def load():
masterpath = database.localpath("awash/counties.csv")
fipsdb = database.StaticCSVDatabase(masterpath, 'fips')
dbs = []
for filepath in glob.glob(database.localpath("groundwater/*.txt")):
if os.path.basename(filepath) == 'notes.txt':
continue
db = database.OrderedVectorDatabase.read_text(
filepath, os.path.basename(filepath[:-4]), 2010, fipsdb)
if os.path.basename(filepath[:-4]) == 'aquifer_depth':
db.set_metainfo(
database.UniformMetainfo("Depth to groundwater table", "m"))
if os.path.basename(filepath[:-4]) == 'piezohead0':
db.set_metainfo(database.UniformMetainfo("piezohead", "m"))
if os.path.basename(filepath[:-4]) == 'county_area':
db.set_metainfo(database.UniformMetainfo("county area", "m^2"))
if os.path.basename(filepath[:-4]) == 'county_elevation':
db.set_metainfo(database.UniformMetainfo("county elevation", "m"))
if os.path.basename(filepath[:-4]) == 'drawdown0':
db.set_metainfo(database.UniformMetainfo("draw down", "m"))
if os.path.basename(filepath[:-4]) == 'vector_storativity':
db.set_metainfo(database.UniformMetainfo(" ", "None"))
dbs.append(db)
return database.ConcatenatedDatabase(dbs)
def load():
crime = database.MatrixCSVDatabase(
database.localpath('crime/baseline.csv'),
'county',
get_varyears=lambda df, var: [2005])
crime.set_metainfo(
database.StoredMetainfo.load(database.localpath('crime/fields.fgh')))
return crime
def __init__(self, crop, includeus=True, includecrop=False):
self.crop = crop
self.includeus = includeus
self.includecrop = includecrop
data = pd.read_csv(localpath("ers/ers.csv"))
self.data = data[data["crop"] == crop]
self.link = pd.read_csv(localpath("ers/reglink.csv"))
def load():
get_fips = lambda df: np.array(df['NHGISST']) * 100 + np.array(df[
'NHGISCTY']) / 10
variable_filter = lambda cols: filter(
lambda col: 'NHGIS' in col or 'mean' in col or 'sum' in col or col ==
'STATENAM', cols)
metainfo = database.StoredMetainfo({
'NHGISNAM': dict(unit="name"),
'NHGISST': dict(unit="code"),
'NHGISCTY': dict(unit="code"),
'STATENAM': dict(unit="name"),
'solarsum': dict(unit="W"),
'solarmean': dict(unit="W/m^2"),
'windsum': dict(unit="m^3/s"),
'windmean': dict(unit="m/s"),
'windpowerm': dict(unit="W"),
'windpowers': dict(unit="W/m^2")
})
db = database.StaticCSVDatabase(
database.localpath("energy/repotential.csv"), get_fips,
variable_filter)
db.set_metainfo(metainfo)
return db
def load():
census = database.MatrixCSVDatabase(
database.localpath('census/DataSet.csv'),
'fips',
get_varyears=lambda df, var: [2000 + int(var[-2:])])
census.set_metainfo(database.FunctionalMetainfo(get_description, get_unit))
return census
def load():
metainfo = database.StoredMetainfo({'NHGISNAM': dict(unit="name"), 'NHGISST': dict(unit="code"), 'NHGISCTY': dict(unit="code"), 'STATENAM': dict(unit="name"), 'bio1_mean': dict(unit='dC'), 'bio2_mean': dict(unit='dC'), 'bio5_mean': dict(unit='dC'), 'bio6_mean': dict(unit='dC'), 'bio7_mean': dict(unit='dC'), 'bio8_mean': dict(unit='dC'), 'bio9_mean': dict(unit='dC'), 'bio10_mean': dict(unit='dC'), 'bio11_mean': dict(unit='dC'), 'bio12_mean': dict(unit='mm'), 'bio13_mean': dict(unit='mm'), 'bio14_mean': dict(unit='mm'), 'bio16_mean': dict(unit='mm'), 'bio17_mean': dict(unit='mm'), 'bio18_mean': dict(unit='mm'), 'bio19_mean': dict(unit='mm')})
get_fips = lambda df: np.array(df['NHGISST']) * 100 + np.array(df['NHGISCTY']) / 10
variable_filter = lambda cols: filter(lambda col: 'NHGIS' in col or '_mean' in col or col == 'STATENAM', cols)
current = database.StaticCSVDatabase(database.localpath("climate/bioclims-current.csv"), get_fips, variable_filter)
current.set_metainfo(metainfo)
dbs = [current]
prefixes = ['current']
for filepath in glob.glob(database.localpath("climate/bioclims-2050/*.csv")):
db = database.StaticCSVDatabase(filepath, get_fips, variable_filter, year=2050)
db.set_metainfo(metainfo)
dbs.append(db)
prefixes.append(filepath[filepath.rindex('/')+1:filepath.rindex('/')+3])
return database.CombinedDatabase(dbs, prefixes, '.')
