Computer Blindness

Background

The Pain

• you need to run the process manually each time you need a notebook (after reboot);
• you have to remember the command line arguments;
• the process takes up a terminal window/tab, or, if you run it in the background, you can accidentally close the tab and your RAM state will be lost.

The Solution

from multiprocessing import Process, Queue
import time

class AsyncFitter(object):
    def __init__(self, model):
        self.queue = Queue()
        self.model = model
        self.proc = None
        self.start_time = None

    def fit(self, x_train, y_train):
        self.terminate()
        self.proc = Process(target=AsyncFitter.async_fit_, 
            args=(self.model, x_train, y_train, self.queue))
        self.start_time = time.time()
        self.proc.start()

    def try_get_result(self):
        if self.queue.empty():
            return None

        return self.queue.get()

    def is_alive(self):
        return self.proc is not None and self.proc.is_alive()

    def terminate(self):
        if self.proc is not None and self.proc.is_alive():
            self.proc.terminate()
        self.proc = None

    def time_elapsed(self):
        if not self.start_time:
            return 0

        return time.time() - self.start_time

    @staticmethod
    def async_fit_(model, x_train, y_train, queue):
        model.fit(x_train, y_train)
        queue.put(model)

Usage

import numpy as np
from sklearn.svm import SVC

model = SVC(C = 1e3, kernel='linear')
fitter = AsyncFitter(model)
x_train = np.random.rand(500, 30)
y_train = np.random.randint(0, 2, size=(500,))
fitter.fit(x_train, y_train)