In [1]:
import yellowbrick as yb
import matplotlib.pyplot as plt
%matplotlib inline
plt.rcParams['figure.figsize'] = (12, 8)
from yellowbrick.features.rankd import Rank2D
from yellowbrick.features.radviz import RadViz
from yellowbrick.features.pcoords import ParallelCoordinates
from yellowbrick.features.scatter import ScatterViz
/usr/local/var/pyenv/versions/3.5.2/envs/yb-dev/lib/python3.5/site-packages/sklearn/cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20. "This module will be removed in 0.20.", DeprecationWarning)
In [2]:
import pandas as pd
url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
col_names = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species']
iris = pd.read_csv(url, header=None, names=col_names)
iris['species_num'] = iris.species.map({'Iris-setosa':0, 'Iris-versicolor':1, 'Iris-virginica':2})
In [3]:
all_features = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species_num']
features = ['petal_length', 'sepal_width']
classes = ['Iris-setosa', 'Iris-versicolor', 'Iris-virginica']
# Extract the numpy arrays from the data frame
X = iris[all_features]
y = iris.species_num.as_matrix()
In [17]:
from yellowbrick.style import palettes
from matplotlib.colors import Colormap
In [21]:
colors = palettes.PALETTES['pastel']
In [22]:
visualizer = ScatterViz(classes=classes, features=features, color=colors)
visualizer.fit(X, y) # Fit the data to the visualizer
visualizer.poof() # Draw/show/poof the data
In [7]:
visualizer.colormap
Out[7]:
['#cbd5e8', '#b3e2cd', '#fdcdac', '#f4cae4', '#fff2ae', '#e6f5c9']
In [ ]: