def test_from_file_with_file_path(self):
"""Should identify the filepath correctly and parse from it."""
# should fail with the expected exception
with self.assertRaises(DissimilarityMatrixFormatError):
DistanceMatrix.from_file(self.bad_dm_fp)
obs = DistanceMatrix.from_file(self.dm_3x3_fp)
self.assertEqual(self.dm_3x3, obs)
self.assertTrue(isinstance(obs, DistanceMatrix))
def test_from_file_with_file_path(self):
"""Should identify the filepath correctly and parse from it."""
# should fail with the expected exception
with self.assertRaises(DissimilarityMatrixFormatError):
DistanceMatrix.from_file(self.bad_dm_fp)
obs = DistanceMatrix.from_file(self.dm_3x3_fp)
self.assertEqual(self.dm_3x3, obs)
self.assertTrue(isinstance(obs, DistanceMatrix))
def setup(self):
with open(get_data_path('PCoA_sample_data_3'), 'U') as lines:
dist_matrix = DistanceMatrix.from_file(lines)
self.ordination = PCoA(dist_matrix)
self.ids = ['PC.636', 'PC.635', 'PC.356', 'PC.481', 'PC.354', 'PC.593',
'PC.355', 'PC.607', 'PC.634']
def setup(self):
with open(get_data_path('PCoA_sample_data_3'), 'U') as lines:
dist_matrix = DistanceMatrix.from_file(lines)
self.ordination = PCoA(dist_matrix)
self.ids = [
'PC.636', 'PC.635', 'PC.356', 'PC.481', 'PC.354', 'PC.593',
'PC.355', 'PC.607', 'PC.634'
]
def setUp(self):
# The test dataset used here is a subset of the Lauber et al. 2009
# "88 Soils" dataset. It has been altered to exercise various aspects
# of the code, including (but not limited to):
#
# - order of distance matrix IDs and IDs in data frame (metadata) are
# not exactly the same
# - data frame has an extra sample that is not in the distance matrix
# - this extra sample has non-numeric and missing values in some of its
# cells
#
# Additional variations of the distance matrix and data frame are used
# to test different orderings of rows/columns, extra non-numeric data
# frame columns, etc.
#
# This dataset is also useful because it is non-trivial in size (6
# samples, 11 environment variables) and it includes positive/negative
# floats and integers in the data frame.
self.dm = DistanceMatrix.from_file(get_data_path('dm.txt'))
# Reordered rows and columns (i.e., different ID order). Still
# conceptually the same distance matrix.
self.dm_reordered = DistanceMatrix.from_file(
get_data_path('dm_reordered.txt'))
self.df = pd.read_csv(get_data_path('df.txt'), sep='\t', index_col=0)
# Similar to the above data frame, except that it has an extra
# non-numeric column, and some of the other rows and columns have been
# reordered.
self.df_extra_column = pd.read_csv(
get_data_path('df_extra_column.txt'), sep='\t', index_col=0)
# All columns in the original data frame (these are all numeric
# columns).
self.cols = self.df.columns.tolist()
# This second dataset is derived from vegan::bioenv's example dataset
# (varespec and varechem). The original dataset includes a site x
# species table (e.g., OTU table) and a data frame of environmental
# variables. Since the bioenv function defined here accepts a distance
# matrix, we use a Bray-Curtis distance matrix that is derived from the
# site x species table (this matches what is done by vegan::bioenv when
# provided an OTU table, using their default distance measure). The
# data frame only includes the numeric environmental variables we're
# interested in for these tests: log(N), P, K, Ca, pH, Al
self.dm_vegan = DistanceMatrix.from_file(
get_data_path('bioenv_dm_vegan.txt'))
self.df_vegan = pd.read_csv(
get_data_path('bioenv_df_vegan.txt'), sep='\t',
converters={0: str})
self.df_vegan.set_index('#SampleID', inplace=True)
# Load expected results.
self.exp_results = pd.read_csv(get_data_path('exp_results.txt'),
sep='\t', index_col=0)
self.exp_results_single_column = pd.read_csv(
get_data_path('exp_results_single_column.txt'), sep='\t',
index_col=0)
self.exp_results_different_column_order = pd.read_csv(
get_data_path('exp_results_different_column_order.txt'), sep='\t',
index_col=0)
self.exp_results_vegan = pd.read_csv(
get_data_path('bioenv_exp_results_vegan.txt'), sep='\t',
index_col=0)
def test_from_file_invalid_input(self):
"""Raises error on invalid distance matrix file."""
# Asymmetric.
with self.assertRaises(DistanceMatrixError):
DistanceMatrix.from_file(self.dm_2x2_asym_f)
def test_from_file_invalid_input(self):
"""Raises error on invalid distance matrix file."""
# Asymmetric.
with self.assertRaises(DistanceMatrixError):
DistanceMatrix.from_file(self.dm_2x2_asym_f)
def setUp(self):
# The test dataset used here is a subset of the Lauber et al. 2009
# "88 Soils" dataset. It has been altered to exercise various aspects
# of the code, including (but not limited to):
#
# - order of distance matrix IDs and IDs in data frame (metadata) are
# not exactly the same
# - data frame has an extra sample that is not in the distance matrix
# - this extra sample has non-numeric and missing values in some of its
# cells
#
# Additional variations of the distance matrix and data frame are used
# to test different orderings of rows/columns, extra non-numeric data
# frame columns, etc.
#
# This dataset is also useful because it is non-trivial in size (6
# samples, 11 environment variables) and it includes positive/negative
# floats and integers in the data frame.
self.dm = DistanceMatrix.from_file(get_data_path('dm.txt'))
# Reordered rows and columns (i.e., different ID order). Still
# conceptually the same distance matrix.
self.dm_reordered = DistanceMatrix.from_file(
get_data_path('dm_reordered.txt'))
self.df = pd.read_csv(get_data_path('df.txt'), sep='\t', index_col=0)
# Similar to the above data frame, except that it has an extra
# non-numeric column, and some of the other rows and columns have been
# reordered.
self.df_extra_column = pd.read_csv(
get_data_path('df_extra_column.txt'), sep='\t', index_col=0)
# All columns in the original data frame (these are all numeric
# columns).
self.cols = self.df.columns.tolist()
# This second dataset is derived from vegan::bioenv's example dataset
# (varespec and varechem). The original dataset includes a site x
# species table (e.g., OTU table) and a data frame of environmental
# variables. Since the bioenv function defined here accepts a distance
# matrix, we use a Bray-Curtis distance matrix that is derived from the
# site x species table (this matches what is done by vegan::bioenv when
# provided an OTU table, using their default distance measure). The
# data frame only includes the numeric environmental variables we're
# interested in for these tests: log(N), P, K, Ca, pH, Al
self.dm_vegan = DistanceMatrix.from_file(
get_data_path('bioenv_dm_vegan.txt'))
self.df_vegan = pd.read_csv(get_data_path('bioenv_df_vegan.txt'),
sep='\t',
converters={0: str})
self.df_vegan.set_index('#SampleID', inplace=True)
# Load expected results.
self.exp_results = pd.read_csv(get_data_path('exp_results.txt'),
sep='\t',
index_col=0)
self.exp_results_single_column = pd.read_csv(
get_data_path('exp_results_single_column.txt'),
sep='\t',
index_col=0)
self.exp_results_different_column_order = pd.read_csv(
get_data_path('exp_results_different_column_order.txt'),
sep='\t',
index_col=0)
self.exp_results_vegan = pd.read_csv(
get_data_path('bioenv_exp_results_vegan.txt'),
sep='\t',
index_col=0)
