Skip to content

finish assignment 9 #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
peimengsui wants to merge 3 commits into
base: master
Choose a base branch
from
Open

finish assignment 9 #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
92aa5b8
finish assignment 9
peimengsui Nov 30, 2016
6ae5918
Delete Untitled.ipynb
peimengsui Nov 30, 2016
67a62b0
add result file
peimengsui Dec 2, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
Empty file added .metadata/.lock
View file
Open in desktop
Empty file.
Binary file added .metadata/.mylyn/.taskListIndex/segments.gen
View file
Open in desktop
Binary file not shown.
Binary file added .metadata/.mylyn/.taskListIndex/segments_1
View file
Open in desktop
Binary file not shown.
Binary file added .metadata/.mylyn/.tasks.xml.zip
View file
Open in desktop
Binary file not shown.
Binary file added .metadata/.mylyn/repositories.xml.zip
View file
Open in desktop
Binary file not shown.
Binary file added .metadata/.mylyn/tasks.xml.zip
View file
Open in desktop
Binary file not shown.
80,723 changes: 80,723 additions & 0 deletions ...gins/com.python.pydev.analysis/python_v1_6cen1corrbqa4et8g7qb79me2/python.pydevsysteminfo
View file
Open in desktop

Large diffs are not rendered by default.

41 changes: 41 additions & 0 deletions .metadata/.plugins/org.eclipse.core.resources/.history/15/d013eb5315b700161b82ee8d880ca29b
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,41 @@
import matplotlib.pyplot as plt
import pandas as pd
'''
Created on Nov 30, 2016

@author: peimengsui
@desc: define functions and a class for data analysis tool
'''
def visual_income_dist(year,dataset):
'''
this function plots distribution over countries of the income per person for a given year
'''
plt.hist(dataset[year].dropna().values)
plt.title("distribution of income per person across all countries_"+str(year))
plt.xlabel("income_per_person")
plt.ylabel("count")

def merge_by_year(coutries,income,year):
'''
this function merges the countries and income data sets for any given year
'''
income_year = pd.DataFrame(income[year])
merged = pd.merge(coutries,income_year,left_index=True,right_index=True)
return merged
class dataTool:
'''
this class includes tools for data ananlysis on income country datasets
'''
def __init__(self, year,dataset):
'''
Constructor
'''
self.year = year
self.dataset = dataset
def box_plot(self):
self.dataset.boxplot('Income', by = 'Region', rot = 90)
plt.xlabel('region')
plt.ylabel('income per person')
plt.savefig('box_'+self.year+'.pdf')
plt.clf()

44 changes: 44 additions & 0 deletions .metadata/.plugins/org.eclipse.core.resources/.history/1f/909174d017b700161b82ee8d880ca29b
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,44 @@
import matplotlib.pyplot as plt
import pandas as pd
'''
Created on Nov 30, 2016

@author: peimengsui
@desc: define functions and a class for data analysis tool
'''
def visual_income_dist(year,dataset):
'''
this function plots distribution over countries of the income per person for a given year
'''
plt.hist(dataset[year].dropna().values)
plt.title("distribution of income per person across all countries_"+str(year))
plt.xlabel("income_per_person")
plt.ylabel("count")

def merge_by_year(coutries,income,year):
'''
this function merges the countries and income data sets for any given year
'''
income_year = pd.DataFrame(income[year])
merged = pd.merge(coutries,income_year,left_index=True,right_index=True)
merged["Country"] = merged.index
merged.rename(columns = {year:'Income'}, inplace = True)
return merged
class dataTool:
'''
this class includes tools for data analysis on income country datasets
'''
def __init__(self, year,dataset):
'''
Constructor
'''
self.year = year
self.dataset = dataset
def box_plot(self):
self.dataset.boxplot('Income', by = 'Region')
plt.xlabel('region')
plt.ylabel('income_per_person')
plt.savefig('boxplot'+str(self.year)+'.pdf')
plt.clf()
def

18 changes: 18 additions & 0 deletions .metadata/.plugins/org.eclipse.core.resources/.history/20/f0d88bd544b700161bd9849ad48630d5
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
'''
Created on Nov 30, 2016

@author: peimengsui
@desc: test the data analysis tool program
'''
import unittest
from dataTool import *

countries = pd.read_csv('countries.csv',index_col=0)
income = pd.read_excel('indicator gapminder gdp_per_capita_ppp.xlsx',index_col=0)
class Test(unittest.TestCase):
def testMerge(self):
self.assertEqual(merge_by_year(countries, income,2000).columns,['Region','Income','Country'])


if __name__ == "__main__":
unittest.main()
52 changes: 52 additions & 0 deletions .metadata/.plugins/org.eclipse.core.resources/.history/22/e0865d1f18b700161b82ee8d880ca29b
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,52 @@
import matplotlib.pyplot as plt
import pandas as pd
'''
Created on Nov 30, 2016

@author: peimengsui
@desc: define functions and a class for data analysis tool
'''
def visual_income_dist(year,dataset):
'''
this function plots distribution over countries of the income per person for a given year
'''
plt.hist(dataset[year].dropna().values)
plt.title("distribution of income per person across all countries_"+str(year))
plt.xlabel("income_per_person")
plt.ylabel("count")

def merge_by_year(coutries,income,year):
'''
this function merges the countries and income data sets for any given year
'''
income_year = pd.DataFrame(income[year])
merged = pd.merge(coutries,income_year,left_index=True,right_index=True)
merged["Country"] = merged.index
merged.rename(columns = {year:'Income'}, inplace = True)
return merged
class dataTool:
'''
this class includes tools for data analysis on income country datasets
'''
def __init__(self, year,dataset):
'''
Constructor
'''
self.year = year
self.dataset = dataset
def boxplot(self):
self.dataset.boxplot('Income', by = 'Region')
plt.title("boxplot of income by region_"+str(self.year))
plt.xlabel('region')
plt.ylabel('income_per_person')
plt.savefig('boxplot_'+str(self.year)+'.pdf')
plt.clf()
def histogram(self):
plt.hist(self.dataset["Income"].dropna().values)
plt.title("histogram of income_"+str(self.year))
plt.xlabel("income_per_person")
plt.ylabel("count")
plt.savefig('histogram_'+self.year+'.pdf')
plt.clf()


34 changes: 34 additions & 0 deletions .metadata/.plugins/org.eclipse.core.resources/.history/33/205fffd43eb7001619c6bfb22cd84311
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
import pandas as pd
from dataTool import *
import sys
'''
Created on Nov 30, 2016

@author: peimengsui
@desc: this program runs a user interactive data analysis tool on income country dataset
'''

if __name__ == '__main__':
countries = pd.read_csv('countries.csv',index_col=0)
income = pd.read_excel('indicator gapminder gdp_per_capita_ppp.xlsx',index_col=0)
income_transpose = income.T
income_transpose.head()
while(True):
try:
year = input("Please enter the year between 1800 and 2012, or 'Finish': ")
if year == 'Finish':
for y in range(2007, 2013, 1):
print ('Plot Year '+str())
merged = merge_by_year(countries, income, y)
tools = dataTool(y,merged)
tools.boxplot()
tools.histogram()
print('Finish!')
sys.exit(0)
elif year.isdigit() and int(year) >= 1800 and int(year) <= 2012:
year = int(year)
visual_income_dist(year,income)
else:
print ('invalid year')
except KeyboardInterrupt:
sys.exit(1)
54 changes: 54 additions & 0 deletions .metadata/.plugins/org.eclipse.core.resources/.history/37/1000204941b700161ef6bd678dc0777a
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,54 @@
import matplotlib.pyplot as plt
import pandas as pd
'''
Created on Nov 30, 2016

@author: peimengsui
@desc: define functions and a class for data analysis tool
'''
def visual_income_dist(year,dataset):
'''
this function plots distribution over countries of the income per person for a given year
'''
plt.hist(dataset[year].dropna().values)
plt.title("distribution of income per person across all countries_"+str(year))
plt.xlabel("income_per_person")
plt.ylabel("count")
plt.draw()
plt.close()
def merge_by_year(coutries,income,year):
'''
this function merges the countries and income data sets for any given year
'''
income_year = pd.DataFrame(income[year])
merged = pd.merge(coutries,income_year,left_index=True,right_index=True)
merged["Country"] = merged.index
merged.rename(columns = {year:'Income'}, inplace = True)
return merged
class dataTool:
'''
this class includes tools for data analysis on income country datasets
'''
def __init__(self, year,dataset):
'''
Constructor
'''
self.year = year
self.dataset = dataset
def boxplot(self):
self.dataset.boxplot('Income', by = 'Region')
plt.title("boxplot of income by region_"+str(self.year))
plt.xlabel('region')
plt.ylabel('income_per_person')
plt.draw()
plt.savefig('boxplot_'+str(self.year)+'.pdf')
plt.close()
def histogram(self):
plt.hist(self.dataset["Income"].dropna().values)
plt.title("histogram of income_"+str(self.year))
plt.xlabel("income_per_person")
plt.ylabel("count")
plt.draw()
plt.savefig('histogram_'+str(self.year)+'.pdf')
plt.close()

