codeboy101

import numpy as np 
import loader

train_features, train_labels, test_features, test_labels = loader.load_images('TrainImages')
train_features = np.reshape(train_features,(500, 4000))
train_labels = np.reshape(train_labels, (500, 2))
test_features = np.reshape(test_features, (550, 4000))
test_labels = np.reshape(test_labels, (550, 2))
train_data = zip(train_features, train_labels)
test_data = zip(test_features, test_labels)

codeboy101

[ 60  76  67 ..., 253 253 243],[ 0.  1.][33 49 22 ..., 94 94 94],[ 1.  0.][ 68  68  60 ..., 227 255 255],[ 0.  1.][164 107  88 ..., 181 164 164],[ 0.  1.][ 72  63  72 ..., 205 205 205],[ 0.  1.][228 228 228 ..., 203 213 220],[ 0.  1.][223 215 215 ...,  72  91 110],[ 1.  0.][251 251 251 ...,  91  99  99],[ 1.  0.][ 54  80  94 ..., 210 196 217],[ 0.  1.][ 12  12  12 ..., 139 131 139],[ 1.  0.][ 44  60  60 ..., 204 211 211],[ 0.  1.][218 218 218 ..., 115 147  67],[ 1.  0.][185 185 185 ..., 111 111 126],[ 1.  0.][102 114 125 ...,  42  53  53],[ 1.  0.][140 188 132 ..., 251 251 251],[ 0.  1.][255 255 255 ...,  59  28   4],[ 1.  0.][116 108 164 ..., 132 139 132],[ 0.  1.][108 123  84 ..., 212 212 131],[ 1.  0.][19 19 27 ..., 83 68 68],[ 1.  0.][ 57  70  57 ...,  89 111  89],[ 0.  1.][ 99  83  68 ..., 212 212 220],[ 0.  1.][220 212 212 ...,  36  36  27],[ 1.  0.][ 35  35  44 ..., 211 211 220],[ 0.  1.][ 20 116 164 ..., 203 212 227],[ 0.  1.][123 123 116 ..., 156 163  83],[ 1.  0.][172 187 195 ..., 116 116 100],[ 1. 

codeboy101

import numpy as np 
import loader

train_features, train_labels, test_features, test_labels = loader.load_images('TrainImages')
train_features = np.reshape(train_features,(500, 4000))
train_labels = np.reshape(train_labels, (500, 2))
test_features = np.reshape(test_features, (550, 4000))
test_labels = np.reshape(test_labels, (550, 2))

train_data = zip(train_features, train_labels)

codeboy101

import numpy as np 
import loader

train_features, train_labels, test_features, test_labels = loader.load_images('TrainImages')
train_features = np.reshape(train_features,(500, 4000))
train_labels = np.reshape(train_labels, (500, 2))
test_features = np.reshape(test_features, (550, 4000))
test_labels = np.reshape(test_labels, (550, 2))

train_data = zip(train_features, train_labels)

codeboy101

import numpy as np
import os
import random
from PIL import Image

def vectorized_result(y):
	f_array = np.zeros((2, 1))
	f_array[y] = 1
	return f_array

codeboy101

import numpy as np 
import loader

train_features, train_labels, test_features, test_labels = loader.load_images('TrainImages')
train_features = np.reshape(train_features,(500, 4000))
train_labels = np.reshape(train_labels, (500, 2))
test_features = np.reshape(test_features, (550, 4000))
test_labels = np.reshape(test_labels, (550, 2))

train_data = zip(train_features, train_labels)

codeboy101

class Queue(object):
	def __init__(self):
		self.queue = []
		self.curr_size = 0

	def enqueue(self, item):
		self.queue.insert(0, item)
		self.curr_size += 1

	def dequeue(self):

codeboy101

import time
import random
from qyu import Queue

class Printer():
	def __init__(self, ppm):
		self.pagerate = ppm
		self.current_task = None
		self.time_remaining = 0

codeboy101

import numpy as np
import random

class Network(object):
    def __init__(self, sizes):
        self.num_layers = len(sizes)
        self.sizes = sizes
        self.biases = [np.random.randn(y, 1) for y in sizes[1:]]
        self.weights = [np.random.randn(y, x) for x, y in zip(sizes[:-1], sizes[1:])]

codeboy101

import numpy as np 
import pandas as pd 
import matplotlib.pyplot as plt
import time

# 1 : malignant ; 0: benign
df = pd.read_csv('data.csv')
df.drop(['id', 'Unnamed: 32'], axis=1, inplace=True)
df['diagnosis'] = df.diagnosis.map({'M':1, 'B':0})
df.insert(0, 'Ones', 1)