python

categorical.py

# After determining with attributes are categorical and which
# are numeric , you'll want descriptive stat for the numeric
# variables and a count of the unique categories in each
# categorical attribute


import urllib2
import sys
import numpy as np


# Read data from the repository

target_url = ("https://archive.ics.uci.edu/ml/machine-learning-"
             "databases/undocumented/connectionist-bench/sonar/"
             "sonar.all-data")

data = urllib2.urlopen(target_url)

#arrange data into list for labels and list of lists for
#attributes

xList = []
labels = []

for line in data:
    #split on comma
    row = line.strip().split(",")
    xList.append(row)

nrow  = len(xList)

ncol = len(xList[1])

# generate summary stats for col 3

col = 3
colData = []
for row in xList:
    colData.append(float(row[col]))


colArray = np.array(colData)
colMean = np.mean(colArray)
colsd = np.std(colArray)

sys.stdout.write("Mean = " + '\t' + str(colMean) + '\t\t' +
                 "standard Deviation = " + '\t' + str(colsd)  +
                 "\n")

# Calaculate qunatile boundaries

ntiles = 4
percentBdry = []

for i in range(ntiles + 1):
    percentBdry.append(np.percentile(colArray, i*(100)/ntiles))

sys.stdout.write("\nBoundaries for 4 Equal Percentiles \n")
print(percentBdry)
sys.stdout.write(" \n")

# Run with 10 equal intervals

ntiles = 10
percentBdry = []

for i in range(ntiles + 1):
    percentBdry.append(np.percentile(colArray, i*(100)/ntiles))

sys.stdout.write("\nBoundaries for 10 Equal Percentiles \n")
print(percentBdry)

# The last column contains categorical values

col = 60
colData = []
for row in xList:
    colData.append(row[col])

unique = set(colData)
sys.stdout.write("Unique Label Values \n")
print(unique)

#count up the number of elements having each value
print "len unique" , len(unique)

catDict  = dict(zip(list(unique), range(len(unique))))

catCount = [0]*2

for elt in colData:
    catCount[catDict[elt]] +=1

print list(unique)

print (catCount)