gist:1c6198cd663165d2dd53

def plot_roc(y, probs, threshmarkers=None):
    fpr, tpr, thresh = sklearn.metrics.roc_curve(y, probs)

    plt.plot(fpr, tpr, lw=2)
    if threshmarkers is None:
        threshmarkers = np.linspace(0, 1, 11)
    for t in threshmarkers:
        k = np.abs(thresh-t).argmin()
        x = fpr[k]
        y = tpr[k]

napsternxg

"""
Author: Shubhanshu Mishra
Posted this on the keras issue tracker at: https://github.com/fchollet/keras/issues/108
Implementing a linear regression using Keras. 
"""

from keras.models import Sequential
from keras.layers.core import Dense, Activation

model = Sequential()

slaypni

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import sys
import math

import numpy as np

sys.path.append('xgboost/wrapper/')
import xgboost as xgb

adewes

To use this bot:

• Download ads_bot.py and requirements.txt.
• Type pip install -r requirements.txt to install the requirements.
• Fill out the required information in the Python file.
• Ideally, create a (free) Slack account and set up a web hook to receive notifications from the bot.
• Run the script :)
• Relax and be ready to answer incoming calls :D

chrisdubois

import graphlab as gl
import math
import random

train = gl.SFrame.read_csv('data/train.csv')
test = gl.SFrame.read_csv('data/test.csv')
del train['id']

def make_submission(m, test, filename):
    preds = m.predict_topk(test, output_type='probability', k=9)

aronwc

""" Example using GenSim's LDA and sklearn. """

import numpy as np

from gensim import matutils
from gensim.models.ldamodel import LdaModel
from sklearn import linear_model
from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import CountVectorizer

mrdwab

stratified <- function(df, group, size, select = NULL, 
                       replace = FALSE, bothSets = FALSE) {
  if (is.null(select)) {
    df <- df
  } else {
    if (is.null(names(select))) stop("'select' must be a named list")
    if (!all(names(select) %in% names(df)))
      stop("Please verify your 'select' argument")
    temp <- sapply(names(select),
                   function(x) df[[x]] %in% select[[x]])

aras-p

// Just before switching jobs:
// Add one of these.
// Preferably into the same commit where you do a large merge.
//
// This started as a tweet with a joke of "C++ pro-tip: #define private public",
// and then it quickly escalated into more and more evil suggestions.
// I've tried to capture interesting suggestions here.
//
// Contributors: @r2d2rigo, @joeldevahl, @msinilo, @_Humus_,
// @YuriyODonnell, @rygorous, @cmuratori, @mike_acton, @grumpygiant,

kljensen

# -*- coding: utf-8 -*-
""" Small script that shows hot to do one hot encoding
    of categorical columns in a pandas DataFrame.

    See:
    http://scikit-learn.org/dev/modules/generated/sklearn.preprocessing.OneHotEncoder.html#sklearn.preprocessing.OneHotEncoder
    http://scikit-learn.org/dev/modules/generated/sklearn.feature_extraction.DictVectorizer.html
"""
import pandas
import random

marcelcaraciolo

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


def load_dataset():
    "Load the sample dataset."
    return [[1, 3, 4], [2, 3, 5], [1, 2, 3, 5], [2, 5]]


def createC1(dataset):
    "Create a list of candidate item sets of size one."