sswt

import time
import numpy as np
nl = np.random.randint(0, 1000, 9*10**6).reshape((3000,3000))

def sq_euclidean(X):
    XX = np.sum(X * X, axis=1)[:, np.newaxis]
    Y = X
    YY = XX.T
    distances = np.dot(X, Y.T)
    distances *= -2

sswt

def eval_map(yhat, dtrain):
    inds = (-yhat).argsort(kind='mergesort')
    X = np.vstack([dtrain.data['display_id'], dtrain.get_label()]).T
    X = X[inds[X[inds, 0].argsort(kind='mergesort')]]
    y_ind = np.where(X[:, 1] == 1)[0]
    y_pr = np.unique(X[:, 0], return_index=True)[1]
    return 'map@12_ob', np.mean(1 / (y_ind - y_pr + 1)), True

sswt

Latency Comparison Numbers (~2012)
----------------------------------
L1 cache reference                           0.5 ns
Branch mispredict                            5   ns
L2 cache reference                           7   ns                      14x L1 cache
Mutex lock/unlock                           25   ns
Main memory reference                      100   ns                      20x L2 cache, 200x L1 cache
Compress 1K bytes with Zippy             3,000   ns        3 us
Send 1K bytes over 1 Gbps network       10,000   ns       10 us
Read 4K randomly from SSD*             150,000   ns      150 us          ~1GB/sec SSD

sswt

# -*- coding: utf-8 -*-

""" Deletes all tweets below a certain retweet threshold.
"""

import tweepy
from datetime import datetime

# Constants
CONSUMER_KEY = ''