def test_rplot3(self):
path = os.path.join(curpath(), 'data/tips.csv')
plt.figure()
self.data = read_csv(path, sep=',')
self.plot = rplot.RPlot(self.data, x='tip', y='total_bill')
self.plot.add(rplot.TrellisGrid(['sex', '.']))
self.plot.add(
rplot.GeomPoint(colour=rplot.ScaleRandomColour('day'),
shape=rplot.ScaleShape('size')))
self.fig = plt.gcf()
self.plot.render(self.fig)
def setUp(self):
path = os.path.join(curpath(), 'data/tips.csv')
self.data = read_csv(path, sep=',')
layer1 = rplot.Layer(self.data)
layer2 = rplot.GeomPoint(x='total_bill', y='tip')
layer3 = rplot.GeomPolyFit(2)
self.layers = rplot.sequence_layers([layer1, layer2, layer3])
self.trellis1 = rplot.TrellisGrid(['sex', 'smoker'])
self.trellis2 = rplot.TrellisGrid(['sex', '.'])
self.trellis3 = rplot.TrellisGrid(['.', 'smoker'])
self.trellised1 = self.trellis1.trellis(self.layers)
self.trellised2 = self.trellis2.trellis(self.layers)
self.trellised3 = self.trellis3.trellis(self.layers)
def test_sequence_layers(self):
layer1 = rplot.Layer(self.data)
layer2 = rplot.GeomPoint(x='SepalLength', y='SepalWidth',
size=rplot.ScaleSize('PetalLength'))
layer3 = rplot.GeomPolyFit(2)
result = rplot.sequence_layers([layer1, layer2, layer3])
self.assertEqual(len(result), 3)
last = result[-1]
self.assertEqual(last.aes['x'], 'SepalLength')
self.assertEqual(last.aes['y'], 'SepalWidth')
self.assertTrue(isinstance(last.aes['size'], rplot.ScaleSize))
self.assertTrue(self.data is last.data)
self.assertTrue(rplot.sequence_layers([layer1])[0] is layer1)
def test_rplot_iris(self):
import matplotlib.pyplot as plt
path = os.path.join(curpath(), 'data/iris.csv')
plt.figure()
self.data = read_csv(path, sep=',')
plot = rplot.RPlot(self.data, x='SepalLength', y='SepalWidth')
plot.add(rplot.GeomPoint(
colour=rplot.ScaleGradient('PetalLength',
colour1=(0.0, 1.0, 0.5),
colour2=(1.0, 0.0, 0.5)),
size=rplot.ScaleSize('PetalWidth', min_size=10.0,
max_size=200.0),
shape=rplot.ScaleShape('Name')))
self.fig = plt.gcf()
plot.render(self.fig)
# **A nonlinear classifier could separate the north from Sardinia!**
# We use the really ugly trellis rplot interface in Pandas to do some hierarchical digging. We plot oleic against linoleic. **We can split Sardinia. We might be able to split East Liguria out but there could be significant misclassification.**
# In[49]:
import pandas.tools.rplot as rplot
dfcopy = df.copy()
dfcopy['region'] = dfcopy['region'].map(rmap)
imap = {e[0]: e[1] for e in zip(df.area.unique(), df.areastring.unique())}
#dfcopy['area']=dfcopy['area'].map(imap)
plot = rplot.RPlot(dfcopy, x='linoleic', y='oleic')
plot.add(rplot.TrellisGrid(['region', '.']))
plot.add(
rplot.GeomPoint(size=40.0,
alpha=0.3,
colour=rplot.ScaleRandomColour('area')))
fig = plot.render()
print df.areastring.unique()
# ### YOUR TURN NOW (10 minutes)
# Plot palmitoleic against palimitic. **What can you separate?** Use the `dfcopy` dataframe.
# In[52]:
#your code here
plot = rplot.RPlot(dfcopy, x='palmitic', y='palmitoleic')
plot.add(rplot.TrellisGrid(['region', '.']))
plot.add(
