fabianp

#/bin/bash
source $HOME/envs/cron/bin/activate
cd $HOME/cron/nisl

# clean all previous code
rm -rf *

# clean import
git fetch origin
git reset --hard origin/master

fabianp

from __future__ import print_function
import numpy as np
from sklearn import linear_model
from datetime import datetime
import pylab as pl
import pylab


def errorfill(x, y, yerr, color=None, alpha_fill=0.3, ax=None, label=None):
    # helper function, stolen from http://tonysyu.github.com/plotting-error-bars.html

fabianp

import numpy as np
from scipy import linalg
from scipy.sparse import linalg as splinalg


def prox_l1(a, b):
    return np.sign(a) * np.fmax(np.abs(a) - b, 0)

def prox(X, t, v0, n_nonzero=1000, n=0, algo='dense', n_svals=10):
    """prox operator for trace norm

fabianp

# .. Memory benchmarks for SciPy's Singular Value Decomposition ..
# .. Author: Fabian Pedregosa <[email protected]>

import numpy as np
from scipy.sparse import linalg as splinalg
from scipy import sparse, linalg
import pylab as pl
from memory_profiler import memory_usage

dims = np.arange(500, 1500, 20)

fabianp

fabianp

import numpy as np

# Author : Fabian Pedregosa <[email protected]>
#
# License : BSD


def isotonic_regression_new(w, y, x_min=None, x_max=None):
    """
    Solve the isotonic regression with complete ordering model:

fabianp

# -*- coding: utf-8 -*-
"""
Strong rules for coordinate descent

Author: Fabian Pedregosa <[email protected]>
"""

import numpy as np
from scipy import linalg

fabianp

# -*- coding: utf-8 -*-
"""
Minimalistic implementation of l1 minimization via coordinate descent.

Reference: www.jstatsoft.org/v33/i01/paper

Author: Fabian Pedregosa <[email protected]>
"""

import numpy as np

fabianp

import numpy as np

# Author : Alexandre Gramfort
# license : BSD


def pav(y):
    """
    PAV uses the pair adjacent violators method to produce a monotonic
    smoothing of y

fabianp

import numpy as np

def isotonic_regression(w, y, x_min=None, x_max=None):
    """
    Solve the isotonic regression model:

        min Sum w_i (y_i - x_i) ** 2

        subject to x_min = x_1 <= x_2 ... <= x_n = x_max