Python increase performance of random.sample - python

I am writing a function to select randomly elements stored in a dictionary:
import random
from liblas import file as lasfile
from collections import defaultdict
def point_random_selection(list,k):
try:
sample_point = random.sample(list,k)
except ValueError:
sample_point = list
return(sample_point)
def world2Pixel_Id(x,y,X_Min,Y_Max,xDist,yDist):
col = int((x - X_Min)/xDist)
row = int((Y_Max - y)/yDist)
return("{0}_{1}".format(col,row))
def point_GridGroups(inFile,X_Min,Y_Max,xDist,yDist):
Groups = defaultdict(list)
for p in lasfile.File(inFile,None,'r'):
id = world2Pixel_Id(p.x,p.y,X_Min,Y_Max,xDist,yDist)
Groups[id].append(p)
return(Groups)
where k is the number of element to select. Groups is the dictionary
file_out = lasfile.File("outPut",mode='w',header= h)
for m in Groups.iteritems():
# select k point for each dictionary key
point_selected = point_random_selection(m[1],k)
for l in xrange(len(point_selected)):
# save the data
file_out.write(point_selected[l])
file_out.close()
My problem is that this approach is extremely slow (for file of ~800 Mb around 4 days)

You could try and update your samples as you read the coordinates. This at least saves you from having to store everything in memory before running your sample. This is not guaranteed to make things faster.
The following is based off of BlkKnght's excellent answer to build a random sample from file input without retaining all the lines. This just expanded it to keep multiple samples instead.
import random
from liblas import file as lasfile
from collections import defaultdict
def world2Pixel_Id(x, y, X_Min, Y_Max, xDist, yDist):
col = int((x - X_Min) / xDist)
row = int((Y_Max - y) / yDist)
return (col, row)
def random_grouped_samples(infile, n, X_Min, Y_Max, xDist, yDist):
"""Select up to n points *per group* from infile"""
groupcounts = defaultdict(int)
samples = defaultdict(list)
for p in lasfile.File(inFile, None, 'r'):
id = world2Pixel_Id(p.x, p.y, X_Min, Y_Max, xDist, yDist)
i = groupcounts[id]
r = random.randint(0, i)
if r < n:
if i < n:
samples[id].insert(r, p) # add first n items in random order
else:
samples[id][r] = p # at a decreasing rate, replace random items
groupcounts[id] += 1
return samples
The above function takes inFile and your boundary coordinates, as well as the sample size n, and returns grouped samples that have at most n items in each group, picked uniformly.
Because all you use the id for is as a group key, I reduced it to only calculating the col, row tuple, there is no need to make it a string.
You can write these out to a file with:
file_out = lasfile.File("outPut",mode='w',header= h)
for group in samples.itervalues():
for p in group:
file_out.write(p)
file_out.close()

Related

Unique ordered ratio of integers

I have two ordered lists of consecutive integers m=0, 1, ... M and n=0, 1, 2, ... N. Each value of m has a probability pm, and each value of n has a probability pn. I am trying to find the ordered list of unique values r=n/m and their probabilities pr. I am aware that r is infinite if n=0 and can even be undefined if m=n=0.
In practice, I would like to run for M and N each be of the order of 2E4, meaning up to 4E8 values of r - which would mean 3 GB of floats (assuming 8 Bytes/float).
For this calculation, I have written the python code below.
The idea is to iterate over m and n, and for each new m/n, insert it in the right place with its probability if it isn't there yet, otherwise add its probability to the existing number. My assumption is that it is easier to sort things on the way instead of waiting until the end.
The cases related to 0 are added at the end of the loop.
I am using the Fraction class since we are dealing with fractions.
The code also tracks the multiplicity of each unique value of m/n.
I have tested up to M=N=100, and things are quite slow. Are there better approaches to the question, or more efficient ways to tackle the code?
Timing:
M=N=30: 1 s
M=N=50: 6 s
M=N=80: 30 s
M=N=100: 82 s
import numpy as np
from fractions import Fraction
import time # For timiing
start_time = time.time() # Timing
M, N = 6, 4
mList, nList = np.arange(1, M+1), np.arange(1, N+1) # From 1 to M inclusive, deal with 0 later
mProbList, nProbList = [1/(M+1)]*(M), [1/(N+1)]*(N) # Probabilities, here assumed equal (not general case)
# Deal with mn=0 later
pmZero, pnZero = 1/(M+1), 1/(N+1) # P(m=0) and P(n=0)
pNaN = pmZero * pnZero # P(0/0) = P(m=0)P(n=0)
pZero = pmZero * (1 - pnZero) # P(0) = P(m=0)P(n!=0)
pInf = pnZero * (1 - pmZero) # P(inf) = P(m!=0)P(n=0)
# Main list of r=m/n, P(r) and mult(r)
# Start with first line, m=1
rList = [Fraction(mList[0], n) for n in nList[::-1]] # Smallest first
rProbList = [mProbList[0] * nP for nP in nProbList[::-1]] # Start with first line
rMultList = [1] * len(rList) # Multiplicity of each element
# Main loop
for m, mP in zip(mList[1:], mProbList[1:]):
for n, nP in zip(nList[::-1], nProbList[::-1]): # Pick an n value
r, rP, rMult = Fraction(m, n), mP*nP, 1
for i in range(len(rList)-1): # See where it fits in existing list
if r < rList[i]:
rList.insert(i, r)
rProbList.insert(i, rP)
rMultList.insert(i, 1)
break
elif r == rList[i]:
rProbList[i] += rP
rMultList[i] += 1
break
elif r < rList[i+1]:
rList.insert(i+1, r)
rProbList.insert(i+1, rP)
rMultList.insert(i+1, 1)
break
elif r == rList[i+1]:
rProbList[i+1] += rP
rMultList[i+1] += 1
break
if r > rList[-1]:
rList.append(r)
rProbList.append(rP)
rMultList.append(1)
break
# Deal with 0
rList.insert(0, Fraction(0, 1))
rProbList.insert(0, pZero)
rMultList.insert(0, N)
# Deal with infty
rList.append(np.Inf)
rProbList.append(pInf)
rMultList.append(M)
# Deal with undefined case
rList.append(np.NAN)
rProbList.append(pNaN)
rMultList.append(1)
print(".... done in %s seconds." % round(time.time() - start_time, 2))
print("************** Final list\nr", 'Prob', 'Mult')
for r, rP, rM in zip(rList, rProbList, rMultList): print(r, rP, rM)
print("************** Checks")
print("mList", mList, 'nList', nList)
print("Sum of proba = ", np.sum(rProbList))
print("Sum of multi = ", np.sum(rMultList), "\t(M+1)*(N+1) = ", (M+1)*(N+1))
Based on the suggestion of #Prune, and on this thread about merging lists of tuples, I have modified the code as below. It's a lot easier to read, and runs about an order of magnitude faster for N=M=80 (I have omitted dealing with 0 - would be done same way as in original post). I assume there may be ways to tweak the merge and conversion back to lists further yet.
# Do calculations
data = [(Fraction(m, n), mProb(m) * nProb(n)) for n in range(1, N+1) for m in range(1, M+1)]
data.sort()
# Merge duplicates using a dictionary
d = {}
for r, p in data:
if not (r in d): d[r] = [0, 0]
d[r][0] += p
d[r][1] += 1
# Convert back to lists
rList, rProbList, rMultList = [], [], []
for k in d:
rList.append(k)
rProbList.append(d[k][0])
rMultList.append(d[k][1])
I expect that "things are quite slow" because you've chosen a known inefficient sort. A single list insertion is O(K) (later list elements have to be bumped over, and there is added storage allocation on a regular basis). Thus a full-list insertion sort is O(K^2). For your notation, that is O((M*N)^2).
If you want any sort of reasonable performance, research and use the best-know methods. The most straightforward way to do this is to make your non-exception results as a simple list comprehension, and use the built-in sort for your penultimate list. Simply append your n=0 cases, and you're done in O(K log K) time.
I the expression below, I've assumed functions for m and n probabilities.
This is a notational convenience; you know how to directly compute them, and can substitute those expressions if you wish.
data = [ (mProb(m) * nProb(n), Fraction(m, n))
for n in range(1, N+1)
for m in range(0, M+1) ]
data.sort()
data.extend([ # generate your "zero" cases here ])

Grouping pairs of combination data based on given condition

Suppose I have a huge array of data and sample of them are :
x= [ 511.31, 512.24, 571.77, 588.35, 657.08, 665.49, -1043.45, -1036.56,-969.39, -955.33]
I used the following code to generate all possible pairs
Pairs=[(x[i],x[j]) for i in range(len(x)) for j in range(i+1, len(x))]
Which gave me all possible pairs. Now, I would like to group these pairs if they are within threshold values of -25 or +25 and label them accordingly.
Any idea or advice on how to do this? Thanks in advance
If I understood correctly your problem, the code below should do the trick. The idea is to generate a dictionary whose keys are the mean value, and just keep appending data onto it:
import numpy as np #I use numpy for the mean.
#Your threshold
threshold = 25
#A dictionary will hold the relevant pairs
mylist = {}
for i in Pairs:
#Check for the threshold and discard otherwise
diff = abs(i[1]-i[0])
if(diff < threshold):
#Name of the entry in the dictionary
entry = str('%d'%int(np.mean(i)))
#If the entry already exists, append. Otherwise, create a container list
if(entry in mylist):
mylist[entry].append(i)
else:
mylist[entry] = [i]
which results in the following output:
{'-1040': [(-1043.45, -1036.56)],
'-962': [(-969.39, -955.33)],
'511': [(511.1, 511.31),
(511.1, 512.24),
(511.1, 512.35),
(511.31, 512.24),
(511.31, 512.35)],
'512': [(511.1, 513.35),
(511.31, 513.35),
(512.24, 512.35),
(512.24, 513.35),
(512.35, 513.35)],
'580': [(571.77, 588.35)],
'661': [(657.08, 665.49)]}
This should be a fast way to do that:
import numpy as np
from scipy.spatial.distance import pdist
# Input data
x = np.array([511.31, 512.24, 571.77, 588.35, 657.08,
665.49, -1043.45, -1036.56,-969.39, -955.33])
thres = 25.0
# Compute pairwise distances
# default distance metric is'euclidean' which
# would be equivalent but more expensive to compute
d = pdist(x[:, np.newaxis], 'cityblock')
# Find distances within threshold
d_idx = np.where(d <= thres)[0]
# Convert "condensed" distance indices to pair of indices
r = np.arange(len(x))
c = np.zeros_like(r, dtype=np.int32)
np.cumsum(r[:0:-1], out=c[1:])
i = np.searchsorted(c[1:], d_idx, side='right')
j = d_idx - c[i] + r[i] + 1
# Get pairs of values
v_i = x[i]
v_j = x[j]
# Find means
m = np.round((v_i + v_j) / 2).astype(np.int32)
# Print result
for idx in range(len(m)):
print(f'{m[idx]}: ({v_i[idx]}, {v_j[idx]})')
Output
512: (511.31, 512.24)
580: (571.77, 588.35)
661: (657.08, 665.49)
-1040: (-1043.45, -1036.56)
-962: (-969.39, -955.33)

Sort (and sorted) not sorting

I have a data file that's built the following way:
source_id, target_id, impressions, clicks
on which I add the following columns:
pair - a tuple of the source and target
CTR - basically clicks/impressions
Lower Bound
Upper Bound
Lower/Upper bound are calculated values (it's irrelevant to my question, but for the curious ones these are the bounds for the Wilson confidence interval.
The thing is, I'm trying to sort the list by the lower bound (position = 6), descending. Tried several things (sort/sorted, using lambda vs. using itemgetter, creating a new list w/o the header and try to sort just that) and still it appears nothing changes. I have the code below.
import csv
from math import sqrt
from operator import itemgetter
#----- Read CSV ----------------------------------------------------------------
raw_data_csv = open('rawdile', "rb")
raw_reader = csv.reader(raw_data_csv)
# transform the values to ints.
raw_data = []
for rownum,row in enumerate(list(raw_reader)):
if rownum == 0: # Header
raw_data.append(row)
else:
r = [] # Col header
r.extend([int(x) for x in row]) # Transforming the values to ints
raw_data.append(r)
# Add cols for pairs (as tuple) and CTR
raw_data[0].append("pair")
for row in raw_data[1:]:
row.append((row[0],row[1])) # tuple
# row.append(float(row[3])/row[2]) # CTR
# ------------------------------------------------------------------------------
z = 1.95996398454005
def confidence(n, clicks):
if n == 0:
return 0
phat = float(clicks) / n
l_bound = ((phat + z*z/(2*n) - z * sqrt((phat*(1-phat)+z*z/(4*n))/n))/(1+z*z/n)) # lower bound
u_bound = ((phat + z*z/(2*n) + z * sqrt((phat*(1-phat)+z*z/(4*n))/n))/(1+z*z/n)) # upper bound
return phat, l_bound, u_bound
raw_data[0].extend(["CTR","Lower Bound","Upper Bound"])
for row in raw_data[1:]:
phat, l_bound, u_bound = confidence(row[2],row[3])
row.extend([phat, l_bound, u_bound])
# raw_data[1:].sort(key=lambda x: x[6], reverse=True)
sorted(raw_data[1:], key=itemgetter(6), reverse=True)
outputfile= open('outputfile.csv', 'wb')
wr = csv.writer(outputfile,quoting = csv.QUOTE_ALL)
wr.writerows(raw_data)
raw_data_csv.close()
outputfile.close()
Can anybody tell why?
Thanks!
You are sorting a slice in one attempt (which creates a new list object), and in your other attempt you ignore the return value of sorted().
You cannot sort part of a list like that; create a new list by concatenating instead:
rows = rows[:1] + sorted(raw_data[1:], key=itemgetter(6), reverse=True)

Get percentile points from a huge list

I have a huge list (45M+ data poitns), with numerical values:
[78,0,5,150,9000,5,......,25,9,78422...]
I can easily get the maximum and minimum values, the number of these values, and the sum of them:
file_handle=open('huge_data_file.txt','r')
sum_values=0
min_value=None
max_value=None
for i,line in enumerate(file_handle):
value=int(line[:-1])
if min_value==None or value<min_value:
min_value=value
if max_value==None or value>max_value:
max_value=value
sum_values+=value
average_value=float(sum_values)/i
However, this is not what I need. I need a list of 10 numbers, where the number of data points between each two consecutive points is equal, for example
median points [0,30,120,325,912,1570,2522,5002,7025,78422]
and we have the number of data points between 0 and 30 or between 30 and 120 to be almost 4.5 million data points.
How can we do this?
=============================
EDIT:
I am well aware that we will need to sort the data. The problem is that I cannot fit all this data in one variable in memory, but I need to read it sequentially from a generator (file_handle)
If you are happy with an approximation, here is a great (and fairly easy to implement) algorithm for computing quantiles from stream data: "Space-Efficient Online Computation of Quantile Summaries" by Greenwald and Khanna.
The silly numpy approach:
import numpy as np
# example data (produced by numpy but converted to a simple list)
datalist = list(np.random.randint(0, 10000000, 45000000))
# converted back to numpy array (start here with your data)
arr = np.array(datalist)
np.percentile(arr, 10), np.percentile(arr, 20), np.percentile(arr, 30)
# ref:
# http://docs.scipy.org/doc/numpy-dev/reference/generated/numpy.percentile.html
You can also hack something together where you just do like:
arr.sort()
# And then select the 10%, 20% etc value, add some check for equal amount of
# numbers within a bin and then calculate the average, excercise for reader :-)
The thing is that calling this function several times will slow it down, so really, just sort the array and then select the elements yourself.
As you said in the comments that you want a solution that can scale to larger datasets then can be stored in RAM, feed the data into an SQLlite3 database. Even if your data set is 10GB and you only have 8GB RAM a SQLlite3 database should still be able to sort the data and give it back to you in order.
The SQLlite3 database gives you a generator over your sorted data.
You might also want to look into going beyond python and take some other database solution.
Here's a pure-python implementation of the partitioned-on-disk sort. It's slow, ugly code, but it works and hopefully each stage is relatively clear (the merge stage is really ugly!).
#!/usr/bin/env python
import os
def get_next_int_from_file(f):
l = f.readline()
if not l:
return None
return int(l.strip())
MAX_SAMPLES_PER_PARTITION = 1000000
PARTITION_FILENAME = "_{}.txt"
# Partition data set
part_id = 0
eof = False
with open("data.txt", "r") as fin:
while not eof:
print "Creating partition {}".format(part_id)
with open(PARTITION_FILENAME.format(part_id), "w") as fout:
for _ in range(MAX_SAMPLES_PER_PARTITION):
line = fin.readline()
if not line:
eof = True
break
fout.write(line)
part_id += 1
num_partitions = part_id
# Sort each partition
for part_id in range(num_partitions):
print "Reading unsorted partition {}".format(part_id)
with open(PARTITION_FILENAME.format(part_id), "r") as fin:
samples = [int(line.strip()) for line in fin.readlines()]
print "Disk-Deleting unsorted {}".format(part_id)
os.remove(PARTITION_FILENAME.format(part_id))
print "In-memory sorting partition {}".format(part_id)
samples.sort()
print "Writing sorted partition {}".format(part_id)
with open(PARTITION_FILENAME.format(part_id), "w") as fout:
fout.writelines(["{}\n".format(sample) for sample in samples])
# Merge-sort the partitions
# NB This is a very inefficient implementation!
print "Merging sorted partitions"
part_files = []
part_next_int = []
num_lines_out = 0
# Setup data structures for the merge
for part_id in range(num_partitions):
fin = open(PARTITION_FILENAME.format(part_id), "r")
next_int = get_next_int_from_file(fin)
if next_int is None:
continue
part_files.append(fin)
part_next_int.append(next_int)
with open("data_sorted.txt", "w") as fout:
while part_files:
# Find the smallest number across all files
min_number = None
min_idx = None
for idx in range(len(part_files)):
if min_number is None or part_next_int[idx] < min_number:
min_number = part_next_int[idx]
min_idx = idx
# Now add that number, and move the relevent file along
fout.write("{}\n".format(min_number))
num_lines_out += 1
if num_lines_out % MAX_SAMPLES_PER_PARTITION == 0:
print "Merged samples: {}".format(num_lines_out)
next_int = get_next_int_from_file(part_files[min_idx])
if next_int is None:
# Remove this partition, it's now finished
del part_files[min_idx:min_idx + 1]
del part_next_int[min_idx:min_idx + 1]
else:
part_next_int[min_idx] = next_int
# Cleanup partition files
for part_id in range(num_partitions):
os.remove(PARTITION_FILENAME.format(part_id))
My code a proposal for finding the result without needing much space. In testing it found a quantile value in 7 minutes 51 seconds for a dataset of size 45 000 000.
from bisect import bisect_left
class data():
def __init__(self, values):
random.shuffle(values)
self.values = values
def __iter__(self):
for i in self.values:
yield i
def __len__(self):
return len(self.values)
def sortedValue(self, percentile):
val = list(self)
val.sort()
num = int(len(self)*percentile)
return val[num]
def init():
numbers = data([x for x in range(1,1000000)])
print(seekPercentile(numbers, 0.1))
print(numbers.sortedValue(0.1))
def seekPercentile(numbers, percentile):
lower, upper = minmax(numbers)
maximum = upper
approx = _approxPercentile(numbers, lower, upper, percentile)
return neighbor(approx, numbers, maximum)
def minmax(list):
minimum = float("inf")
maximum = float("-inf")
for num in list:
if num>maximum:
maximum = num
if num<minimum:
minimum = num
return minimum, maximum
def neighbor(approx, numbers, maximum):
dif = maximum
for num in numbers:
if abs(approx-num)<dif:
result = num
dif = abs(approx-num)
return result
def _approxPercentile(numbers, lower, upper, percentile):
middles = []
less = []
magicNumber = 10000
step = (upper - lower)/magicNumber
less = []
for i in range(1, magicNumber-1):
middles.append(lower + i * step)
less.append(0)
for num in numbers:
index = bisect_left(middles,num)
if index<len(less):
less[index]+= 1
summing = 0
for index, testVal in enumerate(middles):
summing += less[index]
if summing/len(numbers) < percentile:
print(" Change lower from "+str(lower)+" to "+ str(testVal))
lower = testVal
if summing/len(numbers) > percentile:
print(" Change upper from "+str(upper)+" to "+ str(testVal))
upper = testVal
break
precision = 0.01
if (lower+precision)>upper:
return lower
else:
return _approxPercentile(numbers, lower, upper, percentile)
init()
I edited my code a bit and I now think that this way works at least decently even when it's not optimal.

