def setup(self):
"""Data from table 11.3 in Legendre & Legendre 1998
(p. 590). Loaded results as computed with vegan 2.0-8 and
compared with table 11.5 if also there."""
Y = np.loadtxt(get_data_path('example3_Y'))
X = np.loadtxt(get_data_path('example3_X'))
self.ordination = CCA(Y, X[:, :-1])
def setUp(self):
self.methods = ('pearson', 'spearman')
self.alternatives = ('two-sided', 'greater', 'less')
# Small dataset of minimal size (3x3). Mix of floats and ints in a
# native Python nested list structure.
self.minx = [[0, 1, 2], [1, 0, 3], [2, 3, 0]]
self.miny = [[0, 2, 7], [2, 0, 6], [7, 6, 0]]
self.minz = [[0, 0.5, 0.25], [0.5, 0, 0.1], [0.25, 0.1, 0]]
# No variation in distances. Taken from Figure 10.20(b), pg. 603 in L&L
# 3rd edition. Their example is 4x4 but using 3x3 here for easy
# comparison to the minimal dataset above.
self.no_variation = [[0, 0.667, 0.667],
[0.667, 0, 0.667],
[0.667, 0.667, 0]]
# This second dataset is derived from vegan::mantel's example dataset.
# The "veg" distance matrix contains Bray-Curtis distances derived from
# the varespec data (named "veg.dist" in the example). The "env"
# distance matrix contains Euclidean distances derived from scaled
# varechem data (named "env.dist" in the example).
self.veg_dm_vegan = np.loadtxt(
get_data_path('mantel_veg_dm_vegan.txt'))
self.env_dm_vegan = np.loadtxt(
get_data_path('mantel_env_dm_vegan.txt'))
# Expected test statistic when comparing x and y with method='pearson'.
self.exp_x_vs_y = 0.7559289
# Expected test statistic when comparing x and z with method='pearson'.
self.exp_x_vs_z = -0.9897433
def setup(self):
"""Data from table 11.3 in Legendre & Legendre 1998
(p. 590). Loaded results as computed with vegan 2.0-8 and
compared with table 11.5 if also there."""
Y = np.loadtxt(get_data_path('example3_Y'))
X = np.loadtxt(get_data_path('example3_X'))
self.ordination = CCA(Y, X[:, :-1])
def setUp(self):
self.bad_dm_fp = get_data_path('bad_dm.txt')
self.dm_2x2_asym_fp = get_data_path('dm_2x2_asym.txt')
self.dm_3x3_fp = get_data_path('dm_3x3.txt')
fd = open(self.bad_dm_fp, 'U')
self.bad_dm_f2_lines = ''.join(fd.readlines())
fd.close()
fd = open(self.dm_2x2_asym_fp, 'U')
self.dm_2x2_asym_lines = ''.join(fd.readlines())
fd.close()
fd = open(self.dm_3x3_fp, 'U')
self.dm_3x3_lines = ''.join(fd.readlines())
fd.close()
self.dm_1x1_data = [[0.0]]
self.dm_1x1_f = StringIO(DM_1x1_F)
self.dm_2x2_data = [[0.0, 0.123], [0.123, 0.0]]
self.dm_2x2_f = StringIO(DM_2x2_F)
self.dm_2x2_asym_data = [[0.0, 1.0], [-2.0, 0.0]]
self.dm_2x2_asym_f = StringIO(self.dm_2x2_asym_lines)
self.dm_3x3_data = [[0.0, 0.01, 4.2], [0.01, 0.0, 12.0],
[4.2, 12.0, 0.0]]
self.dm_3x3_f = StringIO(self.dm_3x3_lines)
self.dm_3x3_whitespace_f = StringIO('\n'.join(DM_3x3_WHITESPACE_F))
self.bad_dm_f1 = StringIO(BAD_DM_F1)
self.bad_dm_f2 = StringIO(self.bad_dm_f2_lines)
self.bad_dm_f3 = StringIO(BAD_DM_F3)
self.bad_dm_f4 = StringIO(BAD_DM_F4)
self.bad_dm_f5 = StringIO(BAD_DM_F5)
self.bad_dm_f6 = StringIO(BAD_DM_F6)
def setUp(self):
self.bad_dm_fp = get_data_path('bad_dm.txt')
self.dm_2x2_asym_fp = get_data_path('dm_2x2_asym.txt')
self.dm_3x3_fp = get_data_path('dm_3x3.txt')
fd = open(self.bad_dm_fp, 'U')
self.bad_dm_f2_lines = ''.join(fd.readlines())
fd.close()
fd = open(self.dm_2x2_asym_fp, 'U')
self.dm_2x2_asym_lines = ''.join(fd.readlines())
fd.close()
fd = open(self.dm_3x3_fp, 'U')
self.dm_3x3_lines = ''.join(fd.readlines())
fd.close()
self.dm_1x1_data = [[0.0]]
self.dm_1x1_f = StringIO(DM_1x1_F)
self.dm_2x2_data = [[0.0, 0.123], [0.123, 0.0]]
self.dm_2x2_f = StringIO(DM_2x2_F)
self.dm_2x2_asym_data = [[0.0, 1.0], [-2.0, 0.0]]
self.dm_2x2_asym_f = StringIO(self.dm_2x2_asym_lines)
self.dm_3x3_data = [[0.0, 0.01, 4.2], [0.01, 0.0, 12.0],
[4.2, 12.0, 0.0]]
self.dm_3x3_f = StringIO(self.dm_3x3_lines)
self.dm_3x3_whitespace_f = StringIO('\n'.join(DM_3x3_WHITESPACE_F))
self.bad_dm_f1 = StringIO(BAD_DM_F1)
self.bad_dm_f2 = StringIO(self.bad_dm_f2_lines)
self.bad_dm_f3 = StringIO(BAD_DM_F3)
self.bad_dm_f4 = StringIO(BAD_DM_F4)
self.bad_dm_f5 = StringIO(BAD_DM_F5)
self.bad_dm_f6 = StringIO(BAD_DM_F6)
def setUp(self):
self.methods = ('pearson', 'spearman')
self.alternatives = ('two-sided', 'greater', 'less')
# Small dataset of minimal size (3x3). Mix of floats and ints in a
# native Python nested list structure.
self.minx = [[0, 1, 2], [1, 0, 3], [2, 3, 0]]
self.miny = [[0, 2, 7], [2, 0, 6], [7, 6, 0]]
self.minz = [[0, 0.5, 0.25], [0.5, 0, 0.1], [0.25, 0.1, 0]]
# No variation in distances. Taken from Figure 10.20(b), pg. 603 in L&L
# 3rd edition. Their example is 4x4 but using 3x3 here for easy
# comparison to the minimal dataset above.
self.no_variation = [[0, 0.667, 0.667], [0.667, 0, 0.667],
[0.667, 0.667, 0]]
# This second dataset is derived from vegan::mantel's example dataset.
# The "veg" distance matrix contains Bray-Curtis distances derived from
# the varespec data (named "veg.dist" in the example). The "env"
# distance matrix contains Euclidean distances derived from scaled
# varechem data (named "env.dist" in the example).
self.veg_dm_vegan = np.loadtxt(
get_data_path('mantel_veg_dm_vegan.txt'))
self.env_dm_vegan = np.loadtxt(
get_data_path('mantel_env_dm_vegan.txt'))
# Expected test statistic when comparing x and y with method='pearson'.
self.exp_x_vs_y = 0.7559289
# Expected test statistic when comparing x and z with method='pearson'.
self.exp_x_vs_z = -0.9897433
def setup(self):
"""Data from table 11.3 in Legendre & Legendre 1998."""
Y = np.loadtxt(get_data_path('example2_Y'))
X = np.loadtxt(get_data_path('example2_X'))
self.ordination = RDA(Y, X,
['Site0', 'Site1', 'Site2', 'Site3', 'Site4',
'Site5', 'Site6', 'Site7', 'Site8', 'Site9'],
['Species0', 'Species1', 'Species2', 'Species3',
'Species4', 'Species5'])
def test_from_file_error(self):
for test_path in self.fferror_test_paths:
with open(get_data_path(test_path), 'U') as f:
with npt.assert_raises(FileFormatError):
OrdinationResults.from_file(f)
for test_path in self.verror_test_paths:
with open(get_data_path(test_path), 'U') as f:
with npt.assert_raises(ValueError):
OrdinationResults.from_file(f)
def test_from_file_error(self):
for test_path in self.fferror_test_paths:
with open(get_data_path(test_path), 'U') as f:
with npt.assert_raises(FileFormatError):
OrdinationResults.from_file(f)
for test_path in self.verror_test_paths:
with open(get_data_path(test_path), 'U') as f:
with npt.assert_raises(ValueError):
OrdinationResults.from_file(f)
def setup(self):
"""Data from table 11.3 in Legendre & Legendre 1998."""
Y = np.loadtxt(get_data_path('example2_Y'))
X = np.loadtxt(get_data_path('example2_X'))
self.ordination = RDA(Y, X, [
'Site0', 'Site1', 'Site2', 'Site3', 'Site4', 'Site5', 'Site6',
'Site7', 'Site8', 'Site9'
], [
'Species0', 'Species1', 'Species2', 'Species3', 'Species4',
'Species5'
])
def test_scaling2(self):
scores = self.ordination.scores(2)
# Load data as computed with vegan 2.0-8
vegan_species = np.loadtxt(
get_data_path('example2_species_scaling2_from_vegan'))
npt.assert_almost_equal(scores.species, vegan_species, decimal=6)
vegan_site = np.loadtxt(
get_data_path('example2_site_scaling2_from_vegan'))
npt.assert_almost_equal(scores.site, vegan_site, decimal=6)
def test_scaling2(self):
scores = self.ordination.scores(2)
# Load data as computed with vegan 2.0-8
vegan_species = np.loadtxt(get_data_path(
'example2_species_scaling2_from_vegan'))
npt.assert_almost_equal(scores.species, vegan_species, decimal=6)
vegan_site = np.loadtxt(get_data_path(
'example2_site_scaling2_from_vegan'))
npt.assert_almost_equal(scores.site, vegan_site, decimal=6)
def setup(self):
"""Data from table 11.3 in Legendre & Legendre 1998
(p. 590). Loaded results as computed with vegan 2.0-8 and
compared with table 11.5 if also there."""
Y = np.loadtxt(get_data_path('example3_Y'))
X = np.loadtxt(get_data_path('example3_X'))
self.ordination = CCA(Y, X[:, :-1],
['Site0', 'Site1', 'Site2', 'Site3', 'Site4',
'Site5', 'Site6', 'Site7', 'Site8', 'Site9'],
['Species0', 'Species1', 'Species2', 'Species3',
'Species4', 'Species5', 'Species6', 'Species7',
'Species8'])
def setup(self):
"""Data from table 11.3 in Legendre & Legendre 1998
(p. 590). Loaded results as computed with vegan 2.0-8 and
compared with table 11.5 if also there."""
Y = np.loadtxt(get_data_path('example3_Y'))
X = np.loadtxt(get_data_path('example3_X'))
self.ordination = CCA(Y, X[:, :-1], [
'Site0', 'Site1', 'Site2', 'Site3', 'Site4', 'Site5', 'Site6',
'Site7', 'Site8', 'Site9'
], [
'Species0', 'Species1', 'Species2', 'Species3', 'Species4',
'Species5', 'Species6', 'Species7', 'Species8'
])
def test_values(self):
"""Adapted from cogent's `test_principal_coordinate_analysis`:
"I took the example in the book (see intro info), and did the
principal coordinates analysis, plotted the data and it looked
right"."""
with warnings.catch_warnings():
warnings.filterwarnings('ignore', category=RuntimeWarning)
ordination = PCoA(self.dist_matrix)
scores = ordination.scores()
exp_eigvals = np.array([
0.73599103, 0.26260032, 0.14926222, 0.06990457, 0.02956972,
0.01931184, 0., 0., 0., 0., 0., 0., 0., 0.
])
exp_site = np.loadtxt(get_data_path('exp_PCoAzeros_site'))
exp_prop_expl = np.array([
0.58105792, 0.20732046, 0.1178411, 0.05518899, 0.02334502,
0.01524651, 0., 0., 0., 0., 0., 0., 0., 0.
