Reduce inconsistencies between 1996 and 2001 objects

finchie

Sep 7, 2023, 2:35 PM

4YKXEBAVKKIWUC6EIG4MGSTZOHD7XJSO5O4YNU3OK5SPKMIWX7YQC

Dependencies

• [2] 2AE4VE7U Add support for 2001 census
• [3] 7ZN6HHL2 Extract relevant census data
• [4] FCHAPZLD Implement simpler file merging function
• [5] QU7MDQED Add basic support for 1996 census data

Change contents

• edit in project.py at line 70
  [2.468]→[2.468:496](∅→∅)
  − # TODO: use this everywhere
• replacement in project.py at line 83
  [2.786]→[2.786:827](∅→∅)
  − def parse_financial_bracket(start, end):
  [2.786]

  [2.827]
  + def parse_financial_bracket(text):

  + [start, end] = text.split("-")
• edit in project.py at line 120
  [2.1483]→[3.1306:1717](∅→∅),[3.1306]→[3.1306:1717](∅→∅)
  −

  − # Extract the median rent (midpoint between range) for each column

  − median_rents = self.median_rents()

  − # Extract the median household income (midpoint between each range) for each bracket

  − median_incomes = self.median_incomes()

  − # Extract the actual table

  − population_data = self.population_data()

  −

  − from pprint import pprint

  −

  − pprint(population_data)
• replacement in project.py at line 149
  [3.2879]→[3.2879:2921](∅→∅)
  − return (start_ranges, end_ranges)
  [3.2879]

  [3.2921]
  + brackets = []

  +

  + for bracket in range(len(start_ranges)):

  + brackets.append(start_ranges[bracket] + end_ranges[bracket])

  +

  + return brackets
• replacement in project.py at line 157
  [3.3471]→[3.3471:3536](∅→∅)
  − (start_ranges, end_ranges) = self.filter_rent_brackets()
  [3.3471]

  [3.3536]
  + brackets = self.filter_rent_brackets()
• replacement in project.py at line 159
  [3.3615]→[3.3615:3760](∅→∅)
  − rents = []

  − for column in range(len(start_ranges)):

  − start = start_ranges[column]

  − end = end_ranges[column]
  [3.3615]

  [3.3760]
  + rents = {}

  +

  + for bracket in range(len(brackets)):

  + (start, end) = parse_financial_bracket(brackets[bracket])

  +

  + median_rent = (start + end + 1) // 2
• replacement in project.py at line 166
  [3.3761]→[2.1809:1886](∅→∅)
  − # Strip hypen suffix from `start`

  − start = start[:-1]
  [3.3761]

  [2.1886]
  + # Total population is sum of column

  + total_population = 0

  + for row in self.filter_income_brackets():

  + total_population += int(row[bracket + 1])
• replacement in project.py at line 171
  [2.1887]→[2.1887:1950](∅→∅),[2.1950]→[3.3824:3873](∅→∅),[3.3824]→[3.3824:3873](∅→∅)
  − (start, end) = parse_financial_bracket(start, end)

  − rents.append((start + end + 1) // 2)
  [2.1887]

  [3.3873]
  + rents[median_rent] = total_population
• replacement in project.py at line 176
  [3.3934]→[3.3934:3988](∅→∅)
  − rows = self.POPULATION_BY_INCOME.splitlines()
  [3.3934]

  [3.3988]
  + rows = tabulate(self.POPULATION_BY_INCOME)
• replacement in project.py at line 179
  [3.4038]→[3.4038:4321](∅→∅)
  − assert rows[0].startswith("Negative income")

  − assert rows[1].startswith("Nil income")

  − assert rows[-3].startswith('"$2,000 or more"')

  − assert rows[-2].startswith("Partial income stated(a)")

  − assert rows[-1].startswith("All incomes not stated(b)")
  [3.4038]

  [3.4321]
  + assert rows[0][0] == "Negative income"

  + assert rows[1][0] == "Nil income"

  + assert rows[-3][0] == "$2000 or more"

  + assert rows[-2][0] == "Partial income stated(a)"

  + assert rows[-1][0] == "All incomes not stated(b)"
• replacement in project.py at line 185
  [3.4322]→[3.4322:4348](∅→∅)
  − rows = rows[2:-3]
  [3.4322]

  [3.4348]
  + return rows[2:-3]
• edit in project.py at line 187
  [3.4349]→[3.4349:4369](∅→∅),[3.4577]→[3.4577:4578](∅→∅)
  − return rows

