renaming modules

Author: mbucchi

examples/.DS_Store

@@ -0,0 +1,3 @@
+{
+    "python.pythonPath": "/usr/local/bin/python3"
+}

examples/.vscode/settings.json

@@ -0,0 +1,92 @@
+# %%
+import matplotlib.pyplot as plt
+import numpy as np
+from matplotlib.patches import Ellipse
+from multiprocessing import Pool
+from pybalu.feature_extraction.geometric_utils import bbox as _bbox
+from pybalu.feature_extraction import basic_geo_features
+from pybalu.io import imread
+from skimage.measure import label
+
+# %%
+import matplotlib
+matplotlib.rcParams["figure.figsize"] = (7, 7)
+matplotlib.rcParams["axes.titlesize"] = 20
+matplotlib.rcParams["axes.titlepad"] = 15
+matplotlib.rcParams["figure.figsize"] = (7, 7)
+del matplotlib
+
+# %%
+im = imread("feature_extraction/rice.png")
+plt.title("Original Image", fontdict={"fontsize": 20}, pad=20)
+plt.imshow(im, cmap="gray")
+plt.show()
+
+# %%
+im_bin = (im > 140).astype(int)
+labeled, n = label(im_bin, return_num=True)
+labeled_T = labeled.T
+
+
+def calc_ellipse(idx):
+    region = (labeled_T == idx).astype(int)
+    box = _bbox(region)
+    feats = basic_geo_features(region[box])
+    # feats[0]:  center of grav i [px]
+    # feats[1]:  center of grav j [px]
+    # feats[10]: MajorAxisLength  [px]
+    # feats[11]: MinorAxisLength  [px]
+    # feats[12]: Orientation      [deg]
+    return np.array([box[0].start + feats[0], box[1].start + feats[1], feats[10], feats[11], feats[12]])
+
+
+with Pool() as pool:
+    ellipses = np.vstack(pool.map(calc_ellipse, range(1, n)))
+
+# %%
+ax = plt.axes()
+plt.title("Segmented Image")
+plt.imshow(im, cmap="gray")
+
+
+def draw_ellipse(x, y, height, width, angle, axes):
+    ell = Ellipse(xy=(x, y), height=height, width=width,
+                  angle=angle, edgecolor="red", facecolor="none")
+    axes.add_artist(ell)
+    ell.set_clip_box(axes.bbox)
+    return ell
+
+
+for ell in ellipses:
+    draw_ellipse(*ell, axes=ax)
+
+plt.show()
+
+# %%
+plt.title("Mean sized rice grains (major axis)")
+
+major_25 = np.percentile(ellipses[:, 3], 25)
+major_75 = np.percentile(ellipses[:, 3], 75)
+
+valid_labels = 1 + \
+    np.where((ellipses[:, 3] > major_25) & (ellipses[:, 3] < major_75))[0]
+im_mean = np.array(im)
+im_mean[np.where(~np.isin(labeled, valid_labels))] //= 7
+plt.imshow(im_mean, cmap="gray")
+plt.show()
+
+# %%
+
+
+def draw_at_angle(theta):
+    valid_labels = 1 + \
+        np.where((ellipses[:, 4] > theta - 10) &
+                 (ellipses[:, 4] < theta + 10))[0]
+    plt.title(f"Orientation at {theta} deg")
+    im_rotated = np.array(im)
+    im_rotated[np.where(~np.isin(labeled, valid_labels))] //= 7
+    plt.imshow(im_rotated, cmap="gray")
+    plt.show()
+
+
+draw_at_angle(45)

examples/feature_extraction/ellipses.ipynb

@@ -0,0 +1,55 @@
+# %%
+from scipy.io import loadmat
+
+# load a dataset with 810 samples and 294 features
+data = loadmat("feature_selection/realdata")
+features = data["features"]
+classes = data["classes"].squeeze()
+
+# %%
+from pybalu.data_selection import stratify
+from pybalu.feature_transformation import normalize
+
+# Training and Testing data (90% training, 10% testing)
+idx_train, idx_test = stratify(classes, .90)
+f_train = features[idx_train]
+c_train = classes[idx_train]
+f_test = features[idx_test]
+c_test = classes[idx_test]
+
+f_train_norm, a, b = normalize(f_train)
+f_test_norm = f_test * a + b
+
+# %%
+from pybalu.feature_selection import sfs
+
+N_FEATURES = 15
+
+selected_feats = sfs(f_train_norm, c_train, n_features=N_FEATURES,
+                     method="fisher", show=True)
+
+
+# %%
+from pybalu.classification import structure
+from pybalu.performance_eval import performance
+from sklearn.neighbors import KNeighborsClassifier
+import matplotlib.pyplot as plt
+
+def performance_for_features(feat_idxs):
+    # train classifier
+    knn = KNeighborsClassifier(n_neighbors=3)
+    knn.fit(f_train_norm[:, feat_idxs], c_train)
+
+    # predict and evaluate performance
+    prediction = knn.predict(f_test_norm[:, feat_idxs])
+    return performance(prediction, c_test)
+
+
+values = [performance_for_features(selected_feats[:i]) * 100
+          for i in range(1, N_FEATURES + 1)]
+
+plt.plot(values)
+plt.title("Performance vs. number of features")
+plt.xlabel('selected features')
+plt.ylabel('accuracy [%]')
+plt.show()

examples/feature_extraction/ellipses.py

@@ -1,12 +1,14 @@
-from . import classification
-from . import data_selection
-from . import feature_analysis
-from . import feature_extraction
-from . import feature_selection
-from . import feature_transformation
-from . import img_processing
-from . import io
-from . import misc
-from . import performance_eval
+# modules
 
-__version__ = '0.2.1'
+__all__ = ["classification",
+           "data_selection",
+           "feature_analysis",
+           "feature_extraction",
+           "feature_selection",
+           "feature_transformation",
+           "img_processing",
+           "io",
+           "misc",
+           "performance_eval"]
+
+__version__ = '0.2.2'

examples/feature_extraction/rice.png

@@ -1,2 +1,3 @@
-from ._structure import *
-# from ._construct import *
+from .structure import structure
+
+__all__ = ["structure"]