Wondering if you can help me understand where the critical flaw may be with my attempt at implementing Karger's algorithm in python. My program appears to take far too long to run and my computer starts to overwork running large sets of vertices. The purpose of the program is to output the minimum cut of the graph.
from random import choice
from statistics import mode
import math
fhand = open("mincuts.txt", "r")
vertices = fhand.readlines()
d = {}
for index,line in enumerate(vertices):
d["{0}".format(index+1)] = line.split()
def randy(graph, x):
y = str(choice(list(graph)))
if x == y:
y = randy(graph, x)
return y
count = 0
def contract(graph):
global count
if len(graph) == 2:
a = list(graph.keys())[0]
b = list(graph.keys())[1]
for i in range(1, len(graph[a])):
if graph[a][i] in graph[b]:
count = count + 1
#print(graph)
return
x = str(choice(list(graph)))
y = randy(graph, x)
#print(x)
#print(y)
graph[x] = graph[x] + graph[y]
graph.pop(y)
#remove self loops
for key in graph:
#method to remove duplicate entries in the arrays of the vertices. Source: www.w3schools.com
graph[key] = list(dict.fromkeys(graph[key]))
contract(graph)
N = len(d)
runs = int(N*N*(math.log(N)))
outcomes = []
for i in range(runs):
e = d.copy()
count = 0
contract(e)
outcomes.append(count)
print(outcomes)
#returns most common minimum cut value
print(mode(outcomes))
Below is a link to the graph I am running in mincuts.txt:
https://github.com/BigSoundCode/Misc-Algorithm-Implementations/blob/main/mincuts.txt
I'm trying to make speech recognition system with tensorflow.
Input data is an numpy array of size 50000 X 1.
Output data (mapping data) is an numpy array of size 400 X 1.
Input and mapping data is passed in batches of 2 in a list.
I've used this tutorial to design the neural network. Following is the code snippet:
For RNN:
input_data = tf.placeholder(tf.float32, [batch_size, sound_constants.MAX_ROW_SIZE_IN_DATA, sound_constants.MAX_COLUMN_SIZE_IN_DATA], name="train_input")
target = tf.placeholder(tf.float32, [batch_size, sound_constants.MAX_ROW_SIZE_IN_TXT, sound_constants.MAX_COLUMN_SIZE_IN_TXT], name="train_output")
fwd_cell = tf.nn.rnn_cell.BasicLSTMCell(num_hidden, state_is_tuple=True, forget_bias=1.0)
# creating one backward cell
bkwd_cell = tf.nn.rnn_cell.BasicLSTMCell(num_hidden, state_is_tuple=True, forget_bias=1.0)
# creating bidirectional RNN
val, _, _ = tf.nn.static_bidirectional_rnn(fwd_cell, bkwd_cell, tf.unstack(input_data), dtype=tf.float32)
For feeding data:
feed = {g['input_data'] : trb[0], g['target'] : trb[1], g['dropout'] : 0.6}
accuracy_, _ = sess.run([g['accuracy'], g['ts']], feed_dict=feed)
accuracy += accuracy_
When I ran the code, I got this error:
Traceback (most recent call last):
File "/home/wolborg/PycharmProjects/speech-to-text-rnn/src/rnn_train_1.py", line 205, in <module>
tr_losses, te_losses = train_network(g)
File "/home/wolborg/PycharmProjects/speech-to-text-rnn/src/rnn_train_1.py", line 177, in train_network
accuracy_, _ = sess.run([g['accuracy'], g['ts']], feed_dict=feed)
File "/home/wolborg/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/home/wolborg/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1102, in _run
raise ValueError('Tensor %s may not be fed.' % subfeed_t)
ValueError: Tensor Tensor("Const:0", shape=(), dtype=float32) may not be fed.
Process finished with exit code 1
Earlier, I was facing this issue with tf.sparse_placeholder, then after some browsing, I changed input type to tf.placeholder and made related changes. Now I'm clueless on where I'm making the error.
Please suggest something as how should I feed data.
Entire code:
import tensorflow as tf
# for taking MFCC and label input
import numpy as np
import rnn_input_data_1
import sound_constants
# input constants
# Training Parameters
num_input = 10 # mfcc data input
training_data_size = 8 # determines number of files in training and testing module
testing_data_size = num_input - training_data_size
# Network Parameters
learning_rate = 0.0001 # for large training set, it can be set 0.001
num_hidden = 200 # number of hidden layers
num_classes = 28 # total alphabet classes (a-z) + extra symbols (', ' ')
epoch = 1 # number of iterations
batch_size = 2 # number of batches
mfcc_coeffs, text_data = rnn_input_data_1.mfcc_and_text_encoding()
class DataGenerator:
def __init__(self, data_size):
self.ptr = 0
self.epochs = 0
self.data_size = data_size
def next_batch(self):
self.ptr += batch_size
if self.ptr > self.data_size:
self.epochs += 1
self.ptr = 0
return mfcc_coeffs[self.ptr-batch_size : self.ptr], text_data[self.ptr-batch_size : self.ptr]
def reset_graph():
if 'sess' in globals() and sess:
sess.close()
tf.reset_default_graph()
def struct_network():
print ('Inside struct network !!')
reset_graph()
input_data = tf.placeholder(tf.float32, [batch_size, sound_constants.MAX_ROW_SIZE_IN_DATA, sound_constants.MAX_COLUMN_SIZE_IN_DATA], name="train_input")
target = tf.placeholder(tf.float32, [batch_size, sound_constants.MAX_ROW_SIZE_IN_TXT, sound_constants.MAX_COLUMN_SIZE_IN_TXT], name="train_output")
keep_prob = tf.constant(1.0)
fwd_cell = tf.nn.rnn_cell.BasicLSTMCell(num_hidden, state_is_tuple=True, forget_bias=1.0)
# creating one backward cell
bkwd_cell = tf.nn.rnn_cell.BasicLSTMCell(num_hidden, state_is_tuple=True, forget_bias=1.0)
# creating bidirectional RNN
val, _, _ = tf.nn.static_bidirectional_rnn(fwd_cell, bkwd_cell, tf.unstack(input_data), dtype=tf.float32)
# adding dropouts
val = tf.nn.dropout(val, keep_prob)
val = tf.transpose(val, [1, 0, 2])
last = tf.gather(val, int(val.get_shape()[0]) - 1)
# creating bidirectional RNN
print ('BiRNN created !!')
print ('Last Size: ', last.get_shape())
weight = tf.Variable(tf.truncated_normal([num_hidden * 2, sound_constants.MAX_ROW_SIZE_IN_TXT]))
bias = tf.Variable(tf.constant(0.1, shape=[sound_constants.MAX_ROW_SIZE_IN_TXT]))
# mapping to 28 output classes
logits = tf.matmul(last, weight) + bias
prediction = tf.nn.softmax(logits)
prediction = tf.reshape(prediction, shape = [batch_size, sound_constants.MAX_ROW_SIZE_IN_TXT, sound_constants.MAX_COLUMN_SIZE_IN_TXT])
# getting probability distribution
mat1 = tf.cast(tf.argmax(prediction,1),tf.float32)
correct = tf.equal(prediction, target)
accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))
logits = tf.reshape(logits, shape=[batch_size, sound_constants.MAX_ROW_SIZE_IN_TXT, sound_constants.MAX_COLUMN_SIZE_IN_TXT])
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=target))
train_step = tf.train.AdamOptimizer(1e-4).minimize(loss)
# returning components as dictionary elements
return {'input_data' : input_data,
'target' : target,
'dropout': keep_prob,
'loss': loss,
'ts': train_step,
'preds': prediction,
'accuracy': accuracy
}
def train_network(graph):
# initialize tensorflow session and all variables
# tf_gpu_config = tf.ConfigProto(allow_soft_placement = True, log_device_placement = True)
# tf_gpu_config.gpu_options.allow_growth = True
# with tf.Session(config = tf_gpu_config) as sess:
with tf.Session() as sess:
train_instance = DataGenerator(training_data_size)
test_instance = DataGenerator(testing_data_size)
print ('Training data size: ', train_instance.data_size)
print ('Testing data size: ', test_instance.data_size)
sess.run(tf.global_variables_initializer())
print ('Starting session...')
step, accuracy = 0, 0
tr_losses, te_losses = [], []
current_epoch = 0
while current_epoch < epoch:
step += 1
trb = train_instance.next_batch()
feed = {g['input_data'] : trb[0], g['target'] : trb[1], g['dropout'] : 0.6}
accuracy_, _ = sess.run([g['accuracy'], g['ts']], feed_dict=feed)
accuracy += accuracy_
if train_instance.epochs > current_epoch:
current_epoch += 1
tr_losses.append(accuracy / step)
step, accuracy = 0, 0
#eval test set
te_epoch = test_instance.epochs
while test_instance.epochs == te_epoch:
step += 1
print ('Testing round ', step)
trc = test_instance.next_batch()
feed = {g['input_data']: trc[0], g['target']: trc[1]}
accuracy_ = sess.run([g['accuracy']], feed_dict=feed)[0]
accuracy += accuracy_
te_losses.append(accuracy / step)
step, accuracy = 0,0
print("Accuracy after epoch", current_epoch, " - tr:", tr_losses[-1], "- te:", te_losses[-1])
return tr_losses, te_losses
g = struct_network()
tr_losses, te_losses = train_network(g)
You defined keep_prob as a tf.constant, but then trying to feed the value into it. Replace keep_prob = tf.constant(1.0) with keep_prob = tf.placeholder(tf.float32,[]) or keep_prob = tf.placeholder_with_default(1.0,[])
I have copied the text file to excel sheet separating cells by ; delimiter.