def load():
allage = database.StaticCSVDatabase(
database.localpath('mortality/cmf-1999-2010.txt'),
'County Code',
year=2004,
sep='\t')
allage.set_metainfo(metainfo.StoredMetainfo(infos))
byage = database.InterlevedCSVDatabase(
database.localpath("mortality/cmf-age-1999-2010.txt"),
'County Code',
'Age Group',
2004,
sep='\t')
byage.set_metainfo(metainfo.StoredMetainfo(infos))
return database.CombinedDatabase([allage, byage], ['all', 'age'], '.')
def load():
metainfo = database.FunctionalMetainfo(get_description, get_unit)
x20082012 = database.MatrixCSVDatabase(
database.localpath("election/2008-2012.csv"), 'FIPS',
database.variable_filtermap(column2variable_2008), get_varyears_2008,
get_datarows_2008)
x20082012.set_metainfo(metainfo)
x20122016 = database.MatrixCSVDatabase(
database.localpath(
"election/US_County_Level_Presidential_Results_12-16.csv"),
'combined_fips', database.variable_filtermap(column2variable_2016),
get_varyears_2016, get_datarows_2016)
x20122016.set_metainfo(metainfo)
return database.CombinedDatabase([x20082012, x20122016],
['x20082012', 'x20122016'], '.')
def load():
centroid = database.MatrixCSVDatabase(
database.localpath("acra/centroids.csv"),
'fips',
get_varyears=lambda df, var: [None])
centroid.set_metainfo(
database.StoredMetainfo.load(database.localpath("acra/fields.fgh")))
elevation = database.MatrixCSVDatabase(
database.localpath("acra/elevation.csv"),
'fips',
get_varyears=lambda df, var: [None])
elevation.set_metainfo(
database.StoredMetainfo.load(database.localpath("acra/fields.fgh")))
name = database.MatrixCSVDatabase(
database.localpath("acra/us-county-names.csv"),
'fips',
get_varyears=lambda df, var: [None])
name.set_metainfo(
database.StoredMetainfo.load(database.localpath("acra/fields.fgh")))
dbs = [centroid, elevation, name]
prefixes = ['centroid', 'elevation', 'name']
return database.CombinedDatabase(dbs, prefixes, '.')
import database
import re
filepath = database.localpath("USGS/USGS_gw_sw_use.xlsx")
def get_description(variable):
chunks = variable.split('_')
if len(chunks) == 1:
return "unknown"
source = dict(SW="surface water", GW="groundwater",
To="total extractions")[chunks[1]]
demand = dict(PS="public supply",
PT="thermoelectric generation",
DO="domestic use",
IR="irrigation",
IN="industrial use",
MI="mining",
LI="livestock",
TO="total use")[chunks[0]]
return "%s for %s" % (source, demand)
def get_unit(variable):
if re.match(r"^[A-Z]{2}_[GSWTo]{2}$", variable):
return "Mgal/day"
elif variable == 'TP_TotPop':
return "1e3 people"
elif variable == 'YEAR':
def load():
filepath = database.localpath("labor/lab_cty_00_05_sum.csv")
db = database.StaticCSVDatabase(filepath, 'fips', year=2002)
db.set_metainfo(metainfo.StoredMetainfo.load_csv(database.localpath("labor/info.csv"), 'variable', 'description', 'unit'))
return db
def load():
filepath = database.localpath("ccimpacts/county_damage_mapping_data.csv")
db = database.StaticCSVDatabase(filepath, 'fips', year=2090)
db.set_metainfo(metainfo.StoredMetainfo(metas))
return db