def generate_crime_socioecon_data(crime_data, geo_data, population_data,
socio_econ_data):
'''
accepts crime_data, geo_data, population_data and
socio_econ_data tables as parameters,
generate a table with crime rate and
other socio-econ data included in and return it
'''
geo_pop_data = Question3.merge_data(geo_data, population_data)
crime_arrest_rate = Question3.generate_crime_arrest_rate(
crime_data, geo_pop_data)
crime_arrest_rate = crime_arrest_rate[crime_arrest_rate['Year'] == 2018]
crime_socioecon_data =\
crime_arrest_rate.merge(socio_econ_data,
left_on='Community Area',
right_on='Community Area Number')
crime_socioecon_data = crime_socioecon_data.merge(geo_data,
left_on='Community Area',
right_on='commarea_n')
crime_socioecon_data = crime_socioecon_data[[
'COMMUNITY AREA NAME', 'Community Area', 'Year', 'crime_rate',
'PERCENT HOUSEHOLDS '
'BELOW POVERTY', 'PERCENT AGED 16+ UNEMPLOYED',
'PERCENT AGED 25+ WITHOUT '
'HIGH SCHOOL DIPLOMA', 'PERCENT AGED UNDER 18 OR '
'OVER 64', 'geometry'
]].dropna()
return crime_socioecon_data
def test_text_handle(self):
t_list1 = [[55, 57, 90, 87, 43, 65, 60], [57, 60, 78, 74, 89, 45, 43],
[43, 60, 90, 65, 38, 65, 78]]
t_list2 = [[12, 6, 7, 8, 9, 10, 4], [10, 3, 5, 6, 20, 8, 5],
[0, 85, 52, 4, 38, 1, 20]]
self.assertEqual(Question3.list_handle(t_list1),
[89, 65, 38, 74, 43, 45, 78, 55, 87, 57, 90, 60])
self.assertEqual(Question3.list_handle(t_list2),
[0, 1, 3, 4, 5, 6, 7, 8, 9, 10, 38, 12, 20, 85, 52])
def take_time(array):
time_taken = []
for i in range(1, len(array) + 1):
sub_list = array[0:i]
start_time = time()
Question3.sort_list(sub_list)
end_time = time()
time_diff = end_time - start_time
time_taken.append(time_diff)
return time_taken
def take_space(array):
space_taken = []
for i in range(1, len(array) + 1):
sub_list = array[0:i]
h.setrelheap()
Question3.find_maximum(sub_list)
raw_string = repr(h)
raw_string = raw_string.split()
space = raw_string[10]
space_taken.append(space)
return space_taken
def take_space(array):
space_taken = []
for i in range(1, len(array) + 1):
sub_list = array[0:i]
h.setrelheap()
Question3.make_lowercase(sub_list)
raw_string = repr(h)
raw_string = raw_string.split()
space = int(raw_string[10])
space_taken.append(space)
return space_taken
def main():
sns.set()
file_names = os.listdir()
needed_files = ['sentence_length.csv', 'socio_econ.csv',
'Chicago_shape.zip', 'population.csv']
for file_name in needed_files:
if file_name not in file_names:
save_useful_files()
print('file_saved')
crime_data = get_crime_data()
print('get crime data')
geo_data = get_geo_data()
population_data = get_population_data()
sentence_length_data = get_sentence_length_data()
socio_econ_data = get_socio_econ_data()
get_crime_sample(crime_data)
q1 = Question1.Question1(crime_data, sentence_length_data,
geo_data, socio_econ_data)
q1._plot_a_single_year(2018)
q1._plot_change('42 43 45')
q1._safety_ranking(2018)
q2 = Question2.Question2()
q2.aggregate_data(crime_data)
q2.machine_learning()
q2._report_predict('assault', 43, 23)
q2._report_predict('theft', 9, 23)
q2._report_predict('theft', 9, 10)
q2._report_predict('theft', 9, 13)
print('The mean square error of the model is ' + str(q2.mes()))
Question3.Question3(crime_data, geo_data, population_data)
Question4.Question4(crime_data, geo_data, population_data, socio_econ_data)
def main():
sns.set()
file_names = os.listdir()
needed_files = [
'sentence_length.csv', 'socio_econ.csv', 'Chicago_shape.zip',
'population.csv'
]
for file_name in needed_files:
if file_name not in file_names:
