"""
@author: Bin Xu-Sigurdsson, Fraunhofer ISE
"""
import os
import pandas as pd
import geopandas as gpd
from shapely.geometry import Point
import osmnx as ox
import warnings
warnings.simplefilter(action='ignore', category=FutureWarning)
import shapely
import numpy as np
#from pyproj import Proj, transform
from collections import Counter
# may need to change this
filepath = r'C:\street_segmentation'
def read_csv(file):
"""
read csv file and find the centriod of polygons
"""
try:
if os.path.exists(file):
data = pd.read_csv(file, skiprows=[i for i in range(0,19)],header=None, sep =";", decimal = ",")
data.columns = data.iloc[0]
data = data.loc[2:1790]
data.iloc[:,39:52]= data.iloc[:,39:52].apply(pd.to_numeric, errors='coerce', axis=1)
data['Longitude'] = [x.replace(',', '.') for x in data['Longitude']]
data['Longitude'] = data['Longitude'].astype(float)
data['Latitude'] = [x.replace(',', '.') for x in data['Latitude']]
data['Latitude'] = data['Latitude'].astype(float)
data['X-coordinate'] = [x.replace(',', '.') for x in data['X-coordinate']]
data['X-coordinate'] = data['X-coordinate'].astype(float)
data['Y-coordinate'] = [x.replace(',', '.') for x in data['Y-coordinate']]
data['Y-coordinate'] = data['Y-coordinate'].astype(float)
#data['Title'] = data3['Title'].astype(int)
#df = gpd.GeoDataFrame(data, geometry=gpd.points_from_xy(data.Longitude, data.Latitude))
#data.loc[:,'hd_Specific_space_heating_demand']=data.loc[:,'hd_Specific_space_heating_demand'].replace(0, np.nan)
#data= data.dropna(subset=['hd_Specific_space_heating_demand'])
#data=data.drop_duplicates()
#data['centriod_coord'] = data['geometry'].apply(lambda x: x.centroid)
return(data)
except OSError:
print('Error: Input file is missing %s' %(file))
# def proj2lonlat(x1, y1):
# """
# """
# inProj = Proj(init= goal_crs)
# outProj = Proj(init='epsg:4326')
# x2,y2 = transform(inProj,outProj,x1,y1)
# return(x2,y2)
def get_osm(outputfile):
"""
get osm street data
save graph nodes and edges as ESRI shapefiles to disk.
"""
#f = file.total_bounds
#lonmin, latmin = proj2lonlat(f[0], f[1])
#lonmax, latmax = proj2lonlat(f[2], f[3])
n,s,e,w = latmax+0.001,latmin-0.001, lonmax+0.001,lonmin-0.001
custom_filter = '["highway"~"primary|secondary|tertiary|service|residential|living_street|unclassified"]'
graph = ox.graph_from_bbox(n,s,e,w,
network_type=None,
infrastructure='way["highway"]',
custom_filter=custom_filter)
#ox.plot_graph(graph)
ox.save_graph_shapefile(graph, filename= outputfile)
def createFolder(foldername):
"""
create one folder, where downloaded data should be
"""
try:
if not os.path.exists(os.path.join(filepath, foldername)):
os.makedirs(os.path.join(filepath, foldername))
except OSError:
print ('Error: Creating directory. ' + os.path.join(filepath,foldername))
def save_as_shp(dd, output_n):
"""
reprojecting and save as shp
"""
ddf = gpd.GeoDataFrame(dd, geometry='geometry', crs= dd.crs)
#ddf.crs = {"init" :"epsg:4326"}
#ddf.crs = dd.crs
ddf_prj = ddf.to_crs("EPSG:31467")
ddf_prj.to_file(driver = 'ESRI Shapefile', filename = output_n)
def processing_save(dd, intsect_pts, seg_lines):
"""
dd: read osm data
intsect_pts: filename of intersection points(nodes)
seg_lines: filename of edges
"""
edges = gpd.read_file(dd)
edges = edges[(edges['highway'] != 'secondary_link') & (edges['highway'] != 'primary_link') & (edges['highway'] != 'tertiary_link')]
edges = edges[['highway','geometry']]
edges['ID'] = range(1,(len(edges)+1))
# finding all end points of the lines
multi_pts = [ll.boundary for ll in edges['geometry']]
pts_ls = [Point(i.x, i.y) for sim_l in multi_pts for i in sim_l]
dd = pd.DataFrame(pts_ls)
dd.columns = ['geometry']
# convert to wkb
dd.loc[:, 'geometry'] = dd['geometry'].apply(lambda geom: geom.wkb)
# delete duplicates
dd = dd.drop_duplicates(['geometry'])