])
exp_site_ids = [
'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '10', '11', '12',
'13'
]
# Note the absolute value because column can have signs swapped
npt.assert_almost_equal(scores.eigvals, exp_eigvals)
npt.assert_almost_equal(np.abs(scores.site), exp_site)
npt.assert_almost_equal(scores.proportion_explained, exp_prop_expl)
npt.assert_equal(scores.site_ids, exp_site_ids)
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 test_from_file(self):
for exp_scores, test_path in zip(self.scores, self.test_paths):
for file_type in ('file like', 'file name'):
fname = get_data_path(test_path)
if file_type == 'file like':
with open(fname) as fh:
obs = OrdinationResults.from_file(fh)
elif file_type == 'file name':
obs = OrdinationResults.from_file(fname)
yield self.check_OrdinationResults_equal, obs, exp_scores
def test_from_file(self):
for exp_scores, test_path in zip(self.scores, self.test_paths):
for file_type in ('file like', 'file name'):
fname = get_data_path(test_path)
if file_type == 'file like':
with open(fname) as fh:
obs = OrdinationResults.from_file(fh)
elif file_type == 'file name':
obs = OrdinationResults.from_file(fname)
yield self.check_OrdinationResults_equal, obs, exp_scores
def setUp(self):
self.fna1 = get_data_path('fna1.fasta')
self.fna1gz = get_data_path('fna1.fna.gz')
self.fq1 = get_data_path('fq1.fq')
self.fq1gz = get_data_path('fq1.fastq.gz')
self.qual1 = get_data_path('fna1.qual')
self.noext = get_data_path('noextensionfasta')
def setUp(self):
self.fna1 = get_data_path('fna1.fasta')
self.fna1gz = get_data_path('fna1.fna.gz')
self.fq1 = get_data_path('fq1.fq')
self.fq1gz = get_data_path('fq1.fastq.gz')
self.qual1 = get_data_path('fna1.qual')
self.noext = get_data_path('noextensionfasta')
def setUp(self):
self.minx = DistanceMatrix([[0, 1, 2], [1, 0, 3], [2, 3, 0]])
self.miny = DistanceMatrix([[0, 2, 7], [2, 0, 6], [7, 6, 0]])
self.minz = DistanceMatrix([[0, 0.5, 0.25],
[0.5, 0, 0.1],
[0.25, 0.1, 0]])
self.min_dms = (self.minx, self.miny, self.minz)
# Versions of self.minx and self.minz (above) that each have an extra
# ID on the end.
self.x_extra = DistanceMatrix([[0, 1, 2, 7],
[1, 0, 3, 2],
[2, 3, 0, 4],
[7, 2, 4, 0]], ['0', '1', '2', 'foo'])
self.z_extra = DistanceMatrix([[0, 0.5, 0.25, 3],
[0.5, 0, 0.1, 24],
[0.25, 0.1, 0, 5],
[3, 24, 5, 0]], ['0', '1', '2', 'bar'])
# Load expected results. We have to load the p-value column (column
# index 3) as a string dtype in order to compare with the in-memory
# results since we're formatting the p-values as strings with the
# correct number of decimal places. Without this explicit converter,
# the p-value column will be loaded as a float dtype and the frames
# won't compare equal.
p_val_conv = {3: str}
self.exp_results_minimal = pd.read_csv(
get_data_path('pwmantel_exp_results_minimal.txt'), sep='\t',
index_col=(0, 1), converters=p_val_conv)
self.exp_results_minimal_with_labels = pd.read_csv(
get_data_path('pwmantel_exp_results_minimal_with_labels.txt'),
sep='\t', index_col=(0, 1), converters=p_val_conv)
self.exp_results_duplicate_dms = pd.read_csv(
get_data_path('pwmantel_exp_results_duplicate_dms.txt'),
sep='\t', index_col=(0, 1), converters=p_val_conv)
self.exp_results_na_p_value = pd.read_csv(
get_data_path('pwmantel_exp_results_na_p_value.txt'),
sep='\t', index_col=(0, 1), converters=p_val_conv)
self.exp_results_too_few_permutations = pd.read_csv(
get_data_path('pwmantel_exp_results_too_few_permutations.txt'),
sep='\t', index_col=(0, 1), converters=p_val_conv)
self.exp_results_reordered_distance_matrices = pd.read_csv(
get_data_path('pwmantel_exp_results_reordered_distance_matrices'
'.txt'),
sep='\t', index_col=(0, 1), converters=p_val_conv)
def test_to_file(self):
for scores, test_path in zip(self.scores, self.test_paths):
for file_type in ('file like', 'file name'):
if file_type == 'file like':
obs_f = StringIO()
scores.to_file(obs_f)
obs = obs_f.getvalue()