save_useful_files()
print('file_saved')
crime_data = get_crime_data()
print('get crime data')
geo_data = get_geo_data()
population_data = get_population_data()
sentence_length_data = get_sentence_length_data()
socio_econ_data = get_socio_econ_data()
# get_crime_sample(crime_data)
q1 = Question1.Question1(crime_data, sentence_length_data, geo_data,
socio_econ_data)
q1.plot_communities_single_year()
q1.plot_change_through_years()
q1.safety_ranking()
q2 = Question2.Question2()
q2.aggregate_data(crime_data)
q2.machine_learning()
q2.predict()
print('The mean square error of the model is ' + str(q2.mes()))
Question3.Question3(crime_data, geo_data, population_data)
Question4.Question4(crime_data, geo_data, population_data, socio_econ_data)
def main():
Question1.q1()
Question2.q2()
Question3.q3()
Question4.q4()
from time import time
import Question3
# Estimate how long each algorithm would take for inputs of size 1,000,000.
# Algorithm 1
starting_time = time()
Question3.find_maximum([1])
ending_time = time()
time_difference = ending_time - starting_time
print("Time for input size 1: " + str(time_difference))
print("Time for input size 1,000,000: " + str(time_difference))
# Algorithm 2
starting_time1 = time()
Question3.make_lowercase("M")
ending_time1 = time()
time_difference1 = ending_time1 - starting_time1
print("Time for input size 1: " + str(time_difference1))
print("Time for input size 1,000,000: " + str(time_difference1))
# Algorithm 3
starting_time2 = time()
Question3.sort_list([1])
ending_time2 = time()
time_difference2 = ending_time2 - starting_time2
print("Time for input size 1: " + str(time_difference2))
print("Time for input size 1,000,000: " + str(time_difference2))
import Question3
import Question4
import Question5
print("######Computational Finance - Project 1###########")
print("Nitish Ramkumar")
# Question1
n = 10000
seed = 2000
Question1.question1(n, seed)
# Question2
probs = [0.3, 0.35, 0.2, 0.15]
probvals = [-1, 0, 1, 2]
Question2.question2(probs, probvals, n, seed)
# Question3
n = 44
p = 0.64
tot = 1000
Question3.question3(n, p, tot, seed)
# Question 4
lambd = 1.5
n = 10000
Question4.question4(n, lambd, seed)
# Question 5
Question5.question5(seed)
import Question1
import Question2
import Question3
import Question4
import Question5
import Question6
# Question1
seed = 2000
rho = Question1.question1(seed)
print("The Rho value is {0:.4f}".format(rho))
# Question2
val = Question2.question2(seed)
print("The expected value is {0:.4f}".format(val))
# Question3
val = Question3.question3(seed)
# Question 4
Question4.question4(seed)
# Question 5
Question5.question5(seed)
# Question 6
Question6.question6(seed)
import Question1
import Question2
import Question3
import Question4
import Question5
print("######Computational Finance - Project 9###########")
print("Nitish Ramkumar")
# Question1
Question1.question1()
#Question2
Question2.question2()
#Question3
market_price = 110000
oas = Question3.question3(market_price)
#Question4
Question4.question4(market_price, oas)
#Question5
Question5.question5(oas)
import Question3
import json
class UserEncoder(json.JSONEncoder):
def default(self, obj):
if isinstance(obj, Question3.stack):
a = obj
b = []
while not a.isempty():
b.append(a.pop())
return b
return json.JSONEncoder.default(self, obj)
def serialize(object):
return json.dumps(object, cls=UserEncoder)
#Test
if __name__ == '__main__':
a = Question3.stack()
a.push(1)
a.push(2)
a.push(3)
print(serialize(a))
def main():
Question1.q1()
Question2.q2()
Question3.q3()
Question4.q4()