hw submission for sy1253

assignment9.py

@@ -0,0 +1,49 @@
+"""
+Created on Mon Dec  5 01:37:07 2016
+
+@author: Shucheng Yan
+net ID: sy1253
+
+credit wz1070 for data structure insight and unitest
+"""
+
+import pandas as pd
+import matplotlib.pyplot as plt
+import sys
+from dataAnalysis import *
+from summaryInfo import *
+
+def main():
+     countries = pd.read_csv('countries.csv')
+     income = pd.read_excel('indicator gapminder gdp_per_capita_ppp.xlsx', index_col = 0).transpose()
+     print(income.head())
+
+     while True:
+         try:
+             input_year = input("please enter a year between 1800 and 2012 to see income distribution: ")
+             if input_year == 'finish':
+                  for year in range(2007, 2013):
+                      merged_data = mergeByYear(year, income, countries)
+                      # create an obeject for each year
+                      mergedPresent = dataAnalysis(year)
+                      #present each year's histogram and boxplot
+                      mergedPresent.histogram(merged_data)
+                      mergedPresent.boxplot(merged_data)               
+                  break
+
+             elif int(input_year) >= 1800 and int(input_year) <= 2012:
+                  inputYear = int(input_year)
+                  displaySummary(inputYear, income)
+
+         except InputValueException:
+            print("please enter a valid integer year between 1800 and 2012")                        
+         except KeyboardInterrupt:
+             sys.exit()
+         except EOFError:
+             sys.exit()
+
+
+if __name__ == "__main__":
+    main()
+
+

dataAnalysis.py

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Dec  5 10:43:13 2016
+
+@author: kevinyan
+"""
+
+import matplotlib.pyplot as plt
+
+
+
+class dataAnalysis():
+
+    def __init__(self, year):
+        self.year = year
+
+
+    def histogram(self, income):
+        """
+        The function plots a histogram of the distribution of the income per person by region data 
+        """
+        income.hist(by = 'Region', figsize = (12, 12), fontsize = 12)
+        plt.title("histogram of the distribution of the income in " + str(self.year))
+        plt.xlabel('Region')
+        plt.ylabel('Income Per Person')
+        plt.savefig('histogram in' + str(self.year) + '.pdf')
+        plt.show()
+
+
+    def boxplot(self, income):
+        """
+         The function plots a boxplot to show the distribution of the income per person by region data 
+        """
+        income.boxplot(by = 'Region', figsize = (12, 12), fontsize = 12)
+        plt.title("boxplot of the distribution of the income in " + str(self.year))
+        plt.xlabel('Region')
+        plt.ylabel('Income Per Person')
+        plt.savefig('boxplot in ' + str(self.year) + '.pdf')
+        plt.show()

results.txt

@@ -0,0 +1,7 @@
+Over the period,
+
+1. Africa has the largest percentage increase in income per person, but most of countries still remain poor compare to countries in other regions.
+
+2. The European and North America’s income per person decreased noticeably in 2008-2009 potentially due to the financial crisis.
+
+3. Other regions have relatively stable economic landscapes with small increase in the income per person.

summaryInfo.py

@@ -0,0 +1,37 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Dec  5 01:38:39 2016
+
+@author: kevinyan
+"""
+import pandas as pd
+import matplotlib.pyplot as plt
+
+def mergeByYear(year, income, countries):
+    """
+    this function merges the countries and income data sets for any given year
+    """
+    incomeSingle = pd.DataFrame(income.loc[year]).reset_index()
+    #change the category name is the previous file
+    incomeSingle = incomeSingle.rename(columns = {'gdp pc test':'Country'})
+    incomeSingle = incomeSingle.rename(columns = {year:'Income'})
+    mergedYear = pd.merge(countries, incomeSingle, on='Country')
+    return mergedYear
+
+
+def displaySummary(year, income):
+    """
+    this function uses histogram to present the distribution of income per person across all countries
+    """
+    plt.hist(income.loc[year].dropna())
+    plt.title("distribution of income per person across all countries in the world in " + str(year))
+    plt.xlabel("income per person")
+    plt.ylabel("number of countries")
+    plt.show()
+
+
+
+
+
+
+

test.py

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Dec  5 13:21:15 2016
+
+@author: kevinyan
+"""
+
+import unittest
+import pandas as pd
+from summaryInfo import *
+
+countries = pd.read_csv('countries.csv')
+income = pd.read_excel('indicator gapminder gdp_per_capita_ppp.xlsx', index_col = 0).transpose()
+
+
+class Test(unittest.TestCase):
+
+    def testMerged(self):
+        mergedTest = mergeByYear(2007,income,countries)
+        #check if the dataFrame is correctly constructed
+        self.assertTrue(all(map(lambda x: x in ['Country', 'Region', 'Income'], mergedTest)))
+        self.assertTrue(mergedTest['Country'][4], 'Burundi')
+        self.assertTrue(mergedTest['Region'][5], 'AFRICA')
+
+
+if __name__ == "__main__":
+    unittest.main()