obs_f.close()
elif file_type == 'file name':
with tempfile.NamedTemporaryFile('r+') as temp_file:
scores.to_file(temp_file.name)
temp_file.flush()
temp_file.seek(0)
obs = temp_file.read()
with open(get_data_path(test_path), 'U') as f:
exp = f.read()
yield npt.assert_equal, obs, exp
def test_to_file(self):
for scores, test_path in zip(self.scores, self.test_paths):
for file_type in ('file like', 'file name'):
if file_type == 'file like':
obs_f = StringIO()
scores.to_file(obs_f)
obs = obs_f.getvalue()
obs_f.close()
elif file_type == 'file name':
with tempfile.NamedTemporaryFile('r+') as temp_file:
scores.to_file(temp_file.name)
temp_file.flush()
temp_file.seek(0)
obs = temp_file.read()
with open(get_data_path(test_path), 'U') as f:
exp = f.read()
yield npt.assert_equal, obs, exp
def test_values(self):
results = self.ordination.scores()
npt.assert_almost_equal(len(results.eigvals), len(results.site[0]))
expected = np.loadtxt(get_data_path('exp_PCoAEigenResults_site'))
npt.assert_almost_equal(*normalize_signs(expected, results.site))
expected = np.array([0.51236726, 0.30071909, 0.26791207, 0.20898868,
0.19169895, 0.16054235, 0.15017696, 0.12245775,
0.0])
npt.assert_almost_equal(results.eigvals, expected)
expected = np.array([0.2675738328, 0.157044696, 0.1399118638,
0.1091402725, 0.1001110485, 0.0838401162,
0.0784269939, 0.0639511764, 0.0])
npt.assert_almost_equal(results.proportion_explained, expected)
npt.assert_equal(results.site_ids, self.ids)
def test_values(self):
results = self.ordination.scores()
npt.assert_almost_equal(len(results.eigvals), len(results.site[0]))
expected = np.loadtxt(get_data_path('exp_PCoAEigenResults_site'))
npt.assert_almost_equal(*normalize_signs(expected, results.site))
expected = np.array([
0.51236726, 0.30071909, 0.26791207, 0.20898868, 0.19169895,
0.16054235, 0.15017696, 0.12245775, 0.0
])
npt.assert_almost_equal(results.eigvals, expected)
expected = np.array([
0.2675738328, 0.157044696, 0.1399118638, 0.1091402725,
0.1001110485, 0.0838401162, 0.0784269939, 0.0639511764, 0.0
])
npt.assert_almost_equal(results.proportion_explained, expected)
npt.assert_equal(results.site_ids, self.ids)
def test_values(self):
"""Adapted from cogent's `test_principal_coordinate_analysis`:
"I took the example in the book (see intro info), and did the
principal coordinates analysis, plotted the data and it looked
right"."""
with warnings.catch_warnings():
warnings.filterwarnings('ignore', category=RuntimeWarning)
ordination = PCoA(self.dist_matrix)
scores = ordination.scores()
exp_eigvals = np.array([0.73599103, 0.26260032, 0.14926222, 0.06990457,
0.02956972, 0.01931184, 0., 0., 0., 0., 0., 0.,
0., 0.])
exp_site = np.loadtxt(get_data_path('exp_PCoAzeros_site'))
exp_prop_expl = np.array([0.58105792, 0.20732046, 0.1178411,
0.05518899, 0.02334502, 0.01524651, 0., 0.,
0., 0., 0., 0., 0., 0.])
exp_site_ids = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9',
'10', '11', '12', '13']
# Note the absolute value because column can have signs swapped
npt.assert_almost_equal(scores.eigvals, exp_eigvals)
npt.assert_almost_equal(np.abs(scores.site), exp_site)
npt.assert_almost_equal(scores.proportion_explained, exp_prop_expl)
npt.assert_equal(scores.site_ids, exp_site_ids)
def setup(self):
"""Data from table 11.3 in Legendre & Legendre 1998."""
self.Y = np.loadtxt(get_data_path('example3_Y'))
self.X = np.loadtxt(get_data_path('example3_X'))
def setup(self):
"""Data from table 11.3 in Legendre & Legendre 1998."""
self.Y = np.loadtxt(get_data_path('example3_Y'))
self.X = np.loadtxt(get_data_path('example3_X'))
def setup(self):
"""Data from table 9.11 in Legendre & Legendre 1998."""
self.X = np.loadtxt(get_data_path('L&L_CA_data'))
self.ordination = CA(self.X, ['Site1', 'Site2', 'Site3'],
['Species1', 'Species2', 'Species3'])
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 setup(self):
"""Data from table 11.3 in Legendre & Legendre 1998."""
