-
Notifications
You must be signed in to change notification settings - Fork 0
/
genderclassmodel.py
113 lines (92 loc) · 5.63 KB
/
genderclassmodel.py
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
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
""" Now that the user can read in a file this creates a model which uses the price, class and gender
Author : AstroDave
Date : 18th September 2012
Revised : 28 March 2014
"""
import csv as csv
import numpy as np
csv_file_object = csv.reader(open('train.csv', 'rb')) # Load in the csv file
header = csv_file_object.next() # Skip the fist line as it is a header
data=[] # Create a variable to hold the data
for row in csv_file_object: # Skip through each row in the csv file
data.append(row) # adding each row to the data variable
data = np.array(data) # Then convert from a list to an array
# In order to analyse the price column I need to bin up that data
# here are my binning parameters, the problem we face is some of the fares are very large
# So we can either have a lot of bins with nothing in them or we can just lose some
# information by just considering that anythng over 39 is simply in the last bin.
# So we add a ceiling
fare_ceiling = 40
# then modify the data in the Fare column to = 39, if it is greater or equal to the ceiling
data[ data[0::,9].astype(np.float) >= fare_ceiling, 9 ] = fare_ceiling - 1.0
fare_bracket_size = 10
number_of_price_brackets = fare_ceiling / fare_bracket_size
number_of_classes = 3 # I know there were 1st, 2nd and 3rd classes on board.
number_of_classes = len(np.unique(data[0::,2])) # But it's better practice to calculate this from the Pclass directly:
# just take the length of an array of UNIQUE values in column index 2
# This reference matrix will show the proportion of survivors as a sorted table of
# gender, class and ticket fare.
# First initialize it with all zeros
survival_table = np.zeros([2,number_of_classes,number_of_price_brackets],float)
# I can now find the stats of all the women and men on board
for i in xrange(number_of_classes):
for j in xrange(number_of_price_brackets):
women_only_stats = data[ (data[0::,4] == "female") \
& (data[0::,2].astype(np.float) == i+1) \
& (data[0:,9].astype(np.float) >= j*fare_bracket_size) \
& (data[0:,9].astype(np.float) < (j+1)*fare_bracket_size), 1]
men_only_stats = data[ (data[0::,4] != "female") \
& (data[0::,2].astype(np.float) == i+1) \
& (data[0:,9].astype(np.float) >= j*fare_bracket_size) \
& (data[0:,9].astype(np.float) < (j+1)*fare_bracket_size), 1]
#if i == 0 and j == 3:
survival_table[0,i,j] = np.mean(women_only_stats.astype(np.float)) # Female stats
survival_table[1,i,j] = np.mean(men_only_stats.astype(np.float)) # Male stats
# Since in python if it tries to find the mean of an array with nothing in it
# (such that the denominator is 0), then it returns nan, we can convert these to 0
# by just saying where does the array not equal the array, and set these to 0.
survival_table[ survival_table != survival_table ] = 0.
# Now I have my proportion of survivors, simply round them such that if <0.5
# I predict they dont surivive, and if >= 0.5 they do
survival_table[ survival_table < 0.5 ] = 0
survival_table[ survival_table >= 0.5 ] = 1
# Now I have my indicator I can read in the test file and write out
# if a women then survived(1) if a man then did not survived (0)
# First read in test
test_file = open('test.csv', 'rb')
test_file_object = csv.reader(test_file)
header = test_file_object.next()
# Also open the a new file so I can write to it.
predictions_file = open("genderclassmodel.csv", "wb")
predictions_file_object = csv.writer(predictions_file)
predictions_file_object.writerow(["PassengerId", "Survived"])
# First thing to do is bin up the price file
for row in test_file_object:
for j in xrange(number_of_price_brackets):
# If there is no fare then place the price of the ticket according to class
try:
row[8] = float(row[8]) # No fare recorded will come up as a string so
# try to make it a float
except: # If fails then just bin the fare according to the class
bin_fare = 3 - float(row[1])
break # Break from the loop and move to the next row
if row[8] > fare_ceiling: # Otherwise now test to see if it is higher
# than the fare ceiling we set earlier
bin_fare = number_of_price_brackets - 1
break # And then break to the next row
if row[8] >= j*fare_bracket_size\
and row[8] < (j+1)*fare_bracket_size: # If passed these tests then loop through
# each bin until you find the right one
# append it to the bin_fare
# and move to the next loop
bin_fare = j
break
# Now I have the binned fare, passenger class, and whether female or male, we can
# just cross ref their details with our survival table
if row[3] == 'female':
predictions_file_object.writerow([row[0], "%d" % int(survival_table[ 0, float(row[1]) - 1, bin_fare ])])
else:
predictions_file_object.writerow([row[0], "%d" % int(survival_table[ 1, float(row[1]) - 1, bin_fare])])
# Close out the files
test_file.close()
predictions_file.close()