rmurphy2718

This post documents, for quick reference, a very simple strategy for mitigating a possible problem with GridSearchCV in sklearn. What happens if your process crashes in the middle of your grid search? You can lose everything, even hours of tuning. This post documents a very simple solution that can be set up in under a minute.

The idea, suggested on this StackOverflow post is to

1. Use a verbose option, so that sklearn prints the performance of each model after a fold finishes
2. Direct that output to a persistent file on disk.

This solution does not save all the information that is returned after fit() completes. Moreover, it does not provide a way to jump right back into the grid search where the program crashed, and relies in setting up a new search to complete the grid. However, I think we can agree it is much better than losing hours of compute, and has tremendous value for the minimal amount of work

rmurphy2718

"""
 A self-contained script in PyTorch that generates a simple dataset from a
 linear model and fits a neural network.

 Can be used as a starting script for trying out different PyTorch functionalities
 """
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

rmurphy2718

# Function to create a random permutation matrix of some size
import numpy as np


def r_pmatrix(dim):
    """
    Random Permutation Matrix (r_pmatrix)
    Create a random permutation matrix P such that PM shuffles the rows of M, for some matrix M
    :param dim: dimension of (square) permutation matrix
    :return: P, permutation matrix

rmurphy2718

#########################################################################################
# Ryan L Murphy
# Toy illustrative implementation of DEG in
# Heath & Parikh 2011, Generating random graphs with tunable clustering coefficients
# -----------------------------------------------------------------------------------
# The algorithm may get stuck for a while, this toy implementation just exits if
# there is no progress for some number of iterations
#########################################################################################

import networkx as nx

rmurphy2718

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Ryan Murphy
%
% This latex shows:
%   (1) How to make graphs using tikz
%   (2) How to align them as subfigures in a grid
%   (3) Use subfigure-level and figure-level captions
%   (4) Include a description
%   (5) Reference the figure
%

rmurphy2718

##########################################
# Ryan Murphy
# Create all binary lists of length N
# E.g.: [[0, 0], [0, 1], [1, 0], [1, 1]]
##########################################


def all_binary_lists(num):
    superset = []