Y = np.loadtxt(get_data_path('example2_Y'))
X = np.loadtxt(get_data_path('example2_X'))
self.ordination = RDA(Y, X)
def setup(self):
matrix = np.loadtxt(get_data_path('PCoA_sample_data_2'))
self.ids = map(str, range(matrix.shape[0]))
dist_matrix = DistanceMatrix(matrix, self.ids)
self.ordination = PCoA(dist_matrix)
def test_scaling2_site(self):
scores = self.ordination.scores(2)
vegan_site = np.loadtxt(get_data_path(
'example3_site_scaling2_from_vegan'))
npt.assert_almost_equal(scores.site, vegan_site, decimal=4)
def setup(self):
"""Sample data set from page 111 of W.J Krzanowski. Principles
of multivariate analysis, 2000, Oxford University Press."""
matrix = np.loadtxt(get_data_path('PCoA_sample_data'))
dist_matrix = DistanceMatrix(matrix, map(str, range(matrix.shape[0])))
self.dist_matrix = dist_matrix
def setup_class(cls):
# CA results
eigvals = np.array([0.0961330159181, 0.0409418140138])
species = np.array([[0.408869425742, 0.0695518116298],
[-0.1153860437, -0.299767683538],
[-0.309967102571, 0.187391917117]])
site = np.array([[-0.848956053187, 0.882764759014],
[-0.220458650578, -1.34482000302],
[1.66697179591, 0.470324389808]])
biplot = None
site_constraints = None
prop_explained = None
species_ids = ['Species1', 'Species2', 'Species3']
site_ids = ['Site1', 'Site2', 'Site3']
ca_scores = OrdinationResults(eigvals=eigvals, species=species,
site=site, biplot=biplot,
site_constraints=site_constraints,
proportion_explained=prop_explained,
species_ids=species_ids,
site_ids=site_ids)
# CCA results
eigvals = np.array([0.366135830393, 0.186887643052, 0.0788466514249,
0.082287840501, 0.0351348475787, 0.0233265839374,
0.0099048981912, 0.00122461669234,
0.000417454724117])
species = np.loadtxt(get_data_path('exp_OrdRes_CCA_species'))
site = np.loadtxt(get_data_path('exp_OrdRes_CCA_site'))
biplot = np.array([[-0.169746767979, 0.63069090084, 0.760769036049],
[-0.994016563505, 0.0609533148724,
-0.0449369418179],
[0.184352565909, -0.974867543612, 0.0309865007541]])
site_constraints = np.loadtxt(
get_data_path('exp_OrdRes_CCA_site_constraints'))
prop_explained = None
species_ids = ['Species0', 'Species1', 'Species2', 'Species3',
'Species4', 'Species5', 'Species6', 'Species7',
'Species8']
site_ids = ['Site0', 'Site1', 'Site2', 'Site3', 'Site4', 'Site5',
'Site6', 'Site7', 'Site8', 'Site9']
cca_scores = OrdinationResults(eigvals=eigvals, species=species,
site=site, biplot=biplot,
site_constraints=site_constraints,
proportion_explained=prop_explained,
species_ids=species_ids,
site_ids=site_ids)
# PCoA results
eigvals = np.array([0.512367260461, 0.300719094427, 0.267912066004,
0.208988681078, 0.19169895326, 0.16054234528,
0.15017695712, 0.122457748167, 0.0])
species = None
site = np.loadtxt(get_data_path('exp_OrdRes_PCoA_site'))
biplot = None
site_constraints = None
prop_explained = np.array([0.267573832777, 0.15704469605,
0.139911863774, 0.109140272454,
0.100111048503, 0.0838401161912,
0.0784269939011, 0.0639511763509, 0.0])
species_ids = None
site_ids = ['PC.636', 'PC.635', 'PC.356', 'PC.481', 'PC.354', 'PC.593',
'PC.355', 'PC.607', 'PC.634']
pcoa_scores = OrdinationResults(eigvals=eigvals, species=species,
site=site, biplot=biplot,
site_constraints=site_constraints,
proportion_explained=prop_explained,
species_ids=species_ids,
site_ids=site_ids)
# RDA results
eigvals = np.array([25.8979540892, 14.9825779819, 8.93784077262,
6.13995623072, 1.68070536498, 0.57735026919,
0.275983624351])
species = np.loadtxt(get_data_path('exp_OrdRes_RDA_species'))
site = np.loadtxt(get_data_path('exp_OrdRes_RDA_site'))
biplot = np.array([[0.422650019179, -0.559142585857, -0.713250678211],
