In [1]:
%matplotlib inline
import numpy as np
import pandas as pd
import pandas.tools.rplot as rplot
import matplotlib.pyplot as plt
import seaborn as sns
c:\users\vdbosscj\scipy\pandas-joris\pandas\tools\rplot.py:20: FutureWarning: The rplot trellis plotting interface is deprecated and will be removed in a future version. We refer to external packages like seaborn for similar but more refined functionality. See our docs http://pandas.pydata.org/pandas-docs/stable/visualization.html#rplot for some example how to convert your existing code to these packages. "packages.", FutureWarning)
In [2]:
print "pandas: ", pd.__version__
print "seaborn: ", sns.__version__
pandas: 0.15.2-254-g85703a7 seaborn: 0.5.1
In [3]:
tips_data = pd.read_csv('http://wesmckinney.com/files/tips.csv')
Example 1 - histograms for grid of sex+smoker¶
In [4]:
plot = rplot.RPlot(tips_data, x='total_bill', y='tip')
plot.add(rplot.TrellisGrid(['sex', 'smoker']))
plot.add(rplot.GeomHistogram())
plot.render();
In [5]:
g = sns.FacetGrid(tips_data, row="sex", col="smoker")
g.map(plt.hist, "total_bill")
Out[5]:
<seaborn.axisgrid.FacetGrid at 0x18234ef0>
Example 2 - kernel density for grid of sex+smoker¶
In [6]:
plot = rplot.RPlot(tips_data, x='total_bill', y='tip')
plot.add(rplot.TrellisGrid(['sex', 'smoker']))
plot.add(rplot.GeomDensity())
plot.render();
In [7]:
g = sns.FacetGrid(tips_data, row="sex", col="smoker")
g.map(sns.kdeplot, "total_bill")
Out[7]:
<seaborn.axisgrid.FacetGrid at 0x187b2fd0>
Example 3 - scatter plot with polyfit regression on grid of sex+smoker¶
In [8]:
plot = rplot.RPlot(tips_data, x='total_bill', y='tip')
plot.add(rplot.TrellisGrid(['sex', 'smoker']))
plot.add(rplot.GeomScatter())
plot.add(rplot.GeomPolyFit(degree=2))
plot.render();
The scatter plot:
In [9]:
g = sns.FacetGrid(tips_data, row="sex", col="smoker")
g.map(plt.scatter, "total_bill", "tip")
Out[9]:
<seaborn.axisgrid.FacetGrid at 0x183e7eb8>
With regression line, using the dedicated regplot function of seaborn:
In [10]:
g = sns.FacetGrid(tips_data, row="sex", col="smoker", margin_titles=True)
g.map(sns.regplot, "total_bill", "tip", order=2)
Out[10]:
<seaborn.axisgrid.FacetGrid at 0x1b34c940>
Example 4 - 2D kernel density on grid of sex+smoker¶
In [11]:
plot = rplot.RPlot(tips_data, x='total_bill', y='tip')
plot.add(rplot.TrellisGrid(['sex', 'smoker']))
plot.add(rplot.GeomScatter())
plot.add(rplot.GeomDensity2D())
plot.render();
The colors above are not correct, because seaborn altered the default colormaps. See http://pandas.pydata.org/pandas-docs/stable/visualization.html#trellis-plotting-interface for correct colors
In [12]:
g = sns.FacetGrid(tips_data, row="sex", col="smoker")
g.map(plt.scatter, "total_bill", "tip")
g.map(sns.kdeplot, "total_bill", "tip")
Out[12]:
<seaborn.axisgrid.FacetGrid at 0x1a533da0>
Example 5 - grid with one attribute¶
In [13]:
plot = rplot.RPlot(tips_data, x='total_bill', y='tip')
plot.add(rplot.TrellisGrid(['sex', '.']))
plot.add(rplot.GeomHistogram())
plot.render();
In [14]:
g = sns.FacetGrid(tips_data, col="sex")
g.map(plt.hist, "total_bill")
Out[14]:
<seaborn.axisgrid.FacetGrid at 0x1b687048>
In [15]:
g = sns.FacetGrid(tips_data, row="sex")
g.map(plt.hist, "total_bill")
Out[15]:
<seaborn.axisgrid.FacetGrid at 0x19b57630>
Example 6 - scatterplot with third and fourth variable¶
In [16]:
plot = rplot.RPlot(tips_data, x='tip', y='total_bill')
plot.add(rplot.TrellisGrid(['sex', 'smoker']))
plot.add(rplot.GeomPoint(size=80.0, colour=rplot.ScaleRandomColour('day'), shape=rplot.ScaleShape('size'), alpha=1.0))
plot.render();
In [17]:
g = sns.FacetGrid(tips_data, row="sex", col="smoker", hue="day")
g.map(plt.scatter, "tip", "total_bill")
g.add_legend()
Here, in the seaborn example, the fourth variable is not included
In [ ]: