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) dis_shi[i].append(0) for i in range(len(dis_com)): index1 = communities.tolist().index(dis_com[i][1]) index0 = dis_new.index(dis_com[i][0]) dis_shi[index0][0] = dis_shi[index0][0] + com_shi[index1][1] dis_shi[index0][1] = dis_shi[index0][1] + com_shi[index1][3] for i in range(m): dis_shi[i].append(round(dis_shi[i][1] / dis_shi[i][0] * 100, 2)) shi_district = [] for i in range(m): shi_district.append([]) shi_district[i].append(dis_new[i]) shi_district[i].append(dis_shi[i][0]) shi_district[i].append(dis_shi[i][1]) shi_district[i].append(dis_shi[i][2]) processData.write_csv('district_shi.csv', shi_district, ['District', 'total_units', 'shi_units', '%'])
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) processData.write_csv('data\\ct_transportation.csv', X_ct, header_ct)
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) processData.write_csv('data\\ct_housing_vacant.csv', X_ct, header_ct)