Refactor and pylint (#59)

* major rewrite of fit.py
* add evaluate function to returned constraint
* remove generic_resid_fun and its dimensionality tests
* get pylint running

.pylintrc

@@ -60,7 +60,7 @@ confidence=
 # no Warning level messages displayed, use"--disable=all --enable=classes
 # --disable=W"
 #disable=import-star-module-level,old-octal-literal,oct-method,print-statement,unpacking-in-except,parameter-unpacking,backtick,old-raise-syntax,old-ne-operator,long-suffix,dict-view-method,dict-iter-method,metaclass-assignment,next-method-called,raising-string,indexing-exception,raw_input-builtin,long-builtin,file-builtin,execfile-builtin,coerce-builtin,cmp-builtin,buffer-builtin,basestring-builtin,apply-builtin,filter-builtin-not-iterating,using-cmp-argument,useless-suppression,range-builtin-not-iterating,suppressed-message,no-absolute-import,old-division,cmp-method,reload-builtin,zip-builtin-not-iterating,intern-builtin,unichr-builtin,reduce-builtin,standarderror-builtin,unicode-builtin,xrange-builtin,coerce-method,delslice-method,getslice-method,setslice-method,input-builtin,round-builtin,hex-method,nonzero-method,map-builtin-not-iterating
-disable=locally-disabled
+disable=locally-disabled,superfluous-parens,wrong-import-position, fixme, duplicate-code, maybe-no-member
 
 [REPORTS]
 
@@ -108,64 +108,34 @@ name-group=
 include-naming-hint=no
 
 # Regular expression matching correct function names
-function-rgx=[a-z_][a-z0-9_]{2,30}$
-
-# Naming hint for function names
-function-name-hint=[a-z_][a-z0-9_]{2,30}$
+function-rgx=[A-Za-z_][a-z0-9_]{2,30}$
 
 # Regular expression matching correct variable names
-variable-rgx=[a-z_][a-z0-9_]{2,30}$
-
-# Naming hint for variable names
-variable-name-hint=[a-z_][a-z0-9_]{2,30}$
+variable-rgx=[A-Za-z_][A-Za-z0-9_]{0,30}$
 
 # Regular expression matching correct constant names
 const-rgx=(([A-Z_][A-Z0-9_]*)|(__.*__))$
 
-# Naming hint for constant names
-const-name-hint=(([A-Z_][A-Z0-9_]*)|(__.*__))$
-
 # Regular expression matching correct attribute names
-attr-rgx=[a-z_][a-z0-9_]{2,30}$
-
-# Naming hint for attribute names
-attr-name-hint=[a-z_][a-z0-9_]{2,30}$
+attr-rgx=[A-Za-z_][a-z0-9_]{0,30}$
 
 # Regular expression matching correct argument names
-argument-rgx=[a-z_][a-z0-9_]{2,30}$
-
-# Naming hint for argument names
-argument-name-hint=[a-z_][a-z0-9_]{2,30}$
+argument-rgx=[A-Za-z_][a-z0-9_]{0,30}$
 
 # Regular expression matching correct class attribute names
-class-attribute-rgx=([A-Za-z_][A-Za-z0-9_]{2,30}|(__.*__))$
-
-# Naming hint for class attribute names
-class-attribute-name-hint=([A-Za-z_][A-Za-z0-9_]{2,30}|(__.*__))$
+class-attribute-rgx=([A-Za-z_][A-Za-z0-9_]{0,30}|(__.*__))$
 
 # Regular expression matching correct inline iteration names
 inlinevar-rgx=[A-Za-z_][A-Za-z0-9_]*$
 
-# Naming hint for inline iteration names
-inlinevar-name-hint=[A-Za-z_][A-Za-z0-9_]*$
-
 # Regular expression matching correct class names
-class-rgx=[A-Z_][a-zA-Z0-9]+$
-
-# Naming hint for class names
-class-name-hint=[A-Z_][a-zA-Z0-9]+$
+class-rgx=[t_]?|[A-Z_][a-zA-Z0-9]+$
 
 # Regular expression matching correct module names
-module-rgx=(([a-z_][a-z0-9_]*)|([A-Z][a-zA-Z0-9]+))$
-
-# Naming hint for module names
-module-name-hint=(([a-z_][a-z0-9_]*)|([A-Z][a-zA-Z0-9]+))$
+module-rgx=[t_]?|(([a-z_][a-z0-9_]*)|([A-Z][a-zA-Z0-9]+))$
 
 # Regular expression matching correct method names
-method-rgx=[a-z_][a-z0-9_]{2,30}$
-
-# Naming hint for method names
-method-name-hint=[a-z_][a-z0-9_]{2,30}$
+method-rgx=[test_]?[a-z_][a-z0-9_]{2,30}$
 
 # Regular expression which should only match function or class names that do
 # not require a docstring.

docs/source/examples/hoburgabbeel_ex6_1.py

@@ -1,5 +1,6 @@
-from gpfit.fit import fit
+"Fits an example function"
 from numpy import logspace, log, log10, random
+from gpfit.fit import fit
 
 # fixed initial guess for fitting
 random.seed(33404)

gpfit/ba_init.py

@@ -0,0 +1,81 @@
+"Implements ba_init"
+from numpy import ones, hstack, zeros, tile, argmin
+from numpy.linalg import lstsq, matrix_rank
+from numpy.random import permutation as randperm
+
+
+# pylint: disable=too-many-locals
+def ba_init(x, y, K):
+    """
+    Initializes max-affine fit to data (y, x)
+    ensures that initialization has at least K+1 points per partition (i.e.
+    per affine function)
+
+    INPUTS:
+        x:      Independent variable data
+                    2D column vector [nPoints x nDims]
+
+        y:      Dependent variable data
+                    2D column vector [nPoints x 1]
+
+    OUTPUTS:
+        ba:     Initial b and a parameters
+                    2D array [(dimx+1) x k]
+
+    """
+    defaults = {}
+    defaults['bverbose'] = False
+    options = defaults
+
+    npt, dimx = x.shape
+
+    X = hstack((ones((npt, 1)), x))
+    b = zeros((dimx+1, K))
+
+    if K*(dimx+1) > npt:
+        raise ValueError('Not enough data points')
+
+    # Choose K unique indices
+    randinds = randperm(npt)[0:K]
+
+    # partition based on distances
+    sqdists = zeros((npt, K))
+    for k in range(K):
+        sqdists[:, k] = ((x - tile(x[randinds[k], :], (npt, 1))) ** 2).sum(1)
+
+    # index to closest k for each data pt
+    mindistind = argmin(sqdists, axis=1)
+
+    # loop through each partition, making local fits
+    # note we expand partitions that result in singular least squares problems
+    # why this way? some points will be shared by multiple partitions, but
+    # resulting max-affine fit will tend to be good. (as opposed to solving least-norm version)
+    for k in range(K):
+        inds = mindistind == k
+
+        # before fitting, check rank and increase partition size if necessary
+        # (this does create overlaps)
+        if matrix_rank(X[inds, :]) < dimx + 1:
+            sortdistind = sqdists[:, k].argsort()
+
+            i = sum(inds)  # number of points in partition
+            iinit = i
+
+            if i < dimx+1:
+                # obviously, at least need dimx+1 points. fill these in before
+                # checking any ranks
+                inds[sortdistind[i+1:dimx+1]] = 1  # TODO: check index
+                i = dimx+1  # TODO: check index
+
+            # now add points until rank condition satisfied
+            while matrix_rank(X[inds, :]) < dimx+1:
+                i = i+1
+                inds[sortdistind[i]] = 1
+
+            if options['bverbose']:
+                print("ba_init: Added %s points to partition %s to maintain"
+                      "full rank for local fitting." % (i-iinit, k))
+        # now create the local fit
+        b[:, k] = lstsq(X[inds.nonzero()], y[inds.nonzero()])[0][:, 0]
+
+    return b