def test_get_column_definitions_1():
"""
GDF2.get_column_definitions() will return a list of dictionaries
"""
gdf = aseg_gdf2.read(data_src_1)
res = gdf.get_column_definitions()
assert len(res) == 5
for item in res:
assert "name" in item
def test_read_incorrect():
with pytest.raises(OSError):
gdf = aseg_gdf2.read(
str(
repo
/ "tests"
/ "aseg_examples"
/ "Example_AeroMag_MuppetTown_2009.data"
)
)
def test_repr_1():
"""
GDF2's repr will display the number of records: nrecords
"""
gdf = aseg_gdf2.read(data_src_1)
# Gdf.nrecords is not called yet, so it is set to "?"
assert gdf.__repr__().endswith("nrecords=?>")
# Call gdf.nrecords
nrecords = gdf.nrecords
assert nrecords == 23040
# After nrecords is called nrecords will be repored in __repr__
assert gdf.__repr__().endswith("nrecords=23040>")
def test_df_usecols():
gdf = aseg_gdf2.read(dset("9a13704a", "Mugrave_WB_MGA52"))
df = gdf.df(usecols=["LINE", "RUnc"])
assert (df.columns.values == [
"LINE",
"RUnc[0]",
"RUnc[1]",
"RUnc[2]",
"RUnc[3]",
"RUnc[4]",
"RUnc[5]",
"RUnc[6]",
"RUnc[7]",
"RUnc[8]",
"RUnc[9]",
"RUnc[10]",
"RUnc[11]",
"RUnc[12]",
"RUnc[13]",
"RUnc[14]",
"RUnc[15]",
"RUnc[16]",
"RUnc[17]",
"RUnc[18]",
"RUnc[19]",
"RUnc[20]",
"RUnc[21]",
"RUnc[22]",
"RUnc[23]",
"RUnc[24]",
"RUnc[25]",
"RUnc[26]",
"RUnc[27]",
"RUnc[28]",
"RUnc[29]",
]).all()
def test_field_null():
gdf = aseg_gdf2.read(dset("9a13704a", "Mugrave_WB_MGA52"))
assert np.isnan(gdf.get_field("Con_doi")[5, -6])
def test_field_data():
gdf = aseg_gdf2.read(dset("9a13704a", "Mugrave_WB_MGA52"))
assert gdf.get_field("Con_doi")[4, -6] == [174.27675]
def test_df():
gdf = aseg_gdf2.read(dset("3bcfc711", "GA1286_Waveforms"))
assert len(gdf.df()) == 23040
def test_chunksize():
gdf = aseg_gdf2.read(dset("3bcfc711", "GA1286_Waveforms"))
lengths = []
for chunk in gdf.df_chunked(chunksize=10000):
lengths.append(len(chunk))
assert lengths == [10000, 10000, 3040]
def test_iterrows_2():
gdf = aseg_gdf2.read(dset("3bcfc711", "GA1286_Waveforms"))
for row in gdf.iterrows():
pass
assert row["Time"] == 59.9948
def test_iterrows_1():
gdf = aseg_gdf2.read(dset("3bcfc711", "GA1286_Waveforms"))
for row in gdf.iterrows():
assert row["Time"] == 0.0052
break
# We keep the row with the lowest misift
import geopandas as gpd
import numpy as np
import pandas as pd
import aseg_gdf2
from shapely.geometry import Point
import sys
import glob
import os
#load file as pandas dataframe using .dfn file
infile = sys.argv[1]
dat = aseg_gdf2.read(infile)
df_AEM = dat.df()
outfile = infile.replace('.dat', '_fixed.dat')
with open(infile, 'r') as inf:
with open(outfile, 'w') as outf:
for i, line in enumerate(inf):
fid = df_AEM.iloc[i]['fiducial ']
# use mask to find duplicate entries
df_fid = df_AEM[df_AEM['fiducial '] == fid]
if len(df_fid) == 1:
outf.write(line)
elif df_fid['misfit_lowest '].min() == df_AEM.iloc[i]['misfit_lowest ']:
outf.write(line)
def test_find_dat_file():
gdf = aseg_gdf2.read(
str(repo / "tests" / "aseg_examples" / "Example_AeroMag_MuppetTown_2009")
)
assert gdf.dat_filename.lower().endswith("example_aeromag_muppettown_2009.dat")
def test_read_no_ext():
gdf = aseg_gdf2.read(
str(repo / "tests" / "aseg_examples" / "Example_AeroMag_MuppetTown_2009")
)
def test_read_incorrect():
with pytest.raises(OSError):
gdf = aseg_gdf2.read(
here("aseg_examples", "Example_AeroMag_MuppetTown_2009.data")
)
def test_read_no_ext():
gdf = aseg_gdf2.read(here("aseg_examples", "Example_AeroMag_MuppetTown_2009"))
def test_read_ext_dfn():
gdf = aseg_gdf2.read(here("aseg_examples", "Example_AeroMag_MuppetTown_2009.dfn"))