[0.988495963777, 0.150787422017, -0.0117848614073],
[-0.556516618887, 0.817599992718, 0.147714267459],
[-0.404079676685, -0.9058434809, -0.127150316558]])
site_constraints = np.loadtxt(
get_data_path('exp_OrdRes_RDA_site_constraints'))
prop_explained = None
species_ids = ['Species0', 'Species1', 'Species2', 'Species3',
'Species4', 'Species5']
site_ids = ['Site0', 'Site1', 'Site2', 'Site3', 'Site4', 'Site5',
'Site6', 'Site7', 'Site8', 'Site9']
rda_scores = OrdinationResults(eigvals=eigvals, species=species,
site=site, biplot=biplot,
site_constraints=site_constraints,
proportion_explained=prop_explained,
species_ids=species_ids,
site_ids=site_ids)
cls.scores = [ca_scores, cca_scores, pcoa_scores, rda_scores]
cls.test_paths = ['L&L_CA_data_scores', 'example3_scores',
'PCoA_sample_data_3_scores', 'example2_scores']
cls.fferror_test_paths = ['error1', 'error2', 'error3', 'error4',
'error5', 'error6', 'error7']
cls.verror_test_paths = ['v_error1', 'v_error2', 'v_error3',
'v_error4', 'v_error5', 'v_error6',
'v_error7', 'v_error8', 'v_error9',
'v_error10', 'v_error11', 'v_error12',
'v_error13', 'v_error14']
def setup(self):
matrix = np.loadtxt(get_data_path('PCoA_sample_data_2'))
self.ids = [str(i) for i in range(matrix.shape[0])]
dist_matrix = DistanceMatrix(matrix, self.ids)
self.ordination = PCoA(dist_matrix)
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 setup(self):
"""Data from table 9.11 in Legendre & Legendre 1998."""
self.X = np.loadtxt(get_data_path('L&L_CA_data'))
self.ordination = CA(self.X, ['Site1', 'Site2', 'Site3'],
['Species1', 'Species2', 'Species3'])
def test_scaling1_species(self):
scores = self.ordination.scores(1)
vegan_species = np.loadtxt(get_data_path(
'example3_species_scaling1_from_vegan'))
npt.assert_almost_equal(scores.species, vegan_species, decimal=6)
def test_scaling2_site(self):
scores = self.ordination.scores(2)
vegan_site = np.loadtxt(
get_data_path('example3_site_scaling2_from_vegan'))
npt.assert_almost_equal(scores.site, vegan_site, decimal=4)
def setup(self):
"""Sample data set from page 111 of W.J Krzanowski. Principles
of multivariate analysis, 2000, Oxford University Press."""
matrix = np.loadtxt(get_data_path('PCoA_sample_data'))
dist_matrix = DistanceMatrix(matrix, map(str, range(matrix.shape[0])))
self.dist_matrix = dist_matrix
def test_scaling1_species(self):
scores = self.ordination.scores(1)
vegan_species = np.loadtxt(
get_data_path('example3_species_scaling1_from_vegan'))
npt.assert_almost_equal(scores.species, vegan_species, decimal=6)
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_class(cls):
# CA results
eigvals = np.array([0.0961330159181, 0.0409418140138])
species = np.array([[0.408869425742, 0.0695518116298],
[-0.1153860437, -0.299767683538],
[-0.309967102571, 0.187391917117]])
site = np.array([[-0.848956053187, 0.882764759014],
[-0.220458650578, -1.34482000302],
[1.66697179591, 0.470324389808]])
biplot = None
site_constraints = None
prop_explained = None
species_ids = ['Species1', 'Species2', 'Species3']
site_ids = ['Site1', 'Site2', 'Site3']
ca_scores = OrdinationResults(eigvals=eigvals,
species=species,
site=site,
biplot=biplot,
site_constraints=site_constraints,
proportion_explained=prop_explained,
species_ids=species_ids,
site_ids=site_ids)
# CCA results
eigvals = np.array([
0.366135830393, 0.186887643052, 0.0788466514249, 0.082287840501,
0.0351348475787, 0.0233265839374, 0.0099048981912,
0.00122461669234, 0.000417454724117
])
species = np.loadtxt(get_data_path('exp_OrdRes_CCA_species'))
site = np.loadtxt(get_data_path('exp_OrdRes_CCA_site'))
