def _create_story(self):
# Set up an empty list to hold the story
story = []
# Import the report styles
styles = report_styles.get_report_styles()
# Create a page break
story = self._make_page_break(story, self.PORTRAIT)
# Section title
title_str = '<strong>References</strong>'
para = p.Paragraph(title_str, styles['section_style'])
t = p.Table([[para]], colWidths=[7.5 * u.inch])
t.setStyle(
p.TableStyle([
('TOPPADDING', (0, 0), (-1, -1), 6),
('BOTTOMPADDING', (0, 0), (-1, -1), 6),
('BACKGROUND', (0, 0), (-1, -1), '#957348'),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('GRID', (0, 0), (-1, -1), 0.25, colors.black),
]))
story.append(t)
story.append(p.Spacer(0, 0.1 * u.inch))
# List of references used
references = [
'''
Cohen, J. 1960. "A coefficient of agreement for
nominal scales." Educational and Psychological Measurement
20: 37-46.
''',
'''
Kennedy, RE, Z Yang and WB Cohen. 2010. "Detecting trends
in forest disturbance and recovery using yearly Landsat
time series: 1. Landtrendr -- Temporal segmentation
algorithms." Remote Sensing of Environment 114(2010):
2897-2910.
''',
'''
Ohmann, JL, MJ Gregory and HM Roberts. 2014 (in press). "Scale
considerations for integrating forest inventory plot data and
satellite image data for regional forest mapping." Remote
Sensing of Environment.
''',
'''
O'Neil, TA, KA Bettinger, M Vander Heyden, BG Marcot, C Barrett,
TK Mellen, WM Vanderhaegen, DH Johnson, PJ Doran, L Wunder, and
KM Boula. 2001. "Structural conditions and habitat elements of
Oregon and Washington. Pages 115-139 in: Johnson, DH and TA
O'Neil, editors. 2001. "Wildlife-habitat relationships in Oregon
and Washington." Oregon State University Press, Corvallis, OR.
''',
]
# Print all references
for reference in references:
para = p.Paragraph(reference, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.10 * u.inch))
# Return this story
return story
def _create_story(self, scatter_files):
# Set up an empty list to hold the story
story = []
# Import the report styles
styles = report_styles.get_report_styles()
# Create a page break
story = self._make_page_break(story, self.PORTRAIT)
# Section title
title_str = '<strong>Local-Scale Accuracy Assessment: '
title_str += 'Scatterplots of Observed vs. Predicted '
title_str += 'Values for Continuous Variables at '
title_str += 'Plot Locations</strong>'
para = p.Paragraph(title_str, styles['section_style'])
t = p.Table([[para]], colWidths=[7.5 * u.inch])
t.setStyle(
p.TableStyle([
('TOPPADDING', (0, 0), (-1, -1), 6),
('BOTTOMPADDING', (0, 0), (-1, -1), 6),
('BACKGROUND', (0, 0), (-1, -1), '#957348'),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('GRID', (0, 0), (-1, -1), 0.25, colors.black),
]))
story.append(t)
story.append(p.Spacer(0, 0.2 * u.inch))
# Scatter explanation
scatter_str = '''
These scatterplots compare the observed plot values against
predicted (modeled) values for each plot used in the GNN model.
We use a modified leave-one-out (LOO) approach. In traditional
LOO accuracy assessment, a model is run with <i>n</i>-1
plots and then accuracy is determined at the plot left out of
modeling, for all plots used in modeling. Because of computing
limitations, we use a 'second-nearest-neighbor' approach. We
develop our models with all plots, but in determining accuracy, we
don't allow a plot to assign itself as a neighbor at the plot
location. This yields similar accuracy assessment results as
a true cross-validation approach, but probably slightly
underestimates the true accuracy of the distributed
(first-nearest-neighbor) map.<br/><br/>
The observed value comes directly from the plot data,
whereas the predicted value comes from the GNN prediction
for the plot location. The GNN prediction is the mean of
pixel values for a window that approximates the
field plot configuration.<br/><br/>
The correlation coefficients, normalized Root Mean Squared
Errors (RMSE), and coefficients of determination (R-square) are
given. The RMSE is normalized by dividing the RMSE by the
observed mean value.
'''
para = p.Paragraph(scatter_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
# Add the scatterplot images to a list of lists
table_cols = 2
scatter_table = []
scatter_row = []
for (i, fn) in enumerate(scatter_files):
scatter_row.append(p.Image(fn, 3.4 * u.inch, 3.0 * u.inch))
if (i % table_cols) == (table_cols - 1):
scatter_table.append(scatter_row)
scatter_row = []
# Determine if there are any scatterplots left to print
if len(scatter_row) != 0:
for i in range(len(scatter_row), table_cols):
scatter_row.append(p.Paragraph('', styles['body_style']))
scatter_table.append(scatter_row)
# Style this into a reportlab table and add to the story
width = 3.75 * u.inch
t = p.Table(scatter_table, colWidths=[width, width])
t.setStyle(
p.TableStyle([
('ALIGNMENT', (0, 0), (-1, -1), 'CENTER'),
('VALIGN', (0, 0), (-1, -1), 'CENTER'),
('TOPPADDING', (0, 0), (-1, -1), 6.0),
('BOTTOMPADDING', (0, 0), (-1, -1), 6.0),
]))
story.append(t)
# Return this story
return story
def _create_story(self):
# Set up an empty list to hold the story
story = []
# Import the report styles
styles = report_styles.get_report_styles()
# Create a page break
story = self._make_page_break(story, self.PORTRAIT)
# Section title
title_str = '<strong>Data Dictionary</strong>'
para = p.Paragraph(title_str, styles['section_style'])
t = p.Table([[para]], colWidths=[7.5 * u.inch])
t.setStyle(
p.TableStyle([
('TOPPADDING', (0, 0), (-1, -1), 6),
('BOTTOMPADDING', (0, 0), (-1, -1), 6),
('BACKGROUND', (0, 0), (-1, -1), '#957348'),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('GRID', (0, 0), (-1, -1), 0.25, colors.black),
]))
story.append(t)
story.append(p.Spacer(0, 0.1 * u.inch))
# Read in the stand attribute metadata
mp = xsmp.XMLStandMetadataParser(self.stand_metadata_file)
# Subset the attributes to those that are accuracy attributes, are
# identified to go into the report, and are not species variables
attrs = []
for attr in mp.attributes:
if attr.accuracy_attr == 1 and attr.project_attr == 1 and \
attr.species_attr == 0:
attrs.append(attr.field_name)
# Set up the master dictionary table
dictionary_table = []
# Iterate through the attributes and print out the field information
# and codes if present
for attr in attrs:
metadata = mp.get_attribute(attr)
field_name = metadata.field_name
units = metadata.units
description = metadata.description
field_para = p.Paragraph(field_name, styles['body_style_10'])
if units != 'none':
description += ' (' + units + ')'
field_desc_para = p.Paragraph(description, styles['body_style_10'])
# If this field has codes, create a sub table underneath the
# field description
if metadata.codes:
# Set up a container to hold the code rows
code_table = []
# Iterate over all code rows and append to the code_table
for code in metadata.codes:
code_para = \
p.Paragraph(code.code_value, styles['code_style'])
description = self.txt_to_html(code.description)
code_desc_para = \
p.Paragraph(description, styles['code_style'])
code_table.append([code_para, code_desc_para])
# Convert this to a reportlab table
t = p.Table(code_table,
colWidths=[0.75 * u.inch, 4.5 * u.inch])
t.setStyle(
p.TableStyle([
('TOPPADDING', (0, 0), (-1, -1), 3),
('BOTTOMPADDING', (0, 0), (-1, -1), 3),
('BACKGROUND', (0, 0), (-1, -1), '#f7f7ea'),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('GRID', (0, 0), (-1, -1), 0.25, colors.white),
]))
# Create a stack of the field description and field codes
elements = \
[[field_desc_para], [t]]
# If no codes exist, just add the field description
else:
elements = [[field_desc_para]]
# Create a reportlab table of the field description and
# (if present) field codes
description_table = \
p.Table(elements, colWidths=[5.25 * u.inch])
description_table.setStyle(
p.TableStyle([
('TOPPADDING', (0, 0), (-1, 0), 0),
('BOTTOMPADDING', (0, -1), (-1, -1), 0),
('LEFTPADDING', (0, 0), (-1, -1), 0),
('RIGHTPADDING', (0, 0), (-1, -1), 0),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
]))
dictionary_table.append([field_para, description_table])
# Format the dictionary table into a reportlab table
t = p.Table(dictionary_table, colWidths=[1.6 * u.inch, 5.4 * u.inch])
t.setStyle(
p.TableStyle([
('TOPPADDING', (0, 0), (0, -1), 5),
('BOTTOMPADDING', (0, 0), (0, -1), 5),
('GRID', (0, 0), (-1, -1), 1, colors.white),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('BACKGROUND', (0, 0), (-1, -1), '#f1efe4'),
]))
story.append(t)
# Description of the species information that is attached to ArcInfo
# grids. We don't enumerate the codes here, but just give this
# summary information
spp_str = """
Individual species abundances are attached to ArcInfo grids that
LEMMA distributes. For this model, fields designate species
codes based on the <link color="#0000ff"
href="http://plants.usda.gov/">USDA PLANTS database</link> from
the year 2000, and values represent species
"""
if self.model_type in ['sppsz', 'sppba']:
spp_str += " basal area (m^2/ha)."
elif self.model_type in ['trecov', 'wdycov']:
spp_str += " percent cover."
para = p.Paragraph(spp_str, styles['body_style'])
story.append(p.Spacer(0, 0.1 * u.inch))
story.append(para)
# Return this story
return story
def _create_story(self, histogram_files):
# Set up an empty list to hold the story
story = []
# Import the report styles
styles = report_styles.get_report_styles()
# Create a page break
story = self._make_page_break(story, self.PORTRAIT)
# Section title
title_str = '<strong>Regional-Scale Accuracy Assessment:<br/> Area '
title_str += 'Distributions from Regional Inventory Plots vs. '
title_str += 'GNN</strong>'
para = p.Paragraph(title_str, styles['section_style'])
t = p.Table([[para]], colWidths=[7.5 * u.inch])
t.setStyle(
p.TableStyle([
('TOPPADDING', (0, 0), (-1, -1), 6),
('BOTTOMPADDING', (0, 0), (-1, -1), 6),
('BACKGROUND', (0, 0), (-1, -1), '#957348'),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('GRID', (0, 0), (-1, -1), 0.25, colors.black),
]))
story.append(t)
story.append(p.Spacer(0, 0.20 * u.inch))
# Histogram explanation
histo_str = '''
These histograms compare the distributions of land area in
different vegetation conditions as estimated from a regional,
sample- (plot-) based inventory (FIA Annual Plots) to model
predictions from GNN (based on counts of 30-m pixels).
<br/><br/>
For the FIA annual plots, the distributions of forest area
are determined by summing the 'area expansion factors' at the
plot condition-class level. The plot-based estimates are
subject to sampling error, but this is not shown in the graphs
due to complexities involved. For more information about the
FIA Annual inventory sample design, see the
<link href="http://fia.fs.fed.us/library/database-documentation"
color="blue">FIADB Users Manual</link>.
<br/><br/>
Some plots were not visited on the ground due to denied
access or hazardous conditions, so the area these plots
represent cannot be characterized and is included in the bar
labeled 'unsampled.'
<br/><br/>
The bars labeled 'nonforest' also require explanation. For GNN,
this is the area of nonforest in the map, which is derived
from ancillary (non-GNN) spatial data sources such as the
National Land Cover Data (NLCD) or Ecological Systems maps
from the Gap Analysis Program (GAP). This mapped nonforest is
referred to as the GNN 'nonforest mask.'
<br/><br/>
For the plots, the 'nonforest' bar represents the nonforest area
as estimated from the FIA Annual sample.
'''
para = p.Paragraph(histo_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
# Add the histogram images to a list of lists
table_cols = 2
histogram_table = []
histogram_row = []
for (i, fn) in enumerate(histogram_files):
histogram_row.append(p.Image(fn, 3.4 * u.inch, 3.0 * u.inch))
if (i % table_cols) == (table_cols - 1):
histogram_table.append(histogram_row)
histogram_row = []
# Determine if there are any histograms left to print
if len(histogram_row) != 0:
for i in range(len(histogram_row), table_cols):
histogram_row.append(p.Paragraph('', styles['body_style']))
histogram_table.append(histogram_row)
# Style this into a reportlab table and add to the story
width = 3.75 * u.inch
t = p.Table(histogram_table, colWidths=[width, width])
t.setStyle(
p.TableStyle([
('ALIGNMENT', (0, 0), (-1, -1), 'CENTER'),
('VALIGN', (0, 0), (-1, -1), 'CENTER'),
('TOPPADDING', (0, 0), (-1, -1), 6.0),
('BOTTOMPADDING', (0, 0), (-1, -1), 6.0),
]))
story.append(t)
# Return this story
return story
def _create_story(self):
# Set up an empty list to hold the story
story = []
# Import the report styles
styles = report_styles.get_report_styles()
# Create a page break
story = self._make_page_break(story, self.LANDSCAPE)
# This class is somewhat of a hack, in that it likely only works on
# rotated paragraphs which fit into the desired cell area
class RotatedParagraph(p.Paragraph):
def wrap(self, availHeight, availWidth):
h, w = \
p.Paragraph.wrap(self, self.canv.stringWidth(self.text),
self.canv._leading)
return w, h
def draw(self):
self.canv.rotate(90)
self.canv.translate(0.0, -10.0)
p.Paragraph.draw(self)
# Section title
title_str = '<strong>Local-Scale Accuracy Assessment: '
title_str += 'Error Matrix for Vegetation Classes at Plot '
title_str += 'Locations</strong>'
para = p.Paragraph(title_str, styles['section_style'])
t = p.Table([[para]], colWidths=[10.0 * u.inch])
t.setStyle(
p.TableStyle([
('TOPPADDING', (0, 0), (-1, -1), 3),
('BOTTOMPADDING', (0, 0), (-1, -1), 3),
('BACKGROUND', (0, 0), (-1, -1), '#957348'),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('GRID', (0, 0), (-1, -1), 0.25, colors.black),
]))
story.append(t)
story.append(p.Spacer(0, 0.1 * u.inch))
# Read in the vegclass error matrix
names = ['P_' + str(x) for x in range(1, 12)]
names.insert(0, 'OBSERVED')
names.extend(['TOTAL', 'CORRECT', 'FUZZY_CORRECT'])
vc_data = mlab.csv2rec(self.vc_errmatrix_file, skiprows=1, names=names)
vc_data = mlab.rec_drop_fields(vc_data, ['OBSERVED'])
# Read in the stand attribute metadata
mp = xsmp.XMLStandMetadataParser(self.stand_metadata_file)
# Get the class names from the metadata
vegclass_metadata = mp.get_attribute('VEGCLASS')
vc_codes = vegclass_metadata.codes
# Create a list of lists to hold the vegclass table
vegclass_table = []
# Add an empty row which will be a span row for the predicted label
header_row = []
for i in xrange(2):
header_row.append('')
prd_str = '<strong>Predicted Class</strong>'
para = p.Paragraph(prd_str, styles['body_style_10_center'])
header_row.append(para)
for i in xrange(len(vc_data) - 1):
header_row.append('')
vegclass_table.append(header_row)
# Add the predicted labels
summary_labels = ('Total', '% Correct', '% FCorrect')
header_row = []
for i in xrange(2):
header_row.append('')
for code in vc_codes:
label = re.sub('-', '-<br/>', code.label)
para = p.Paragraph(label, styles['body_style_10_right'])
header_row.append(para)
for label in summary_labels:
label = re.sub(' ', '<br/>', label)
para = p.Paragraph(label, styles['body_style_10_right'])
header_row.append(para)
vegclass_table.append(header_row)
# Set a variable to distinguish between plot counts and percents
# in order to format them differently
format_break = 11
# Set the cells which should be blank
blank_cells = \
[(11, 12), (11, 13), (12, 11), (12, 13), (13, 11), (13, 12)]
# Add the data
for (i, row) in enumerate(vc_data):
vegclass_row = []
for (j, elem) in enumerate(row):
# Blank cells
if (i, j) in blank_cells:
elem_str = ''
# Cells that represent plot counts
elif i <= format_break and j <= format_break:
elem_str = '%d' % int(elem)
# Cells that represent percentages
else:
elem_str = '%.1f' % float(elem)
para = p.Paragraph(elem_str, styles['body_style_10_right'])
vegclass_row.append(para)
# Add the observed labels at the beginning of each data row
if i == 0:
obs_str = '<strong>Observed Class</strong>'
para = \
RotatedParagraph(obs_str, styles['body_style_10_center'])
else:
para = ''
vegclass_row.insert(0, para)
if i < len(vc_codes):
label = vc_codes[i].label
else:
index = i - len(vc_codes)
label = summary_labels[index]
para = p.Paragraph(label, styles['body_style_10_right'])
vegclass_row.insert(1, para)
# Add this row to the table
vegclass_table.append(vegclass_row)
# Set up the widths for the table cells
widths = []
widths.append(0.3)
widths.append(0.85)
for i in xrange(len(vc_codes)):
widths.append(0.56)
for i in xrange(3):
widths.append(0.66)
widths = [x * u.inch for x in widths]
# Convert the vegclass table into a reportlab table
t = p.Table(vegclass_table, colWidths=widths)
t.setStyle(
p.TableStyle([
('SPAN', (0, 0), (1, 1)),
('SPAN', (0, 2), (0, -1)),
('SPAN', (2, 0), (-1, 0)),
('BACKGROUND', (0, 0), (-1, -1), '#f1efe4'),
('GRID', (0, 0), (-1, -1), 1, colors.white),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('VALIGN', (0, 2), (0, -1), 'MIDDLE'),
('VALIGN', (2, 1), (-1, 1), 'MIDDLE'),
('TOPPADDING', (0, 0), (-1, -1), 2),
('BOTTOMPADDING', (0, 0), (-1, -1), 3),
]))
# Set up the shading for the truly correct cells
correct = {}
for i in xrange(len(vc_codes)):
val = i + 1
correct[val] = val
for key in correct:
val = correct[key]
t.setStyle(
p.TableStyle([
('BACKGROUND', (key + 1, val + 1), (key + 1, val + 1),
'#aaaaaa'),
]))
# Set up the shading for the fuzzy correct cells
fuzzy = {}
fuzzy[1] = [2]
fuzzy[2] = [1, 3, 5, 8]
fuzzy[3] = [2, 4, 5]
fuzzy[4] = [3, 6, 7]
fuzzy[5] = [2, 3, 6, 8]
fuzzy[6] = [4, 5, 7, 9]
fuzzy[7] = [4, 6, 10, 11]
fuzzy[8] = [2, 5, 9]
fuzzy[9] = [6, 8, 10]
fuzzy[10] = [7, 9, 11]
fuzzy[11] = [7, 10]
for key in fuzzy:
for elem in fuzzy[key]:
t.setStyle(
p.TableStyle([
('BACKGROUND', (key + 1, elem + 1),
(key + 1, elem + 1), '#dddddd'),
]))
# Add this table to the story
story.append(t)
story.append(p.Spacer(0, 0.1 * u.inch))
# Explanation and definitions of vegetation class categories
cell_str = """
Cell values are model plot counts. Dark gray cells represent
plots where the observed class matches the predicted class
and are included in the percent correct. Light gray cells
represent cases where the observed and predicted differ
slightly (within +/- one class) based on canopy cover,
hardwood proportion or average stand diameter, and are
included in the percent fuzzy correct.
"""
para = p.Paragraph(cell_str, styles['body_style_9'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
head_str = '''
<strong>Vegetation Class (VEGCLASS) Definitions</strong> --
CANCOV (canopy cover of all live trees), BAH_PROP (proportion of
hardwood basal area), and QMD_DOM (quadratic mean diameter of
all dominant and codominant trees).
'''
para = p.Paragraph(head_str, styles['body_style_9'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
# Print out the vegclass code definitions
for code in vc_codes:
label = code.label
desc = self.txt_to_html(code.description)
doc_str = '<strong>' + label + ':</strong> ' + desc
para = p.Paragraph(doc_str, styles['body_style_9'])
story.append(para)
return story
def _create_story(self):
# Set up an empty list to hold the story
story = []
# Import the report styles
styles = report_styles.get_report_styles()
# Create a page break
story = self._make_page_break(story, self.PORTRAIT)
# Section title
title_str = '<strong>Local-Scale Accuracy Assessment:<br/>'
title_str += 'Species Accuracy at Plot Locations'
title_str += '</strong>'
para = p.Paragraph(title_str, styles['section_style'])
t = p.Table([[para]], colWidths=[7.5 * u.inch])
t.setStyle(
p.TableStyle([
('TOPPADDING', (0, 0), (-1, -1), 6),
('BOTTOMPADDING', (0, 0), (-1, -1), 6),
('BACKGROUND', (0, 0), (-1, -1), '#957348'),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('GRID', (0, 0), (-1, -1), 0.25, colors.black),
]))
story.append(t)
story.append(p.Spacer(0, 0.2 * u.inch))
# Kappa explanation
kappa_str = '''
Cohen's kappa coefficient (Cohen, 1960) is a statistical measure
of reliability, accounting for agreement occurring by chance.
The equation for kappa is:
'''
para = p.Paragraph(kappa_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.05 * u.inch))
kappa_str = '''
kappa = (Pr(a) - Pr(e)) / (1.0 - Pr(e))
'''
para = p.Paragraph(kappa_str, styles['indented'])
story.append(para)
story.append(p.Spacer(0, 0.05 * u.inch))
kappa_str = '''
where Pr(a) is the relative observed agreement among
raters, and Pr(e) is the probability that agreement is
due to chance.<br/><br/>
<strong>Abbreviations Used:</strong><br/>
OP/PP = Observed Present / Predicted Present<br/>
OA/PP = Observed Absent / Predicted Present
(errors of commission)<br/>
OP/PA = Observed Present / Predicted Absent
(errors of ommission)<br/>
OA/PA = Observed Absent / Predicted Absent
'''
para = p.Paragraph(kappa_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.2 * u.inch))
# Create a list of lists to hold the species accuracy information
species_table = []
# Header row
header_row = []
spp_str = '<strong>Species PLANTS Code<br/>'
spp_str += 'Scientific Name / Common Name</strong>'
para = p.Paragraph(spp_str, styles['body_style_10'])
header_row.append(para)
spp_str = '<strong>Species prevalence</strong>'
para = p.Paragraph(spp_str, styles['body_style_10'])
header_row.append(para)
p1 = p.Paragraph('<strong>OP/PP</strong>',
styles['body_style_10_right'])
p2 = p.Paragraph('<strong>OP/PA</strong>',
styles['body_style_10_right'])
p3 = p.Paragraph('<strong>OA/PP</strong>',
styles['body_style_10_right'])
p4 = p.Paragraph('<strong>OA/PA</strong>',
styles['body_style_10_right'])
header_cells = [[p1, p2], [p3, p4]]
t = p.Table(header_cells, colWidths=[0.75 * u.inch, 0.75 * u.inch])
t.setStyle(
p.TableStyle([
('GRID', (0, 0), (-1, -1), 1, colors.white),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('TOPPADDING', (0, 0), (-1, -1), 2),
('BOTTOMPADDING', (0, 0), (-1, -1), 2),
]))
header_row.append(t)
kappa_str = '<strong>Kappa coefficient</strong>'
para = p.Paragraph(kappa_str, styles['body_style_10'])
header_row.append(para)
species_table.append(header_row)
# Open the species accuracy file into a recarray
spp_data = utilities.csv2rec(self.species_accuracy_file)
# Read in the stand attribute metadata
mp = xsmp.XMLStandMetadataParser(self.stand_metadata_file)
# Read in the report metadata if it exists
if self.report_metadata_file:
rmp = xrmp.XMLReportMetadataParser(self.report_metadata_file)
else:
rmp = None
# Subset the attributes to just species
attrs = []
for attr in mp.attributes:
if attr.species_attr == 1 and 'NOTALY' not in attr.field_name:
attrs.append(attr.field_name)
# Iterate over the species and print out the statistics
for spp in attrs:
# Empty row to hold the formatted output
species_row = []
# Get the scientific and common names from the report metadata
# if it exists; otherwise, just use the species symbol
if rmp is not None:
# Strip off any suffix if it exists
try:
spp_plain = spp.split('_')[0]
spp_info = rmp.get_species(spp_plain)
spp_str = spp_info.spp_symbol + '<br/>'
spp_str += spp_info.scientific_name + ' / '
spp_str += spp_info.common_name
except IndexError:
spp_str = spp
else:
spp_str = spp
para = p.Paragraph(spp_str, styles['body_style_10'])
species_row.append(para)
# Get the statistical information
data = spp_data[spp_data.SPECIES == spp][0]
counts = [data.OP_PP, data.OP_PA, data.OA_PP, data.OA_PA]
prevalence = data.PREVALENCE
kappa = data.KAPPA
# Species prevalence
prevalence_str = '%.4f' % prevalence
para = p.Paragraph(prevalence_str, styles['body_style_10_right'])
species_row.append(para)
# Capture the plot counts in an inner table
count_cells = []
count_row = []
for i in range(0, 4):
para = p.Paragraph(
'%d' % counts[i], styles['body_style_10_right'])
count_row.append(para)
if i % 2 == 1:
count_cells.append(count_row)
count_row = []
t = p.Table(count_cells, colWidths=[0.75 * u.inch, 0.75 * u.inch])
t.setStyle(
p.TableStyle([
('GRID', (0, 0), (-1, -1), 1, colors.white),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('TOPPADDING', (0, 0), (-1, -1), 2),
('BOTTOMPADDING', (0, 0), (-1, -1), 2),
]))
species_row.append(t)
# Print out the kappa statistic
kappa_str = '%.4f' % kappa
para = p.Paragraph(kappa_str, styles['body_style_10_right'])
species_row.append(para)
# Push this row to the master species table
species_table.append(species_row)
# Style this into a reportlab table and add to the story
col_widths = [(x * u.inch) for x in [4.0, 0.75, 1.5, 0.75]]
t = p.Table(species_table, colWidths=col_widths)
t.setStyle(
p.TableStyle([
('BACKGROUND', (0, 0), (-1, -1), '#f1efe4'),
('GRID', (0, 0), (-1, -1), 2, colors.white),
('TOPPADDING', (0, 0), (0, -1), 2),
('BOTTOMPADDING', (0, 0), (0, -1), 2),
('LEFTPADDING', (0, 0), (0, -1), 6),
('RIGHTPADDING', (0, 0), (0, -1), 6),
('ALIGNMENT', (0, 0), (0, -1), 'LEFT'),
('VALIGN', (0, 0), (0, -1), 'TOP'),
('TOPPADDING', (1, 0), (1, -1), 2),
('BOTTOMPADDING', (1, 0), (1, -1), 2),
('LEFTPADDING', (1, 0), (1, -1), 6),
('RIGHTPADDING', (1, 0), (1, -1), 6),
('ALIGNMENT', (1, 0), (1, -1), 'RIGHT'),
('VALIGN', (1, 0), (1, 0), 'TOP'),
('VALIGN', (1, 1), (1, -1), 'MIDDLE'),
('TOPPADDING', (2, 0), (2, -1), 0),
('BOTTOMPADDING', (2, 0), (2, -1), 0),
('LEFTPADDING', (2, 0), (2, -1), 0),
('RIGHTPADDING', (2, 0), (2, -1), 0),
('ALIGNMENT', (2, 0), (2, -1), 'LEFT'),
('VALIGN', (2, 0), (2, -1), 'TOP'),
('TOPPADDING', (3, 0), (3, -1), 2),
('BOTTOMPADDING', (3, 0), (3, -1), 2),
('LEFTPADDING', (3, 0), (3, -1), 6),
('RIGHTPADDING', (3, 0), (3, -1), 6),
('ALIGNMENT', (3, 0), (3, -1), 'RIGHT'),
('VALIGN', (3, 0), (3, 0), 'TOP'),
('VALIGN', (3, 1), (3, -1), 'MIDDLE'),
]))
story.append(t)
story.append(p.Spacer(0, 0.1 * u.inch))
rare_species_str = """
Note that some very rare species do not appear in this accuracy
report, because these species were not included when building
the initial ordination model. The full set of species is
available upon request.
"""
para = p.Paragraph(rare_species_str, styles['body_style'])
story.append(para)
# Return this story
return story
def _create_story(self, scatter_files):
# Set up an empty list to hold the story
story = []
# Import the report styles
styles = report_styles.get_report_styles()
# Create a page break
story = self._make_page_break(story, self.PORTRAIT)
# Section title
title_str = "<strong>Local-Scale Accuracy Assessment: "
title_str += "Scatterplots of Observed vs. Predicted "
title_str += "Values for Continuous Variables at "
title_str += "Plot Locations</strong>"
para = p.Paragraph(title_str, styles["section_style"])
t = p.Table([[para]], colWidths=[7.5 * u.inch])
t.setStyle(
p.TableStyle(
[
("TOPPADDING", (0, 0), (-1, -1), 6),
("BOTTOMPADDING", (0, 0), (-1, -1), 6),
("BACKGROUND", (0, 0), (-1, -1), "#957348"),
("ALIGNMENT", (0, 0), (-1, -1), "LEFT"),
("VALIGN", (0, 0), (-1, -1), "TOP"),
("GRID", (0, 0), (-1, -1), 0.25, colors.black),
]
)
)
story.append(t)
story.append(p.Spacer(0, 0.2 * u.inch))
# Scatter explanation
scatter_str = """
These scatterplots compare the observed plot values against
predicted (modeled) values for each plot used in the GNN model.
We use a modified leave-one-out (LOO) approach. In traditional
LOO accuracy assessment, a model is run with <i>n</i>-1
plots and then accuracy is determined at the plot left out of
modeling, for all plots used in modeling. Because of computing
limitations, we use a 'second-nearest-neighbor' approach. We
develop our models with all plots, but in determining accuracy, we
don't allow a plot to assign itself as a neighbor at the plot
location. This yields similar accuracy assessment results as
a true cross-validation approach, but probably slightly
underestimates the true accuracy of the distributed
(first-nearest-neighbor) map.<br/><br/>
The observed value comes directly from the plot data,
whereas the predicted value comes from the GNN prediction
for the plot location. The GNN prediction is the mean of
pixel values for a window that approximates the
field plot configuration.<br/><br/>
The correlation coefficients, normalized Root Mean Squared
Errors (RMSE), and coefficients of determination (R-square) are
given. The RMSE is normalized by dividing the RMSE by the
observed mean value.
"""
para = p.Paragraph(scatter_str, styles["body_style"])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
# Add the scatterplot images to a list of lists
table_cols = 2
scatter_table = []
scatter_row = []
for (i, fn) in enumerate(scatter_files):
scatter_row.append(p.Image(fn, 3.4 * u.inch, 3.0 * u.inch))
if (i % table_cols) == (table_cols - 1):
scatter_table.append(scatter_row)
scatter_row = []
# Determine if there are any scatterplots left to print
if len(scatter_row) != 0:
for i in range(len(scatter_row), table_cols):
scatter_row.append(p.Paragraph("", styles["body_style"]))
scatter_table.append(scatter_row)
# Style this into a reportlab table and add to the story
width = 3.75 * u.inch
t = p.Table(scatter_table, colWidths=[width, width])
t.setStyle(
p.TableStyle(
[
("ALIGNMENT", (0, 0), (-1, -1), "CENTER"),
("VALIGN", (0, 0), (-1, -1), "CENTER"),
("TOPPADDING", (0, 0), (-1, -1), 6.0),
("BOTTOMPADDING", (0, 0), (-1, -1), 6.0),
]
)
)
story.append(t)
# Return this story
return story
def _create_story(self):
# Set up an empty list to hold the story
story = []
# Import the report styles
styles = report_styles.get_report_styles()
# Open the report metadata
rmp = xrmp.XMLReportMetadataParser(self.report_metadata_file)
# Offset on this first page
story.append(p.Spacer(0.0, 0.43 * u.inch))
# Report title
title_str = 'GNN Accuracy Assessment Report'
title = p.Paragraph(title_str, styles['title_style'])
story.append(title)
# Model region name and number
mr_name = rmp.model_region_name
subtitle_str = mr_name + ' (Modeling Region ' + str(self.mr) + ')'
para = p.Paragraph(subtitle_str, styles['sub_title_style'])
story.append(para)
# Model type information
model_type_dict = {
'sppsz': 'Basal-Area by Species-Size Combinations',
'trecov': 'Tree Percent Cover by Species',
'wdycov': 'Woody Percent Cover by Species',
'sppba': 'Basal-Area by Species',
}
model_type_str = 'Model Type: '
model_type_str += model_type_dict[self.model_type]
para = p.Paragraph(model_type_str, styles['sub_title_style'])
story.append(para)
story.append(p.Spacer(0.0, 0.7 * u.inch))
# Image and flowable to hold MR image and region description
substory = []
mr_image_path = rmp.image_path
image = p.Image(mr_image_path, 3.0 * u.inch, 3.86 * u.inch,
mask='auto')
para = p.Paragraph('Overview', styles['heading_style'])
substory.append(para)
overview = rmp.model_region_overview
para = p.Paragraph(overview, styles['body_style'])
substory.append(para)
image_flowable = p.ImageAndFlowables(image, substory, imageSide='left',
imageRightPadding=6)
story.append(image_flowable)
story.append(p.Spacer(0.0, 0.2 * u.inch))
# Contact information
para = p.Paragraph('Contact Information:', styles['heading_style'])
story.append(para)
story.append(p.Spacer(0.0, 0.1 * u.inch))
contacts = rmp.contacts
contact_table = []
contact_row = []
table_cols = 3
for (i, contact) in enumerate(contacts):
contact_str = '<b>' + contact.name + '</b><br/>'
contact_str += contact.position_title + '<br/>'
contact_str += contact.affiliation + '<br/>'
contact_str += 'Phone: ' + contact.phone_number + '<br/>'
contact_str += 'Email: ' + contact.email_address
para = p.Paragraph(contact_str, styles['body_style_9'])
contact_row.append(para)
if (i % table_cols) == (table_cols - 1):
contact_table.append(contact_row)
contact_row = []
t = p.Table(contact_table)
t.setStyle(
p.TableStyle([
('TOPPADDING', (0, 0), (-1, -1), 4),
('BOTTOMPADDING', (0, 0), (-1, -1), 4),
('LEFTPADDING', (0, 0), (-1, -1), 6),
('RIGHTPADDING', (0, 0), (-1, -1), 6),
('BACKGROUND', (0, 0), (-1, -1), '#f1efe4'),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('GRID', (0, 0), (-1, -1), 1.0, colors.white),
]))
story.append(t)
story.append(p.Spacer(0, 0.15 * u.inch))
# Website link
web_str = '<strong>LEMMA Website:</strong> '
web_str += '<link color="#0000ff" '
web_str += 'href="http://lemma.forestry.oregonstate.edu/">'
web_str += 'http://lemma.forestry.oregonstate.edu</link>'
para = p.Paragraph(web_str, styles['body_style'])
story.append(para)
# Page break
story = self._make_page_break(story, self.PORTRAIT)
# General model information
para = p.Paragraph('General Information', styles['heading_style'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
# Report date
current_time = datetime.now()
now = current_time.strftime("%Y.%m.%d")
time_str = '<strong>Report Date:</strong> ' + now
para = p.Paragraph(time_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
# Model region area
locale.setlocale(locale.LC_ALL, "")
mr_area_ha = rmp.model_region_area
mr_area_ac = mr_area_ha * self.ACRES_PER_HECTARE
ha = locale.format('%d', mr_area_ha, True)
ac = locale.format('%d', mr_area_ac, True)
area_str = '<strong>Model Region Area:</strong> '
area_str += str(ha) + ' hectares (' + str(ac) + ' acres)'
para = p.Paragraph(area_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
# Model imagery date
mr_imagery_str = '<strong>Model Imagery Date:</strong> '
mr_imagery_str += str(self.model_year)
para = p.Paragraph(mr_imagery_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
# Plot matching
if self.model_type == 'sppsz':
plot_title = '''
<strong>Matching Plots to Imagery for Model Development:
</strong>
'''
para = p.Paragraph(plot_title, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
imagery_str = """
The current versions of the GNN maps were developed using
data from inventory plots that span a range of dates, and
from a yearly time-series of Landsat imagery mosaics from
1984 to 2012 developed with the LandTrendr algorithms
(Kennedy et al., 2010). For model development, plots were
matched to spectral data for the same year as plot
measurement. In addition, because as many as four plots were
measured at a given plot location, we constrained the
imputation for a given map year to only one plot from each
location -- the plot nearest in date to the imagery (map)
year. See Ohmann et al. (in press) for more detailed
information about the GNN modeling process.
"""
para = p.Paragraph(imagery_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.10 * u.inch))
# Mask information
mask_title = '<strong>Nonforest Mask Information:</strong>'
para = p.Paragraph(mask_title, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
mask_str = '''
An important limitation of the GNN map products is the separation
of forest and nonforest lands. The GNN modeling applies to forest
areas only, where we have detailed field plot data. Nonforest
areas are 'masked' as such using an ancillary map. In California,
Oregon, Washington and parts of adjacent states, we are using
maps of Ecological Systems developed for the Gap Analysis
Program (GAP) as our nonforest mask. There are 'unmasked'
versions of our GNN maps available upon request,
in case you have an alternative map of nonforest for your area
of interest that you would like to apply to the GNN maps.
'''
para = p.Paragraph(mask_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
# Spatial uncertainty
nn_dist_title = \
'<strong>Spatial Depictions of GNN Map Uncertainty:</strong>'
para = p.Paragraph(nn_dist_title, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
nn_dist_str = '''
In addition to the map diagnostics provided in this report, we
develop spatial depictions of map uncertainty (available upon
request). The value shown in the grid for a pixel is the distance
from that pixel to the nearest-neighbor plot that was imputed to
the pixel by GNN, and whose vegetation attributes are associated
with the pixel. 'Distance' is Euclidean distance in
multi-dimensional gradient space from the gradient model, where
the axes are weighted by how much variation they explain. The
nearest-neighbor distance is in gradient (model) space, not
geographic space. The nearest-neighbor-distance grid can be
interpreted as a map of potential map accuracy, although it is an
indicator of accuracy rather than a direct measure. In general,
the user of a GNN map would have more confidence in map
reliability for areas where nearest-neighbor distance is short,
where a similar plot was available (nearby) for the model, and
less confidence (more uncertainty) where nearest-neighbor
distance is long. Typically, high nearest-neighbor distances are
seen in areas with lower sampling intensity of inventory plots.
'''
para = p.Paragraph(nn_dist_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
# Page break
story = self._make_page_break(story, self.PORTRAIT)
# Inventory plots by date
plot_title = '<strong>Inventory Plots in Model Development</strong>'
para = p.Paragraph(plot_title, styles['heading_style'])
story.append(para)
story.append(p.Spacer(0, 0.10 * u.inch))
# Get all the data sources from the report metadata file
data_sources = rmp.plot_data_sources
# Track the total number of plots
total_plots = 0
# Create an empty master table
plot_table = []
# Create the header row
p1 = p.Paragraph('<strong>Data Source</strong>',
styles['contact_style'])
p2 = p.Paragraph('<strong>Description</strong>',
styles['contact_style'])
p3 = p.Paragraph('<strong>Plot Count by Year</strong>',
styles['contact_style'])
plot_table.append([p1, p2, p3])
# Iterate over all data sources
for ds in data_sources:
# Iterate over all assessment years for this data source and
# build an inner table that gives this information
pc_table = []
# pc_row = []
# Hack to avoid the table row being too long. Should only
# impact models that use R6_ECO plots
if len(ds.assessment_years) > 30:
# Increment the total plot count and track the
# number of plots in this data source
ds_count = 0
for ay in ds.assessment_years:
total_plots += ay.plot_count
ds_count += ay.plot_count
# Get the minimum and maximum years
years = [x.assessment_year for x in ds.assessment_years]
min_year = min(years)
max_year = max(years)
para_str = str(min_year) + '-' + str(max_year) + ': '
para_str += str(ds_count)
para = p.Paragraph(para_str, styles['contact_style_right'])
pc_table.append([[para]])
else:
for ay in ds.assessment_years:
year = ay.assessment_year
plot_count = str(ay.plot_count)
# Increment the plot count for total
total_plots += ay.plot_count
# Add the table row for this year's plot count
pc_row = []
para = p.Paragraph(year, styles['contact_style_right'])
pc_row.append(para)
para = p.Paragraph(plot_count,
styles['contact_style_right'])
pc_row.append(para)
pc_table.append(pc_row)
# Create the inner table
t = p.Table(pc_table)
# Table style
t.setStyle(
p.TableStyle([
('GRID', (0, 0), (-1, -1), 1, colors.white),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('TOPPADDING', (0, 0), (-1, -1), 2),
('BOTTOMPADDING', (0, 0), (-1, -1), 2),
]))
# Add data_source and description to the table
p1 = p.Paragraph(ds.data_source, styles['contact_style'])
p2 = p.Paragraph(ds.description, styles['contact_style'])
# Append these to the master table
plot_table.append([p1, p2, t])
# Now append the plot count - columns 1 and 2 will be merged in the
# table formatting upon return
p1 = p.Paragraph('Total Plots', styles['contact_style_right_bold'])
p2 = p.Paragraph(str(total_plots), styles['contact_style_right_bold'])
plot_table.append(['', p1, p2])
# Format the table into reportlab
t = p.Table(plot_table,
colWidths=[1.3 * u.inch, 4.2 * u.inch, 1.3 * u.inch])
t.hAlign = 'LEFT'
t.setStyle(
p.TableStyle([
('GRID', (0, 0), (-1, -2), 1.5, colors.white),
('BOX', (0, -1), (-1, -1), 1.5, colors.white),
('LINEAFTER', (1, -1), (1, -1), 1.5, colors.white),
('BACKGROUND', (0, 0), (-1, -1), '#f1efe4'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('TOPPADDING', (0, 0), (1, -2), 2),
('BOTTOMPADDING', (0, 0), (1, -2), 2),
('LEFTPADDING', (0, 0), (1, -2), 6),
('RIGHTPADDING', (0, 0), (1, -2), 6),
('ALIGNMENT', (0, 0), (1, -2), 'LEFT'),
('TOPPADDING', (2, 0), (2, 0), 2),
('BOTTOMPADDING', (2, 0), (2, 0), 2),
('LEFTPADDING', (2, 0), (2, 0), 6),
('RIGHTPADDING', (2, 0), (2, 0), 6),
('ALIGNMENT', (2, 0), (2, 0), 'LEFT'),
('TOPPADDING', (2, 1), (2, -2), 0),
('BOTTOMPADDING', (2, 1), (2, -2), 0),
('LEFTPADDING', (2, 1), (2, -2), 0),
('RIGHTPADDING', (2, 1), (2, -2), 0),
('ALIGNMENT', (2, 1), (2, -2), 'LEFT'),
('TOPPADDING', (0, -1), (2, -1), 4),
('BOTTOMPADDING', (0, -1), (2, -1), 4),
('LEFTPADDING', (0, -1), (2, -1), 6),
('RIGHTPADDING', (0, -1), (2, -1), 6),
('ALIGNMENT', (0, -1), (2, -1), 'RIGHT'),
]))
# Append this table to the main story
story.append(t)
# Page break
story = self._make_page_break(story, self.PORTRAIT)
# Print out the spatial predictor variables that are in this model
ord_title = 'Spatial Predictor Variables in Model Development'
para = p.Paragraph(ord_title, styles['heading_style'])
story.append(para)
story.append(p.Spacer(0, 0.10 * u.inch))
ord_var_str = """
The list below represents the spatial predictor
(GIS/remote sensing) variables that were used in creating
this model.
"""
para = p.Paragraph(ord_var_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
# Empty container for ordination_rows
ordination_table = []
# Create the header row
p1 = p.Paragraph('<strong>Variable</strong>',
styles['contact_style'])
p2 = p.Paragraph('<strong>Description</strong>',
styles['contact_style'])
p3 = p.Paragraph('<strong>Data Source</strong>',
styles['contact_style'])
ordination_table.append([p1, p2, p3])
# Read in the ordination variable list and, for each variable,
# print out the variable name, description, and source into a table
for var in rmp.ordination_variables:
name = p.Paragraph(var.field_name, styles['contact_style'])
desc = p.Paragraph(var.description, styles['contact_style'])
source = p.Paragraph(var.source, styles['contact_style'])
ordination_table.append([name, desc, source])
# Create a reportlab table from this list
t = p.Table(ordination_table,
colWidths=[1.0 * u.inch, 2.3 * u.inch, 3.5 * u.inch])
t.hAlign = 'LEFT'
t.setStyle(
p.TableStyle([
('GRID', (0, 0), (-1, -1), 1.5, colors.white),
('BACKGROUND', (0, 0), (-1, -1), '#f1efe4'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
]))
# Add to the story
story.append(t)
# Return the story
return story
def _create_story(self):
# Set up an empty list to hold the story
story = []
# Import the report styles
styles = report_styles.get_report_styles()
# Create a page break
story = self._make_page_break(story, self.LANDSCAPE)
# This class is somewhat of a hack, in that it likely only works on
# rotated paragraphs which fit into the desired cell area
class RotatedParagraph(p.Paragraph):
def wrap(self, availHeight, availWidth):
h, w = \
p.Paragraph.wrap(self, self.canv.stringWidth(self.text),
self.canv._leading)
return w, h
def draw(self):
self.canv.rotate(90)
self.canv.translate(0.0, -10.0)
p.Paragraph.draw(self)
# Section title
title_str = '<strong>Local-Scale Accuracy Assessment: '
title_str += 'Error Matrix for Vegetation Classes at Plot '
title_str += 'Locations</strong>'
para = p.Paragraph(title_str, styles['section_style'])
t = p.Table([[para]], colWidths=[10.0 * u.inch])
t.setStyle(
p.TableStyle([
('TOPPADDING', (0, 0), (-1, -1), 3),
('BOTTOMPADDING', (0, 0), (-1, -1), 3),
('BACKGROUND', (0, 0), (-1, -1), '#957348'),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('GRID', (0, 0), (-1, -1), 0.25, colors.black),
]))
story.append(t)
story.append(p.Spacer(0, 0.1 * u.inch))
# Read in the vegclass error matrix
names = ['P_' + str(x) for x in range(1, 12)]
names.insert(0, 'OBSERVED')
names.extend(['TOTAL', 'CORRECT', 'FUZZY_CORRECT'])
vc_data = mlab.csv2rec(self.vc_errmatrix_file, skiprows=1,
names=names)
vc_data = mlab.rec_drop_fields(vc_data, ['OBSERVED'])
# Read in the stand attribute metadata
mp = xsmp.XMLStandMetadataParser(self.stand_metadata_file)
# Get the class names from the metadata
vegclass_metadata = mp.get_attribute('VEGCLASS')
vc_codes = vegclass_metadata.codes
# Create a list of lists to hold the vegclass table
vegclass_table = []
# Add an empty row which will be a span row for the predicted label
header_row = []
for i in xrange(2):
header_row.append('')
prd_str = '<strong>Predicted Class</strong>'
para = p.Paragraph(prd_str, styles['body_style_10_center'])
header_row.append(para)
for i in xrange(len(vc_data) - 1):
header_row.append('')
vegclass_table.append(header_row)
# Add the predicted labels
summary_labels = ('Total', '% Correct', '% FCorrect')
header_row = []
for i in xrange(2):
header_row.append('')
for code in vc_codes:
label = re.sub('-', '-<br/>', code.label)
para = p.Paragraph(label, styles['body_style_10_right'])
header_row.append(para)
for label in summary_labels:
label = re.sub(' ', '<br/>', label)
para = p.Paragraph(label, styles['body_style_10_right'])
header_row.append(para)
vegclass_table.append(header_row)
# Set a variable to distinguish between plot counts and percents
# in order to format them differently
format_break = 11
# Set the cells which should be blank
blank_cells = \
[(11, 12), (11, 13), (12, 11), (12, 13), (13, 11), (13, 12)]
# Add the data
for (i, row) in enumerate(vc_data):
vegclass_row = []
for (j, elem) in enumerate(row):
# Blank cells
if (i, j) in blank_cells:
elem_str = ''
# Cells that represent plot counts
elif i <= format_break and j <= format_break:
elem_str = '%d' % int(elem)
# Cells that represent percentages
else:
elem_str = '%.1f' % float(elem)
para = p.Paragraph(elem_str, styles['body_style_10_right'])
vegclass_row.append(para)
# Add the observed labels at the beginning of each data row
if i == 0:
obs_str = '<strong>Observed Class</strong>'
para = \
RotatedParagraph(obs_str, styles['body_style_10_center'])
else:
para = ''
vegclass_row.insert(0, para)
if i < len(vc_codes):
label = vc_codes[i].label
else:
index = i - len(vc_codes)
label = summary_labels[index]
para = p.Paragraph(label, styles['body_style_10_right'])
vegclass_row.insert(1, para)
# Add this row to the table
vegclass_table.append(vegclass_row)
# Set up the widths for the table cells
widths = []
widths.append(0.3)
widths.append(0.85)
for i in xrange(len(vc_codes)):
widths.append(0.56)
for i in xrange(3):
widths.append(0.66)
widths = [x * u.inch for x in widths]
# Convert the vegclass table into a reportlab table
t = p.Table(vegclass_table, colWidths=widths)
t.setStyle(
p.TableStyle([
('SPAN', (0, 0), (1, 1)),
('SPAN', (0, 2), (0, -1)),
('SPAN', (2, 0), (-1, 0)),
('BACKGROUND', (0, 0), (-1, -1), '#f1efe4'),
('GRID', (0, 0), (-1, -1), 1, colors.white),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('VALIGN', (0, 2), (0, -1), 'MIDDLE'),
('VALIGN', (2, 1), (-1, 1), 'MIDDLE'),
('TOPPADDING', (0, 0), (-1, -1), 2),
('BOTTOMPADDING', (0, 0), (-1, -1), 3),
]))
# Set up the shading for the truly correct cells
correct = {}
for i in xrange(len(vc_codes)):
val = i + 1
correct[val] = val
for key in correct:
val = correct[key]
t.setStyle(
p.TableStyle([
('BACKGROUND', (key + 1, val + 1), (key + 1, val + 1),
'#aaaaaa'),
]))
# Set up the shading for the fuzzy correct cells
fuzzy = {}
fuzzy[1] = [2]
fuzzy[2] = [1, 3, 5, 8]
fuzzy[3] = [2, 4, 5]
fuzzy[4] = [3, 6, 7]
fuzzy[5] = [2, 3, 6, 8]
fuzzy[6] = [4, 5, 7, 9]
fuzzy[7] = [4, 6, 10, 11]
fuzzy[8] = [2, 5, 9]
fuzzy[9] = [6, 8, 10]
fuzzy[10] = [7, 9, 11]
fuzzy[11] = [7, 10]
for key in fuzzy:
for elem in fuzzy[key]:
t.setStyle(
p.TableStyle([
('BACKGROUND', (key + 1, elem + 1),
(key + 1, elem + 1), '#dddddd'),
]))
# Add this table to the story
story.append(t)
story.append(p.Spacer(0, 0.1 * u.inch))
# Explanation and definitions of vegetation class categories
cell_str = """
Cell values are model plot counts. Dark gray cells represent
plots where the observed class matches the predicted class
and are included in the percent correct. Light gray cells
represent cases where the observed and predicted differ
slightly (within +/- one class) based on canopy cover,
hardwood proportion or average stand diameter, and are
included in the percent fuzzy correct.
"""
para = p.Paragraph(cell_str, styles['body_style_9'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
head_str = '''
<strong>Vegetation Class (VEGCLASS) Definitions</strong> --
CANCOV (canopy cover of all live trees), BAH_PROP (proportion of
hardwood basal area), and QMD_DOM (quadratic mean diameter of
all dominant and codominant trees).
'''
para = p.Paragraph(head_str, styles['body_style_9'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
# Print out the vegclass code definitions
for code in vc_codes:
label = code.label
desc = self.txt_to_html(code.description)
doc_str = '<strong>' + label + ':</strong> ' + desc
para = p.Paragraph(doc_str, styles['body_style_9'])
story.append(para)
return story
def _create_story(self):
# Set up an empty list to hold the story
story = []
# Import the report styles
styles = report_styles.get_report_styles()
# Create a page break
story = self._make_page_break(story, self.PORTRAIT)
# Section title
title_str = "<strong>Data Dictionary</strong>"
para = p.Paragraph(title_str, styles["section_style"])
t = p.Table([[para]], colWidths=[7.5 * u.inch])
t.setStyle(
p.TableStyle(
[
("TOPPADDING", (0, 0), (-1, -1), 6),
("BOTTOMPADDING", (0, 0), (-1, -1), 6),
("BACKGROUND", (0, 0), (-1, -1), "#957348"),
("ALIGNMENT", (0, 0), (-1, -1), "LEFT"),
("VALIGN", (0, 0), (-1, -1), "TOP"),
("GRID", (0, 0), (-1, -1), 0.25, colors.black),
]
)
)
story.append(t)
story.append(p.Spacer(0, 0.1 * u.inch))
# Read in the stand attribute metadata
mp = xsmp.XMLStandMetadataParser(self.stand_metadata_file)
# Subset the attributes to those that are accuracy attributes, are
# identified to go into the report, and are not species variables
attrs = []
for attr in mp.attributes:
if attr.accuracy_attr == 1 and attr.project_attr == 1 and attr.species_attr == 0:
attrs.append(attr.field_name)
# Set up the master dictionary table
dictionary_table = []
# Iterate through the attributes and print out the field information
# and codes if present
for attr in attrs:
metadata = mp.get_attribute(attr)
field_name = metadata.field_name
units = metadata.units
description = metadata.description
field_para = p.Paragraph(field_name, styles["body_style_10"])
if units != "none":
description += " (" + units + ")"
field_desc_para = p.Paragraph(description, styles["body_style_10"])
# If this field has codes, create a sub table underneath the
# field description
if metadata.codes:
# Set up a container to hold the code rows
code_table = []
# Iterate over all code rows and append to the code_table
for code in metadata.codes:
code_para = p.Paragraph(code.code_value, styles["code_style"])
description = self.txt_to_html(code.description)
code_desc_para = p.Paragraph(description, styles["code_style"])
code_table.append([code_para, code_desc_para])
# Convert this to a reportlab table
t = p.Table(code_table, colWidths=[0.75 * u.inch, 4.5 * u.inch])
t.setStyle(
p.TableStyle(
[
("TOPPADDING", (0, 0), (-1, -1), 3),
("BOTTOMPADDING", (0, 0), (-1, -1), 3),
("BACKGROUND", (0, 0), (-1, -1), "#f7f7ea"),
("ALIGNMENT", (0, 0), (-1, -1), "LEFT"),
("VALIGN", (0, 0), (-1, -1), "TOP"),
("GRID", (0, 0), (-1, -1), 0.25, colors.white),
]
)
)
# Create a stack of the field description and field codes
elements = [[field_desc_para], [t]]
# If no codes exist, just add the field description
else:
elements = [[field_desc_para]]
# Create a reportlab table of the field description and
# (if present) field codes
description_table = p.Table(elements, colWidths=[5.25 * u.inch])
description_table.setStyle(
p.TableStyle(
[
("TOPPADDING", (0, 0), (-1, 0), 0),
("BOTTOMPADDING", (0, -1), (-1, -1), 0),
("LEFTPADDING", (0, 0), (-1, -1), 0),
("RIGHTPADDING", (0, 0), (-1, -1), 0),
("ALIGNMENT", (0, 0), (-1, -1), "LEFT"),
("VALIGN", (0, 0), (-1, -1), "TOP"),
]
)
)
dictionary_table.append([field_para, description_table])
# Format the dictionary table into a reportlab table
t = p.Table(dictionary_table, colWidths=[1.6 * u.inch, 5.4 * u.inch])
t.setStyle(
p.TableStyle(
[
("TOPPADDING", (0, 0), (0, -1), 5),
("BOTTOMPADDING", (0, 0), (0, -1), 5),
("GRID", (0, 0), (-1, -1), 1, colors.white),
("ALIGNMENT", (0, 0), (-1, -1), "LEFT"),
("VALIGN", (0, 0), (-1, -1), "TOP"),
("BACKGROUND", (0, 0), (-1, -1), "#f1efe4"),
]
)
)
story.append(t)
# Description of the species information that is attached to ArcInfo
# grids. We don't enumerate the codes here, but just give this
# summary information
spp_str = """
Individual species abundances are attached to ArcInfo grids that
LEMMA distributes. For this model, fields designate species
codes based on the <link color="#0000ff"
href="http://plants.usda.gov/">USDA PLANTS database</link> from
the year 2000, and values represent species
"""
if self.model_type in ["sppsz", "sppba"]:
spp_str += " basal area (m^2/ha)."
elif self.model_type in ["trecov", "wdycov"]:
spp_str += " percent cover."
para = p.Paragraph(spp_str, styles["body_style"])
story.append(p.Spacer(0, 0.1 * u.inch))
story.append(para)
# Return this story
return story
def _create_story(self, histogram_files):
# Set up an empty list to hold the story
story = []
# Import the report styles
styles = report_styles.get_report_styles()
# Create a page break
story = self._make_page_break(story, self.PORTRAIT)
# Section title
title_str = '<strong>Regional-Scale Accuracy Assessment:<br/> Area '
title_str += 'Distributions from Regional Inventory Plots vs. '
title_str += 'GNN</strong>'
para = p.Paragraph(title_str, styles['section_style'])
t = p.Table([[para]], colWidths=[7.5 * u.inch])
t.setStyle(
p.TableStyle([
('TOPPADDING', (0, 0), (-1, -1), 6),
('BOTTOMPADDING', (0, 0), (-1, -1), 6),
('BACKGROUND', (0, 0), (-1, -1), '#957348'),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('GRID', (0, 0), (-1, -1), 0.25, colors.black),
]))
story.append(t)
story.append(p.Spacer(0, 0.20 * u.inch))
# Histogram explanation
histo_str = '''
These histograms compare the distributions of land area in
different vegetation conditions as estimated from a regional,
sample- (plot-) based inventory (FIA Annual Plots) to model
predictions from GNN (based on counts of 30-m pixels).
<br/><br/>
For the FIA annual plots, the distributions of forest area
are determined by summing the 'area expansion factors' at the
plot condition-class level. The plot-based estimates are
subject to sampling error, but this is not shown in the graphs
due to complexities involved. For more information about the
FIA Annual inventory sample design, see the
<link href="http://fia.fs.fed.us/library/database-documentation"
color="blue">FIADB Users Manual</link>.
<br/><br/>
Some plots were not visited on the ground due to denied
access or hazardous conditions, so the area these plots
represent cannot be characterized and is included in the bar
labeled 'unsampled.'
<br/><br/>
The bars labeled 'nonforest' also require explanation. For GNN,
this is the area of nonforest in the map, which is derived
from ancillary (non-GNN) spatial data sources such as the
National Land Cover Data (NLCD) or Ecological Systems maps
from the Gap Analysis Program (GAP). This mapped nonforest is
referred to as the GNN 'nonforest mask.'
<br/><br/>
For the plots, the 'nonforest' bar represents the nonforest area
as estimated from the FIA Annual sample.
'''
para = p.Paragraph(histo_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.1 * u.inch))
# Add the histogram images to a list of lists
table_cols = 2
histogram_table = []
histogram_row = []
for (i, fn) in enumerate(histogram_files):
histogram_row.append(p.Image(fn, 3.4 * u.inch, 3.0 * u.inch))
if (i % table_cols) == (table_cols - 1):
histogram_table.append(histogram_row)
histogram_row = []
# Determine if there are any histograms left to print
if len(histogram_row) != 0:
for i in range(len(histogram_row), table_cols):
histogram_row.append(p.Paragraph('', styles['body_style']))
histogram_table.append(histogram_row)
# Style this into a reportlab table and add to the story
width = 3.75 * u.inch
t = p.Table(histogram_table, colWidths=[width, width])
t.setStyle(
p.TableStyle([
('ALIGNMENT', (0, 0), (-1, -1), 'CENTER'),
('VALIGN', (0, 0), (-1, -1), 'CENTER'),
('TOPPADDING', (0, 0), (-1, -1), 6.0),
('BOTTOMPADDING', (0, 0), (-1, -1), 6.0),
]))
story.append(t)
# Return this story
return story
def _create_story(self):
# Set up an empty list to hold the story
story = []
# Import the report styles
styles = report_styles.get_report_styles()
# Create a page break
story = self._make_page_break(story, self.PORTRAIT)
# Section title
title_str = '<strong>Local-Scale Accuracy Assessment:<br/>'
title_str += 'Species Accuracy at Plot Locations'
title_str += '</strong>'
para = p.Paragraph(title_str, styles['section_style'])
t = p.Table([[para]], colWidths=[7.5 * u.inch])
t.setStyle(
p.TableStyle([
('TOPPADDING', (0, 0), (-1, -1), 6),
('BOTTOMPADDING', (0, 0), (-1, -1), 6),
('BACKGROUND', (0, 0), (-1, -1), '#957348'),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('GRID', (0, 0), (-1, -1), 0.25, colors.black),
]))
story.append(t)
story.append(p.Spacer(0, 0.2 * u.inch))
# Kappa explanation
kappa_str = '''
Cohen's kappa coefficient (Cohen, 1960) is a statistical measure
of reliability, accounting for agreement occurring by chance.
The equation for kappa is:
'''
para = p.Paragraph(kappa_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.05 * u.inch))
kappa_str = '''
kappa = (Pr(a) - Pr(e)) / (1.0 - Pr(e))
'''
para = p.Paragraph(kappa_str, styles['indented'])
story.append(para)
story.append(p.Spacer(0, 0.05 * u.inch))
kappa_str = '''
where Pr(a) is the relative observed agreement among
raters, and Pr(e) is the probability that agreement is
due to chance.<br/><br/>
<strong>Abbreviations Used:</strong><br/>
OP/PP = Observed Present / Predicted Present<br/>
OA/PP = Observed Absent / Predicted Present
(errors of commission)<br/>
OP/PA = Observed Present / Predicted Absent
(errors of ommission)<br/>
OA/PA = Observed Absent / Predicted Absent
'''
para = p.Paragraph(kappa_str, styles['body_style'])
story.append(para)
story.append(p.Spacer(0, 0.2 * u.inch))
# Create a list of lists to hold the species accuracy information
species_table = []
# Header row
header_row = []
spp_str = '<strong>Species PLANTS Code<br/>'
spp_str += 'Scientific Name / Common Name</strong>'
para = p.Paragraph(spp_str, styles['body_style_10'])
header_row.append(para)
spp_str = '<strong>Species prevalence</strong>'
para = p.Paragraph(spp_str, styles['body_style_10'])
header_row.append(para)
p1 = p.Paragraph('<strong>OP/PP</strong>',
styles['body_style_10_right'])
p2 = p.Paragraph('<strong>OP/PA</strong>',
styles['body_style_10_right'])
p3 = p.Paragraph('<strong>OA/PP</strong>',
styles['body_style_10_right'])
p4 = p.Paragraph('<strong>OA/PA</strong>',
styles['body_style_10_right'])
header_cells = [[p1, p2], [p3, p4]]
t = p.Table(header_cells, colWidths=[0.75 * u.inch, 0.75 * u.inch])
t.setStyle(
p.TableStyle([
('GRID', (0, 0), (-1, -1), 1, colors.white),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('TOPPADDING', (0, 0), (-1, -1), 2),
('BOTTOMPADDING', (0, 0), (-1, -1), 2),
]))
header_row.append(t)
kappa_str = '<strong>Kappa coefficient</strong>'
para = p.Paragraph(kappa_str, styles['body_style_10'])
header_row.append(para)
species_table.append(header_row)
# Open the species accuracy file into a recarray
spp_data = utilities.csv2rec(self.species_accuracy_file)
# Read in the stand attribute metadata
mp = xsmp.XMLStandMetadataParser(self.stand_metadata_file)
# Read in the report metadata if it exists
if self.report_metadata_file:
rmp = xrmp.XMLReportMetadataParser(self.report_metadata_file)
else:
rmp = None
# Subset the attributes to just species
attrs = []
for attr in mp.attributes:
if attr.species_attr == 1 and 'NOTALY' not in attr.field_name:
attrs.append(attr.field_name)
# Iterate over the species and print out the statistics
for spp in attrs:
# Empty row to hold the formatted output
species_row = []
# Get the scientific and common names from the report metadata
# if it exists; otherwise, just use the species symbol
if rmp is not None:
# Strip off any suffix if it exists
try:
spp_plain = spp.split('_')[0]
spp_info = rmp.get_species(spp_plain)
spp_str = spp_info.spp_symbol + '<br/>'
spp_str += spp_info.scientific_name + ' / '
spp_str += spp_info.common_name
except IndexError:
spp_str = spp
else:
spp_str = spp
para = p.Paragraph(spp_str, styles['body_style_10'])
species_row.append(para)
# Get the statistical information
data = spp_data[spp_data.SPECIES == spp][0]
counts = [data.OP_PP, data.OP_PA, data.OA_PP, data.OA_PA]
prevalence = data.PREVALENCE
kappa = data.KAPPA
# Species prevalence
prevalence_str = '%.4f' % prevalence
para = p.Paragraph(prevalence_str, styles['body_style_10_right'])
species_row.append(para)
# Capture the plot counts in an inner table
count_cells = []
count_row = []
for i in range(0, 4):
para = p.Paragraph('%d' % counts[i],
styles['body_style_10_right'])
count_row.append(para)
if i % 2 == 1:
count_cells.append(count_row)
count_row = []
t = p.Table(count_cells, colWidths=[0.75 * u.inch, 0.75 * u.inch])
t.setStyle(
p.TableStyle([
('GRID', (0, 0), (-1, -1), 1, colors.white),
('ALIGNMENT', (0, 0), (-1, -1), 'LEFT'),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('TOPPADDING', (0, 0), (-1, -1), 2),
('BOTTOMPADDING', (0, 0), (-1, -1), 2),
]))
species_row.append(t)
# Print out the kappa statistic
kappa_str = '%.4f' % kappa
para = p.Paragraph(kappa_str, styles['body_style_10_right'])
species_row.append(para)
# Push this row to the master species table
species_table.append(species_row)
# Style this into a reportlab table and add to the story
col_widths = [(x * u.inch) for x in [4.0, 0.75, 1.5, 0.75]]
t = p.Table(species_table, colWidths=col_widths)
t.setStyle(
p.TableStyle([
('BACKGROUND', (0, 0), (-1, -1), '#f1efe4'),
('GRID', (0, 0), (-1, -1), 2, colors.white),
('TOPPADDING', (0, 0), (0, -1), 2),
('BOTTOMPADDING', (0, 0), (0, -1), 2),
('LEFTPADDING', (0, 0), (0, -1), 6),
('RIGHTPADDING', (0, 0), (0, -1), 6),
('ALIGNMENT', (0, 0), (0, -1), 'LEFT'),
('VALIGN', (0, 0), (0, -1), 'TOP'),
('TOPPADDING', (1, 0), (1, -1), 2),
('BOTTOMPADDING', (1, 0), (1, -1), 2),
('LEFTPADDING', (1, 0), (1, -1), 6),
('RIGHTPADDING', (1, 0), (1, -1), 6),
('ALIGNMENT', (1, 0), (1, -1), 'RIGHT'),
('VALIGN', (1, 0), (1, 0), 'TOP'),
('VALIGN', (1, 1), (1, -1), 'MIDDLE'),
('TOPPADDING', (2, 0), (2, -1), 0),
('BOTTOMPADDING', (2, 0), (2, -1), 0),
('LEFTPADDING', (2, 0), (2, -1), 0),
('RIGHTPADDING', (2, 0), (2, -1), 0),
('ALIGNMENT', (2, 0), (2, -1), 'LEFT'),
('VALIGN', (2, 0), (2, -1), 'TOP'),
('TOPPADDING', (3, 0), (3, -1), 2),
('BOTTOMPADDING', (3, 0), (3, -1), 2),
('LEFTPADDING', (3, 0), (3, -1), 6),
('RIGHTPADDING', (3, 0), (3, -1), 6),
('ALIGNMENT', (3, 0), (3, -1), 'RIGHT'),
('VALIGN', (3, 0), (3, 0), 'TOP'),
('VALIGN', (3, 1), (3, -1), 'MIDDLE'),
]))
story.append(t)
story.append(p.Spacer(0, 0.1 * u.inch))
rare_species_str = """
Note that some very rare species do not appear in this accuracy
report, because these species were not included when building
the initial ordination model. The full set of species is
available upon request.
"""
para = p.Paragraph(rare_species_str, styles['body_style'])
story.append(para)
# Return this story
return story