# convert back to shapely geometry
dd.loc[:, 'geometry'] = dd['geometry'].apply(lambda geom: shapely.wkb.loads(geom))
dd['ID'] = range(1,(len(dd)+1))
dd.crs = edges.crs
save_as_shp(dd, intsect_pts)
save_as_shp(edges, seg_lines)
def find_neigh(file_p, file_l):
"""
file_p: file of intersection points(nodes)
file_l: file of edges
calculate the length of each edges
and find adjacent edges
"""
point_f = gpd.read_file(file_p)
lines_f = gpd.read_file(file_l)
lines_f['start_p'] = np.nan
lines_f['end_p'] = np.nan
for index, row in lines_f.iterrows():
myrow = str(lines_f.geometry[index])
res_str = myrow[myrow.find("(")+1:myrow.find(")")]
res = res_str.split(',')
lines_f.loc[index,'start_p'] = res[0]
lines_f.loc[index,'end_p'] = res[-1].strip()
connected_str = []
for i, r in point_f.iterrows():
this_row = str(point_f.geometry[i])
this_row_str = this_row[this_row.find("(")+1:this_row.find(")")]
t = lines_f[(lines_f['start_p'] == this_row_str) | (lines_f['end_p'] == this_row_str)].ID.tolist()
connected_str.append(t)
final_res =[]
for i in range(1,len(lines_f)+1):
mergerd = list(filter(lambda x: i in x, connected_str))
mergerd_flatting = [val for sublist in mergerd for val in sublist]
mergerd_flatting_clean = list(set(mergerd_flatting))
m1 = [x for x in mergerd_flatting_clean if x != i]
m2 = [i] + m1
final_res.append(m2)
lines_f['neighbor'] = [i[1:] for i in final_res]
#lines_f= lines_f.to_crs(goal_crs)
lines_f.loc[:, 'length'] = round(lines_f['geometry'].length,3)
# Change order of the columns
lines_f = lines_f[['ID','geometry','length','neighbor']]
return(lines_f)
def get_index_minvalue(mylist):
"""
find the smallest value in a list and its index
"""
min_val = min(mylist)
myindex = [i for i, x in enumerate(mylist) if x == min(mylist)]
return(min_val, myindex)
def reclassiy_building_age(row):
if row["Year of construction"] <= 1948:
return('Before 1948')
elif (row["Year of construction"] >= 1949) and (row["Year of construction"] <= 1971):
return('1949-1971')
elif (row["Year of construction"] >= 1972) and (row["Year of construction"] <= 1990):
return('1972-1990')
elif (row["Year of construction"] >= 1991) and (row["Year of construction"] <= 2010):
return('1991-2010')
else:
return('After 2011')
def listToString(org_list, seperator=' '):
""" Convert list to string, by joining all item in list with given separator.
Returns the concatenated string """
if org_list is None:
return ''
else:
return seperator.join(org_list)
def min_distance(hf, outputf, output_n):
"""
hf: heating demand file (building)
find the nearest road segment
"""
# creating a geometry column
#hf['geometry'] = [Point(xy) for xy in zip(hf['X-coordinate'],hf['Y-coordinate'])]
hf["nearest_distance"] = np.nan
hf["ID"] = np.nan
line = find_neigh(save_pts, save_lines)
hf = gpd.GeoDataFrame(hf, geometry=gpd.points_from_xy(hf['X-coordinate'], hf['Y-coordinate']))
for i, r in hf.iterrows():
value_list = []
p = hf.loc[i,"geometry"]
for index, row in line.iterrows():
value_list.append(p.distance(row["geometry"]))
val_min, val_ind = get_index_minvalue(value_list)
hf.loc[i, "nearest_distance"] = round(val_min,1)
hf.loc[i, "ID"] = int(line.ID[val_ind].tolist()[0])# get the ID of line
merged = pd.merge(left = hf, right = line, how = 'left',left_on='ID', right_on='ID')
merged["Year of construction"] = merged["Year of construction"].apply(pd.to_numeric)
merged["Class year of construction"] = merged.apply(reclassiy_building_age, axis=1)
merged.iloc[:,39:52]= merged.iloc[:,39:52].apply(pd.to_numeric, errors='coerce', axis=1)
merge_sum = merged.groupby(["ID"]).sum()
#merge_sum = merge_sum.iloc[:,1:16]
df = pd.DataFrame(columns=["ID"])
col = ["GMLId", "Class year of construction","PrimaryUsageZoneType"]
for j in col:
res = merged.groupby(["ID"])[j].apply(lambda group_series: group_series.tolist()).reset_index()
