Briq/camelot-py
8
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[MRG + 1] Create a new figure and test each plot type #127 (#179)

Browse Source 
* [MRG] Create a new figure and test each plot type #127

 - move `plot()` to `plotting.py` as `plot_pdf()`
 - modify plotting functions to return matplotlib figures
 - add `test_plotting.py` and baseline images
 - import `plot_pdf()` in `__init__`
 - update `cli.py` to use `plot_pdf()`
 - update advanced usage docs to reflect changes

* Change matplotlib backend for image comparison tests

* Update plotting and tests
 - use matplotlib rectangle instead of `cv2.rectangle` in
`plot_contour()`
 - set matplotlib backend in `tests/__init__`
 - update contour plot baseline image
 - update `test_plotting` with more checks

* Update plot tests and config
 - remove unnecessary asserts
 - update setup.cfg and makefile with `--mpl`

* Add  to

* Add tolerance

* remove text from baseline plots
update plot tests with `remove_text`

* Change method name, update docs and add pep8

* Update docs
This commit is contained in:
Suyash Behera
2018-11-02 20:57:02 +05:30
committed by Vinayak Mehta
parent 79db6e3d1b
commit c0e9235164
16 changed files with 186 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files
camelot/__init__.py
+1
View File
@@ -6,6 +6,7 @@ from click import HelpFormatter
from .__version__ import __version__
from .io import read_pdf
from .plotting import plot
def _write_usage(self, prog, args='', prefix='Usage: '):
camelot/cli.py
+8 -4
View File
@@ -3,9 +3,11 @@
import logging
import click
import matplotlib.pyplot as plt
from . import __version__
from .io import read_pdf
from .plotting import plot
logger = logging.getLogger('camelot')
@@ -81,7 +83,7 @@ def cli(ctx, *args, **kwargs):
help='Number of times for erosion/dilation will be applied.')
@click.option('-plot', '--plot_type',
type=click.Choice(['text', 'table', 'contour', 'joint', 'line']),
help='Plot geometry found on PDF page, for debugging.')
help='Plot elements found on PDF page for visual debugging.')
@click.argument('filepath', type=click.Path(exists=True))
@pass_config
def lattice(c, *args, **kwargs):
@@ -107,7 +109,8 @@ def lattice(c, *args, **kwargs):
click.echo('Found {} tables'.format(tables.n))
if plot_type is not None:
for table in tables:
table.plot(plot_type)
plot(table, plot_type=plot_type)
plt.show()
else:
if output is None:
raise click.UsageError('Please specify output file path using --output')
@@ -128,7 +131,7 @@ def lattice(c, *args, **kwargs):
' used to combine text horizontally, to generate columns.')
@click.option('-plot', '--plot_type',
type=click.Choice(['text', 'table']),
help='Plot geometry found on PDF page for debugging.')
help='Plot elements found on PDF page for visual debugging.')
@click.argument('filepath', type=click.Path(exists=True))
@pass_config
def stream(c, *args, **kwargs):
@@ -153,7 +156,8 @@ def stream(c, *args, **kwargs):
click.echo('Found {} tables'.format(tables.n))
if plot_type is not None:
for table in tables:
table.plot(plot_type)
plot(table, plot_type=plot_type)
plt.show()
else:
if output is None:
raise click.UsageError('Please specify output file path using --output')
camelot/core.py
-29
View File
@@ -7,8 +7,6 @@ import tempfile
import numpy as np
import pandas as pd
from .plotting import *
class Cell(object):
"""Defines a cell in a table with coordinates relative to a
@@ -321,33 +319,6 @@ class Table(object):
cell.hspan = True
return self
def plot(self, geometry_type):
"""Plot geometry found on PDF page based on geometry_type
specified, useful for debugging and playing with different
parameters to get the best output.
Parameters
----------
geometry_type : str
The geometry type for which a plot should be generated.
Can be 'text', 'table', 'contour', 'joint', 'line'
"""
if self.flavor == 'stream' and geometry_type in ['contour', 'joint', 'line']:
raise NotImplementedError("{} cannot be plotted with flavor='stream'".format(
geometry_type))
if geometry_type == 'text':
plot_text(self._text)
elif geometry_type == 'table':
plot_table(self)
elif geometry_type == 'contour':
plot_contour(self._image)
elif geometry_type == 'joint':
plot_joint(self._image)
elif geometry_type == 'line':
plot_line(self._segments)
def to_csv(self, path, **kwargs):
"""Writes Table to a comma-separated values (csv) file.
camelot/handlers.py
-3
View File
@@ -141,9 +141,6 @@ class PDFHandler(object):
-------
tables : camelot.core.TableList
List of tables found in PDF.
geometry : camelot.core.GeometryList
List of geometry objects (contours, lines, joints) found
in PDF.
"""
tables = []
camelot/plotting.py
+101 -24
View File
@@ -1,15 +1,59 @@
import cv2
# -*- coding: utf-8 -*-
import matplotlib.pyplot as plt
import matplotlib.patches as patches
def plot(table, plot_type='text', filepath=None):
"""Plot elements found on PDF page based on plot_type
specified, useful for debugging and playing with different
parameters to get the best output.
Parameters
----------
table: Table
A Camelot Table.
plot_type : str, optional (default: 'text')
{'text', 'table', 'contour', 'joint', 'line'}
The element type for which a plot should be generated.
filepath: str, optional (default: None)
Absolute path for saving the generated plot.
Returns
-------
fig : matplotlib.fig.Figure
"""
if table.flavor == 'stream' and plot_type in ['contour', 'joint', 'line']:
raise NotImplementedError("{} cannot be plotted with flavor='stream'".format(
plot_type))
if plot_type == 'text':
fig = plot_text(table._text)
elif plot_type == 'table':
fig = plot_table(table)
elif plot_type == 'contour':
fig = plot_contour(table._image)
elif plot_type == 'joint':
fig = plot_joint(table._image)
elif plot_type == 'line':
fig = plot_line(table._segments)
if filepath:
plt.savefig(filepath)
return fig
def plot_text(text):
"""Generates a plot for all text present on the PDF page.
"""Generates a plot for all text elements present
on the PDF page.
Parameters
----------
text : list
Returns
-------
fig : matplotlib.fig.Figure
"""
fig = plt.figure()
ax = fig.add_subplot(111, aspect='equal')
@@ -26,83 +70,116 @@ def plot_text(text):
)
ax.set_xlim(min(xs) - 10, max(xs) + 10)
ax.set_ylim(min(ys) - 10, max(ys) + 10)
plt.show()
return fig
def plot_table(table):
"""Generates a plot for the table.
"""Generates a plot for the detected tables
on the PDF page.
Parameters
----------
table : camelot.core.Table
Returns
-------
fig : matplotlib.fig.Figure
"""
fig = plt.figure()
ax = fig.add_subplot(111, aspect='equal')
for row in table.cells:
for cell in row:
if cell.left:
plt.plot([cell.lb[0], cell.lt[0]],
ax.plot([cell.lb[0], cell.lt[0]],
[cell.lb[1], cell.lt[1]])
if cell.right:
plt.plot([cell.rb[0], cell.rt[0]],
ax.plot([cell.rb[0], cell.rt[0]],
[cell.rb[1], cell.rt[1]])
if cell.top:
plt.plot([cell.lt[0], cell.rt[0]],
ax.plot([cell.lt[0], cell.rt[0]],
[cell.lt[1], cell.rt[1]])
if cell.bottom:
plt.plot([cell.lb[0], cell.rb[0]],
ax.plot([cell.lb[0], cell.rb[0]],
[cell.lb[1], cell.rb[1]])
plt.show()
return fig
def plot_contour(image):
"""Generates a plot for all table boundaries present on the
PDF page.
"""Generates a plot for all table boundaries present
on the PDF page.
Parameters
----------
image : tuple
Returns
-------
fig : matplotlib.fig.Figure
"""
img, table_bbox = image
fig = plt.figure()
ax = fig.add_subplot(111, aspect='equal')
for t in table_bbox.keys():
cv2.rectangle(img, (t[0], t[1]),
(t[2], t[3]), (255, 0, 0), 20)
plt.imshow(img)
plt.show()
ax.add_patch(
patches.Rectangle(
(t[0], t[1]),
t[2] - t[0],
t[3] - t[1],
fill=None,
edgecolor='red'
)
)
ax.imshow(img)
return fig
def plot_joint(image):
"""Generates a plot for all line intersections present on the
PDF page.
"""Generates a plot for all line intersections present
on the PDF page.
Parameters
----------
image : tuple
Returns
-------
fig : matplotlib.fig.Figure
"""
img, table_bbox = image
fig = plt.figure()
ax = fig.add_subplot(111, aspect='equal')
x_coord = []
y_coord = []
for k in table_bbox.keys():
for coord in table_bbox[k]:
x_coord.append(coord[0])
y_coord.append(coord[1])
plt.plot(x_coord, y_coord, 'ro')
plt.imshow(img)
plt.show()
ax.plot(x_coord, y_coord, 'ro')
ax.imshow(img)
return fig
def plot_line(segments):
"""Generates a plot for all line segments present on the PDF page.
"""Generates a plot for all line segments present
on the PDF page.
Parameters
----------
segments : tuple
Returns
-------
fig : matplotlib.fig.Figure
"""
fig = plt.figure()
ax = fig.add_subplot(111, aspect='equal')
vertical, horizontal = segments
for v in vertical:
plt.plot([v[0], v[2]], [v[1], v[3]])
ax.plot([v[0], v[2]], [v[1], v[3]])
for h in horizontal:
plt.plot([h[0], h[2]], [h[1], h[3]])
plt.show()
ax.plot([h[0], h[2]], [h[1], h[3]])
return fig