biplot = np.array(
[[-0.169746767979, 0.63069090084, 0.760769036049],
[-0.994016563505, 0.0609533148724, -0.0449369418179],
[0.184352565909, -0.974867543612, 0.0309865007541]])
site_constraints = np.loadtxt(
get_data_path('exp_OrdRes_CCA_site_constraints'))
prop_explained = None
species_ids = [
'Species0', 'Species1', 'Species2', 'Species3', 'Species4',
'Species5', 'Species6', 'Species7', 'Species8'
]
site_ids = [
'Site0', 'Site1', 'Site2', 'Site3', 'Site4', 'Site5', 'Site6',
'Site7', 'Site8', 'Site9'
]
cca_scores = OrdinationResults(eigvals=eigvals,
species=species,
site=site,
biplot=biplot,
site_constraints=site_constraints,
proportion_explained=prop_explained,
species_ids=species_ids,
site_ids=site_ids)
# PCoA results
eigvals = np.array([
0.512367260461, 0.300719094427, 0.267912066004, 0.208988681078,
0.19169895326, 0.16054234528, 0.15017695712, 0.122457748167, 0.0
])
species = None
site = np.loadtxt(get_data_path('exp_OrdRes_PCoA_site'))
biplot = None
site_constraints = None
prop_explained = np.array([
0.267573832777, 0.15704469605, 0.139911863774, 0.109140272454,
0.100111048503, 0.0838401161912, 0.0784269939011, 0.0639511763509,
0.0
])
species_ids = None
site_ids = [
'PC.636', 'PC.635', 'PC.356', 'PC.481', 'PC.354', 'PC.593',
'PC.355', 'PC.607', 'PC.634'
]
pcoa_scores = OrdinationResults(eigvals=eigvals,
species=species,
site=site,
biplot=biplot,
site_constraints=site_constraints,
proportion_explained=prop_explained,
species_ids=species_ids,
site_ids=site_ids)
# RDA results
eigvals = np.array([
25.8979540892, 14.9825779819, 8.93784077262, 6.13995623072,
1.68070536498, 0.57735026919, 0.275983624351
])
species = np.loadtxt(get_data_path('exp_OrdRes_RDA_species'))
site = np.loadtxt(get_data_path('exp_OrdRes_RDA_site'))
biplot = np.array([[0.422650019179, -0.559142585857, -0.713250678211],
[0.988495963777, 0.150787422017, -0.0117848614073],
[-0.556516618887, 0.817599992718, 0.147714267459],
[-0.404079676685, -0.9058434809, -0.127150316558]])
site_constraints = np.loadtxt(
get_data_path('exp_OrdRes_RDA_site_constraints'))
prop_explained = None
species_ids = [
'Species0', 'Species1', 'Species2', 'Species3', 'Species4',
'Species5'
]
site_ids = [
'Site0', 'Site1', 'Site2', 'Site3', 'Site4', 'Site5', 'Site6',
'Site7', 'Site8', 'Site9'
]
rda_scores = OrdinationResults(eigvals=eigvals,
species=species,
site=site,
biplot=biplot,
site_constraints=site_constraints,
proportion_explained=prop_explained,
species_ids=species_ids,
site_ids=site_ids)
cls.scores = [ca_scores, cca_scores, pcoa_scores, rda_scores]
cls.test_paths = [
'L&L_CA_data_scores', 'example3_scores',
'PCoA_sample_data_3_scores', 'example2_scores'
]
cls.fferror_test_paths = [
'error1', 'error2', 'error3', 'error4', 'error5', 'error6'
]
cls.verror_test_paths = [
'v_error1', 'v_error2', 'v_error3', 'v_error4', 'v_error5',
'v_error6', 'v_error7', 'v_error8', 'v_error9', 'v_error10'
]
def setup(self):
"""Data from table 9.11 in Legendre & Legendre 1998."""
self.X = np.loadtxt(get_data_path('L&L_CA_data'))
self.ordination = CA(self.X)
def setup(self):
"""Data from table 9.11 in Legendre & Legendre 1998."""
self.X = np.loadtxt(get_data_path('L&L_CA_data'))
self.ordination = CA(self.X)
def test_get_data_path():
fn = 'parrot'
path = os.path.dirname(os.path.abspath(__file__))
data_path = os.path.join(path, 'data', fn)
data_path_2 = get_data_path(fn)
npt.assert_string_equal(data_path_2, data_path)
def setup(self):
"""Data from table 11.3 in Legendre & Legendre 1998."""
Y = np.loadtxt(get_data_path('example2_Y'))
X = np.loadtxt(get_data_path('example2_X'))
self.ordination = RDA(Y, X)