  −
• replacement in project.py at line 188
  [3.4608]→[3.4608:4629](∅→∅)
  − incomes = []
  [3.4608]

  [3.4629]
  + incomes = {}
• replacement in project.py at line 191
  [2.2001]→[3.4734:4849](∅→∅),[3.4734]→[3.4734:4849](∅→∅),[3.4849]→[2.2002:2047](∅→∅)
  − # Two dollar amounts separated by a hyphen ('-')

  − # row[0] will be values such as: '$1-$39'

  − [start, end] = row[0].split("-")
  [2.2001]

  [3.4895]
  + (start, end) = parse_financial_bracket(row[0])

  + median_rent = (start + end + 1) // 2
• replacement in project.py at line 194
  [3.4896]→[3.4896:5034](∅→∅),[3.5034]→[2.2048:2087](∅→∅),[2.2087]→[3.5074:5316](∅→∅),[3.5074]→[3.5074:5316](∅→∅)
  − # Make sure we've got data in the right shape

  − assert start.startswith("$")

  − assert end.startswith("$")

  − assert should_keep(row[0])

  −

  − # Strip prefixes

  − start = start[1:]

  − end = end[1:]

  −

  − # Downcast and calculate midpoint

  − start = int(start)

  − end = int(end)

  − incomes.append((start + end + 1) // 2)
  [3.4896]

  [3.5316]
  + # The last column is a 'total' amount

  + population = int(row[-1])

  + incomes[median_rent] = population
• replacement in project.py at line 234
  [2.2668]→[2.2668:2775](∅→∅)
  − brackets = []

  − for row in rows:

  − brackets.append(row[0])

  − return brackets
  [2.2668]

  [2.2775]
  + return rows
• edit in project.py at line 238
  [2.2850]

  [2.2850]
  + median_rents = {}
• replacement in project.py at line 243
  [2.3024]→[2.3024:3137](∅→∅)
  − [start, end] = rents[rent].split("-")

  − (start, end) = parse_financial_bracket(start, end)
  [2.3024]

  [2.3137]
  + (start, end) = parse_financial_bracket(rents[rent][0])
• replacement in project.py at line 245
  [2.3138]→[2.3138:3187](∅→∅)
  − rents[rent] = (start + end + 1) // 2
  [2.3138]

  [2.3187]
  + median_rent = (start + end + 1) // 2

  + total_population = int(rents[rent][-1])
• replacement in project.py at line 248
  [2.3188]→[2.3188:3209](∅→∅)
  − return rents
  [2.3188]

  [3.5782]
  + median_rents[median_rent] = total_population

  +

  + return median_rents
• replacement in project.py at line 261
  [2.3532]→[2.3532:3613](∅→∅)
  − incomes = []

  − for row in rows:

  − incomes.append(row[0])
  [2.3532]

  [2.3613]
  + return rows
• edit in project.py at line 263
  [2.3614]→[2.3614:3638](∅→∅)
  − return incomes

  −
• edit in project.py at line 265
  [2.3718]

  [2.3718]
  + median_incomes = {}
• replacement in project.py at line 268
  [2.3762]→[2.3762:3879](∅→∅)
  − [start, end] = incomes[income].split("-")

  − (start, end) = parse_financial_bracket(start, end)
  [2.3762]

  [2.3879]
  + (start, end) = parse_financial_bracket(incomes[income][0])
• replacement in project.py at line 270
  [2.3880]→[2.3880:3933](∅→∅)
  − incomes[income] = (start + end + 1) // 2
  [2.3880]

  [2.3933]
  + median_income = (start + end + 1) // 2

  + total_population = int(incomes[income][-1])

  +

  + median_incomes[median_income] = total_population
• replacement in project.py at line 275
  [2.3934]→[2.3934:3957](∅→∅)
  − return incomes
  [2.3934]

  [2.3957]
  + return median_incomes
• edit in project.py at line 506
  [3.6014]→[2.3960:3982](∅→∅)
  − # data = Census1996()
• replacement in project.py at line 507
  [2.3983]→[2.3983:4020](∅→∅)
  − data = Census2001().median_incomes()
  [2.3983]

  [3.7984]
  + print(Census1996().median_incomes())

  + print(Census1996().median_rents())

  + print(Census2001().median_incomes())

  + print(Census2001().median_rents())