import analysis
import processData
import numpy as np
# read data from csv file
X_housing = processData.import_csv('data\\Housing_Final.csv')
# calculate transit score
numMax = np.max(X_housing['numTransitStops'].tolist())
X_housing['TransitScore'] = 0.5 * X_housing[
'numTransitStops'] / numMax * 100 + 0.5 * X_housing['walkscore']
# calculate available land value
X_housing[
'available_land_sqft'] = X_housing['lot_areaft'] - X_housing['bldg_area']
# filter none_vacant parcels
X_housing_non_vacant = analysis.filter_luc(X_housing, 'housing_non_vacant')
# group data by district and city_and_town
X_housing_non_vacant_district = X_housing_non_vacant.pivot_table(
index=['District'],
values=['available_land_sqft', 'TransitScore', 'median_hh_income'],
aggfunc=[np.sum, np.mean])
X_housing_non_vacant_district.to_csv('data\\district_housing_non_vacant.csv')
X_housing_non_vacant_ct = X_housing_non_vacant.pivot_table(
index=['muni'],
values=['available_land_sqft', 'TransitScore', 'median_hh_income'],
aggfunc=[np.sum, np.mean])
X_housing_non_vacant_ct.to_csv('data\\ct_housing_non_vacant.csv')
import processData
import numpy as np
# read data
district_transportation = processData.import_csv(
'data\\district_transportation.csv')
ct_transportation = processData.import_csv('data\\ct_transportation.csv')
district_shi = processData.import_csv('data\\district_shi.csv')
ct_shi = processData.import_csv('data\\ct_shi.csv')
# add a column to ct_transportation and district_transportation of percentage of shi units
ct_value = ct_shi.values
district_value = district_shi.values
ct_list = ct_value[:, 0].tolist()
district_list = district_value[:, 0].tolist()
ct_transportation_list = ct_transportation.values.tolist()
district_transportation_list = district_transportation.values.tolist()
for i in district_transportation_list:
index = district_list.index(i[0])
i.append(district_value[index][3])
for i in ct_transportation_list:
index = ct_list.index(i[0])
i.append(ct_value[index][4])
# write back to file
X_district = np.array(district_transportation_list)
header_district = district_transportation.columns.values.tolist()
header_district.append('percentage_of_shi_units')
X_ct = np.array(ct_transportation_list)
header_ct = ct_transportation.columns.values.tolist()
header_ct.append('percentage_of_shi_units')
processData.write_csv('data\\district_transportation.csv', X_district,
header_district)
import processData
import numpy as np
# Read from district and communities
dis_com_df = processData.import_csv('data\\dis_com.csv')
dis_com = dis_com_df.values
# Read from communities shi form
com_shi_df = processData.import_csv('SHI_new.csv')
com_shi = com_shi_df.values
# Confine districts and communities
confined_dis_com = []
confined_dis_com.append(dis_com[0])
for i in range(1, len(dis_com)):
if dis_com[i][0] != dis_com[i - 1][0] or dis_com[i][1] != dis_com[i -
1][1]:
confined_dis_com.append(dis_com[i])
confined_dis_com = np.array(confined_dis_com)
# Select districts and communities
districts = confined_dis_com[:, 0]
communities = com_shi[:, 0]
# Transfer to set to remove duplications
dis_set = set(districts)
com_set = set(communities)
# Form a new list without duplications
dis_new = list(dis_set)
# Combine shi data according to districts
dis_shi = []
m = len(dis_set)
for i in range(m):
dis_shi.append([])
dis_shi[i].append(0)
import processData
import numpy as np
# read data from csv file
X_transportation = processData.import_csv('data\\Transportation_Final.csv')
# calculate transit score
numMax = np.max(X_transportation['numTransitStops'].tolist())
X_transportation['TransitScore'] = 0.5 * X_transportation['numTransitStops'] / numMax * 100 + 0.5 * X_transportation[
'walkscore']
# calculate available land value
X_transportation['available_land_sqft'] = X_transportation['lot_areaft'] - X_transportation['bldg_area']
# group data by district and city_and_town
X_transportation_district = X_transportation.pivot_table(index=['District'],
values=['available_land_sqft', 'TransitScore',
'median_hh_income'],
aggfunc=[np.sum, np.mean])
X_transportation_district.to_csv('data\\district_transportation.csv')
X_transportation_ct = X_transportation.pivot_table(index=['muni'],
values=['available_land_sqft', 'TransitScore', 'median_hh_income'],
aggfunc=[np.sum, np.mean])
X_transportation_ct.to_csv('data\\ct_transportation.csv')
import processData
import numpy as np
# read data
district_vacant_housing = processData.import_csv(
'data\\district_housing_vacant.csv')
ct_vacant_housing = processData.import_csv('data\\ct_housing_vacant.csv')
district_shi = processData.import_csv('data\\district_shi.csv')
ct_shi = processData.import_csv('data\\ct_shi.csv')
# add a column to ct_vacant_housing and district_vacant_housing of percentage of shi units
ct_value = ct_shi.values
district_value = district_shi.values
ct_list = ct_value[:, 0].tolist()
district_list = district_value[:, 0].tolist()
ct_vacant_housing_list = ct_vacant_housing.values.tolist()
district_vacant_housing_list = district_vacant_housing.values.tolist()
for i in district_vacant_housing_list:
index = district_list.index(i[0])
i.append(district_value[index][3])
for i in ct_vacant_housing_list:
index = ct_list.index(i[0])
i.append(ct_value[index][4])
# write back to file
X_district = np.array(district_vacant_housing_list)
header_district = district_vacant_housing.columns.values.tolist()
header_district.append('percentage_of_shi_units')
X_ct = np.array(ct_vacant_housing_list)
header_ct = ct_vacant_housing.columns.values.tolist()
header_ct.append('percentage_of_shi_units')
processData.write_csv('data\\district_housing_vacant.csv', X_district,
header_district)