Clean up notebooks, address review comments

* Improve explanations of network, hybrid, and lattice parsers
* Remove dead code from parser comparison notebook
* Clean-up notebook variables to reduce size and make diffs cleaner
* Revert changes that were peripheral to the core changes

.deepsource.toml

@@ -1,10 +1,5 @@
 version = 1
 
-test_patterns = [
-  "tests/**",
-  "test_*.py"
-]
-
 exclude_patterns = [
   "camelot/ext/**"
 ]

.gitignore

@@ -4,10 +4,8 @@ __pycache__/
 
 build/
 dist/
-prof/
 *.egg-info/
 .eggs/
-.tox/
 .coverage
 coverage.xml
 
@@ -18,6 +16,4 @@ _build/
 htmlcov/
 
 # vscode
-.vscode
-
-.DS_Store
+.vscode

.travis.yml

@@ -1,3 +1,4 @@
+sudo: true
 language: python
 cache: pip
 addons:

camelot/image_processing.py

@@ -4,11 +4,8 @@ import cv2
 import numpy as np
 
 
-def adaptive_threshold(
-        imagename, process_background=False,
-        blocksize=15, c=-2):
+def adaptive_threshold(imagename, process_background=False, blocksize=15, c=-2):
     """Thresholds an image using OpenCV's adaptiveThreshold.
-
     Parameters
     ----------
     imagename : string
@@ -18,31 +15,24 @@ def adaptive_threshold(
     blocksize : int, optional (default: 15)
         Size of a pixel neighborhood that is used to calculate a
         threshold value for the pixel: 3, 5, 7, and so on.
-
-        For more information, refer `OpenCV's adaptiveThreshold <https://docs.opencv.org/2.4/modules/imgproc/doc/miscellaneous_transformations.html#adaptivethreshold>`_.  # noqa
+        For more information, refer `OpenCV's adaptiveThreshold <https://docs.opencv.org/2.4/modules/imgproc/doc/miscellaneous_transformations.html#adaptivethreshold>`_.
     c : int, optional (default: -2)
         Constant subtracted from the mean or weighted mean.
         Normally, it is positive but may be zero or negative as well.
-
-        For more information, refer `OpenCV's adaptiveThreshold <https://docs.opencv.org/2.4/modules/imgproc/doc/miscellaneous_transformations.html#adaptivethreshold>`_.  # noqa
-
+        For more information, refer `OpenCV's adaptiveThreshold <https://docs.opencv.org/2.4/modules/imgproc/doc/miscellaneous_transformations.html#adaptivethreshold>`_.
     Returns
     -------
     img : object
         numpy.ndarray representing the original image.
     threshold : object
         numpy.ndarray representing the thresholded image.
-
     """
     img = cv2.imread(imagename)
     gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
 
     if process_background:
         threshold = cv2.adaptiveThreshold(
-            gray,
-            255,
-            cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
-            cv2.THRESH_BINARY, blocksize, c
+            gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, blocksize, c
         )
     else:
         threshold = cv2.adaptiveThreshold(
@@ -57,12 +47,10 @@ def adaptive_threshold(
 
 
 def find_lines(
-    threshold, regions=None,
-    direction="horizontal", line_scale=15, iterations=0
+    threshold, regions=None, direction="horizontal", line_scale=15, iterations=0
 ):
     """Finds horizontal and vertical lines by applying morphological
     transformations on an image.
-
     Parameters
     ----------
     threshold : object
@@ -76,14 +64,11 @@ def find_lines(
     line_scale : int, optional (default: 15)
         Factor by which the page dimensions will be divided to get
         smallest length of lines that should be detected.
-
         The larger this value, smaller the detected lines. Making it
         too large will lead to text being detected as lines.
     iterations : int, optional (default: 0)
         Number of times for erosion/dilation is applied.
-
-        For more information, refer `OpenCV's dilate <https://docs.opencv.org/2.4/modules/imgproc/doc/filtering.html#dilate>`_.  # noqa
-
+        For more information, refer `OpenCV's dilate <https://docs.opencv.org/2.4/modules/imgproc/doc/filtering.html#dilate>`_.
     Returns
     -------
     dmask : object
@@ -93,7 +78,6 @@ def find_lines(
         List of tuples representing vertical/horizontal lines with
         coordinates relative to a left-top origin in
         image coordinate space.
-
     """
     lines = []
 
@@ -104,15 +88,13 @@ def find_lines(
         size = threshold.shape[1] // line_scale
         el = cv2.getStructuringElement(cv2.MORPH_RECT, (size, 1))
     elif direction is None:
-        raise ValueError(
-            "Specify direction as either 'vertical' or 'horizontal'"
-        )
+        raise ValueError("Specify direction as either 'vertical' or 'horizontal'")
 
     if regions is not None:
         region_mask = np.zeros(threshold.shape)
         for region in regions:
             x, y, w, h = region
-            region_mask[y:y + h, x:x + w] = 1
+            region_mask[y : y + h, x : x + w] = 1
         threshold = np.multiply(threshold, region_mask)
 
     threshold = cv2.erode(threshold, el)
@@ -121,14 +103,12 @@ def find_lines(
 
     try:
         _, contours, _ = cv2.findContours(
-            threshold.astype(np.uint8), cv2.RETR_EXTERNAL,
-            cv2.CHAIN_APPROX_SIMPLE
+            threshold.astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE
         )
     except ValueError:
         # for opencv backward compatibility
         contours, _ = cv2.findContours(
-            threshold.astype(np.uint8), cv2.RETR_EXTERNAL,
-            cv2.CHAIN_APPROX_SIMPLE
+            threshold.astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE
         )
 
     for c in contours:
@@ -145,21 +125,18 @@ def find_lines(
 
 def find_contours(vertical, horizontal):
     """Finds table boundaries using OpenCV's findContours.
-
     Parameters
     ----------
     vertical : object
         numpy.ndarray representing pixels where vertical lines lie.
     horizontal : object
         numpy.ndarray representing pixels where horizontal lines lie.
-
     Returns
     -------
     cont : list
         List of tuples representing table boundaries. Each tuple is of
         the form (x, y, w, h) where (x, y) -> left-top, w -> width and
         h -> height in image coordinate space.
-
     """
     mask = vertical + horizontal
 
@@ -185,7 +162,6 @@ def find_contours(vertical, horizontal):
 
 def find_joints(contours, vertical, horizontal):
     """Finds joints/intersections present inside each table boundary.
-
     Parameters
     ----------
     contours : list
@@ -196,7 +172,6 @@ def find_joints(contours, vertical, horizontal):
         numpy.ndarray representing pixels where vertical lines lie.
     horizontal : object
         numpy.ndarray representing pixels where horizontal lines lie.
-
     Returns
     -------
     tables : dict
@@ -204,13 +179,12 @@ def find_joints(contours, vertical, horizontal):
         in that boundary as their value.
         Keys are of the form (x1, y1, x2, y2) where (x1, y1) -> lb
         and (x2, y2) -> rt in image coordinate space.
-
     """
     joints = np.multiply(vertical, horizontal)
     tables = {}
     for c in contours:
         x, y, w, h = c
-        roi = joints[y:y + h, x:x + w]
+        roi = joints[y : y + h, x : x + w]
         try:
             __, jc, __ = cv2.findContours(
                 roi.astype(np.uint8), cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE
@@ -229,4 +203,4 @@ def find_joints(contours, vertical, horizontal):
             joint_coords.append((c1, c2))
         tables[(x, y + h, x + w, y)] = joint_coords
 
-    return tables
+    return tables