raghavrv

from types import FunctionType
import inspect

def undecorate(func):
    funcs = []
    
    # python 3.5
    if hasattr(func, '__wrapped__'):
        while hasattr(func, '__wrapped__'):
            func = func.__wrapped__

raghavrv

%%cython

# cython: wraparound=False
# cython: boundscheck=False
# cython: cdivision=True
# cython: nonecheck=False
# cython: profile=False

cimport numpy as np
import numpy as np

raghavrv

from cpython cimport Py_INCREF, PyObject
from libc.stdlib cimport malloc, free, calloc, realloc

import numpy as np
cimport numpy as np
np.import_array()

from sklearn.externals import joblib

raghavrv

cdef struct SplitRecord:
    # Data to track sample splitting process
    # This structure also store the best split found so far
    SIZE_t feature         # Which feature to split on.
    SIZE_t start
    SIZE_t end
    SIZE_t pos             # Split samples array at the given position,
                           # i.e. count of samples below threshold for feature.
                           # pos is >= end if the node is a leaf.

raghavrv

New structure of tree builders/splitter/criterion

So right now what I've come up with is this:

A new criterion (only for mse) which will compute the stats for all the nodes. The criterion design will be as much similar as possible to the old one.

Two important data structures -

• (node_stats numpy double array)

raghavrv

import os, time, gc, psutil
from pympler import tracker

import numpy as np
from sklearn.ensemble import ExtraTreesClassifier

tracker.memory_tracker = tracker.SummaryTracker()
def get_mem():
    return "{:.0f}MB".format(p.memory_info().rss / 1e6)

raghavrv

import os, time, gc, psutil
from pympler import tracker

import numpy as np
from sklearn.ensemble import RandomForestRegressor

tracker.memory_tracker = tracker.SummaryTracker()
def get_mem():
    return "{:.0f}MB".format(p.memory_info().rss / 1e6)

raghavrv

Test script

import os, time, gc, psutil
from pympler import tracker

import numpy as np
from sklearn.linear_model import LogisticRegression

tracker.memory_tracker = tracker.SummaryTracker()

raghavrv

// ==UserScript==
// @name         URL in title
// @version      0.1
// @description  try to take over the world!
// @author       Raghav RV
// @updateURL https://gist.githubusercontent.com/raghavrv/eb2f44b43ef7d3287327a5fd5e3ee205/raw/url_in_title.js
// @downloadURL https://gist.githubusercontent.com/raghavrv/eb2f44b43ef7d3287327a5fd5e3ee205/raw/url_in_title.js
// @include http://*/*
// @include https://*/*
// @grant unsafeWindow

raghavrv

Keybase proof

I hereby claim:

• I am raghavrv on github.
• I am raghavrv (https://keybase.io/raghavrv) on keybase.
• I have a public key whose fingerprint is B127 1CD1 4F49 36C3 2FD0 2992 E301 E3AA 24EB 94A7

To claim this, I am signing this object: