def rstfld_to_slope(rst_folder, dclv_folder, out_name, perc_folder=None):
"""
Run slope for each raster in folder
"""
import os
import pandas as pd
import re
import multiprocessing as mp
from glass.g.wenv.grs import run_grass
from glass.pys.oss import cpu_cores, lst_ff
from glass.pys.oss import fprop
from glass.ng.pd.split import df_split
def run_slope(tid, inrsts, outfolder, oname, percentage):
"""
Thread function
"""
iirsts = inrsts.mdt.tolist()
# Create GRASS GIS Location
loc_name = f'thread_{str(tid)}'
gbase = run_grass(
outfolder, location=loc_name, srs=iirsts[0]
)
# Start GRASS GIS Session
import grass.script as grass
import grass.script.setup as gsetup
gsetup.init(gbase, outfolder, loc_name, 'PERMANENT')
from glass.g.it.rst import rst_to_grs, grs_to_rst
from glass.g.rst.surf import slope
from glass.g.wenv.grs import rst_to_region
for rst in iirsts:
# Import data
mdt = rst_to_grs(rst, fprop(rst, 'fn'))
# Set region
rst_to_region(mdt)
# Get ID in name
mdt_id = re.search(r'\d+', mdt).group()
# Get slope
if percentage:
slope_perc = slope(
mdt, f"pp_{oname}_{mdt_id}",
data='percent'
)
slope_degr = slope(
mdt, f"{oname}_{mdt_id}", data='degrees'
)
# Export
if percentage:
grs_to_rst(slope_perc, os.path.join(
percentage, slope_degr + '.tif'
))
grs_to_rst(slope_degr, os.path.join(
outfolder, slope_degr + '.tif'
))
# List Rasters
rsts = pd.DataFrame(
lst_ff(rst_folder, file_format='.tif'),
columns=['mdt']
)
# Split rasters by threads
ncpu = cpu_cores()
dfs = df_split(rsts, ncpu)
# Run slope using multiprocessing
thrds = [mp.Process(
target=run_slope, name=f"th_{str(i)}",
args=(i+1, dfs[i], dclv_folder, out_name, perc_folder)
) for i in range(len(dfs))]
for t in thrds:
t.start()
for t in thrds:
t.join()
return dclv_folder
def thrd_dem(countours_folder, ref_folder, dem_folder, attr,
refFormat='.tif', countoursFormat='.shp', demFormat='.tif',
cellsize=10, masksFolder=None, masksFormat='.tif',
method="COUNTOURS"):
"""
Produce DEM using GRASS GIS for all Feature Classes in countours_Folder
E.g. countours_folder
1 | data_1.shp
2 | data_2.shp
E.g. ref_folder
1 | lmt_dem_1.tif
2 | lmt_dem_2.tif
Filenames must have their id before the extension; '_' must be used to
separate id from basename.
Methods Available:
* IDW;
* BSPLINE;
* SPLINE;
* CONTOUR;
"""
import os
import multiprocessing as mp
import pandas as pd
from glass.pys.oss import cpu_cores, lst_ff, mkdir
from glass.ng.pd.split import df_split
# List Ref Files
ref = [[
int(l.split('.')[0].split('_')[-1]), l
] for l in lst_ff(
ref_folder, file_format=refFormat, rfilename=True
)]
# List Countours Files
countours = [[
int(c.split('.')[0].split('_')[-1]), c
] for c in lst_ff(
countours_folder, file_format=countoursFormat, rfilename=True
)]
# List masks if necessary
masks = None if not masksFolder else [[
int(m.split('.')[0].split('_')[-1]), m
] for m in lst_ff(
masksFolder, file_format=masksFormat, rfilename=True
)]
# Produce DataFrame to better mapping
df = pd.DataFrame(ref, columns=['fid', 'ref'])
jdf = pd.DataFrame(countours, columns=['jfid', 'countours'])
df = df.merge(jdf, how='left', left_on='fid', right_on='jfid')
# Add masks meta to df
if masksFolder:
mdf = pd.DataFrame(masks, columns=['mfid', 'masks'])
df = df.merge(mdf, how='left', left_on='fid', right_on='mfid')
# List DEMs already produced
dems = lst_ff(dem_folder, file_format=demFormat, rfilename=True)
# Delete rows when dem already exists
def check_dem_exists(row):
# Get DEM name
dem_f = 'dem_{}{}'.format(str(row.fid), demFormat)
row['exists'] = 1 if dem_f in dems else 0
return row
df = df.apply(lambda x: check_dem_exists(x), axis=1)
df = df[df.exists == 0]
# Split Dfs
n_cpu = cpu_cores()
dfs = df_split(df, n_cpu)
# Function to produce DEM
def prod_dem(_df):
for idx, row in _df.iterrows():
# Get DEM name
dem_f = 'dem_{}{}'.format(str(row.fid), demFormat)
# Get GRASS GIS Workspace
gw = mkdir(os.path.join(
ref_folder, 'gw_{}'.format(str(row.fid))
), overwrite=True)
# Get mask
msk = None if not masksFolder else None if pd.isna(row.masks)\
else os.path.join(masksFolder, row.masks)
# Produce DEM
make_dem(gw, os.path.join(countours_folder, row.countours),
attr, os.path.join(dem_folder, dem_f),
os.path.join(ref_folder, row.ref),
method="CONTOUR", cell_size=cellsize, mask=msk
)
# Produce DEM
thrds = [mp.Process(
target=prod_dem, name='th-{}'.format(str(i+1)),
args=(dfs[i],)
) for i in range(len(dfs))]
for t in thrds:
t.start()
for t in thrds:
t.join()
def get_not_used_tags(OSM_FILE, OUT_TBL):
"""
Use a file OSM to detect tags not considered in the
OSM2LULC procedure
"""
import os
from glass.ng.wt import obj_to_tbl
from glass.g.tbl.filter import sel_by_attr
from glass.ng.sql.q import q_to_obj
from glass.ng.pd.split import df_split
from glass.pys.oss import fprop
from glass.g.it.osm import osm_to_gpkg
OSM_TAG_MAP = {
"DB" : os.path.join(
os.path.dirname(os.path.dirname(os.path.abspath(__file__))),
'osmtolulc.sqlite'
),
"OSM_FEAT" : "osm_features",
"KEY_COL" : "key",
"VALUE_COL" : "value",
"GEOM_COL" : "geom"
}
WORKSPACE = os.path.dirname(OUT_TBL)
sqdb = osm_to_gpkg(OSM_FILE, os.path.join(
WORKSPACE, fprop(OSM_FILE, 'fn') + '.gpkg'
))
# Get Features we are considering
ourOSMFeatures = q_to_obj(OSM_TAG_MAP["DB"], (
"SELECT {key} AS key_y, {value} AS value_y, {geom} AS geom_y "
"FROM {tbl}"
).format(
key=OSM_TAG_MAP["KEY_COL"], value=OSM_TAG_MAP["VALUE_COL"],
geom=OSM_TAG_MAP["GEOM_COL"], tbl=OSM_TAG_MAP["OSM_FEAT"]
), db_api='sqlite')
# Get Features in File
TABLES_TAGS = {
'points' : ['highway', 'man_made', 'building'],
'lines' : ['highway', 'waterway', 'aerialway', 'barrier',
'man_made', 'railway'],
'multipolygons' : ['aeroway', 'amenity', 'barrier', 'building',
'craft', 'historic', 'land_area', ''
'landuse', 'leisure', 'man_made', 'military',
'natural', 'office', 'place', 'shop',
'sport', 'tourism', 'waterway', 'power',
'railway', 'healthcare', 'highway']
}
Qs = [
" UNION ALL ".join([(
"SELECT '{keycol}' AS key, {keycol} AS value, "
"'{geomtype}' AS geom FROM {tbl} WHERE "
"{keycol} IS NOT NULL"
).format(
keycol=c, geomtype='Point' if table == 'points' else 'Line' \
if table == 'lines' else 'Polygon',
tbl=table
) for c in TABLES_TAGS[table]]) for table in TABLES_TAGS
]
fileOSMFeatures = q_to_obj(sqdb, (
"SELECT key, value, geom FROM ({}) AS foo "
"GROUP BY key, value, geom"
).format(" UNION ALL ".join(Qs)), db_api='sqlite')
_fileOSMFeatures = fileOSMFeatures.merge(
ourOSMFeatures, how='outer',
left_on=["key", "value", "geom"],
right_on=["key_y", "value_y", "geom_y"]
)
# Select OSM Features of file without correspondence
_fileOSMFeatures["isnew"] =_fileOSMFeatures.key_y.fillna(value='nenhum')
newTags = _fileOSMFeatures[_fileOSMFeatures.isnew == 'nenhum']
newTags["value"] = newTags.value.str.replace("'", "''")
newTags["whr"] = newTags.key + "='" + newTags.value + "'"
# Export tags not being used to new shapefile
def to_regular_str(row):
san_str = row.whr
row["whr_san"] = san_str
return row
for t in TABLES_TAGS:
if t == 'points':
filterDf = newTags[newTags.geom == 'Point']
elif t == 'lines':
filterDf = newTags[newTags.geom == 'Line']
elif t == 'multipolygons':
filterDf = newTags[newTags.geom == 'Polygon']
if filterDf.shape[0] > 500:
dfs = df_split(filterDf, 500, nrows=True)
else:
dfs = [filterDf]
Q = "SELECT * FROM {} WHERE {}".format(
t, filterDf.whr.str.cat(sep=" OR "))
i = 1
for df in dfs:
fn = t + '.shp' if len(dfs) == 1 else '{}_{}.shp'.format(
t, str(i)
)
try:
shp = sel_by_attr(sqdb, Q.format(
t, df.whr.str.cat(sep=" OR ")
), os.path.join(WORKSPACE, fn), api_gis='ogr')
except:
__df = df.apply(lambda x: to_regular_str(x), axis=1)
shp = sel_by_attr(sqdb, Q.format(
t, __df.whr.str.cat(sep=" OR ")
), os.path.join(WORKSPACE, fn))
i += 1
# Export OUT_TBL with tags not being used
newTags.drop(['key_y', 'value_y', 'geom_y', 'isnew', 'whr'], axis=1, inplace=True)
obj_to_tbl(newTags, OUT_TBL, sheetsName="new_tags", sanitizeUtf8=True)
return OUT_TBL
def closest_facility(incidents,
incidents_id,
facilities,
output,
impedance='TravelTime'):
"""
impedance options:
* TravelTime;
* WalkTime;
"""
import requests
import pandas as pd
import numpy as np
from glass.cons.esri import rest_token, CF_URL
from glass.g.it.esri import json_to_gjson
from glass.g.rd.shp import shp_to_obj
from glass.g.wt.shp import df_to_shp
from glass.ng.pd.split import df_split
from glass.ng.pd import merge_df
from glass.g.prop.prj import get_shp_epsg
from glass.g.prj.obj import df_prj
from glass.g.it.pd import df_to_geodf
from glass.g.it.pd import json_obj_to_geodf
from glass.cons.esri import get_tv_by_impedancetype
# Get API token
token = rest_token()
# Data to Pandas DataFrames
fdf = shp_to_obj(facilities)
idf = shp_to_obj(incidents)
# Re-project to WGS84
fdf = df_prj(fdf, 4326)
idf = df_prj(idf, 4326)
# Geomtries to Str - inputs for requests
fdf['coords'] = fdf.geometry.x.astype(str) + ',' + fdf.geometry.y.astype(
str)
idf['coords'] = idf.geometry.x.astype(str) + ',' + idf.geometry.y.astype(
str)
# Delete geometry from facilities DF
idf.drop(['geometry'], axis=1, inplace=True)
# Split data
# ArcGIS API only accepts 100 facilities
# # and 100 incidents in each request
fdfs = df_split(fdf, 100, nrows=True) if fdf.shape[0] > 100 else [fdf]
idfs = df_split(idf, 100, nrows=True) if idf.shape[0] > 100 else [idf]
for i in range(len(idfs)):
idfs[i].reset_index(inplace=True)
idfs[i].drop(['index'], axis=1, inplace=True)
for i in range(len(fdfs)):
fdfs[i].reset_index(inplace=True)
fdfs[i].drop(['index'], axis=1, inplace=True)
# Get travel mode
tv = get_tv_by_impedancetype(impedance)
# Ask for results
results = []
drop_cols = [
'ObjectID', 'FacilityID', 'FacilityRank', 'Name',
'IncidentCurbApproach', 'FacilityCurbApproach', 'IncidentID',
'StartTime', 'EndTime', 'StartTimeUTC', 'EndTimeUTC', 'Total_Minutes',
'Total_TruckMinutes', 'Total_TruckTravelTime', 'Total_Miles'
]
if impedance == 'WalkTime':
tv_col = 'walktime'
rn_cols = {'Total_WalkTime': tv_col}
ndrop = ['Total_Kilometers', 'Total_TravelTime', 'Total_Minutes']
elif impedance == 'metric':
tv_col = 'kilomts'
rn_cols = {'Total_Kilometers': tv_col}
ndrop = ['Total_WalkTime', 'Total_TravelTime', 'Total_Minutes']
else:
tv_col = 'traveltime'
rn_cols = {'Total_TravelTime': tv_col}
ndrop = ['Total_Kilometers', 'Total_WalkTime', 'Total_Minutes']
drop_cols.extend(ndrop)
for i_df in idfs:
incidents_str = i_df.coords.str.cat(sep=';')
for f_df in fdfs:
facilities_str = f_df.coords.str.cat(sep=';')
# Make request
r = requests.get(CF_URL,
params={
'facilities': facilities_str,
'incidents': incidents_str,
'token': token,
'f': 'json',
'travelModel': tv,
'defaultTargetFacilityCount': '1',
'returnCFRoutes': True,
'travelDirection':
'esriNATravelDirectionToFacility',
'impedanceAttributeName': impedance
})
if r.status_code != 200:
raise ValueError('Error when requesting from: {}'.format(
str(r.url)))
# Convert ESRI json to GeoJson
esri_geom = r.json()
geom = json_to_gjson(esri_geom.get('routes'))
# GeoJSON to GeoDataFrame
gdf = json_obj_to_geodf(geom, 4326)
# Delete unwanted columns
gdf.drop(drop_cols, axis=1, inplace=True)
# Rename some interest columns
gdf.rename(columns=rn_cols, inplace=True)
# Add to results original attributes of incidents
r_df = gdf.merge(i_df,
how='left',
left_index=True,
right_index=True)
results.append(r_df)
# Compute final result
# Put every DataFrame in a single DataFrame
fgdf = merge_df(results)
# Since facilities were divided
# The same incident has several "nearest" facilities
# We just want one neares facility
# Lets group by using min operator
gpdf = pd.DataFrame(fgdf.groupby([incidents_id]).agg({tv_col: 'min'
})).reset_index()
gpdf.rename(columns={incidents_id: 'iid', tv_col: 'impcol'}, inplace=True)
# Recovery geometry
fgdf = fgdf.merge(gpdf, how='left', left_on=incidents_id, right_on='iid')
fgdf = fgdf[fgdf[tv_col] == fgdf.impcol]
fgdf = df_to_geodf(fgdf, 'geometry', 4326)
# Remove repeated units
g = fgdf.groupby('iid')
fgdf['rn'] = g[tv_col].rank(method='first')
fgdf = fgdf[fgdf.rn == 1]
fgdf.drop(['iid', 'rn'], axis=1, inplace=True)
# Re-project to original SRS
epsg = get_shp_epsg(facilities)
fgdf = df_prj(fgdf, epsg)
# Export result
df_to_shp(fgdf, output)
return output
'/home/jasp/mrgis/cos_union/cos18/shape7.shp',
'/home/jasp/mrgis/cos_union/cos95/shape7.shp'
],
[
'/home/jasp/mrgis/cos_union/cos18/shape8.shp',
'/home/jasp/mrgis/cos_union/cos95/shape8.shp'
],
]
outshp = '/home/jasp/mrgis/cos_union/result'
srs_epsg = 3763
cpu_n = cpu_cores() / 2
df_shp = pd.DataFrame(shp_pairs, columns=['shp_a', 'shp_b'])
dfs = df_split(df_shp, cpu_n)
thrds = [
mp.Process(target=multi_run,
name='th-{}'.format(str(i + 1)),
args=(i + 1, dfs[i], outshp)) for i in range(len(dfs))
]
for t in thrds:
t.start()
for t in thrds:
t.join()
def service_areas(facilities, breaks, output, impedance='TravelTime'):
"""
Produce Service Areas Polygons
"""
import requests
from glass.cons.esri import rest_token, SA_URL
from glass.g.rd.shp import shp_to_obj
from glass.g.prj.obj import df_prj
from glass.g.it.esri import json_to_gjson
from glass.g.it.pd import json_obj_to_geodf
from glass.g.wt.shp import df_to_shp
from glass.cons.esri import get_tv_by_impedancetype
from glass.ng.pd.split import df_split
from glass.ng.pd import merge_df
from glass.g.prop.prj import get_shp_epsg
# Get Token
token = rest_token()
# Get data
pntdf = shp_to_obj(facilities)
pntdf = df_prj(pntdf, 4326)
pntdf['coords'] = pntdf.geometry.x.astype(
str) + ',' + pntdf.geometry.y.astype(str)
pntdf.drop(['geometry'], axis=1, inplace=True)
dfs = df_split(pntdf, 100, nrows=True)
# Make requests
gdfs = []
for df in dfs:
facilities_str = df.coords.str.cat(sep=';')
tv = get_tv_by_impedancetype(impedance)
r = requests.get(
SA_URL,
params={
'facilities': facilities_str,
'token': token,
'f': 'json',
'travelModel': tv,
'defaultBreaks': ','.join(breaks),
'travelDirection': 'esriNATravelDirectionToFacility',
#'travelDirection' : 'esriNATravelDirectionFromFacility',
'outputPolygons': 'esriNAOutputPolygonDetailed',
'impedanceAttributeName': impedance
})
if r.status_code != 200:
raise ValueError('Error when requesting from: {}'.format(str(
r.url)))
esri_geom = r.json()
geom = json_to_gjson(esri_geom.get('saPolygons'))
gdf = json_obj_to_geodf(geom, 4326)
gdf = gdf.merge(df, how='left', left_index=True, right_index=True)
gdfs.append(gdf)
# Compute final result
fgdf = merge_df(gdfs)
epsg = get_shp_epsg(facilities)
fgdf = df_prj(fgdf, epsg)
df_to_shp(fgdf, output)
return output
def thrd_viewshed_v2(dbname, dem, pnt_obs, obs_id):
"""
Compute Viewshed for all points in pnt_obs using
a multiprocessing approach
"""
import os
import pandas as pd
import numpy as np
from osgeo import gdal
import multiprocessing as mp
from glass.g.rd.shp import shp_to_obj
from glass.pys.oss import cpu_cores, mkdir
from glass.ng.pd.split import df_split
from glass.g.wenv.grs import run_grass
from glass.g.prop.prj import get_shp_epsg
from glass.g.wt.sql import df_to_db
from glass.pys.oss import del_file
from glass.ng.sql.db import create_db
from glass.pys.num import get_minmax_fm_seq_values
# Get Work EPSG
epsg = get_shp_epsg(pnt_obs)
# Points to DataFrame
obs_df = shp_to_obj(pnt_obs)
# Split DF by the number of cores
n_cpu = cpu_cores()
dfs = df_split(obs_df, n_cpu)
def run_viewshed_by_cpu(tid, db, obs, dem, srs,
vis_basename='vis', maxdst=None, obselevation=None):
# Create Database
new_db = create_db("{}_{}".format(db, str(tid)), api='psql')
# Points to Database
pnt_tbl = df_to_db(
new_db, obs, 'pnt_tbl', api='psql',
epsg=srs, geomType='Point', colGeom='geometry')
# Create GRASS GIS Session
workspace = mkdir(os.path.join(
os.path.dirname(dem), 'work_{}'.format(str(tid))
))
loc_name = 'vis_loc'
gbase = run_grass(workspace, location=loc_name, srs=dem)
# Start GRASS GIS Session
import grass.script as grass
import grass.script.setup as gsetup
gsetup.init(gbase, workspace, loc_name, 'PERMANENT')
from glass.g.it.rst import rst_to_grs, grs_to_rst
from glass.g.rst.surf import grs_viewshed
from glass.g.deldt import del_rst
# Send DEM to GRASS GIS
grs_dem = rst_to_grs(dem, 'grs_dem', as_cmd=True)
# Produce Viewshed for each point in obs
for idx, row in obs.iterrows():
# Get Viewshed raster
vrst = grs_viewshed(
grs_dem, (row.geometry.x, row.geometry.y),
'{}_{}'.format(vis_basename, str(row[obs_id])),
max_dist=maxdst, obs_elv=obselevation
)
# Export Raster to File
frst = grs_to_rst(vrst, os.path.join(workspace, vrst + '.tif'))
# Raster to Array
img = gdal.Open(frst)
num = img.ReadAsArray()
# Two Dimension to One Dimension
# Reshape Array
numone = num.reshape(num.shape[0] * num.shape[1])
# Get Indexes with visibility
visnum = np.arange(numone.shape[0]).astype(np.uint32)
visnum = visnum[numone == 1]
# Get Indexes intervals
visint = get_minmax_fm_seq_values(visnum)
# Get rows indexes
_visint = visint.reshape(visint.shape[0] * visint.shape[1])
visrow = _visint / num.shape[1]
visrow = visrow.astype(np.uint32)
# Get cols indexes
viscol = _visint - (visrow * num.shape[1])
# Reshape
visrow = visrow.reshape(visint.shape)
viscol = viscol.reshape(visint.shape)
# Split array
irow, erow = np.vsplit(visrow.T, 1)[0]
icol, ecol = np.vsplit(viscol.T, 1)[0]
# Visibility indexes to Pandas DataFrame
idxnum = np.full(irow.shape, row[obs_id])
visdf = pd.DataFrame({
'pntid' : idxnum, 'rowi' : irow, 'rowe' : erow,
'coli': icol, 'cole' : ecol
})
# Pandas DF to database
# Create Visibility table
df_to_db(
new_db, visdf, vis_basename,
api='psql', colGeom=None,
append=None if not idx else True
)
# Delete all variables
numone = None
visnum = None
visint = None
_visint = None
visrow = None
viscol = None
irow = None
erow = None
icol = None
ecol = None
idxnum = None
visdf = None
del img
# Delete GRASS GIS File
del_rst(vrst)
# Delete TIFF File
del_file(frst)
frst = None
thrds = [mp.Process(
target=run_viewshed_by_cpu, name='th-{}'.format(str(i+1)),
args=(i+1, dbname, dfs[i], dem, epsg,
'vistoburn', 10000, 500)
) for i in range(len(dfs))]
for t in thrds:
t.start()
for t in thrds:
t.join()
return 1
def thrd_viewshed(dem, pnt_obs, obs_id, out_folder):
"""
Compute Viewshed for all points in pnt_obs using
a multiprocessing approach
"""
import os
import multiprocessing as mp
from glass.g.rd.shp import shp_to_obj
from glass.pys.oss import cpu_cores
from glass.ng.pd.split import df_split
from glass.g.wenv.grs import run_grass
# Points to DataFrame
obs_df = shp_to_obj(pnt_obs)
# Split DF by the number of cores
n_cpu = cpu_cores()
dfs = df_split(obs_df, n_cpu)
def run_viewshed_by_cpu(tid, obs, dem, output,
vis_basename='vis', maxdst=None, obselevation=None):
# Create GRASS GIS location
loc_name = 'loc_' + str(tid)
gbase = run_grass(output, location=loc_name, srs=dem)
# Start GRASS GIS Session
import grass.script as grass
import grass.script.setup as gsetup
gsetup.init(gbase, output, loc_name, 'PERMANENT')
from glass.g.it.rst import rst_to_grs, grs_to_rst
from glass.g.rst.surf import grs_viewshed
# Send DEM to GRASS GIS
grs_dem = rst_to_grs(dem, 'grs_dem', as_cmd=True)
# Produce Viewshed for each point in obs
for idx, row in obs.iterrows():
vrst = grs_viewshed(
grs_dem, (row.geometry.x, row.geometry.y),
'{}_{}'.format(vis_basename, str(row[obs_id])),
max_dist=maxdst, obs_elv=obselevation
)
frst = grs_to_rst(vrst, os.path.join(output, vrst + '.tif'))
thrds = [mp.Process(
target=run_viewshed_by_cpu, name='th-{}'.format(str(i+1)),
args=(i+1, dfs[i], dem, out_folder,
'vistoburn', 10000, 200)
) for i in range(len(dfs))]
for t in thrds:
t.start()
for t in thrds:
t.join()
return out_folder
def osmlulc_to_s2grid(ref_raster, osmtolulc, lucol, tmp_folder, results):
"""
OSM LULC to Sentinel-2 GRID
"""
from glass.g.smp import nfishnet_fm_rst
from glass.pys.oss import lst_ff, cpu_cores
from glass.ng.wt import obj_to_tbl
from glass.ng.pd.split import df_split
from glass.g.rd.shp import shp_to_obj
from glass.g.wt.shp import df_to_shp
from glass.g.gp.ext import shpext_to_boundshp
# Create Fishnets
fishnets = mkdir(os.path.join(tmp_folder, 'fishnets_shp'))
fnet = nfishnet_fm_rst(ref_raster, 500, 500, fishnets)
# List Fishnet
df_fnet = pd.DataFrame(fnet, columns=['fishnet'])
# List results
lst_lulc = lst_ff(osmtolulc, file_format='.shp')
# Produce boundaries for each fishnet
bf = mkdir(os.path.join(tmp_folder, 'boundaries'))
def produce_bound(row):
row['bound'] = shpext_to_boundshp(
row.fishnet, os.path.join(bf, os.path.basename(row.fishnet)))
return row
df_fnet = df_fnet.apply(lambda x: produce_bound(x), axis=1)
df_fnet['idx'] = df_fnet.index
# Get CPU Numbers
n_cpu = cpu_cores()
# Split data by CPU
dfs = df_split(df_fnet, n_cpu)
thrds = [
mp.Process(target=thrd_lulc_by_cell,
name='th_{}'.format(str(i + 1)),
args=(i + 1, dfs[i], lst_lulc, tmp_folder))
for i in range(len(dfs))
]
for i in thrds:
i.start()
for i in thrds:
i.join()
# Re-list fishnets
fish_files = df_fnet.fishnet.tolist()
for fishp in fish_files:
# List Intersection files for each fishnet
int_files = lst_ff(os.path.join(tmp_folder, fprop(fishp, 'fn')),
file_format='.shp')
if not len(int_files):
continue
# Open Fishnet
fish_df = shp_to_obj(fishp)
fish_df.rename(columns={'FID': 'fid'}, inplace=True)
fish_df['area'] = fish_df.geometry.area
# Open other files
for f in int_files:
fn = fprop(f, 'fn')
df = shp_to_obj(f)
if fn != 'ovl_union':
df = df[~df['b_' + lucol].isnull()]
clsid = df['b_' + lucol].unique()[0]
else:
df = df[~df.b_refid.isnull()]
clsid = None
if fn == 'ovl_union':
df['areav'] = df.geometry.area
df = pd.DataFrame({
'areav':
df.groupby(['a_FID'])['areav'].agg('sum')
}).reset_index()
fish_df = fish_df.merge(df,
how='left',
left_on='fid',
right_on='a_FID')
if fn != 'ovl_union':
fish_df['lu_' +
str(clsid)] = fish_df.areav * 100 / fish_df.area
else:
fish_df['overlay'] = fish_df.areav * 100 / fish_df.area
fish_df.drop(['areav', 'a_FID'], axis=1, inplace=True)
# Save file
df_to_shp(fish_df, os.path.join(results, os.path.basename(fishp)))
# Write List of Fishnet
obj_to_tbl(df_fnet, os.path.join(results, 'fishnet_list.xlsx'))
return results
def search_by_keyword(db, out_tbl, qarea, wgrp=None):
"""
Get data using keywords
"""
import os
import pandas as pd
from multiprocessing import Process, Manager
from glass.cons.dsn import search_words, tw_key
from glass.ng.pd import merge_df
from glass.ng.pd.split import df_split
from glass.g.wt.sql import df_to_db
# Get API Keys
keys = tw_key()
# Get search words
words = search_words(group=wgrp)
# Split search words
search_words = [words] if len(keys) == 1 else df_split(words, len(keys))
# Search for data
with Manager() as manager:
DFS = manager.list()
LOG_LST = manager.list()
DROP_COLS = ["retweeted"]
# Create Threads
thrds = [Process(
name='tk{}'.format(str(i)), target=get_tweets,
args=(DFS, LOG_LST, search_words[i], qarea, keys[i], DROP_COLS, i)
) for i in range(len(search_words))]
for t in thrds:
t.start()
for t in thrds:
t.join()
if not len(DFS):
raise ValueError('NoData was collected!')
# Merge all dataframes
if len(DFS) == 1:
all_df = DFS[0]
else:
all_df = merge_df(DFS, ignIndex=True, ignoredfstype=True)
all_df.rename(columns={"user" : "username"}, inplace=True)
# Sanitize time reference
all_df['daytime'] = pd.to_datetime(all_df.tweet_time)
all_df.daytime = all_df.daytime.astype(str)
all_df.daytime = all_df.daytime.str.slice(start=0, stop=-6)
all_df.drop('tweet_time', axis=1, inplace=True)
# Rename cols
all_df.rename(columns={
'text' : 'txt', 'tweet_lang' : 'tlang', 'user_id' : 'userid',
'user_location' : 'userloc', 'place_country' : 'placecountry',
'place_countryc' : 'placecountryc', 'place_name' : 'placename',
'place_box' : 'placebox', 'place_id' : 'placeid',
'followers_count' : 'followersn'
}, inplace=True)
# Data to new table
df_to_db(db, all_df, out_tbl, append=True, api='psql')
# Write log file
log_txt = os.path.join(
os.path.dirname(os.path.abspath(__file__)),
'{}-log.txt'.format(out_tbl)
)
with open(log_txt, 'w') as f:
f.write("\n".join(LOG_LST))
return log_txt
