def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
data, comments = parse_mapping_file_to_dict(opts.input_path)
column_headers = []
if ',' not in opts.column:
column_data = []
column_name = opts.column
for i in data:
if column_name not in data[i]:
raise ValueError(
"No column: '%s' in the mapping file. Existing columns are: %s" %
(column_name, data[i].keys()))
try:
column_data.append(float(data[i][opts.column]))
except ValueError:
raise ValueError(
"All the values in the column '%s' must be numeric but '%s' has '%s'" %
(column_name, i, data[i][column_name]))
column_headers.append(i)
dtx_mtx = compute_distance_matrix_from_metadata(column_data)
else:
latitudes = []
longitudes = []
try:
latitude, longitude = opts.column.split(',')
except ValueError:
raise ValueError(
"This script accepts a maximum of 2 colums separated by comma and you passed: %s" %
(opts.column))
for i in data:
if latitude not in data[i] or longitude not in data[i]:
raise ValueError(
"One of these columns or both do not exist: '%s' or '%s' in the mapping file. Existing columns are: %s" %
(latitude, longitude, data[i].keys()))
try:
latitudes.append(float(data[i][latitude]))
longitudes.append(float(data[i][longitude]))
except ValueError:
raise ValueError(
"All the values in the columnd '%s' & '%s' must be numeric but '%s' has '%s'" %
(latitude, longitude, i, data[i][column_name]))
column_headers.append(i)
dtx_mtx = calculate_dist_vincenty(latitudes, longitudes)
dtx_txt = format_distance_matrix(column_headers, dtx_mtx)
outfilepath = os.path.join(opts.output_fp)
f = open(outfilepath, 'w')
f.write(dtx_txt)
f.close()
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
data, comments = parse_mapping_file_to_dict(opts.input_path)
column_headers = []
if ',' not in opts.column:
column_data = []
column_name = opts.column
for i in data:
if column_name not in data[i]:
raise ValueError(
"No column: '%s' in the mapping file. Existing columns are: %s"
% (column_name, data[i].keys()))
try:
column_data.append(float(data[i][opts.column]))
except ValueError:
raise ValueError(
"All the values in the column '%s' must be numeric but '%s' has '%s'"
% (column_name, i, data[i][column_name]))
column_headers.append(i)
dtx_mtx = compute_distance_matrix_from_metadata(column_data)
else:
latitudes = []
longitudes = []
try:
latitude, longitude = opts.column.split(',')
except ValueError:
raise ValueError(
"This script accepts a maximum of 2 colums separated by comma and you passed: %s"
% (opts.column))
for i in data:
if latitude not in data[i] or longitude not in data[i]:
raise ValueError(
"One of these columns or both do not exist: '%s' or '%s' in the mapping file. Existing columns are: %s"
% (latitude, longitude, data[i].keys()))
try:
latitudes.append(float(data[i][latitude]))
longitudes.append(float(data[i][longitude]))
except ValueError:
raise ValueError(
"All the values in the columnd '%s' & '%s' must be numeric but '%s' has '%s'"
% (latitude, longitude, i, data[i][column_name]))
column_headers.append(i)
dtx_mtx = calculate_dist_vincenty(latitudes, longitudes)
dtx_txt = format_distance_matrix(column_headers, dtx_mtx)
outfilepath = os.path.join(opts.output_fp)
f = open(outfilepath, 'w')
f.write(dtx_txt)
f.close()
def test_compute_distance_matrix_from_metadata_int(self):
""" distance calculations on ints should throw no errors"""
exp_out = array([[0, 0, 92, 9096, 9992, 9894, 18898, 18898, 18898], [0, 0, 92, 9096, 9992, 9894, 18898, 18898, 18898],
[92, 92, 0, 9188, 10084, 9986, 18990, 18990, 18990], [9096, 9096, 9188, 0, 896, 798, 9802, 9802, 9802],
[9992, 9992, 10084, 896, 0, 98, 8906, 8906, 8906], [9894, 9894, 9986, 798, 98, 0, 9004, 9004, 9004],
[18898, 18898, 18990, 9802, 8906, 9004, 0, 0, 0], [18898, 18898, 18990, 9802, 8906, 9004, 0, 0, 0],
[18898, 18898, 18990, 9802, 8906, 9004, 0, 0, 0]])
res_out = compute_distance_matrix_from_metadata(self.DOB)
self.assertFloatEqual(exp_out, res_out)
def test_compute_distance_matrix_from_metadata_floats(self):
""" distance calculations on floats should throw no errors"""
# testing floats
exp_out = array([[0., 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8], [0.1, 0., 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7],
[0.2, 0.1, 0., 0.1, 0.2, 0.3, 0.4, 0.5, 0.6], [0.3, 0.2, 0.1, 0., 0.1, 0.2, 0.3, 0.4, 0.5],
[0.4, 0.3, 0.2, 0.1, 0., 0.1, 0.2, 0.3, 0.4], [0.5, 0.4, 0.3, 0.2, 0.1, 0., 0.1, 0.2, 0.3],
[0.6, 0.5, 0.4, 0.3, 0.2, 0.1, 0., 0.1, 0.2], [0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1, 0., 0.1],
[0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1, 0.]])
res_out = compute_distance_matrix_from_metadata(self.Float_Col)
self.assertFloatEqual(exp_out, res_out)
def test_compute_distance_matrix_from_metadata_int(self):
""" distance calculations on ints should throw no errors"""
exp_out = array([[0, 0, 92, 9096, 9992, 9894, 18898, 18898, 18898],
[0, 0, 92, 9096, 9992, 9894, 18898, 18898, 18898],
[92, 92, 0, 9188, 10084, 9986, 18990, 18990, 18990],
[9096, 9096, 9188, 0, 896, 798, 9802, 9802, 9802],
[9992, 9992, 10084, 896, 0, 98, 8906, 8906, 8906],
[9894, 9894, 9986, 798, 98, 0, 9004, 9004, 9004],
[18898, 18898, 18990, 9802, 8906, 9004, 0, 0, 0],
[18898, 18898, 18990, 9802, 8906, 9004, 0, 0, 0],
[18898, 18898, 18990, 9802, 8906, 9004, 0, 0, 0]])
res_out = compute_distance_matrix_from_metadata(self.DOB)
assert_almost_equal(exp_out, res_out)
def test_compute_distance_matrix_from_metadata_floats(self):
""" distance calculations on floats should throw no errors"""
# testing floats
exp_out = array([[0., 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8],
[0.1, 0., 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7],
[0.2, 0.1, 0., 0.1, 0.2, 0.3, 0.4, 0.5, 0.6],
[0.3, 0.2, 0.1, 0., 0.1, 0.2, 0.3, 0.4, 0.5],
[0.4, 0.3, 0.2, 0.1, 0., 0.1, 0.2, 0.3, 0.4],
[0.5, 0.4, 0.3, 0.2, 0.1, 0., 0.1, 0.2, 0.3],
[0.6, 0.5, 0.4, 0.3, 0.2, 0.1, 0., 0.1, 0.2],
[0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1, 0., 0.1],
[0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1, 0.]])
res_out = compute_distance_matrix_from_metadata(self.Float_Col)
assert_almost_equal(exp_out, res_out)