res["Stat_" + j] = res[j].apply(lambda x: Counter(x))
df = pd.merge(res,df, on = "ID",how='outer')
df = df[["ID", "GMLId","Stat_PrimaryUsageZoneType","Stat_Class year of construction"]]
df["Building_Count"]= df["GMLId"].apply(lambda x: len(x))
df_res = pd.merge(df,merge_sum, on = "ID",how='outer')
df_res_f = pd.merge(df_res,line, on = "ID",how='outer')
df_res_f = df_res_f.round(3)
df_res_f = df_res_f[['ID', 'GMLId', 'Stat_PrimaryUsageZoneType',
'Stat_Class year of construction', 'Building_Count',
'Total Yearly Heat+DHW demand', 'January Heating Demand',
'February Heating Demand', 'March Heating Demand',
'April Heating Demand', 'May Heating Demand', 'June Heating Demand',
'July Heating Demand', 'August Heating Demand',
'September Heating Demand', 'October Heating Demand',
'November Heating Demand', 'December Heating Demand',
'nearest_distance', 'length_y', 'geometry', 'neighbor']]
df_res_f.rename(columns = {'nearest_distance': 'Total Distance',
'Stat_PrimaryUsageZoneType': 'Stat PrimaryUsageZoneType',
'Stat_Class year of construction': 'Stat Class year of construction',
'Building_Count': 'Building Count',
'length_y': 'Length'}, inplace = True)
df_res_f.to_csv(outputf, sep=";", decimal= ',', index = False)
df_res_shp = gpd.GeoDataFrame(df_res_f, geometry='geometry')
df_res_shp.crs = "EPSG:31467"
# # convert columns to string
# mycols = ['ID','GMLId', 'Building Count',
# 'Total Yearly Heat+DHW demand', 'January Heating Demand',
# 'February Heating Demand', 'March Heating Demand',
# 'April Heating Demand', 'May Heating Demand', 'June Heating Demand',
# 'July Heating Demand', 'August Heating Demand',
# 'September Heating Demand', 'October Heating Demand',
# 'November Heating Demand', 'December Heating Demand', 'Total Distance',
# 'Length']
# df_res_shp[mycols] = df_res_shp[mycols].astype(str)
mycols = ["ID","GMLId", "neighbor"]
df_res_shp[mycols] = df_res_shp[mycols].astype(str)
df_res_shp.to_file(driver = 'ESRI Shapefile', filename = output_n)
if __name__ == '__main__':
fname = os.path.join(filepath,"medium_stoeckach_lod1_lod2_merge_yoc_DIN18599_HEATING.csv")
#input_zip_file = 'stoeckach_20200514.zip'
#unzipfile(input_zip_file)
#fname = os.path.join(filepath, '2_geodatabase', ('.').join(input_zip_file.split('.')[:-1]) + '.gdb')
heating_f = read_csv(fname)
heating_f.iloc[:,39:52]= heating_f.iloc[:,39:52].apply(pd.to_numeric, errors='coerce', axis=1)
# saving building as pts
my_building_pts= gpd.GeoDataFrame(heating_f, geometry=gpd.points_from_xy(heating_f['X-coordinate'], heating_f['Y-coordinate']))
my_building_pts.crs = "EPSG:31467"
my_building_pts.to_file(driver = 'ESRI Shapefile', filename = os.path.join(filepath, 'Results', 'HFT_building_as_point.shp'))
lonmin, latmin = min(heating_f['Longitude']),min(heating_f['Latitude'])
lonmax, latmax = max (heating_f['Longitude']),max(heating_f['Latitude'])
#heating_f = heating_f[heating_f['PrimaryUsageZoneType'] != 'industry']
place = "Stoeckach, Stuttgart, Germany"
goal_crs = "EPSG:31467"
area = place.split(',')[0]
folder_name =['OSM', 'Results']
[createFolder(i) for i in folder_name]
get_osm(os.path.join(filepath, 'OSM'))
ed = os.path.join(filepath, 'OSM', 'edges', 'edges.shp')
save_pts =os.path.join(filepath, 'Results', 'Intersection_pts_v2102.shp')
save_lines =os.path.join(filepath, 'Results', 'Segmentaion_lines_v2102.shp')
if os.path.exists(ed):
processing_save(ed, save_pts, save_lines)
min_distance(heating_f, os.path.join(filepath, 'Results','stat_lines_with_industry_v2102.csv'),os.path.join(filepath, 'Results','stat_lines_with_industry_v2102.shp'))
#min_distance(heating_f, os.path.join(filepath, 'Results','stat_lines_without_industry_v2102.csv'),os.path.join(filepath, 'Results','stat_lines_without_industry_v2102.shp'))