def inreg_db(argo_db):
crs = {"init": "epsg:4326"}
fix_lon = argo_db.copy()
fix_lon["lon"] = fix_lon["lon"].apply(lambda x: x - 360 if x > 180 else x)
geometry = [Point(xy) for xy in zip(fix_lon["lon"], fix_lon["lat"])]
starts = gpd.GeoDataFrame(fix_lon, crs=crs, geometry=geometry)
SA_200 = gpd.read_file("/data/users/grivera/Shapes/costa_200mn_mask.shp")
SA_100 = gpd.read_file("/data/users/grivera/Shapes/costa_100mn_mask.shp")
SA_50 = gpd.read_file("/data/users/grivera/Shapes/costa_50mn_mask.shp")
# SA_300['geometry'] = SA_300.geometry.buffer(1)
pointIn200 = sjoin(starts, SA_200, how="left", op="within")
pointIn200 = pointIn200.dropna()
pointIn100 = sjoin(starts, SA_100, how="left", op="within")
pointIn100 = pointIn100.dropna()
pointIn50 = sjoin(starts, SA_50, how="left", op="within")
pointIn50 = pointIn50.dropna()
argo_db["in200"] = "0"
argo_db["in100"] = "0"
argo_db["in50"] = "0"
argo_db.loc[pointIn200.index, "in200"] = "1"
argo_db.loc[pointIn100.index, "in100"] = "1"
argo_db.loc[pointIn50.index, "in50"] = "1"
return argo_db
def test_sjoin_values(self):
# GH190
self.polydf.index = [1, 3, 4, 5, 6]
df = sjoin(self.pointdf, self.polydf, how='left')
self.assertEquals(df.shape, (21,8))
df = sjoin(self.polydf, self.pointdf, how='left')
self.assertEquals(df.shape, (12,8))
def _get_HU8_units_for_gdf(self, gdf: GDF) -> GDF:
"""Get HU8 units that intersect gdf
Args:
- gdf: GeoDataFrame to intersect with
Returns:
GeoDataFrame of HU8 boundaries that intersect gdf
"""
gdf = gdf.to_crs(epsg=4326)
# First find HU2 units that intersect gdf
intersecting_hu2 = []
for hu2_id in self.hu2_list:
hu2 = self._load_HU8_boundaries(hu2_id=hu2_id, region_size='HU2')
hu2 = hu2.to_crs(epsg=4326)
intersecting_hu2.append(sjoin(hu2, gdf, how='inner'))
int_hu2_gdf = gpd.GeoDataFrame(pd.concat(intersecting_hu2))
hu2_ids = int_hu2_gdf['HUC2'].values
# Npw just look within the large regions that I know gdf is in
intersecting_hu8 = []
for hu2_id in hu2_ids:
hu8 = self._load_HU8_boundaries(hu2_id=hu2_id, region_size='HU8')
hu8 = hu8.to_crs(epsg=4326)
intersecting_hu8.append(sjoin(hu8, gdf, how='inner'))
return gpd.GeoDataFrame(pd.concat(intersecting_hu8))
def test_sjoin_values(self):
# GH190
self.polydf.index = [1, 3, 4, 5, 6]
df = sjoin(self.pointdf, self.polydf, how='left')
self.assertEquals(df.shape, (21, 8))
df = sjoin(self.polydf, self.pointdf, how='left')
self.assertEquals(df.shape, (12, 8))
def _hydro_point(self, hydro, files, buffer):
point = hydro.read_files(files=files, layer='NHDPoint')
SPRING = 45800
WATERFALL = 48700
WELL = 48800
keep = [SPRING, WATERFALL]
point = point[point['FCode'].isin(keep)]
point = sjoin(point, buffer, how='inner')
len(point)
point = to_2d(point)
point
point
if len(point) > 0:
raise NotImplementedError('Water points near trail')
areal = hydro.read_files(files=files, layer='NHDArea')
areal = sjoin(areal, trail, how='inner')
if len(point) > 0:
raise NotImplementedError('Areal near trail')
w_areal = hydro.read_files(files=files, layer='NHDWaterbody')
w_areal = sjoin(w_areal, trail, how='inner')
if len(point) > 0:
raise NotImplementedError('Areal near trail')
len(w_areal)
self.buffer
def download(self,
trail: gpd.GeoDataFrame,
buffer_dist=None,
buffer_unit='mile',
overwrite=False):
"""Download polygon shapefile and intersect with PCT track
Args:
- trail: gdf of trail to use to find polygons that intersect
- buffer_dist: distance to use for trail buffer when intersecting with polygons. By default is None, so no buffer will be used.
- buffer_unit: unit to use for buffer
- overwrite: whether to overwrite existing data
"""
assert self.save_dir is not None, 'self.save_dir must be set'
assert self.url is not None, 'self.url must be set'
assert self.filename is not None, 'self.filename must be set'
# Cache original download in self.raw_dir
parsed_url = urlparse(self.url)
raw_fname = Path(parsed_url.path).name
raw_path = self.raw_dir / raw_fname
if overwrite or (not raw_path.exists()):
urlretrieve(self.url, raw_path)
# Now load the saved file as a GeoDataFrame
with open(raw_path, 'rb') as f:
with fiona.BytesCollection(f.read()) as fcol:
crs = fcol.crs
gdf = gpd.GeoDataFrame.from_features(fcol, crs=crs)
# Reproject to WGS84
gdf = gdf.to_crs(epsg=4326)
# Use provided `trail` object
trail = trail.to_crs(epsg=4326)
# Intersect with the trail
if buffer_dist is not None:
buf = geom.buffer(trail, distance=buffer_dist, unit=buffer_unit)
# Returned as GeoSeries; coerce to GDF
if not isinstance(buf, gpd.GeoDataFrame):
buf = gpd.GeoDataFrame(geometry=buf)
buf = buf.to_crs(epsg=4326)
intersection = sjoin(gdf, buf, how='inner')
else:
intersection = sjoin(gdf, trail, how='inner')
# Make sure I have valid geometries
intersection = geom.validate_geom_gdf(intersection)
# Do any specific steps, to be overloaded in subclasses
intersection = self._post_download(intersection)
# Save to GeoJSON
self.save_dir.mkdir(exist_ok=True, parents=True)
intersection.to_file(self.save_dir / self.filename, driver='GeoJSON')
def test_sjoin_right(self):
# the inverse of left
df = sjoin(self.pointdf, self.polydf, how="right")
df2 = sjoin(self.polydf, self.pointdf, how="left")
self.assertEquals(df.shape, (12, 8))
self.assertEquals(df.shape, df2.shape)
for i, row in df.iterrows():
self.assertEquals(row.geometry.type, 'MultiPolygon')
for i, row in df2.iterrows():
self.assertEquals(row.geometry.type, 'MultiPolygon')
def test_sjoin_op(self):
# points within polygons
df = sjoin(self.pointdf, self.polydf, how="left", op="within")
