Data Visualisation Principles: Tufte-Coursera

In [6]:

%matplotlib inline

In [7]:

import matplotlib as mpl
mpl.get_backend()

Out[7]:

'module://ipykernel.pylab.backend_inline'

In [8]:

import matplotlib.pyplot as plt

In [11]:

plt.plot(3, 2,"x")

Out[11]:

[<matplotlib.lines.Line2D at 0x11823b668>]

Scatter Plots¶

In [12]:

import numpy as np

x = np.array([1,2,3,4,5,6,7,8])
y = x

plt.figure()
plt.scatter(x, y) # similar to plt.plot(x, y, '.'), but the underlying child objects in the axes are not Line2D

Out[12]:

<matplotlib.collections.PathCollection at 0x1184092b0>

In [13]:

import numpy as np

x = np.array([1,2,3,4,5,6,7,8])
y = x

# create a list of colors for each point to have
# ['green', 'green', 'green', 'green', 'green', 'green', 'green', 'red']
colors = ['green']*(len(x)-1)
colors.append('red')

plt.figure()

# plot the point with size 100 and chosen colors
plt.scatter(x, y, s=100, c=colors)

Out[13]:

<matplotlib.collections.PathCollection at 0x1185241d0>

Line Plots¶

In [14]:

import numpy as np

linear_data = np.array([1,2,3,4,5,6,7,8])
exponential_data = linear_data**2

plt.figure()
# plot the linear data and the exponential data
plt.plot(linear_data, '-o', exponential_data, '-o')

Out[14]:

[<matplotlib.lines.Line2D at 0x1185aa780>,
 <matplotlib.lines.Line2D at 0x1185aa8d0>]

In [16]:

import numpy as np

linear_data = np.array([1,2,3,4,5,6,7,8])
exponential_data = linear_data**2

plt.figure()
# plot the linear data and the exponential data
plt.plot(linear_data, '-o', exponential_data, '-o')


plt.gca().fill_between(range(len(linear_data)), 
                       linear_data, exponential_data, 
                       facecolor='blue', 
                       alpha=0.25)

Out[16]:

<matplotlib.collections.PolyCollection at 0x11867b240>

In [22]:

plt.figure()
observation_dates = np.arange('2017-01-01', '2017-01-09', dtype='datetime64[D]')
observation_dates = list(map(pd.to_datetime, observation_dates)) # convert the map to a list to get rid of the error
plt.plot(observation_dates, linear_data, '-o',  observation_dates, exponential_data, '-o')

x = plt.gca().xaxis

# rotate the tick labels for the x axis
for item in x.get_ticklabels():
    item.set_rotation(90)
# adjust the subplot so the text doesn't run off the image
plt.subplots_adjust(bottom=0.25)

Bar plot¶

In [23]:

linear_data

Out[23]:

array([1, 2, 3, 4, 5, 6, 7, 8])

In [24]:

exponential_data

Out[24]:

array([ 1,  4,  9, 16, 25, 36, 49, 64])

In [33]:

plt.figure()
xvals = range(len(linear_data))
plt.bar(xvals, linear_data, width = 0.3)

Out[33]:

<Container object of 8 artists>

In [32]:

plt.figure()
xvals = range(len(linear_data))
plt.bar(xvals, linear_data, width = 0.3)
new_xvals = []
for val in xvals:
    new_xvals.append(val+0.3)
plt.bar(new_xvals, exponential_data, width = 0.3 ,color='red')

Out[32]:

<Container object of 8 artists>

Stacked bar chart¶

In [34]:

# stacked bar charts are also possible
plt.figure()
xvals = range(len(linear_data))
plt.bar(xvals, linear_data, width = 0.3, color='b')
plt.bar(xvals, exponential_data, width = 0.3, bottom=linear_data, color='r')

Out[34]:

<Container object of 8 artists>

In [40]:

# stacked bar charts are also possible
plt.figure()
xvals = range(len(linear_data))
plt.barh(xvals, linear_data, height = 0.3, color='b')
plt.barh(xvals, exponential_data, height = 0.3, left=linear_data, color='r')

Out[40]:

<Container object of 8 artists>

Exercise¶

In [41]:

import matplotlib.pyplot as plt
import numpy as np

plt.figure()

languages =['Python', 'SQL', 'Java', 'C++', 'JavaScript']
pos = np.arange(len(languages))
popularity = [56, 39, 34, 34, 29]

plt.bar(pos, popularity, align='center')
plt.xticks(pos, languages)
plt.ylabel('% Popularity')
plt.title('Top 5 Languages for Math & Data \nby % popularity on Stack Overflow', alpha=0.8)

#TODO: remove all the ticks (both axes), and tick labels on the Y axis

plt.show()

remove all the ticks (both axes), and tick labels on the Y axis¶

In [46]:

# import matplotlib.pyplot as plt
import numpy as np

plt.figure()

languages =['Python', 'SQL', 'Java', 'C++', 'JavaScript']
pos = np.arange(len(languages))
popularity = [56, 39, 34, 34, 29]

plt.bar(pos, popularity, align='center')
plt.xticks(pos, languages)
plt.ylabel('% Popularity')
plt.title('Top 5 Languages for Math & Data \nby % popularity on Stack Overflow', alpha=0.8)

# remove all the ticks (both axes), and tick labels on the Y axis
plt.tick_params(top='off', bottom='off', left='off', right='off', labelleft='off', labelbottom='on')
plt.show()

remove the frame of the chart¶

In [43]:

import matplotlib.pyplot as plt
import numpy as np

plt.figure()

languages =['Python', 'SQL', 'Java', 'C++', 'JavaScript']
pos = np.arange(len(languages))
popularity = [56, 39, 34, 34, 29]

plt.bar(pos, popularity, align='center')
plt.xticks(pos, languages)
plt.ylabel('% Popularity')
plt.title('Top 5 Languages for Math & Data \nby % popularity on Stack Overflow', alpha=0.8)

# remove all the ticks (both axes), and tick labels on the Y axis
plt.tick_params(top='off', bottom='off', left='off', right='off', labelleft='off', labelbottom='on')

# remove the frame of the chart
for spine in plt.gca().spines.values():
    spine.set_visible(False)
plt.show()

In [44]:

import matplotlib.pyplot as plt
import numpy as np

plt.figure()

languages =['Python', 'SQL', 'Java', 'C++', 'JavaScript']
pos = np.arange(len(languages))
popularity = [56, 39, 34, 34, 29]

# change the bar colors to be less bright blue
bars = plt.bar(pos, popularity, align='center', linewidth=0, color='lightslategrey')
# make one bar, the python bar, a contrasting color
bars[0].set_color('#1F77B4')

# soften all labels by turning grey
plt.xticks(pos, languages, alpha=0.8)
plt.ylabel('% Popularity', alpha=0.8)
plt.title('Top 5 Languages for Math & Data \nby % popularity on Stack Overflow', alpha=0.8)

# remove all the ticks (both axes), and tick labels on the Y axis
plt.tick_params(top='off', bottom='off', left='off', right='off', labelleft='off', labelbottom='on')

# remove the frame of the chart
for spine in plt.gca().spines.values():
    spine.set_visible(False)
plt.show()

direct label each bar with Y axis values¶

In [45]:

import matplotlib.pyplot as plt
import numpy as np

plt.figure()

languages =['Python', 'SQL', 'Java', 'C++', 'JavaScript']
pos = np.arange(len(languages))
popularity = [56, 39, 34, 34, 29]

# change the bar color to be less bright blue
bars = plt.bar(pos, popularity, align='center', linewidth=0, color='lightslategrey')
# make one bar, the python bar, a contrasting color
bars[0].set_color('#1F77B4')

# soften all labels by turning grey
plt.xticks(pos, languages, alpha=0.8)
# remove the Y label since bars are directly labeled
#plt.ylabel('% Popularity', alpha=0.8)
plt.title('Top 5 Languages for Math & Data \nby % popularity on Stack Overflow', alpha=0.8)

# remove all the ticks (both axes), and tick labels on the Y axis
plt.tick_params(top='off', bottom='off', left='off', right='off', labelleft='off', labelbottom='on')

# remove the frame of the chart
for spine in plt.gca().spines.values():
    spine.set_visible(False)
    
# direct label each bar with Y axis values
for bar in bars:
    plt.gca().text(bar.get_x() + bar.get_width()/2, bar.get_height() - 5, str(int(bar.get_height())) + '%', 
                 ha='center', color='w', fontsize=11)
plt.show()

In [ ]: