def lme_summary(output_dir: str, model: LMEModel, ndim=10) -> None:
""" Summarizes the ordinary linear mixed effects model.
Parameters
----------
output_dir : str
Directory where all of the regression results and
summaries will be stored.
model : LMEModel
Linear Mixed Effects model that contains the model fit and the
regression results.
ndim : int
The number of dimensions to summarize.
"""
# log likelihood
loglike = pd.Series({
r.model.endog_names: r.model.loglike(r.params)
for r in model.results
})
# Summary object
smry = model.summary(ndim=10)
t = _decorate_tree(model.tree, -loglike)
p1 = radialplot(t, edge_color='color', figsize=(800, 800))
p1.title.text = 'Loglikelihood of submodels'
p1.title_location = 'above'
p1.title.align = 'center'
p1.title.text_font_size = '18pt'
# 2D scatter plot for prediction on PB
p2 = _projected_prediction(model)
p3 = _projected_residuals(model)
p23 = row(p2, p3)
# Deposit all regression results
_deposit_results(model, output_dir)
index_fp = os.path.join(output_dir, 'index.html')
with open(index_fp, 'w') as index_f:
index_f.write('<html><body>\n')
index_f.write('<h1>Simplicial Linear Mixed Effects Summary</h1>\n')
index_f.write(smry.as_html())
_deposit_results_html(index_f)
ess_tree_html = file_html(p1, CDN, 'Loglikelihood')
index_f.write(ess_tree_html)
reg_smry_html = file_html(p23, CDN, 'Prediction and Residual plot')
index_f.write(reg_smry_html)
index_f.write('</body></html>\n')
def test_basic_plot(self):
self.maxDiff = None
exp_edges = {
'dest_node': ['0', '1', '2', 'y3'],
'edge_color': ['#00FF00', '#00FF00', '#00FF00', '#FF0000'],
'edge_width': [2, 2, 2, 2],
'src_node': ['y3', 'y4', 'y3', 'y4'],
'x0': [
338.2612593838583, 193.1688862557773, 338.2612593838583,
193.1688862557773
],
'x1':
[487.5, 12.499999999999972, 324.89684138234867, 338.2612593838583],
'y0': [
271.7282256126416, 365.95231443706376, 271.7282256126416,
365.95231443706376
],
'y1': [
347.7691620070637, 483.2800610261029, 16.719938973897143,
271.7282256126416
]
}
exp_nodes = {
'child0': [np.nan, np.nan, np.nan, '0', '1'],
'child1': [np.nan, np.nan, np.nan, '2', 'y3'],
'color': ['#1C9099', '#1C9099', '#1C9099', '#FF999F', '#FF999F'],
'hover_var': [None, None, None, None, None],
'is_tip': [True, True, True, False, False],
'node_size': [10, 10, 10, 10, 10],
'x': [
12.499999999999972, 487.5, 324.89684138234867,
338.26125938385832, 193.16888625577729
],
'y': [
483.28006102610289, 347.7691620070637, 16.719938973897143,
271.72822561264161, 365.95231443706376
]
}
np.random.seed(0)
num_otus = 3 # otus
x = np.random.rand(num_otus)
dm = DistanceMatrix.from_iterable(x, lambda x, y: np.abs(x - y))
lm = ward(dm.condensed_form())
t = TreeNode.from_linkage_matrix(lm, np.arange(len(x)).astype(np.str))
t = UnrootedDendrogram.from_tree(t)
# incorporate colors in tree
for i, n in enumerate(t.postorder(include_self=True)):
if not n.is_tip():
n.name = "y%d" % i
n.color = '#FF999F'
n.edge_color = '#FF0000'
n.node_size = 10
else:
n.color = '#1C9099'
n.edge_color = '#00FF00'
n.node_size = 10
n.length = np.random.rand() * 3
n.edge_width = 2
p = radialplot(t,
node_color='color',
edge_color='edge_color',
node_size='node_size',
edge_width='edge_width')
for e in exp_edges.keys():
if isinstance(exp_edges[e], float):
npt.assert_allclose(p.renderers[0].data_source.data[e],
np.array(exp_edges[e]))
else:
self.assertListEqual(list(p.renderers[0].data_source.data[e]),
exp_edges[e])
for e in exp_nodes.keys():
self.assertListEqual(list(p.renderers[1].data_source.data[e]),
exp_nodes[e])
self.assertTrue(isinstance(t, TreeNode))
def ols_summary(output_dir: str, model: OLSModel, ndim=10) -> None:
""" Summarizes the ordinary least squares fit.
Parameters
----------
output_dir : str
Directory where all of the regression results and
summaries will be stored.
model : OLSModel
Ordinary Least Squares model that contains the model fit and the
regression results.
ndim : int
The number of dimensions to summarize.
"""
# Cross validation
cv = model.loo()
# Relative importance of explanatory variables
relimp = model.lovo()
w, h = 400, 400 # plot width and height
# Histogram of model mean squared error from cross validation
mse_p = figure(title="Cross Validation Mean Squared Error",
plot_width=w,
plot_height=h)
mse_hist, edges = np.histogram(cv.mse, density=True, bins=20)
mse_p.quad(top=mse_hist,
bottom=0,
left=edges[:-1],
right=edges[1:],
fill_color="#FFFF00",
line_color="#033649",
fill_alpha=0.5,
legend='CV Mean Squared Error')
mse_p.ray(x=model.mse,
y=0,
length=h,
angle=1.57079633,
color='red',
legend='Model Error',
line_width=0.5)
# Histogram of prediction error from cross validation
pred_p = figure(title="Prediction Error", plot_width=w, plot_height=h)
pred_hist, edges = np.histogram(cv.pred_err, density=True, bins=20)
pred_p.quad(top=pred_hist,
bottom=0,
left=edges[:-1],
right=edges[1:],
fill_color="#00FFFF",
line_color="#033649",
fill_alpha=0.5,
legend='Prediction Error')
pred_p.ray(x=model.mse,
y=0,
length=h,
angle=1.57079633,
color='red',
legend='Model Error',
line_width=0.5)
cvp = row(mse_p, pred_p)
# Explained sum of squares
ess = pd.Series({r.model.endog_names: r.ess for r in model.results})
# Summary object
smry = model.summary(ndim=10)
t = _decorate_tree(model.tree, ess)
p1 = radialplot(t, edge_color='color', figsize=(800, 800))
p1.title.text = 'Explained Sum of Squares'
p1.title_location = 'above'
p1.title.align = 'center'
p1.title.text_font_size = '18pt'
# 2D scatter plot for prediction on PB
p2 = _projected_prediction(model)
p3 = _projected_residuals(model)
p23 = row(p2, p3)
_deposit_results(model, output_dir)
index_fp = os.path.join(output_dir, 'index.html')
with open(index_fp, 'w') as index_f:
index_f.write('<html><body>\n')
index_f.write('<h1>Simplicial Linear Regression Summary</h1>\n')
index_f.write(smry.as_html())
index_f.write('<th>Relative importance</th>\n')
index_f.write(relimp.to_html())
_deposit_results_html(index_f)
index_f.write('<th>Cross Validation</th>')
cv_html = file_html(cvp, CDN, 'Cross Validation')
index_f.write(cv_html)
ess_tree_html = file_html(p1, CDN, 'Explained Sum of Squares')
index_f.write(ess_tree_html)
reg_smry_html = file_html(p23, CDN, 'Prediction and Residual plot')
index_f.write(reg_smry_html)
index_f.write('</body></html>\n')
def test_basic_plot(self):
self.maxDiff = None
exp_edges = {'dest_node': ['0', '1', '2', 'y3'],
'edge_color': ['#00FF00', '#00FF00',
'#00FF00', '#FF0000'],
'edge_width': [2, 2, 2, 2],
'src_node': ['y3', 'y4', 'y3', 'y4'],
'x0': [338.2612593838583,
193.1688862557773,
338.2612593838583,
193.1688862557773],
'x1': [487.5, 12.499999999999972,
324.89684138234867, 338.2612593838583],
'y0': [271.7282256126416,
365.95231443706376,
271.7282256126416,
365.95231443706376],
'y1': [347.7691620070637,
483.2800610261029,
16.719938973897143,
271.7282256126416]}
exp_nodes = {'child0': [np.nan, np.nan, np.nan, '0', '1'],
'child1': [np.nan, np.nan, np.nan, '2', 'y3'],
'color': ['#1C9099', '#1C9099', '#1C9099',
'#FF999F', '#FF999F'],
'hover_var': [None, None, None, None, None],
'is_tip': [True, True, True, False, False],
'node_size': [10, 10, 10, 10, 10],
'x': [487.5,
12.499999999999972,
324.89684138234867,
338.26125938385832,
193.16888625577729],
'y': [347.7691620070637,
483.28006102610289,
16.719938973897143,
271.72822561264161,
365.95231443706376]}
np.random.seed(0)
num_otus = 3 # otus
x = np.random.rand(num_otus)
dm = DistanceMatrix.from_iterable(x, lambda x, y: np.abs(x-y))
lm = ward(dm.condensed_form())
t = TreeNode.from_linkage_matrix(lm, np.arange(len(x)).astype(np.str))
t = UnrootedDendrogram.from_tree(t)
# incorporate colors in tree
for i, n in enumerate(t.postorder(include_self=True)):
if not n.is_tip():
n.name = "y%d" % i
n.color = '#FF999F'
n.edge_color = '#FF0000'
n.node_size = 10
else:
n.color = '#1C9099'
n.edge_color = '#00FF00'
n.node_size = 10
n.length = np.random.rand()*3
n.edge_width = 2
p = radialplot(t, node_color='color', edge_color='edge_color',
node_size='node_size', edge_width='edge_width')
for e in exp_edges.keys():
self.assertListEqual(
list(p.renderers[0].data_source.data[e]),
exp_edges[e])
for e in exp_nodes.keys():
self.assertListEqual(
list(p.renderers[1].data_source.data[e]),
exp_nodes[e])
self.assertTrue(isinstance(t, TreeNode))
def lme_summary(output_dir: str, model: LMEModel, tree: TreeNode) -> None:
""" Summarizes the ordinary linear mixed effects model.
Parameters
----------
output_dir : str
Directory where all of the regression results and
summaries will be stored.
model : LMEModel
Linear Mixed Effects model that contains the model fit and the
regression results.
tree : TreeNode
Tree object that defines the partitions of the features. Each of the
leaves correspond to the balances in the model.
"""
# log likelihood
loglike = pd.Series({
r.model.endog_names: r.model.loglike(r.params)
for r in model.results
})
w, h = 500, 300 # plot width and height
# Summary object
smry = model.summary()
t = _decorate_tree(tree, -loglike)
p1 = radialplot(t, figsize=(800, 800))
p1.title.text = 'Loglikelihood of submodels'
p1.title_location = 'above'
p1.title.align = 'center'
p1.title.text_font_size = '18pt'
# 2D scatter plot for prediction on PB
p2 = _projected_prediction(model, plot_width=w, plot_height=h)
p3 = _projected_residuals(model, plot_width=w, plot_height=h)
hm_p = _heatmap_summary(model.pvalues.T,
model.coefficients().T,
plot_width=900,
plot_height=400)
# combine the cross validation, explained sum of squares tree and
# residual plots into a single plot
p = row(column(p2, p3), p1)
p = column(hm_p, p)
# Deposit all regression results
_deposit_results(model, output_dir)
index_fp = os.path.join(output_dir, 'index.html')
with open(index_fp, 'w') as index_f:
index_f.write('<html><body>\n')
index_f.write('<h1>Simplicial Linear Mixed Effects Summary</h1>\n')
index_f.write(smry.as_html())
index_f.write(('<th>Coefficients</th>\n'
'<a href="coefficients.csv">'
'Download as CSV</a><br>\n'
'<th>Coefficient pvalues</th>\n'
'<a href="pvalues.csv">'
'Download as CSV</a><br>\n'
'<th>Predicted Balances</th>\n'
'<a href="predicted.csv">'
'Download as CSV</a><br>\n'
'<th>Residuals</th>\n'
'<a href="residuals.csv">'
'Download as CSV</a><br>\n'))
diag_html = file_html(p, CDN, 'Diagnostic plots')
index_f.write(diag_html)
index_f.write('</body></html>\n')
def ols_summary(output_dir: str, model: OLSModel, tree: TreeNode) -> None:
""" Summarizes the ordinary least squares fit.
Parameters
----------
output_dir : str
Directory where all of the regression results and
summaries will be stored.
model : OLSModel
Ordinary Least Squares model that contains the model fit and the
regression results.
tree : TreeNode
Tree object that defines the partitions of the features. Each of the
leaves correspond to the balances in the model.
"""
# Cross validation
w, h = 500, 300 # plot width and height
# Explained sum of squares
ess = model.ess
# Summary object
_k, _l = model.kfold(), model.lovo()
smry = model.summary(_k, _l)
_deposit_results(model, output_dir)
t = _decorate_tree(tree, ess)
p1 = radialplot(t, figsize=(800, 800))
p1.title.text = 'Explained Sum of Squares'
p1.title_location = 'above'
p1.title.align = 'center'
p1.title.text_font_size = '18pt'
# 2D scatter plot for prediction on PB
p2 = _projected_prediction(model, plot_width=w, plot_height=h)
p3 = _projected_residuals(model, plot_width=w, plot_height=h)
hm_p = _heatmap_summary(model.pvalues.T, model.coefficients().T)
# combine the cross validation, explained sum of squares tree and
# residual plots into a single plot
p = row(column(p2, p3), p1)
p = column(hm_p, p)
index_fp = os.path.join(output_dir, 'index.html')
with open(index_fp, 'w') as index_f:
index_f.write('<html><body>\n')
index_f.write('<h1>Simplicial Linear Regression Summary</h1>\n')
index_f.write(smry.as_html())
index_f.write(('<th>Coefficients</th>\n'
'<a href="coefficients.csv">'
'Download as CSV</a><br>\n'
'<th>Coefficient pvalues</th>\n'
'<a href="pvalues.csv">'
'Download as CSV</a><br>\n'
'<th>Predicted Balances</th>\n'
'<a href="predicted.csv">'
'Download as CSV</a><br>\n'
'<th>Residuals</th>\n'
'<a href="residuals.csv">'
'Download as CSV</a><br>\n'))
plot_html = file_html(p, CDN, 'Diagnostics')
index_f.write(plot_html)
index_f.write('</body></html>\n')
def lme_summary(output_dir: str, model: LMEModel, tree: TreeNode) -> None:
""" Summarizes the ordinary linear mixed effects model.
Parameters
----------
output_dir : str
Directory where all of the regression results and
summaries will be stored.
model : LMEModel
Linear Mixed Effects model that contains the model fit and the
regression results.
tree : TreeNode
Tree object that defines the partitions of the features. Each of the
leaves correspond to the balances in the model.
"""
# log likelihood
loglike = pd.Series({r.model.endog_names: r.model.loglike(r.params)
for r in model.results})
w, h = 500, 300 # plot width and height
# Summary object
smry = model.summary()
t = _decorate_tree(tree, -loglike)
p1 = radialplot(t, figsize=(800, 800))
p1.title.text = 'Loglikelihood of submodels'
p1.title_location = 'above'
p1.title.align = 'center'
p1.title.text_font_size = '18pt'
# 2D scatter plot for prediction on PB
p2 = _projected_prediction(model, plot_width=w, plot_height=h)
p3 = _projected_residuals(model, plot_width=w, plot_height=h)
hm_p = _heatmap_summary(model.pvalues.T, model.coefficients().T,
plot_width=900, plot_height=400)
# combine the cross validation, explained sum of squares tree and
# residual plots into a single plot
p = row(column(p2, p3), p1)
p = column(hm_p, p)
# Deposit all regression results
_deposit_results(model, output_dir)
index_fp = os.path.join(output_dir, 'index.html')
with open(index_fp, 'w') as index_f:
index_f.write('<html><body>\n')
index_f.write('<h1>Simplicial Linear Mixed Effects Summary</h1>\n')
index_f.write(smry.as_html())
index_f.write(
('<th>Coefficients</th>\n'
'<a href="coefficients.csv">'
'Download as CSV</a><br>\n'
'<th>Coefficient pvalues</th>\n'
'<a href="pvalues.csv">'
'Download as CSV</a><br>\n'
'<th>FDR corrected coefficient pvalues</th>\n'
'<a href="fdr-corrected-pvalues.csv">'
'Download as CSV</a><br>\n'
'<th>Predicted Balances</th>\n'
'<a href="predicted.csv">'
'Download as CSV</a><br>\n'
'<th>Residuals</th>\n'
'<a href="residuals.csv">'
'Download as CSV</a><br>\n')
)
diag_html = file_html(p, CDN, 'Diagnostic plots')
index_f.write(diag_html)
index_f.write('</body></html>\n')
def ols_summary(output_dir: str, model: OLSModel,
tree: TreeNode) -> None:
""" Summarizes the ordinary least squares fit.
Parameters
----------
output_dir : str
Directory where all of the regression results and
summaries will be stored.
model : OLSModel
Ordinary Least Squares model that contains the model fit and the
regression results.
tree : TreeNode
Tree object that defines the partitions of the features. Each of the
leaves correspond to the balances in the model.
"""
# Cross validation
w, h = 500, 300 # plot width and height
# Explained sum of squares
ess = model.ess
# Summary object
_k, _l = model.kfold(), model.lovo()
smry = model.summary(_k, _l)
_deposit_results(model, output_dir)
t = _decorate_tree(tree, ess)
p1 = radialplot(t, figsize=(800, 800))
p1.title.text = 'Explained Sum of Squares'
p1.title_location = 'above'
p1.title.align = 'center'
p1.title.text_font_size = '18pt'
# 2D scatter plot for prediction on PB
p2 = _projected_prediction(model, plot_width=w, plot_height=h)
p3 = _projected_residuals(model, plot_width=w, plot_height=h)
hm_p = _heatmap_summary(model.pvalues.T, model.coefficients().T)
# combine the cross validation, explained sum of squares tree and
# residual plots into a single plot
p = row(column(p2, p3), p1)
p = column(hm_p, p)
index_fp = os.path.join(output_dir, 'index.html')
with open(index_fp, 'w') as index_f:
index_f.write('<html><body>\n')
index_f.write('<h1>Simplicial Linear Regression Summary</h1>\n')
index_f.write(smry.as_html())
index_f.write(
('<th>Coefficients</th>\n'
'<a href="coefficients.csv">'
'Download as CSV</a><br>\n'
'<th>Coefficient pvalues</th>\n'
'<a href="pvalues.csv">'
'Download as CSV</a><br>\n'
'<th>FDR corrected coefficient pvalues</th>\n'
'<a href="fdr-corrected-pvalues.csv">'
'Download as CSV</a><br>\n'
'<th>Predicted Balances</th>\n'
'<a href="predicted.csv">'
'Download as CSV</a><br>\n'
'<th>Residuals</th>\n'
'<a href="residuals.csv">'
'Download as CSV</a><br>\n')
)
plot_html = file_html(p, CDN, 'Diagnostics')
index_f.write(plot_html)
index_f.write('</body></html>\n')