I need to plot a chart using the same file which I achieved. Since all the values copied are type=str my chart gives me wrong points.
Please suggest to overcome this. Plot is should be made of int values
from datetime import date
from openpyxl import Workbook,load_workbook
from openpyxl.chart import (
LineChart,
Reference,
Series,
)
from openpyxl.chart.axis import DateAxis
excelfile = "C:\Users\lenovo\Desktop\how\openpychart.xlsx"
wb = Workbook()
ws = wb.active
f = open("C:\Users\lenovo\Desktop\sample.txt")
data = []
num = f.readlines()
for line in num:
line = line.split(";")
ws.append(line)
f.close()
wb.save(excelfile)
wb.close()
wb = load_workbook(excelfile, data_only=True)
ws = wb.active
c1 = LineChart()
c1.title = "Line Chart"
##c1.style = 13
c1.y_axis.title = 'Size'
c1.x_axis.title = 'Test Number'
data = Reference(ws, min_col=6, min_row=2, max_col=6, max_row=31)
series = Series(data, title='4th average')
c1.append(series)
data = Reference(ws, min_col=7, min_row=2, max_col=7, max_row=31)
series = Series(data, title='Defined Capacity')
c1.append(series)
##c1.add_data(data, titles_from_data=True)
# Style the lines
s1 = c1.series[0]
s1.marker.symbol = "triangle"
s1.marker.graphicalProperties.solidFill = "FF0000" # Marker filling
s1.marker.graphicalProperties.line.solidFill = "FF0000" # Marker outline
s1.graphicalProperties.line.noFill = True
s2 = c1.series[1]
s2.graphicalProperties.line.solidFill = "00AAAA"
s2.graphicalProperties.line.dashStyle = "sysDot"
s2.graphicalProperties.line.width = 100050 # width in EMUs
##s2 = c1.series[2]
##s2.smooth = True # Make the line smooth
ws.add_chart(c1, "A10")
##
##from copy import deepcopy
##stacked = deepcopy(c1)
##stacked.grouping = "stacked"
##stacked.title = "Stacked Line Chart"
##ws.add_chart(stacked, "A27")
##
##percent_stacked = deepcopy(c1)
##percent_stacked.grouping = "percentStacked"
##percent_stacked.title = "Percent Stacked Line Chart"
##ws.add_chart(percent_stacked, "A44")
##
### Chart with date axis
##c2 = LineChart()
##c2.title = "Date Axis"
##c2.style = 12
##c2.y_axis.title = "Size"
##c2.y_axis.crossAx = 500
##c2.x_axis = DateAxis(crossAx=100)
##c2.x_axis.number_format = 'd-mmm'
##c2.x_axis.majorTimeUnit = "days"
##c2.x_axis.title = "Date"
##
##c2.add_data(data, titles_from_data=True)
##dates = Reference(ws, min_col=1, min_row=2, max_row=7)
##c2.set_categories(dates)
##
##ws.add_chart(c2, "A61")
### setup and append the first series
##values = Reference(ws, (1, 1), (9, 1))
##series = Series(values, title="First series of values")
##chart.append(series)
##
### setup and append the second series
##values = Reference(ws, (1, 2), (9, 2))
##series = Series(values, title="Second series of values")
##chart.append(series)
##
##ws.add_chart(chart)
wb.save(excelfile)
wb.close()
I have modified below code in for loop and it worked.
f = open("C:\Users\lenovo\Desktop\sample.txt")
data = []
num = f.readlines()
for line in num:
line = line.split(";")
new_line=[]
for x in line:
if x.isdigit():
x=int(x)
new_line.append(x)
else:
new_line.append(x)
ws.append(new_line)
f.close()
wb.save(excelfile)
wb.close()
For each list,for each value check if its a digit, if yes converts to integer and store in another list.
Using x=map(int,x) didnt work since I have character values too.
