def test_merge_by_year_3(self):
"""this is to test for the third time"""
countries = pd.read_csv("countries.csv", sep=",")
income = pd.read_excel("indicator gapminder gdp_per_capita_ppp.xlsx", sheetname="Data", index_col=0)
income2 = income.transpose()
result = data_process_functions.merge_by_year(1800, countries, income2)
self.assertEqual(result["Country"][27], "Mauritius")
self.assertEqual(result["Region"][27], "AFRICA")
self.assertEqual(int(result["Income"][27]), 799)
def test_merge_by_year_1(self):
"""this is to test for the first time"""
countries = pd.read_csv("./countries.csv", sep=",")
income = pd.read_excel("./indicator gapminder gdp_per_capita_ppp.xlsx", sheetname="Data", index_col=0)
income2 = income.transpose()
result = data_process_functions.merge_by_year(1800, countries, income2)
self.assertEqual(result["Country"][176], "Venezuela")
self.assertEqual(result["Region"][176], "SOUTH AMERICA")
self.assertEqual(int(result["Income"][176]), 442)
def test_merge_by_year_case4(self):
#load the data
countries = pd.read_csv('countries.csv',sep=',')
income = pd.read_excel('indicator gapminder gdp_per_capita_ppp.xlsx',sheetname='Data',index_col=0)
income_new = income.transpose()
#merge function
merged_result = data_process_functions.merge_by_year(2012,countries,income_new)
self.assertEqual(merged_result['Country'][147],'Saint Kitts and Nevis')
self.assertEqual(merged_result['Region'][147],'NORTH AMERICA')
self.assertEqual(int(merged_result['Income'][147]),12659)
def test_merge_by_year_case3(self):
#load the data
countries = pd.read_csv('countries.csv',sep=',')
income = pd.read_excel('indicator gapminder gdp_per_capita_ppp.xlsx',sheetname='Data',index_col=0)
income_new = income.transpose()
#merge function
merged_result = data_process_functions.merge_by_year(1800,countries,income_new)
self.assertEqual(merged_result['Country'][176],'Venezuela')
self.assertEqual(merged_result['Region'][176],'SOUTH AMERICA')
self.assertEqual(int(merged_result['Income'][176]),442)
def test_merge_by_year_case1(self):
#load the data
countries = pd.read_csv('countries.csv',sep=',')
income = pd.read_excel('indicator gapminder gdp_per_capita_ppp.xlsx',sheetname='Data',index_col=0)
income_new = income.transpose()
#merge function
merged_result = data_process_functions.merge_by_year(2003,countries,income_new)
self.assertEqual(merged_result['Country'][27],'Mauritius')
self.assertEqual(merged_result['Region'][27],'AFRICA')
self.assertEqual(int(merged_result['Income'][27]),9564)
def generate_answers_hw9():
'''this function will generate answers of assignment 9 '''
#Q1
countries = pd.read_csv('countries.csv',sep=',')
#Q2 load the xlsx data and on the sheet 'Data'
income = pd.read_excel('indicator gapminder gdp_per_capita_ppp.xlsx',sheetname='Data',index_col=0)
#Q3
income_new = income.transpose()#the transpose of the dataframe income
print "The head of the data set:"
print income_new.head()
print "The data has been loaded successfully!\n"
#the user interaction part
while True:
try:
print "Please Enter a year from 1800 to 2012 to check the income distribution (for example: 2003), enter 'finish' to stop checking"
print "(Hint:Close the plot window to continue)"
year_input = raw_input()
if year_input == "finish": #quit the program
print "the check process is finished"
break
if year_input == "": #test empty input
raise Empty_Input_Error
if not re.match(r'^[1-9][0-9][0-9][0-9]$',year_input):
raise Invalid_Input_Error
else:
year_number = int(year_input)
if year_number in income_new.index:
#Q4 display the distribution of income per person across all countries for the given year
data_process_functions.display_income_dist_by_year(year_number,income_new)
else:
raise Invalid_Input_Error
except Empty_Input_Error:
print "Warning: The input is empty! please re-enter the list"
except Invalid_Input_Error:
print "Warning: The input number is not valid! please re-enter the year"
#generate the plots from 2007 and 2012
print "the program is generating graphs for the years 2007-2012..."
for year_ind in range(2007,2013):
merged_data = data_process_functions.merge_by_year(year_ind,countries,income_new) # Q5
data_analysis_instance = data_analysis_tools.Data_Analysis_Tools(year_ind, merged_data) #Q6
data_analysis_instance.plot_boxplots() #Q8
data_analysis_instance.plot_histograms() #Q8
print "Congratulations! the results are saved succeffully, thanks for trying ,bye"
def generate_answers():
'''this is to generate the answers'''
# question 1
countries = pd.read_csv('./countries.csv', sep= ',')
# question 2
income = pd.read_excel('./indicator gapminder gdp_per_capita_ppp.xlsx', sheetname='Data', index_col=0)
# question 3
income2 = income.transpose()
print "The head of the data set is:"
print income2.head()
while True:
try:
print "Please Enter a year from 1800 to 2012 to check the income distribution (hint: enter 'finish' to stop displaying)"
year_input = raw_input()
if year_input == "finish":
break
if year_input == "":
raise Empty_Input_Error
if not re.match(r'^[1-9][0-9][0-9][0-9]$',year_input):
raise Invalid_Input_Error
else:
year_number = int(year_input)
if year_number in income2.index:
# question4: display the distribution of income per person across all countries for the given year
data_process_functions.display_income_distribution(year_number,income2)
else:
raise Invalid_Input_Error
except Empty_Input_Error:
pass
except Invalid_Input_Error:
pass
# question 8: generate graphs for the years of 2007-2012
print "The graphs for 2007-2012 are generating..."
for year_i in range(2007,2013):
merged_data = data_process_functions.merge_by_year(year_i, countries, income2)
graph_data = data_analysis_tools.data_analysis(year_i, merged_data)
graph_data.plot_histograms()
graph_data.plot_boxplots()
print "The graphs for 2007-2012 have been successfully generated. Please check the directory. Thanks!"