51 changes: 51 additions & 0 deletions .metadata/.plugins/org.eclipse.core.resources/.history/3d/d052b18d3fb700161ef6bd678dc0777a
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
import matplotlib.pyplot as plt
import pandas as pd
'''
Created on Nov 30, 2016

@author: peimengsui
@desc: define functions and a class for data analysis tool
'''
def visual_income_dist(year,dataset):
'''
this function plots distribution over countries of the income per person for a given year
'''
plt.hist(dataset[year].dropna().values)
plt.title("distribution of income per person across all countries_"+str(year))
plt.xlabel("income_per_person")
plt.ylabel("count")

def merge_by_year(coutries,income,year):
'''
this function merges the countries and income data sets for any given year
'''
income_year = pd.DataFrame(income[year])
merged = pd.merge(coutries,income_year,left_index=True,right_index=True)
merged["Country"] = merged.index
merged.rename(columns = {year:'Income'}, inplace = True)
return merged
class dataTool:
'''
this class includes tools for data analysis on income country datasets
'''
def __init__(self, year,dataset):
'''
Constructor
'''
self.year = year
self.dataset = dataset
def boxplot(self):
self.dataset.boxplot('Income', by = 'Region')
plt.title("boxplot of income by region_"+str(self.year))
plt.xlabel('region')
plt.ylabel('income_per_person')
plt.savefig('boxplot_'+str(self.year)+'.pdf')
plt.close()
def histogram(self):
plt.hist(self.dataset["Income"].dropna().values)
plt.title("histogram of income_"+str(self.year))
plt.xlabel("income_per_person")
plt.ylabel("count")
plt.savefig('histogram_'+str(self.year)+'.pdf')
plt.close()

33 changes: 33 additions & 0 deletions .metadata/.plugins/org.eclipse.core.resources/.history/46/9031e16e44b700161bd9849ad48630d5
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,33 @@
import pandas as pd
from dataTool import *
import sys
'''
Created on Nov 30, 2016

@author: peimengsui
@desc: this program runs a user interactive data analysis tool on income country dataset
'''

if __name__ == '__main__':
countries = pd.read_csv('countries.csv',index_col=0)
income = pd.read_excel('indicator gapminder gdp_per_capita_ppp.xlsx',index_col=0)
income_transpose = income.T
print(income_transpose.head())
while(True):
try:
year = input("Please enter the year between 1800 and 2012, or 'Finish': ")
if year == 'Finish':
for y in range(2007, 2013, 1):
merged = merge_by_year(countries, income, y)
tools = dataTool(y,merged)
tools.boxplot()
tools.histogram()
print('Finish!')
sys.exit(0)
elif year.isdigit() and int(year) >= 1800 and int(year) <= 2012:
year = int(year)
visual_income_dist(year,income)
else:
print ('invalid year')
except KeyboardInterrupt:
sys.exit(1)
49 changes: 49 additions & 0 deletions .metadata/.plugins/org.eclipse.core.resources/.history/47/505dd8651ab700161b82ee8d880ca29b
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,49 @@
import matplotlib.pyplot as plt
import pandas as pd
'''
Created on Nov 30, 2016

@author: peimengsui
@desc: define functions and a class for data analysis tool
'''
def visual_income_dist(year,dataset):
'''
this function plots distribution over countries of the income per person for a given year
'''
plt.hist(dataset[year].dropna().values)
plt.title("distribution of income per person across all countries_"+str(year))
plt.xlabel("income_per_person")
plt.ylabel("count")

def merge_by_year(coutries,income,year):
'''
this function merges the countries and income data sets for any given year
'''
income_year = pd.DataFrame(income[year])
merged = pd.merge(coutries,income_year,left_index=True,right_index=True)
merged["Country"] = merged.index
merged.rename(columns = {year:'Income'}, inplace = True)
return merged
class dataTool:
'''
this class includes tools for data analysis on income country datasets
'''
def __init__(self, year,dataset):
'''
Constructor
'''
self.year = year
self.dataset = dataset
def boxplot(self):
self.dataset.boxplot('Income', by = 'Region')
plt.title("boxplot of income by region_"+str(self.year))
plt.xlabel('region')
plt.ylabel('income_per_person')
plt.savefig('boxplot_'+str(self.year)+'.pdf')
def histogram(self):
plt.hist(self.dataset["Income"].dropna().values)
plt.title("histogram of income_"+str(self.year))
plt.xlabel("income_per_person")
plt.ylabel("count")
plt.savefig('histogram_'+str(self.year)+'.pdf')

Loading