self.assertEquals(df.shape, (21,8))
self.assertEquals(df.ix[1]['BoroName'], 'Staten Island')
# points contain polygons? never happens so we should have nulls
df = sjoin(self.pointdf, self.polydf, how="left", op="contains")
self.assertEquals(df.shape, (21, 8))
self.assertTrue(np.isnan(df.ix[1]['Shape_Area']))
def test_sjoin_right(self):
# the inverse of left
df = sjoin(self.pointdf, self.polydf, how="right")
df2 = sjoin(self.polydf, self.pointdf, how="left")
self.assertEquals(df.shape, (12, 8))
self.assertEquals(df.shape, df2.shape)
for i, row in df.iterrows():
self.assertEquals(row.geometry.type, 'MultiPolygon')
for i, row in df2.iterrows():
self.assertEquals(row.geometry.type, 'MultiPolygon')
def test_sjoin_op(self):
# points within polygons
df = sjoin(self.pointdf, self.polydf, how="left", op="within")
self.assertEquals(df.shape, (21, 8))
self.assertAlmostEquals(df.ix[1]['Shape_Leng'], 330454.175933)
# points contain polygons? never happens so we should have nulls
df = sjoin(self.pointdf, self.polydf, how="left", op="contains")
self.assertEquals(df.shape, (21, 8))
self.assertTrue(np.isnan(df.ix[1]['Shape_Area']))
def test_sjoin_op(self):
# points within polygons
df = sjoin(self.pointdf, self.polydf, how="left", op="within")
self.assertEquals(df.shape, (21,8))
self.assertAlmostEquals(df.ix[1]['Shape_Leng'], 330454.175933)
# points contain polygons? never happens so we should have nulls
df = sjoin(self.pointdf, self.polydf, how="left", op="contains")
self.assertEquals(df.shape, (21, 8))
self.assertTrue(np.isnan(df.ix[1]['Shape_Area']))
def compute_spatial_join(df):
df = gpd.GeoDataFrame(df,
geometry=gpd.points_from_xy(df.lon, df.lat),
crs="epsg:4326")
df = sjoin(df, gdf_regions, how='left')
return df[['nuts_id', 'amenity', 'osm_id']]
def print_cid_count(node_array_x, node_array_y):
gridx = np.linspace(300000, 800000, 5)
gridy = np.linspace(3700000, 5500000, 5)
grid, _, _ = np.histogram2d(node_array_x, node_array_y, bins=[gridx, gridy])
# plotting
# plt.figure(figsize=(9, 7), dpi=90, facecolor='w', edgecolor='k')
# plt.plot(node_array_x, node_array_y, 'ro')
# plt.grid(True)
# plt.figure(figsize=(9, 7), dpi=90, facecolor='w', edgecolor='k')
# plt.pcolormesh(gridx, gridy, grid)
# plt.plot(node_array_x, node_array_y, 'ro')
# plt.colorbar()
# plt.show()
points = gpd.GeoDataFrame({"x":node_array_x,"y":node_array_y})
points['geometry'] = points.apply(lambda p: Point(p.x, p.y), axis=1)
# print(points.head(2))
# np mesh-grid to shapely polygons
hlines = [((x1, yi), (x2, yi)) for x1, x2 in list(zip(gridx[:-1], gridx[1:])) for yi in gridy]
vlines = [((xi, y1), (xi, y2)) for y1, y2 in zip(gridy[:-1], gridy[1:]) for xi in gridx]
polys = list(polygonize(MultiLineString(hlines + vlines)))
grids = list(polygonize(MultiLineString(hlines + vlines)))
cid = [i for i in range(len(grids))]
grid = gpd.GeoDataFrame({"cid":cid,"geometry":polys})
# print(grid.head(2))
# number of points in polygons
pointInPolys = sjoin(points, grid, how='left')
print(pointInPolys.groupby(['cid']).size().reset_index(name='count'))
def spatial_join(sm_geom, lg_geom):
"""
Spatially join two geographies adding data from
the larger geometry to the smaller. Then add the
geometry from the smaller geographical unit back
onto the new dataset one. Returns a GeoDataFrame.
Parameters
----------
sm_geom : GeoDataFrame
GeoDataFrame to receive data
lg_geom : GeoDataFrame
Large GeoDataFrame to apply data
"""
sm_original = sm_geom
sm_geom = sm_geom.to_crs(lg_geom.crs)
sm_geom['geometry'] = sm_geom['geometry'].centroid
df = sjoin(sm_geom, lg_geom, how="left", op="within")
df.drop(['geometry', 'index_right'], axis=1, inplace=True)
df = df.join(pd.DataFrame(sm_original['geometry'], columns=['geometry']))
return df
def createInlandList(inputDF):
'''Requires TimeStep be populated; run before calc maxwindspeed.'''
TimeStepList = []
try:
point = geopandas.GeoDataFrame(
inputDF,
geometry=geopandas.points_from_xy(
inputDF.Longitude, inputDF.Latitude)).copy()
point.crs = "epsg:4326"
try:
#polygonPath = './src/assets/spatial/inlandPolygon.shp'
polygonPath = './src/assets/spatial/inlandPolygon.json'
polygon = geopandas.GeoDataFrame.from_file(polygonPath)
except Exception as e:
print('polygon issue')
print(polygonPath)
print(e)
pointInPolys = sjoin(point, polygon, how='left')
inlandPoints = pointInPolys[
pointInPolys.index_right.notnull()].copy()
inlandPointsDF = pd.DataFrame(
inlandPoints.drop(columns='geometry'))
TimeStepList = inlandPointsDF['TimeStep'].to_list()
except Exception as e:
print('inlandlist issue')
print(e)
return TimeStepList
def test_sjoin_left(self):
df = sjoin(self.pointdf, self.polydf, how='left')
self.assertEquals(df.shape, (21,8))
for i, row in df.iterrows():
self.assertEquals(row.geometry.type, 'Point')
self.assertTrue('pointattr1' in df.columns)
self.assertTrue('BoroCode' in df.columns)
def get_neighborhood(locations, neighborhoods_geom):
points = gpd.GeoDataFrame()
points['geom'] = locations.apply(lambda x: Point(x['lng'], x['lat']),
axis=1)
points = points.set_geometry('geom')
result = sjoin(points, neighborhoods_geom, how='left')
return result['Name']
def copy_csd_data(gdf, csd):
"""
Copy csd field data/calculate geometry data to geodataframe
Attributes
----------
gdf: geodataframe
Geodataframe containing the building footprint data
csd: geodataframe
Geodataframe containing the Census Subdivision data
Returns
-------
gdf: geodataframe
An updated geodataframe with new fields containing csd and geometry data.
"""
gdf_centroids = gpd.GeoDataFrame(gdf.centroid,
geometry=gdf.centroid,
crs=gdf.crs)
gdf_centroids_csd_join = sjoin(gdf_centroids, csd, how='left', op='within')
gdf = gdf.to_crs('epsg:4326')
gdf['CSDUID'] = gdf_centroids_csd_join['CSDUID']
gdf['CSDNAME'] = gdf_centroids_csd_join['CSDNAME']
gdf['Shape_Area'] = gdf_centroids_csd_join.geometry.area
gdf['Shape_Leng'] = gdf_centroids_csd_join.geometry.length
# Update joined centroids dataframe to epsg:4326 to provide DD values
gdf_centroids_csd_join = gdf_centroids_csd_join.to_crs('epsg:4326')
gdf['Longitude'] = gdf_centroids_csd_join.geometry.x
gdf['Latitude'] = gdf_centroids_csd_join.geometry.y
return gdf
def copy_csduid(gdf, csd):
"""
Copy csd field data/calculate geometry data to geodataframe
Attributes
----------
gdf: geodataframe
Geodataframe containing the building footprint data
csd: geodataframe
Geodataframe containing the Census Subdivision data
Returns
-------
gdf: geodataframe
An updated geodataframe with new fields containing csd and geometry data.
"""
gdf_centroids = gpd.GeoDataFrame(gdf.centroid,
geometry=gdf.centroid,
crs=gdf.crs)
gdf_centroids_csd_join = sjoin(gdf_centroids, csd, how='left', op='within')
gdf = gdf.to_crs('epsg:4326')
gdf['CSDUID'] = gdf_centroids_csd_join['CSDUID']
return gdf
def brdrPctFull(zns, brdr, ncol, acol='AreaSqKM'):
'''
Arguments
---------
zns : geoDF of basin polygons
brdr : geoDF of CONUS polygon
ncol : name of the column that uniquely identifies zns polygons
acol : name of column that holds area (sq. KM)
'''
# move poly to albers, need to stay in this CRS to cal. area later
if brdr.crs != zns.crs:
brdr.to_crs(zns.crs,inplace=True)
touch = sjoin(zns,brdr,op='within')
nwin = zns.ix[~zns[ncol].isin(touch[ncol])].copy()
if len(nwin) == 0:
return pd.DataFrame()
tot = pd.DataFrame()
for idx, row in nwin.iterrows():
p = gpd.GeoDataFrame({ncol: [row[ncol]],
acol: [row[acol]]},
geometry=[row.geometry],
crs=nwin.crs)
clip = gpd.overlay(brdr, p, how='intersection')
if len(clip) == 0:
p['CatPctFull'] = 0
tot = pd.concat([tot,p.set_index(ncol)[['CatPctFull']]])
else:
out = clip.dissolve(by=ncol)
out['Area_CONUS'] = out.geometry.area * 1e-6
out['CatPctFull'] = (out['Area_CONUS'] / out[acol]) * 100
tot = pd.concat([tot,out[['CatPctFull']]])
assert len(tot) == len(nwin)
return tot
def main(): # Read in Data grid = GeoDataFrame.from_file(igrid) points = pd.read_csv(ipoints) # create geopoints geopoints = points2geo(points, lat, lon) # match projection info: ## Points - should already be in wgs84 geopoints.crs =wgs84 geopoints['geometry'] = geopoints['geometry'].to_crs(epsg=4326) ## Grid - project from meters to wgs84 grid.crs = gridproj grid['geometry'] = grid['geometry'].to_crs(epsg=4326) # create uid to groupby grid['id'] = [i for i in range(len(grid))] # Spatial join points to grid join_inner_df = sjoin(grid, geopoints, how="inner") # Group by the uid and geometry - return mean join_inner_df = join_inner_df.groupby(['id','geometry'])['Decibel'].mean() # join_inner_df = join_inner_df.groupby(['id','geometry'])['Decibel'].max() # Create geodataframe & reset the index of the file output = GeoDataFrame(join_inner_df) output = output.reset_index() # output # write to file output.to_file(ofile)
def pts_poly_join(pts, poly, poly_id_col):
"""
Simple function to join the attributes of the polygon to the points. Specifically for an ID field in the polygon.
Parameters
----------
pts: GeoDataFrame
A GeoDataFrame of points with the site names as the index.
poly: GeoDataFrame
A GeoDataFrame of polygons with the site names as the index.
poly_id_col: str or list of str
The names of the columns to join.
Returns
-------
GeoDataFrame
"""
if isinstance(poly_id_col, str):
poly_id_col = [poly_id_col]
cols = poly_id_col.copy()
cols.extend(['geometry'])
poly2 = poly[cols].copy()
poly3 = poly2.dissolve(poly_id_col).reset_index()
join1 = sjoin(pts.copy(), poly3.copy(), how='inner', op='within')
cols = set(pts.columns)
cols.update(set(poly3.columns))
join1.drop([i for i in join1.columns if i not in cols], axis=1, inplace=True)
return join1, poly3
def add_loc_ocean2df(df=None, LatVar='lat', LonVar='lon'):
"""
Add the ocean of a location to dataframe
Parameters
-------
df (pd.DataFrame): DataFrame of data
LatVar (str): variable name in DataFrame for latitude
LonVar (str): variable name in DataFrame for longitude
Returns
-------
(pd.DataFrame)
"""
from geopandas.tools import sjoin
# Get the shapes for the ocean
featurecla='ocean'
group = AC.get_shapes4oceans(rtn_group=True, featurecla=featurecla)
# Turn the dataframe into a geopandas dataframe
gdf = geopandas.GeoDataFrame(
df, geometry=geopandas.points_from_xy(df[LonVar], df[LatVar]))
# Work out if any of the points are within the polys
pointInPolys = sjoin(gdf, group, how='left')
# Check how many were assigned to a region
Nnew = float(pointInPolys['name'].dropna().shape[0])
N = float(df.shape[0])
if N != Nnew:
pstr = 'WARNING: Only {:.2f}% assigned ({} of {})'
print( pstr.format( (Nnew/N)*100, int(Nnew), int(N)) )
# Add the ocean assignment
df[featurecla] = pointInPolys['name'].values
return df
def points_in_shp(points_list, shapefile_gpd):
'''
Check if the points_list generated by libpypack.visualization.generate_maps.lat_lon_to_points()
is in the Shapefile.
Parameters
----------
point_list: list
A list of all lat, lon points generated by:
libpypack.visualization.generate_maps.lat_lon_to_points()
shapefile_gpd: dataframe
A dataframe created from a Shapefile.
Returns
-------
: list, Pandas DataFrame
pointInPolys: A list of all points that are contained in the Shapefile.
grouped: A DataFrame which has been grouped.
'''
pnts = geopandas.GeoDataFrame(geometry=points_list,
index=range(0, len(points_list)))
pointInPolys = sjoin(pnts, shapefile_gpd, how='left')
grouped = pointInPolys.groupby('index_right', as_index=False)
return pointInPolys, grouped
def covert():
# coordinates
coordinates = request.files['file']
df = pd.read_csv(coordinates)
# convert to geographic data
tmp = df[['Longitude','Latitude']].dropna()
geometry = [Point(xy) for xy in zip(tmp.Longitude, tmp.Latitude)]
crs = {'init': 'epsg:4326'} # http://www.spatialreference.org/ref/epsg/2263/
geo_df = gp.GeoDataFrame(tmp, crs=crs, geometry=geometry)
# shapefile
print(request.form)
#shfile = request.files['shfile']
#filename = secure_filename(shfile.filename)
#shfile.save('data/'+filename)
print(request.form['shfile'])
if request.form['shfile'] == 'standard':
filename = 'W:/OSZ/OMXF/SHAPEFILES/Standardized_admin_areas/ADM2/global_adm2.shp'
if request.form['shfile'] == 'RBD':
filename = 'W:/OSZ/OMXF/SHAPEFILES/RBD_GAUL_REV2019/rbd_vam_cod_bnd_admin_level_2_gaul_revised_20190304.shp'
shpf = gp.GeoDataFrame.from_file(filename)
pointInPolys = sjoin(geo_df, shpf, how='left')
output = pd.DataFrame(pointInPolys.drop('geometry', axis=1))
df = df.merge(output, on=['Longitude','Latitude'], how='left')
resp = make_response(df.to_csv())
resp.headers["Content-Disposition"] = "attachment; filename=export.csv"
resp.headers["Content-Type"] = "text/csv"
return resp
def get_stations(basin):
"""retrieves list of stations within a basin.
Parameters
----------
basin : str
Name of basin to get hydrological stations.
Returns
-------
list
list containing stations ID.
"""
points = gpd.GeoDataFrame.from_file(os.path.join(os.getcwd(),
'Station',
'stations.shp'))
polys = gpd.GeoDataFrame.from_file(os.path.join(os.getcwd(),
'basins',
'rbasin_polygon.shp'))
poly_subset = polys[polys['BNAME'] == basin]
pointInPolys = sjoin(points,
poly_subset,
how='left')
grouped = pointInPolys.groupby('index_right')
list_of_stations = list(grouped)
basin_stations = list_of_stations[0][1]
basin_stations_list = basin_stations['ID'].tolist()
return list(set(basin_stations_list))
def test_sjoin_left(self):
df = sjoin(self.pointdf, self.polydf, how='left')
self.assertEquals(df.shape, (21, 8))
for i, row in df.iterrows():
self.assertEquals(row.geometry.type, 'Point')
self.assertTrue('pointattr1' in df.columns)
self.assertTrue('BoroCode' in df.columns)
def spatial_join_pt(pt_file, poly_file, lat='lat', lon='lon'):
# """Spatially join polygon attributes to point data.
#
# 'pt_file' is a csv file with latitude and longitude attributes that
# can be interpreted as points.
#
# 'poly_file' is a geojson file that contains polygon data.
#
# lat --> latitude field in the point df
# lon --> longitude field in the point df
#
# Both layers must use the same CRS.
#
# This function returns a DataFrame, not a Geodataframe.
# """
logging.info('Loading both layers.')
df = pd.read_csv(pt_file)
pt = df_to_geodf_pt(df, lat, lon)
poly = geojson_to_geodf(poly_file)
pt.crs = poly.crs
logging.info('Operating spatial join.')
pt_join = sjoin(pt, poly, how='left')
pt_join = pt_join.drop(['geometry', 'index_right'], axis=1)
logging.info('Successfully spatially joined data.')
return pt_join
def main(inputs_dir, split_data, split_field):
"""
Entry point for merge and split processing script
Attributes:
------------
:param inputs_dir {string} - Path to the directory containing input data
:param split_data {string} - Path to the geospatial file used for splitting the combined input data
:param split_field {string} - Field name in split data used for dividing up combined input data
"""
# Combine input files into a single input dataframe
inputs_df = combine_inputs(inputs_dir)
# Read geospatial features used for splitting data
split_features = gpd.read_file(split_data)
split_features = split_features.to_crs(INPUT_CRS)
# Create centroids for all input data
input_centroids = gpd.GeoDataFrame(inputs_df.centroid,
geometry=inputs_df.centroid,
crs=inputs_df.crs)
# Intersect split data with input centroids
intersected_data = gdptools.sjoin(input_centroids,
split_features,
how='left',
op='within')
# Copy intersected split field value to input dataframe
inputs_df[split_field] = intersected_data[split_field]
# Split input data used split data
split_data_by_split_field(inputs_df, split_field)
def polygonsInPolygons(contained_polygons, container_polygons, new_file):
contained_polygons = loadFile(contained_polygons)
container_polygons = loadFile(container_polygons)
selected_contained_polygons = sjoin(contained_polygons,
container_polygons,
op='within')
selected_contained_polygons.to_file(new_file)
return selected_contained_polygons
def geoCode(df):
"""all geoprocessing part"""
df = df[(pd.notnull(df.lat)) & (pd.notnull(df.lon))] # filter tweets without geocoordinates
gdf = toGeoDataFrame(df, lat="lat", lon="lon")
zips = gp.read_file("DATAVAULT/misc/zipcodes.geojson")[["geometry", "postalCode"]]
return sjoin(gdf, zips, how="left", op="within")
def points_in_shp(points_list, shapefile_gpd):
pnts = geopandas.GeoDataFrame(geometry=points_list,
index=range(0, len(points_list)))
pointInPolys = sjoin(pnts, shapefile_gpd, how='left')
grouped = pointInPolys.groupby('index_right', as_index=False)
return pointInPolys, grouped
def main(dbPath, zipPath):
'''generates sintetic csv
from master df with zipcodes'''
gdf = toGeoDataFrame(getDF(dbPath), lat='lon',lon='lat') ### mesed with lat_long
zips = gp.read_file(zipPath)[['geometry', 'postalCode']]
datum = sjoin(gdf, zips, how="left")[['timestamp', 'postalCode', 'user_id', 'id']]
datum.to_csv('sintetic.csv')
def joinTrafficCounts(data_grid, utm10n):
data_grid['gid'] = data_grid.id
data_grid.crs = utm10n; print data_grid.crs
osm_trafficCounts_centroids = GeoDataFrame.from_file(os.getcwd()+'/diysco2-db/_main_/yvr-open-data-traffic-counts/generated-traffic-counts-osm-split/'+'osm_trafficCounts_split_dev_'+str(50)+'_centroids.shp')
gridded_traffic_counts = sjoin(data_grid, osm_trafficCounts_centroids, how="left")
print len(gridded_traffic_counts)
return gridded_traffic_counts
def main(dbPath, zipPath):
'''generates sintetic csv
from master_df with zipcodes'''
gdf = toGeoDataFrame(getDF(dbPath), lat='lon',lon='lat') ### mesed with lat_long
zips = gp.read_file(zipPath)[['geometry', 'postalCode']]
datum = sjoin(gdf, zips, how="left")[['timestamp', 'postalCode', 'user_id', 'id']]
datum = datum[pd.notnull(datum.postalCode)] # remove failed sjoin
datum.to_csv('sintetic.csv')
def polygons_in_polygons(contained_polygons, container_polygons, new_file):
contained_polygons = load_file(contained_polygons)
container_polygons = load_file(container_polygons)
selected_contained_polygons = sjoin(contained_polygons,
container_polygons,
op='within')
selected_contained_polygons = remove_multipolygons(
selected_contained_polygons)
selected_contained_polygons.to_file(new_file)
return selected_contained_polygons
def everything(path):
''''''
pD = gp.read_file(PARQA + 'data/SHP/Park_Districts/ParkDistrict.shp')[['SYSTEM','geometry']]
df = toGeoDataFrame(pd.read_csv(oath, index_col=0))
df = df.to_crs(pDistricts.crs)
df = sjoin(df, pD, how="left").rename(columns={'SYSTEM':'parkDistrict'})
df = df.to_crs(epsg=4326)
rPath = path.replace('.csv','.json')
writeGeoJson(df, rPath)
def geoCode(df):
'''all geoprocessing part'''
df = df[(pd.notnull(df.lat)) &
(pd.notnull(df.lon))] # filter tweets without geocoordinates
gdf = toGeoDataFrame(df, lat='lat', lon='lon')
zips = gp.read_file('DATAVAULT/misc/zipcodes.geojson')[[
'geometry', 'postalCode'
]]
return sjoin(gdf, zips, how="left", op='within')
def get_bounding_shape(lat, lon, gdf, name):
h=pd.DataFrame({'Lat':[lat], 'Lon':[lon]})
geometry = [Point(xy) for xy in zip([lon], [lat])]
hg = gpd.GeoDataFrame(h, geometry=geometry)
hg.crs = {'init' :'epsg:4326'}
hg_1 = hg.to_crs(gdf.crs)
r = sjoin(gdf,hg_1)
if r.empty:
return None
else:
return r[name].tolist()[0]
def spatial_join(gdf_amenity, gdf_nuts):
gdf_amenity = gpd.GeoDataFrame(
gdf_amenity,
geometry=gpd.points_from_xy(gdf_amenity.lon, gdf_amenity.lat),
crs="epsg:4326").drop(columns=['lon', 'lat'])
gdf_amenity.sindex
gdf = sjoin(gdf_nuts, gdf_amenity, how='left')
s_counts = gdf.groupby(['nuts_id', 'amenity'])['geometry'].count()
s_counts.name = "counts"
return s_counts.reset_index()
def pts_poly_join(pts, poly, poly_id_col):
"""
Simple function to join the attributes of the polygon to the points. Specifically for an ID field in the polygon.
"""
poly2 = poly[[poly_id_col, 'geometry']]
poly3 = poly2.dissolve(by=poly_id_col)
join1 = sjoin(pts, poly3, how='inner', op='within')
join1.rename(columns={join1.columns[-1]: poly_id_col}, inplace=True)
return ([join1, poly3])
def occupation(dataframe): #colone pour regrouper donnes
data_centroid=gpd.GeoDataFrame(dataframe.copy()) #On ne prend que les centroid des polygone (seuil bas)
data_centroid['geometry']=dataframe['geometry'].centroid
try :
occup=sjoin(maillage[['ID','geometry']],data_centroid[['geometry']])
occup=occup.drop_duplicates(['geometry']) #On vire les doublons
except ValueError:
print("erreur sjoin")
occup=gpd.GeoDataFrame()
occup["geometry"]=[""]
return occup
def spatial_join_pt(pt_file, poly_file, lat='lat', lon='lon'):
"""Spatially join polygon attributes to point data.
'pt_file' is a csv file with latitude and longitude attributes that
can be interpreted as points.
'poly_file' is a geojson file that contains polygon data.
lat --> latitude field in the point df
lon --> longitude field in the point df
Both layers must use the same CRS.
This function returns a DataFrame, not a Geodataframe.
"""
logging.info('Loading point file')
df = pd.read_csv(pt_file,low_memory=False)
logging.info('Starting with {} rows in point file'.format(df.shape[0]))
df = df.reset_index(drop=True)
df_cols = df.columns.values.tolist()
logging.info('Converting point file to geodf')
pt = df_to_geodf_pt(df, lat, lon)
logging.info('Loading poly file as geodf')
poly = geojson_to_geodf(poly_file)
pt.crs = poly.crs
logging.info('Operating spatial join.')
pt_join = sjoin(pt, poly, how='left')
pt_join = pt_join.drop(['geometry', 'index_right'], axis=1)
logging.info('Successfully spatially joined data.')
join_cols = pt_join.columns.values.tolist()
new_cols = [x for x in join_cols if x not in df_cols]
# We will not keep the results for points
# that join to multiple polygons
pt_join = pt_join.reset_index().drop_duplicates(subset="index",keep=False).set_index("index")
# We must join the result back to original dataframe to keep all rows
final = pd.merge(df,pt_join[new_cols],left_index=True,right_index=True,how="left")
logging.info('Finished with {} rows'.format(final.shape[0]))
return final
def addNeighborhoods(data, utm10n):
hoods = GeoDataFrame.from_file(os.getcwd()+'/diysco2-db/_main_/yvr-open-data-neighborhoods/csg_neighborhood_areas.shp'); print hoods.crs
hoods.crs = utm10n
output = data.copy()
output.iscopy = False
print len(output)
output = sjoin(output, hoods, how="left")
output['temp'] = [str(i.bounds) for i in output.geometry]
print output['temp'].head()
output = output.drop_duplicates('temp', keep="last")
print len(output)
# output.index = [i for i in range(len(otu))]
for i in range(len(output)):
if output['NAME'].iloc[i] is None:
output['NAME'].iloc[i] = "Stanley Park"
if output["MAPID"].iloc[i] is None:
output['MAPID'].iloc[i] = "SP1"
# output = output[pd.isnull(output.co2_avg_e]
print len(output)
return output
def rarete_espece(datasp,maille,seuil):
if len(datasp)<1: #si 0 donnees
return gpd.pd.DataFrame()
try :
occupation=sjoin(grille[['ID','geometry']],datasp[['geometry']])
except:
print("erreur jointure (pas en picardie ?")
return gpd.pd.DataFrame()
occupation=occupation.drop_duplicates(['geometry']) #On vire les doublons
nb_mailles=len(occupation)
rr=(1-(float(len(occupation))/nbMaillesTotal))*100
for indice,seuil in seuil_orig.items():#Pour trouver quel indice
if rr >= seuil[0] and rr < seuil[1]:
indice_base=indice
break
else:
indice_base='TTC' #Si on depasse le 100pour100 (citations mini > 1)
for indice,seuil in seuil_ajust.items():#Pour trouver quel indice
if rr >= seuil[0] and rr < seuil[1]:
indice_ajust=indice
break
else:
indice_ajust='TTC' #Si on depasse le 100pour100 (citations mini > 1)
rapport=gpd.pd.DataFrame()
rapport["id_esp"]=[datasp.id_esp.values[0]]
rapport["nom_s"]=[datasp.nom_s.values[0]]
rapport["nb_mailles"]=[nb_mailles]
rapport["rr"]=[rr]
rapport["indiceBrute"]=indice_base
rapport["indicePondere"]=indice_ajust
return rapport
def makeGrid(ipoints, experiment, gridsize):
# Projections
gridproj = {'init': 'epsg:3740', 'no_defs': True}
wgs84 = {'datum':'WGS84', 'no_defs':True, 'proj':'longlat'}
# import grid script
sys.path.insert(0, os.getcwd()+'/mapping/libs/')
import grid as g
opath = os.getcwd() + '/diysco2-db/campaigns/'+experiment+'/diysco2-grid'
if(os.path.isdir(opath)):
print "already a folder!"
else:
os.mkdir(opath)
# gridsize = 200
ogridname = "grid_"+str(gridsize)+"m.shp"
ofile = opath + "/" + ogridname
print "making grid"
g.main(ofile, ipoints.total_bounds[0], ipoints.total_bounds[2],
ipoints.total_bounds[1], ipoints.total_bounds[3],
gridsize, gridsize)
print "grid complete! "
# read in the grid that was just made
grid = GeoDataFrame.from_file(ofile)
grid.crs = gridproj
# create grid id to groupby
grid['id'] = [i for i in range(len(grid))]
# Read in transect to spatial subset grids in transect
transect = GeoDataFrame.from_file(os.getcwd()+'/diysco2-db/_main_/study-area/' +'transect_epicc2sp_woss.shp')
transect.crs = gridproj
# subset grid
# transectgrid = grid[grid.geometry.intersects(transect.geometry)]; print transectgrid
sagrid = []
for i in range(len(grid)):
if np.array(transect.intersects(grid.geometry[i]))[0] != False:
sagrid.append(grid.geometry[i])
transectgrid = GeoDataFrame(sagrid)
transectgrid.columns = ['geometry']
transectgrid['id'] = [i for i in range(len(transectgrid))]
transectgrid.crs = gridproj
transectgrid.to_file(ofile[:-4]+"_transect.shp")
# transectgrid.to_file(ofile[:-4]+"_transect.geojson",driver="GeoJSON")
## !!!Some weird things with reading in data makes the sjoin work !!! :(
transectgrid = GeoDataFrame.from_file(ofile[:-4]+"_transect.shp")
transectgrid.crs = gridproj
print transectgrid.head()
ipoints = GeoDataFrame.from_file( os.getcwd() + '/diysco2-db/campaigns/'+experiment+'/diysco2-filtered-points/all_20150528.shp')
ipoints.crs = gridproj
print ipoints.head()
# ipoints['id'] = [i for i in range(len(ipoints))]
# Spatial join points to grid
oname = "gridjoin_"+str(gridsize)+"m.shp"
# join_inner_df = sjoin(transectgrid, ipoints, how="inner")
join_inner_df = sjoin(transectgrid, ipoints, how="left", op='intersects')
# join_inner_df.to_file(opath+ "/"+oname)
return join_inner_df
subdata=gpd.GeoDataFrame(data[data["date_obs"].dt.year.isin(years)])#selection sur la periode de ref
mcp_ref = subdata['geometry'].unary_union.convex_hull #mcp total sur la periode de ref
mcp_ref = gpd.GeoSeries(mcp_ref)
mcp_ref.to_file(path+'/out/occurence_ref.shp')
##### Zone d occupation #####
##Par annne et par periode
occup_an=occupation('annee')
occup_an.to_file(path+'/out/occup_an.shp')
occup_per=occupation('periode')
occup_per.to_file(path+'/out/occup_per.shp')
#Caclule de la zone pour la periode de ref
data_centroid=gpd.GeoDataFrame(data.copy())
data_centroid['geometry']=data['geometry'].centroid
data_centroid_ref=data_centroid[data_centroid["date_obs"].dt.year.isin(years)]
occup_ref=sjoin(maillage[['ID','geometry']],data_centroid_ref[['geometry']])
occup_ref=occup_ref.drop_duplicates(['geometry'])
occup_ref.to_file(path+'/out/occupation.shp')
##### Stats #####
ref=pd.DataFrame()
ref["annee"]=years #Pour les jointures
##Surface des mcps par an
mcp_an["mcp_area"]=mcp_an.area/1000000
stats=pd.merge(ref,mcp_an[["annee","mcp_area"]], on="annee",how="left")
#mcp_ref.area.sum() #sur la periode de ref
##Surface des mailles par an et sur la periode de ref
occup_an["occup_area"]=occup_an.area/1000000
occup_grp=pd.DataFrame(occup_an.groupby('annee')["occup_area"].sum())
occup_grp["annee"]=occup_grp.index #il faudrait que j apprenne a utiliser les index sur pandas
def occupation(col): #colone pour regrouper donnes data_centroid=gpd.GeoDataFrame(data[data[col].notnull()].copy()) #On ne prend que les centroid des polygone (seuil bas) data_centroid['geometry']=data['geometry'].centroid occup=sjoin(maillage[['ID','geometry']],data_centroid[[col,'geometry']]) occup=occup.drop_duplicates(['geometry',col]) #On vire les doublons return occup
census_blocks_file = 'nycb2010_15b/nycb2010.shp' pluto_file = 'Update/NYC_PLUTO.shp' print "Reading files..." pluto = gp.GeoDataFrame.from_file(os.path.join(dpath, pluto_file)) dsny_sections = gp.GeoDataFrame.from_file(os.path.join(dpath, dsny_section_file)) census_blocks = gp.GeoDataFrame.from_file(os.path.join(dpath, census_blocks_file)) census_blocks.to_crs(dsny_sections.crs, inplace=True) pluto.crs = dsny_sections.crs pluto['geometry'] = pluto['geometry'].centroid print "Begin spatial joins..." census_pluto = sjoin(pluto, census_blocks, how="left", op="within") census_pluto.drop(['geometry', 'CB2010_right', 'CT2010_right','Shape_Area','Shape_Leng','index_right'], axis=1, inplace=True) # -- # Re-merge the old file to use the Polygon instead of the point census_pluto = census_pluto.merge(census_blocks[['geometry', 'BCTCB2010']]) census_pluto['geometry'] = census_pluto['geometry'].centroid dsny_pluto_census = sjoin(census_pluto, dsny_sections, how="left", op="within") writePath = dpath + 'Output/' writePathFile = writePath + 'nyc.shp' dsny_pluto_census['AssessTot'] = dsny_pluto_census['AssessTot'].astype(str)
#### DECLARE FILE PATHS
utility = '/home/kircheis/data/shp/Electric_Retail_Service_Ter.shp'
util = gpd.read_file(utility)
urbarea = '/home/kircheis/data/shp/census/cb_2013_us_ua10_500k/cb_2013_us_ua10_500k.shp'
ua = gpd.read_file(urbarea)
ua = ua.to_crs(util.crs)
urbpop = '/home/kircheis/data/census/ua/ua_list_all.txt'
uapop = pd.read_fwf(urbpop, colspecs=[(0,5), (10,70), (75,84), (89,98), (103,117), (122,131), (136,150), (155,164), (169,178), (183,185)], names=['UACE', 'NAME', 'POP', 'HU', 'AREALAND', 'AREALANDSQMI', 'AREAWATER', 'AREAWATERSQMI', 'POPDEN', 'LSADC'], skiprows=1)
uapop['UACE'] = uapop['UACE'].astype(str).str.pad(5, side='left', fillchar='0')
uapop = uapop.set_index('UACE')
#### FIND WHICH URBAN AREAS ARE IN WHICH UTILITY SERVICE AREAS
j = tools.sjoin(util, ua)
#### ALLOCATE GRID FOR TEMPERATURE FORCINGS
g = rect_grid((-130, 24, -65, 50), 0.125)
coords = g.centroid.apply(lambda x: x.coords[0])
coordstr = coords.apply(lambda x: 'data_%s_%s' % (x[1], x[0]))
g = gpd.GeoDataFrame(geometry=g.geometry, index=g.index)
g.crs = util.crs
g['coordstr'] = coordstr
#### JOIN UTILITY SERVICE AREAS WITH TEMPERATURE FORCINGS
ua_g = tools.sjoin(ua, g)
rapport_list=[]
for file in os.listdir(pathData):
if file.endswith('.shp') and file.startswith("espace_"):
shapes.append(file)
for shape in shapes:
listData.append(gpd.GeoDataFrame.from_file(pathData+'/'+shape))
data=gpd.GeoDataFrame(gpd.pd.concat(listData,ignore_index=True))
data.geometry=data.geometry.centroid
data.crs=lamb93
listSp=set(data.nom_s.values)
#Compter le nombre de mailles prospectees
occup_total=sjoin(grille[['ID','geometry']],data[['geometry']])
occup_total_agreg=occup_total.groupby(['geometry']).count() #ici, geometry est l index
occup_total_agreg=gpd.GeoDataFrame(occup_total_agreg)
occup_total_agreg.geometry=occup_total_agreg.index.values.copy() #Copy de l'index dans la colonne geometry
occup_total_agreg.reset_index(drop=True, inplace=True) #On remplace par un index normal
occup_total_agreg["nb_cit"]=occup_total_agreg["index_right"].values.copy()
del occup_total_agreg["ID"]
del occup_total_agreg["index_right"]
nbMaillesProsp=len(occup_total_agreg[occup_total_agreg["nb_cit"]>=citation_mini])
P=100*float((nbMaillesTotal-nbMaillesProsp))/nbMaillesTotal
#Ajuster les seuils des indicdes de rarete
for indice,seuil in seuil_orig.items():
seuil_ajust[indice][0]=seuil[0]+P-(seuil[0]*P/100)
seuil_ajust[indice][1]=seuil[1]+P-(seuil[1]*P/100)
def rarete_espece(datasp,maille,seuil):
def test_sjoin_outer(self):
df = sjoin(self.pointdf, self.polydf, how="outer")
self.assertEquals(df.shape, (21,8))
# finish
new_regions.append(new_region.tolist())
return new_regions, np.asarray(new_vertices)
b = gpd.GeoDataFrame.from_file('/home/akagi/Desktop/electricity_data/Electric_Retail_Service_Ter.shp')
#### LOOP THROUGH UTILITY SERVICE AREAS
sub = gpd.read_file(substations)
util = gpd.read_file(utility)
invalid_util = util[~util['geometry'].apply(lambda x: x.is_valid)]
util.loc[invalid_util.index, 'geometry'] = util.loc[invalid_util.index, 'geometry'].apply(lambda x: x.buffer(0))
sub_util = tools.sjoin(sub, util, op='within', how='left')
sub_xy = np.vstack(sub['geometry'].apply(lambda u: np.concatenate(u.xy)).values)
#util_poly = b.set_index('UNIQUE_ID')['geometry']
vor = spatial.Voronoi(sub_xy)
reg, vert = voronoi_finite_polygons_2d(vor,1)
v_poly = gpd.GeoSeries(pd.Series(reg).apply(lambda x: geometry.Polygon(vert[x])))
v_gdf = gpd.GeoDataFrame(pd.concat([sub.drop('geometry', axis=1), v_poly], axis=1)).rename(columns={0:'geometry'})
v_gdf.crs = sub.crs
j = tools.sjoin(util, v_gdf, op='intersects')
j['right_geom'] = j['UNIQUE_ID_right'].map(v_gdf.set_index('UNIQUE_ID')['geometry'])
j = j.dropna(subset=['geometry', 'right_geom']).set_index('UNIQUE_ID_left')
def test_sjoin_duplicate_column_name(self):
pointdf2 = self.pointdf.rename(columns={'pointattr1': 'Shape_Area'})
df = sjoin(pointdf2, self.polydf, how="left")
self.assertTrue('Shape_Area_left' in df.columns)
self.assertTrue('Shape_Area_right' in df.columns)
output["occup"]=""
output["citations"]=""
for file in os.listdir(path):
if file.endswith('.shp') and file.startswith("espace_"):
shapes.append(file)
for shape in shapes:
listData.append(gpd.GeoDataFrame.from_file(path+'/'+shape))
data=gpd.GeoDataFrame(pd.concat(listData,ignore_index=True))
###Travail sur lot de donnees
data=data[data["nb"] >= 0] #filtre des obs négative
data=data[data.geometry.area < 5000000] #filtre des polygon sup a 5km2
data["date_obs"]=pd.to_datetime(data["date_obs"]) #convertire la date
data["annee"]=data["date_obs"].dt.year
for debut in range(annee_min,annee_max+1-4):
for fin in range(debut+5-1,annee_max+1):
print str(debut)+" - "+str(fin)
data_centroid=gpd.GeoDataFrame(data[data["annee"].between(debut,fin)].copy()) #On ne prend que les centroid des data qui entre dans la periode
data_centroid['geometry']=data['geometry'].centroid
count=len(data_centroid.index)
occup=sjoin(maillage[['ID','geometry']],data_centroid[['geometry']])
occup=occup.drop_duplicates(['geometry']) #On vire les doublons
line=pd.DataFrame({'debut':debut,'fin':fin,'occup':occup.area.sum()/1000000,'citations':count},index=[0])
output=output.append(line,ignore_index=True)
output.to_csv(path+"data_grp.csv",index=False)
def test_sjoin_inner(self):
df = sjoin(self.pointdf, self.polydf, how="inner")
self.assertEquals(df.shape, (11, 8))
# line_shp = gpd.read_file(network_shp_file) country_shp = gpd.read_file(country_shp_file) myanmar = country_shp[country_shp.ADMIN=='Myanmar'] nigeria = country_shp[country_shp.ADMIN=='Nigeria'] osm_places_mmr = osm.query_osm(typ='node', bbox=myanmar.total_bounds, recurse='down', tags='place') osm_power_mmr = osm.query_osm(typ='node', bbox=myanmar.total_bounds, recurse='down', tags='power') osm_places_nga = osm.query_osm(typ='node', bbox=nigeria.total_bounds, recurse='down', tags='place') osm_power_nga = osm.query_osm(typ='node', bbox=nigeria.total_bounds, recurse='down', tags='power') osm_power_way_nga = osm.query_osm(typ='way', bbox=nigeria.total_bounds, recurse='down', tags='power') # find places that have a population places_nga = osm_places_nga[['geometry', 'population', 'name']] places_nga = sjoin(places_nga, nigeria, how="inner", op="within") places_nga = places_nga[~pd.isnull(places_nga.population)] # find length of power line data in nigeria power_lines_nga = osm_power_way_nga[osm_power_way_nga.geom_type == 'LineString'][['geometry']] power_lines_nga = sjoin(power_lines_nga, nigeria, how="inner", op="within") # assign line distances back to geopandas df and add styling to display via geojson.io power_lines_nga['line_length_m'] = power_lines_nga.geometry.apply(lambda linestring: sum(su.linestring_distances(linestring))) # style red power_lines_nga['stroke'] = "#00ff00" # output as geojson power_line_json = "/home/cjn/geodata/nga_power_lines_osm.json" json_file = open(power_line_json, mode='w') json_file.write(power_lines_nga.to_json())
from shapely.geometry import Point
here = os.path.dirname(os.path.abspath('__file__'))
data_dir = os.path.join(here, '..', 'data')
vector_file = os.path.join(here, 'nybb_15b', 'nybb.shp')
boros = read_file(vector_file)
xmin, ymin, xmax, ymax = boros.total_bounds
N = 1000
X = np.random.uniform(low=xmin, high=xmax, size=N)
Y = np.random.uniform(low=ymin, high=ymax, size=N)
points = GeoDataFrame(geometry=GeoSeries([Point(x, y) for x, y in zip(X, Y)]))
points.crs = boros.crs
joined = sjoin(points, boros, how='inner')
joined.geometry = joined.buffer(2000)
ax = plt.subplot(121)
boros.plot(column='BoroCode', categorical=True, axes=ax)
points.plot(axes=ax)
ax.set_aspect('equal')
locs, labels = plt.xticks()
plt.setp(labels, rotation=90)
ax = plt.subplot(122)
joined.plot(column='BoroCode', categorical=True, axes=ax)
ax.set_aspect('equal')
locs, labels = plt.xticks()
plt.setp(labels, rotation=90)
plt.tight_layout()
con = sqlite3.connect('test.db')
df = pd.read_sql_query('select * from telemetry where boat_id =5', con, parse_dates=['received'], index_col=['received'])
# geopandas requires this to be called 'geometry'
df['geometry'] = df.apply(lambda y: Point(y.lat, y.lon), axis=1)
return df
def label_dockings(data):
""" add a label to indicate when the bus was stopped at one of the docks """
for row in data:
import pdb
pdb.set_trace()
return data
def label_arrive(data):
""" add a label to indicate when the bus arrives at one of the docks """
pass
def label_depart(data):
""" add a label to indicate when the bus departs one of the docks """
if __name__ == '__main__':
print 'creating bounds'
spots = GeoDataFrame({'geometry': [bounds['WATERFRONT'], bounds['LONSDALE'], bounds['PARKING']]})
print 'loading bus data'
data = loadbus()
gdf = gpd.GeoDataFrame(data)
print 'joining'
joined = sjoin(gdf, spots, how='left', op='contains')
import pdb
pdb.set_trace()
import numpy as np
import pandas as pd
import geopandas as gpd
from geopandas import tools
census_old = '/home/kircheis/data/shp/census/census_tracts_all/census_tracts_1990.shp'
census_new = '/home/kircheis/data/shp/census/census_tracts_all/census_tracts_2014.shp'
df_90 = gpd.read_file(census_old)
df_14 = gpd.read_file(census_new)
df_14_c = df_14.copy()
df_14_c['geometry'] = df_14_c.centroid
j = tools.sjoin(df_90, df_14_c, op='contains')
#### FORMAT CENSUS TRACT NAMES
#### NONDECIMAL ENTRIES
j['TRACT_NAME'][~j['TRACT_NAME'].str.contains('\.')] = (j['TRACT_NAME'][~j['TRACT_NAME'].str.contains('\.')] + '00').str.pad(6, side='left', fillchar='0')
#### DECIMAL ENTRIES
j['TRACT_NAME'][j['TRACT_NAME'].str.contains('\.')] = j['TRACT_NAME'][j['TRACT_NAME'].str.contains('\.')].str.replace('.', '').str.pad(6, side='left', fillchar='0')
#### CREATE FIPS
j['GEOID_1990'] = j['ST'].astype(str).str.cat(j['CO'].astype(str)).str.cat(j['TRACT_NAME'])
j_cross = j.rename(columns={'GEOID':'GEOID_2014'})[['GEOID_1990', 'GEOID_2014']].sort('GEOID_1990')
