ogrisel

# Benchmark script for a scikit-learn model that does not use
# BLAS / LAPACK routines
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.datasets import fetch_covtype
from sklearn.cross_validation import train_test_split
from time import time

seed = 0

print("Getting covertype data...")

ogrisel

All tests pass for the following setups:

- numpy on Python 3.4 64 with OPENBLAS_CORETYPE="Nehalem"
- sklearn on Python 2.7 32
- sklearn on Python 3.4 64 with OPENBLAS_CORETYPE="Nehalem"

Note: the default CORETYPE detected on those VM is "Barcelona".

ogrisel

def first_ten(np.uint32_t seed):
    cdef double *x_data_i = NULL
    cdef int *x_indices_i = NULL
    cdef int x_nnz_i = 0
    cdef double y_i = 0.0
    cdef double sw_i = 1.0
    
    n_samples = 100
    n_features = 10
    

ogrisel

import matplotlib.pyplot as plt
import pandas as pd

import theano
import theano.tensor as tt
import numpy as np
from time import time

m, k, n = 1000, 1000, 2000
A = np.random.normal(size=(m, k)).astype(np.float32)

ogrisel

*.swp
*.pyc
*.png
data/*
build

ogrisel

# Sample single piped shell unix commands to estimate the top 10 popular DBpedia resources
# by counting incoming links between matching wikipedia articles

% time curl http://downloads.dbpedia.org/3.5/en/page_links_en.nt.bz2 \
  | bzcat \
  | head -1000000  \
  | sed -e 's/.*\/\(.*\)> \./\1/' \
  | sort \
  | uniq -c  \
  | sort -nr \

ogrisel

*.pyc
mnist2500*

build/
pip-log.txt
text-documents/

ogrisel

asynchronous buffer forging
anonymous identity injection
asynchronous SQL skewing
synchronous buffer analysis
reverse jail fuzzing
tainted state inspection
multi-modal integrity recovery
deep state engineering
social state breaking
monotonic state forging

ogrisel

#!/bin/bash

sudo apt-get update
sudo apt-get install -y byobu couchdb python-pip python-lxml

sudo pip install -U tweepy couchdbkit restkit

ogrisel

"""Evaluating the impact of PCA + whitening on low rank data"""
import numpy as np
from pprint import pprint

from scikits.learn.datasets.samples_generator import make_regression_dataset
from scikits.learn.pca import PCA
from scikits.learn.linear_model import ElasticNetCV

data_opts = {
    'n_train_samples': 5000,