neilslater

One

System: You are a helpful assistant

User: Dave can dig a hole in 5 hours, Bob can dig a hole of the same size in 4 hours, Adam can dig a hole of the same size in 3 hours. How long would they take to dig the hole if they worked together?

Assistant: To solve this problem, we can find the rate at which each person can dig the hole by calculating the fraction of the hole they can dig in one hour.

Dave's rate ## 1 hole / 5 hours ## 1/5 hole per hour Bob's rate ## 1 hole / 4 hours ## 1/4 hole per hour

neilslater

import numpy as np
import matplotlib.pyplot as plt

from keras.models import Sequential
from keras.layers import Dense, Activation
from keras.optimizers import SGD
from keras.utils import to_categorical

def get_data():
    X = np.array([[1,2], [1,12], [1,17], [9,33], [48,49], [48,50]])

neilslater

#improves the output of keras on Windows
import os
os.environ['TF_CPP_MIN_LOG_LEVEL']='3'
import tensorflow as tf
tf.logging.set_verbosity(tf.logging.ERROR)
import logging
logging.getLogger("tensorflow").setLevel(logging.WARNING)

import numpy as np
import keras as K

neilslater

# Define size of the layers, as well as the learning rate alpha and the max error
inputLayerSize = 2
hiddenLayerSize = 3
outputLayerSize = 1
alpha = 0.5
maxError = 0.001

# Import dependencies
import numpy
from sklearn import preprocessing

neilslater

# Define size of the layers, as well as the learning rate alpha and the max error
inputLayerSize = 2
hiddenLayerSize = 3
outputLayerSize = 1
alpha = 0.01
maxError = 0.001

# Import dependencies
import numpy
from sklearn import preprocessing

neilslater

# -*- coding: utf-8 -*-
import numpy as np
import os
import cv2
import pandas as pd

from sklearn.cross_validation import train_test_split
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D

neilslater

# Related to: http://rpg.stackexchange.com/questions/37270/how-can-i-get-anydice-to-determine-these-odds

require 'games_dice'

die_types = [ 4, 6, 8, 10, 12, 20 ]

die_types.each_cons(2) do |type_lower, type_upper|
  (0..6).each do |num_upper|
    num_lower = 6 - num_upper

neilslater

require 'narray'
require 'fftw3'
require 'raiff'
require 'rmagick'

# This class models audio power spectrum generation from audio sources (as .aiff files)
# An instance of this class represents a single audio clip and its spectrogram
class AudioSpectrum
  # TODO: Over time, we want to improve on these crude hard-coded values, and either take them
  # as params (e.g. number of windows, min/max frequency to store), or read from the audio file