1 from pylab import *

     2 from scipy import *

     3 from scipy import stats

     4 

     5 scores = [[], [], [], [], []]

     6 ninety_percents = [{}, {}, {}, {}, {}]

     7 

     8 for record in open('sslc1.txt'):

     9     record = record.strip()

    10     fields = record.split(';')

    11 

    12     region_code = fields[0].strip()

    13    

    14     for i, field in enumerate(fields[3:8]):

    15         if region_code not in ninety_percents[i]:

    16             ninety_percents[i][region_code] = 0

    17         score_str = field.strip()

    18         score = 0 if score_str == 'AA' else int(score_str)

    19         scores[i].append(score)

    20         if score > 90:

    21             ninety_percents[i][region_code] += 1

    22 

    23 subj_total = []

    24 for subject in ninety_percents:

    25     subj_total.append(sum(subject.values()))

    26 

    27 

    28 figure(1)

    29 pie(ninety_percents[3].values(), labels=ninety_percents[3].keys())

    30 title('Students scoring 90% and above in science by region')

    31 savefig('/tmp/science.png')

    32 

    33 figure(2)

    34 pie(subj_total, labels=['English', 'Hindi', 'Maths', 'Science', 'Social'])

    35 title('Students scoring more than 90% by subject(All regions combined).')

    36 savefig('/tmp/all_regions.png')

    37 

    38 math_scores = array(scores[2])

    39 # Mean score in Maths(All regions combined)

    40 print "Mean: ", mean(math_scores)

    41 

    42 # Median score in Maths(All regions combined)

    43 print "Median: ", median(math_scores)

    44 

    45 # Mode score in Maths(All regions combined)

    46 print "Mode: ", stats.mode(math_scores)

    47 

    48 # Standard deviation of scores in Maths(All regions combined)

    49 print "Standard Deviation: ", std(math_scores)

    50