I felt above is much more easy than using x=map(int,x) with try and Except
Thanks
Basha
I currently have a piece of code that works in two segments. The first segment opens the existing text file from a specific path on my local drive and then arranges, based on certain indices, into a list of sub list. In the second segment I take the sub-lists I have created and group them on a similar index to simplify them (starts at def merge_subs). I am getting no error code but I am not receiving a result when I try to print the variable answer. Am I not correctly looping the original list of sub-lists? Ultimately I would like to have a variable that contains the final product from these loops so that I may write the contents of it to a new text file. Here is the code I am working with:
from itertools import groupby, chain
from operator import itemgetter
with open ("somepathname") as g:
# reads text from lines and turns them into a list sub-lists
lines = g.readlines()
for line in lines:
matrix = line.split()
JD = matrix [2]
minTime= matrix [5]
maxTime= matrix [7]
newLists = [JD,minTime,maxTime]
L = newLists
def merge_subs(L):
dates = {}
for sub in L:
date = sub[0]
if date not in dates:
dates[date] = []
dates[date].extend(sub[1:])
answer = []
for date in sorted(dates):
answer.append([date] + dates[date])
new code
def openfile(self):
filename = askopenfilename(parent=root)
self.lines = open(filename)
def simplify(self):
g = self.lines.readlines()
for line in g:
matrix = line.split()
JD = matrix[2]
minTime = matrix[5]
maxTime = matrix[7]
self.newLists = [JD, minTime, maxTime]
print(self.newLists)
dates = {}
for sub in self.newLists:
date = sub[0]
if date not in dates:
dates[date] = []
dates[date].extend(sub[1:])
answer = []
for date in sorted(dates):
print(answer.append([date] + dates[date]))
enter code here
enter code here
Please could you help me by figuring out what is the wrong with my code.
I am trying to write a program that generates random walks in two dimensions and that determines statistics about the position of the walker after 500 steps when the number of walks is 1000, the max step size is 0.9, and the separation between the two positions is 0.001.
import math
import random
import time
print "RANDOM WALKS ANALYSIS IN ONE DIMENSION"
NOFW_ = 1000 #The number of walks
NOFS_= 500 #The number of steps in each walk
MSS_ = 0.9 # The maximum step size[m]
SOFP_ = 0.001 # The separation of positions considered equal[m]
print " Number of walks: %3g"% NOFW_
print " Number of steps in each Walk: %3g"% NOFS_
print " Maximum step size: %3g"% MSS_,"m"
print "Separation of positions considered equal: %3g"% SOFP_,"m"
print
print "Please wait while random walks are generated and analyzed..."
print "Date:" + time.ctime()
print
def initialPosition():
return (0.0, 0.0)
def distance(posA, posB):
"""Calculates the distance between two positions posA and posB"""
distance = math.sqrt((posB[0] - posA[0])**2 + (posB[1] - posA[1])**2)
return distance
def printstats(description, numbers):
minimum_value_ = min(numbers)
numbers.sort()
Tenth_percentile = abs(0.10*len(numbers) + 0.5)
Mean_value_ = (1./float(len(numbers))*sum(numbers))
A = 0
for values in numbers:
B = distance(values, Mean_value_)
B = B**2
A = B + A
Standard_deviation = math.sqrt((1./(len(numbers)-1))*A)
Newposition_ = int(0.90*(len(numbers) + 0.5))
Ninetieth_percentile =numbers[Newposition_]
maximum_value_ = max(numbers)
print "Analysis for"""+ description
print "Minimum value: %9.1f" % minimum_value_
print "10th percentile: %7.1f" % Tenth_percentile
print "Mean value: %12.1f" % Mean_value_
print "Standard deviation: %4.1f" % Standard_deviation
print "90th percentile: %7.1f" % Ninetieth_percentile
print "Maximum value: %9.1f" % maximum_value_
list_1 = [minimum_value_, Tenth_percentile, Mean_value_, Standard_deviation, Ninetieth_percentile,maximum_value_]
return list_1
def takeStep(prevPosition, maxStep):
x = random.random()
y = random.random()
minStep = -maxStep
Z = random.random()*2*math.pi
stepsize_ = random.random()*0.9
Stepx= stepsize_*math.cos(Z)
Stepy= stepsize_*math.sin(Z)
New_positionx = prevPosition[0] + Stepx
New_positiony = prevPosition[1] + Stepy
return (New_positionx, New_positiony)
Step_100 = []
Step_500 = []
count_list = []
for walk in range(NOFW_):
Step1 = []
Position = (0.0,0.0)
count = 0
for step in range(NOFS_):
Next_Step_ = takeStep(Position, MSS_)
for word in Step1:
if distance(Next_Step_, word) <= SOFP_:
count +=1
position = Next_Step_
Step1.append(Next_Step_)
Step_100.append(Step1[-1])
Step_500.append(Step1[-1])
count_list.append(count)
Step_100 = printstats("distance from start at step 100 [m]", Step_100)
Step_500 = printstats("distance from start at step 500 [m]", Step_500)
count_list = printstats("times position revisited", count_list)
Your problem is here
Mean_value_ = (1./float(len(numbers))*sum(numbers))
sum() is supposed to get some numbers but your variable numbers is actually containing some tuples of 2 values
You may want to define your own sum function for tuples of 2 numbers, or to sum the first values and second values separately