Last active
December 27, 2015 03:48
-
-
Save ggauravr/7261723 to your computer and use it in GitHub Desktop.
this code demonstrates and describes basic visualization(2 out of four features) of the Iris Dataset, provided in the sklearn package.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from matplotlib import pyplot as plt | |
from sklearn.datasets import load_iris | |
import numpy as np | |
# load the dataset to be used | |
iris = load_iris() | |
# get the 150*4 features into varibale features | |
features = iris.data | |
# optional : useful to give labels to the axes | |
feature_names = iris.feature_names | |
# holds an array of nSamples(150 in this case), with class labels(Iris Setose=0, Iris Versicolor=1, Iris Virginica=2) | |
target = iris.target | |
print feature_names # prints ['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)'] | |
# zip function returns tuples, in i-th iteration, gives tuples containing i-th element of each argument passes | |
for t, marker, c in zip(xrange(3), ">oo", "rgb"): | |
plt.scatter(features[target == t, 1], | |
features[target == t, 2], | |
marker = marker, | |
c=c) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment