FilesExpand file tree

master

/

AnalyzeHellinger.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

81 lines (50 loc) · 1.81 KB

master

/

AnalyzeHellinger.py

Copy path

Top

File metadata and controls

• Code
• Blame

81 lines (50 loc) · 1.81 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

__author__ = 'greglakomski'

import numpy as np

import csv

import re

# Read in the saved Hellinger Data from file

combined_output_file_in = '/Users/greglakomski/Desktop/GibbsLDA++-0.2/models/Medicare/TwentyClustersStop/combined_output.csv'

savedfile = "/Users/greglakomski/Desktop/GibbsLDA++-0.2/models/Medicare/TwentyClustersStop/hellingerdata.txt"

target_to_peer_data_out = '/Users/greglakomski/Desktop/GibbsLDA++-0.2/models/Medicare/TwentyClustersStop/target_to_peer_data_out.csv'

newhellinger = np.loadtxt(savedfile)

writer = csv.writer(open(target_to_peer_data_out,'w+'),delimiter = ' ')

target_prov = "1740243245"

target_prov_type = ""

target_row = 0

peer_row = []

# first find row and type for target, then find all peer rows

with open(combined_output_file_in,'r') as f:

reader = csv.reader(f, delimiter="%")

rownum = 0

for row in reader:

rownum += 1

if row[0] == target_prov:

target_row = rownum

row[1] = row[1].lstrip(' ')

target_prov_type = row[1]

break

print(target_prov_type)

with open(combined_output_file_in,'r') as f:

reader = csv.reader(f, delimiter="%")

rownum = 0

for row in reader:

rownum += 1

if row[1].lstrip(' ') == target_prov_type or row[1].lstrip(' ') == "Ophthalmology":

peer_row.append(rownum)

# now analyze the hellinger data

# array is zero based

print len(peer_row)

print(peer_row)

hellinger_set = []

for i in range(0,len(peer_row)):

print(newhellinger[target_row,peer_row[i]])

hellinger_set.append(newhellinger[target_row,peer_row[i]])

# get rid of the zero associated with the target

hellinger_set.remove(0)

print(hellinger_set)

for i in hellinger_set:

writer.writerow([i])

avg = reduce(lambda x,y:x+y,hellinger_set)/(len(peer_row)-1)

print(avg)

print(max(hellinger_set))

print(min(hellinger_set))