Looping back to the next column in a csv

I'm trying to get a script to run on each individual column of a csv file. I've figured out how to tell python which column I would like to run the script on but I want it to analyze column one, output the results, the move to column two and continue on and on through the file. What I want is a "if etc goto etc" command. I've found how to do this with simple oneliners but I have a larger script. Any help would be great as I'm sure I'm just missing something. Like if I could loop back to where I define my data (h=data) but tell it to choose the next column. Here is my script.
import numpy as np
import matplotlib.pyplot as plt
from pylab import *
import pylab
from scipy import linalg
import sys
import scipy.interpolate as interpolate
import scipy.optimize as optimize
a=raw_input("Data file name? ") #Name of the data file including the directory, must be .csv
datafile = open(a, 'r')
data = []
for row in datafile:
data.append(row.strip().split(',')) #opening and organizing the csv file
print('Data points= ', len(data))
print data
c=raw_input("Is there a header row? y/n?") #Remove header line if present
if c is ('y'):
del data[0]
data2=data
print('Raw data= ', data2)
else:
print('Raw data= ', data)
'''
#if I wanted to select a column
b=input("What column to analyze?") #Asks what column depth data is in
if b is 1:
h=[[rowa[i] for rowa in data] for i in range(1)] #first row
'''
h=data # all columns
g=reduce(lambda x,y: x+y,h) #prepares data for calculations
a=map(float, g)
a.sort()
print ('Organized data= ',a)
def GRLC(values):
'''
Calculate Gini index, Gini coefficient, Robin Hood index, and points of
Lorenz curve based on the instructions given in
www.peterrosenmai.com/lorenz-curve-graphing-tool-and-gini-coefficient-calculator
Lorenz curve values as given as lists of x & y points [[x1, x2], [y1, y2]]
#param values: List of values
#return: [Gini index, Gini coefficient, Robin Hood index, [Lorenz curve]]
'''
n = len(values)
assert(n > 0), 'Empty list of values'
sortedValues = sorted(values) #Sort smallest to largest
#Find cumulative totals
cumm = [0]
for i in range(n):
cumm.append(sum(sortedValues[0:(i + 1)]))
#Calculate Lorenz points
LorenzPoints = [[], []]
sumYs = 0 #Some of all y values
robinHoodIdx = -1 #Robin Hood index max(x_i, y_i)
for i in range(1, n + 2):
x = 100.0 * (i - 1)/n
y = 100.0 * (cumm[i - 1]/float(cumm[n]))
LorenzPoints[0].append(x)
LorenzPoints[1].append(y)
sumYs += y
maxX_Y = x - y
if maxX_Y > robinHoodIdx: robinHoodIdx = maxX_Y
giniIdx = 100 + (100 - 2 * sumYs)/n #Gini index
return [giniIdx, giniIdx/100, robinHoodIdx, LorenzPoints]
result = GRLC(a)
print 'Gini Index', result[0]
print 'Gini Coefficient', result[1]
print 'Robin Hood Index', result[2]
I'm ignoring all of that GRLC function and just solving the looping question. Give this a try. It uses while True: to loop forever (you can just break out by ending the program; Ctrl+C in Windows, depends on OS). Just load the data from the csv once then each time it loops, you can re-build some variables. If you have questions please ask. Also, I didn't test it as I don't have all the NumPy packages installed :)
import numpy as np
import matplotlib.pyplot as plt
from pylab import *
import pylab
from scipy import linalg
import sys
import scipy.interpolate as interpolate
import scipy.optimize as optimize
def GRLC(values):
'''
Calculate Gini index, Gini coefficient, Robin Hood index, and points of
Lorenz curve based on the instructions given in
www.peterrosenmai.com/lorenz-curve-graphing-tool-and-gini-coefficient-calculator
Lorenz curve values as given as lists of x & y points [[x1, x2], [y1, y2]]
#param values: List of values
#return: [Gini index, Gini coefficient, Robin Hood index, [Lorenz curve]]
'''
n = len(values)
assert(n > 0), 'Empty list of values'
sortedValues = sorted(values) #Sort smallest to largest
#Find cumulative totals
cumm = [0]
for i in range(n):
cumm.append(sum(sortedValues[0:(i + 1)]))
#Calculate Lorenz points
LorenzPoints = [[], []]
sumYs = 0 #Some of all y values
robinHoodIdx = -1 #Robin Hood index max(x_i, y_i)
for i in range(1, n + 2):
x = 100.0 * (i - 1)/n
y = 100.0 * (cumm[i - 1]/float(cumm[n]))
LorenzPoints[0].append(x)
LorenzPoints[1].append(y)
sumYs += y
maxX_Y = x - y
if maxX_Y > robinHoodIdx: robinHoodIdx = maxX_Y
giniIdx = 100 + (100 - 2 * sumYs)/n #Gini index
return [giniIdx, giniIdx/100, robinHoodIdx, LorenzPoints]
#Name of the data file including the directory, must be .csv
a=raw_input("Data file name? ")
datafile = open(a.strip(), 'r')
data = []
#opening and organizing the csv file
for row in datafile:
data.append(row.strip().split(','))
#Remove header line if present
c=raw_input("Is there a header row? y/n?")
if c.strip().lower() == ('y'):
del data[0]
while True :
#if I want the first column, that's index 0.
b=raw_input("What column to analyze?")
# Validate that the column input data is correct here. Otherwise it might be out of range, etc.
# Maybe try this. You might want more smarts in there, depending on your intent:
b = int(b.strip())
# If you expect the user to inpt "2" to mean the second column, you're going to use index 1 (list indexes are 0 based)
h=[[rowa[b-1] for rowa in data] for i in range(1)]
# prepares data for calculations
g=reduce(lambda x,y: x+y,h)
a=map(float, g)
a.sort()
print ('Organized data= ',a)
result = GRLC(a)
print 'Gini Index', result[0]
print 'Gini Coefficient', result[1]
print 'Robin Hood Index', result[2]

Categories