Merge pull request #100 from ricardomourarpm/master

Changes in hitmap mainly, done by me to correct positions

sompy/__init__.py

@@ -1,6 +1,7 @@
-from logging.config import dictConfig
 
+from logging.config import dictConfig
 import matplotlib
+
 #matplotlib.use('Agg')  # Use whatever backend is available
 
 dictConfig({
@@ -24,5 +25,7 @@
     }
 })
 
+
+
 from .sompy import SOMFactory
 from .visualization import *

sompy/codebook.py

@@ -1,7 +1,8 @@
 import numpy as np
 import scipy as sp
-from sklearn.decomposition import PCA
 
+from sklearn.decomposition import PCA
+#from sklearn.decomposition import RandomizedPCA# (randomizedpca is deprecated)
 from .decorators import timeit
 
 
@@ -12,14 +13,13 @@ class InvalidNodeIndexError(Exception):
 class InvalidMapsizeError(Exception):
     pass
 
-
 def generate_hex_lattice(n_rows, n_columns):
     x_coord = []
     y_coord = []
     for i in range(n_rows):
         for j in range(n_columns):
-            x_coord.append(i * 1.5)
-            y_coord.append(np.sqrt(2 / 3) * (2 * j + (1 + i) % 2))
+            x_coord.append(i*1.5)
+            y_coord.append(np.sqrt(2/3)*(2*j+(1+i)%2))
     coordinates = np.column_stack([x_coord, y_coord])
     return coordinates
 
@@ -35,13 +35,13 @@ def __init__(self, mapsize, lattice='rect'):
         elif 1 == len(mapsize):
             _size = [1, mapsize[0]]
             print('input was considered as the numbers of nodes')
-            print('map size is [{dlen},{dlen}]'.format(dlen=int(mapsize[0] / 2)))
+            print('map size is [{dlen},{dlen}]'.format(dlen=int(mapsize[0]/2)))
         else:
             raise InvalidMapsizeError(
                 "Mapsize is expected to be a 2 element list or a single int")
 
         self.mapsize = _size
-        self.nnodes = mapsize[0] * mapsize[1]
+        self.nnodes = mapsize[0]*mapsize[1]
         self.matrix = np.asarray(self.mapsize)
         self.initialized = False
 
@@ -59,7 +59,7 @@ def random_initialization(self, data):
         """
         mn = np.tile(np.min(data, axis=0), (self.nnodes, 1))
         mx = np.tile(np.max(data, axis=0), (self.nnodes, 1))
-        self.matrix = mn + (mx - mn) * (np.random.rand(self.nnodes, data.shape[1]))
+        self.matrix = mn + (mx-mn)*(np.random.rand(self.nnodes, data.shape[1]))
         self.initialized = True
 
     @timeit()
@@ -108,8 +108,8 @@ def pca_linear_initialization(self, data):
 
         mx = np.max(coord, axis=0)
         mn = np.min(coord, axis=0)
-        coord = (coord - mn) / (mx - mn)
-        coord = (coord - .5) * 2
+        coord = (coord - mn)/(mx-mn)
+        coord = (coord - .5)*2
         me = np.mean(data, 0)
         data = (data - me)
         tmp_matrix = np.tile(me, (self.nnodes, 1))
@@ -122,11 +122,11 @@ def pca_linear_initialization(self, data):
         eigvec = pca.components_
         eigval = pca.explained_variance_
         norms = np.sqrt(np.einsum('ij,ij->i', eigvec, eigvec))
-        eigvec = ((eigvec.T / norms) * eigval).T
+        eigvec = ((eigvec.T/norms)*eigval).T
 
         for j in range(self.nnodes):
             for i in range(eigvec.shape[0]):
-                tmp_matrix[j, :] = tmp_matrix[j, :] + coord[j, i] * eigvec[i, :]
+                tmp_matrix[j, :] = tmp_matrix[j, :] + coord[j, i]*eigvec[i, :]
 
         self.matrix = np.around(tmp_matrix, decimals=6)
         self.initialized = True
@@ -169,7 +169,7 @@ def _rect_dist(self, node_ind):
         dist = None
 
         # bmu should be an integer between 0 to no_nodes
-        if 0 <= node_ind <= (rows * cols):
+        if 0 <= node_ind <= (rows*cols):
             node_col = int(node_ind % cols)
             node_row = int(node_ind / cols)
         else:
@@ -179,7 +179,7 @@ def _rect_dist(self, node_ind):
         if rows > 0 and cols > 0:
             r = np.arange(0, rows, 1)[:, np.newaxis]
             c = np.arange(0, cols, 1)
-            dist2 = (r - node_row)**2 + (c - node_col)**2
+            dist2 = (r-node_row)**2 + (c-node_col)**2
 
             dist = dist2.ravel()
         else:

sompy/examples/AirFlights_hexagonal_grid.ipynb

@@ -354,12 +354,10 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "raw",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "%time\n",
+    "%%time\n",
     "# Train the model with different parameters. The more, the better. Each iteration is stored in disk for further study\n",
     "for i in range(1000):\n",
     "    sm = SOMFactory().build(data, mapsize=[random.choice(list(range(15, 25))), \n",

sompy/neighborhood.py

@@ -1,8 +1,7 @@
+import numpy as np
 import inspect
 import sys
 
-import numpy as np
-
 small = .000000000001
 
 
@@ -25,7 +24,7 @@ class GaussianNeighborhood(object):
 
     @staticmethod
     def calculate(distance_matrix, radius, dim):
-        return np.exp(-1.0 * distance_matrix / (2.0 * radius**2)).reshape(dim, dim)
+        return np.exp(-1.0*distance_matrix/(2.0*radius**2)).reshape(dim, dim)
 
     def __call__(self, *args, **kwargs):
         return self.calculate(*args)
@@ -39,7 +38,7 @@ class BubbleNeighborhood(object):
     def calculate(distance_matrix, radius, dim):
         def l(a, b):
             c = np.zeros(b.shape)
-            c[a - b >= 0] = 1
+            c[a-b >= 0] = 1
             return c
 
         return l(radius,

sompy/normalization.py

@@ -1,7 +1,6 @@
-import inspect
-import sys
-
 import numpy as np
+import sys
+import inspect
 
 
 class NormalizerFactory(object):
@@ -38,12 +37,12 @@ def _mean_and_standard_dev(self, data):
     def normalize(self, data):
         me, st = self._mean_and_standard_dev(data)
         st[st == 0] = 1  # prevent: when sd = 0, normalized result = NaN
-        return (data - me) / st
+        return (data-me)/st
 
     def normalize_by(self, raw_data, data):
         me, st = self._mean_and_standard_dev(raw_data)
         st[st == 0] = 1  # prevent: when sd = 0, normalized result = NaN
-        return (data - me) / st
+        return (data-me)/st
 
     def denormalize_by(self, data_by, n_vect):
         me, st = self._mean_and_standard_dev(data_by)