_1", b="experiment_2", 
                   c='experiment_3', hover_name="group", color="gender")

Facets

# You can create numerous subplots
df_tips = px.data.tips()
df_tips.head()

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4

px.scatter(df_tips, x="total_bill", y="tip", color="smoker", facet_col="sex")

# We can line up data in rows and columns
px.histogram(df_tips, x="total_bill", y="tip", color="sex", facet_row="time", facet_col="day",
       category_orders={"day": ["Thur", "Fri", "Sat", "Sun"], "time": ["Lunch", "Dinner"]})

# This dataframe provides scores for different students based on the level
# of attention they could provide during testing
att_df = sns.load_dataset("attention")
att_df.head()

	Unnamed: 0	subject	attention	solutions	score
0	0	1	divided	1	2.0
1	1	2	divided	1	3.0
2	2	3	divided	1	3.0
3	3	4	divided	1	5.0
4	4	5	divided	1	4.0

fig = px.line(att_df, x='solutions', y='score', facet_col='subject',
             facet_col_wrap=5, title='Scores Based on Attention')
fig

Animated Plots

# Create an animated plot that you can use to cycle through continent
# GDP & life expectancy changes
df_cnt = px.data.gapminder()
df_cnt.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
0	Afghanistan	Asia	1952	28.801	8425333	779.445314	AFG	4
1	Afghanistan	Asia	1957	30.332	9240934	820.853030	AFG	4
2	Afghanistan	Asia	1962	31.997	10267083	853.100710	AFG	4
3	Afghanistan	Asia	1967	34.020	11537966	836.197138	AFG	4
4	Afghanistan	Asia	1972	36.088	13079460	739.981106	AFG	4

px.scatter(df_cnt, x="gdpPercap", y="lifeExp", animation_frame="year", 
           animation_group="country",
           size="pop", color="continent", hover_name="country",
           log_x=True, size_max=55, range_x=[100,100000], range_y=[25,90])

# Watch as bars chart population changes
px.bar(df_cnt, x="continent", y="pop", color="continent",
  animation_frame="year", animation_group="country", range_y=[0,4000000000])

References

• https://github.com/derekbanas/plotly-tutorial