Show Sidebar Hide Sidebar

Path with L1- Logistic Regression in Scikit-learn

Computes path on IRIS dataset.

New to Plotly?

Plotly's Python library is free and open source! Get started by downloading the client and reading the primer.
You can set up Plotly to work in online or offline mode, or in jupyter notebooks.
We also have a quick-reference cheatsheet (new!) to help you get started!

Version

In [1]:
import sklearn
sklearn.__version__
Out[1]:
'0.18.1'

Imports

This tutorial imports l1_min_c.

In [2]:
import plotly.plotly as py
import plotly.graph_objs as go

from datetime import datetime
import numpy as np
from sklearn import linear_model
from sklearn import datasets
from sklearn.svm import l1_min_c

Calculations

In [3]:
iris = datasets.load_iris()
X = iris.data
y = iris.target

X = X[y != 2]
y = y[y != 2]

X -= np.mean(X, 0)

Demo path functions

In [4]:
cs = l1_min_c(X, y, loss='log') * np.logspace(0, 3)


print("Computing regularization path ...")
start = datetime.now()
clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
coefs_ = []
for c in cs:
    clf.set_params(C=c)
    clf.fit(X, y)
    coefs_.append(clf.coef_.ravel().copy())
print("This took ", datetime.now() - start)
Computing regularization path ...
('This took ', datetime.timedelta(0, 0, 60255))

Plot Results

In [5]:
coefs_ = np.array(coefs_)
y_ = []

for col in range(0, len(coefs_[0])):
    y_.append([ ])
    for row in range(0, len(coefs_)):
        y_[col].append(coefs_[row][col])
        
data = []

for i in range(1, len(y_)):
    trace = go.Scatter(x=np.log10(cs), y=y_[i], 
                       mode='lines')
    data.append(trace)


layout = go.Layout(title='Logistic Regression Path',
                   showlegend=False,
                   xaxis=dict(title='log(C)', zeroline=False),
                   yaxis=dict(title='Coefficients'))
fig = go.Figure(data=data, layout=layout)
In [6]:
py.iplot(fig)
Out[6]:

License

Author:

    Alexandre Gramfort <alexandre.gramfort@inria.fr>

License:

    BSD 3 clause
Still need help?
Contact Us

For guaranteed 24 hour response turnarounds, upgrade to a Developer Support Plan.