# Commits

committed 25b9963

try angles all positive to ease calculations

# mi.py

`     return binned.astype(np.int16)-1`
` `
` def bin_angle_naive(a, n_bins):`
`-    return bin_naive(a, n_bins, range=(-sp.pi, sp.pi))`
`+    return bin_naive(a, n_bins, range=(0.pi, 2*sp.pi))`
` `
` def choose_n_bins(n_data_points, test=True):`
`     """according to Cellucci et al (2005), the maximal number of bins is given`
` `
` def angle(x,y):`
`     """trivial helper for wicks MI calculations - gives the angle of a 2d`
`-    vector`
`+    vector, wrapped into [0, 2pi).`
` `
`     >>> angle([1,1,0,-1,-1], [0,1,1,1,0])`
`-    array([ 1.57079633,  0.78539816,  0., -0.78539816, -1.57079633])`
`+    array([ 1.57079633,  0.78539816,  0.,  5.49778714,  4.71238898])`
`     """`
`-    return np.arctan2(x,y)`
`+    return (np.arctan2(x,y) + 2*np.pi) % (2*np.pi)`
` `
` def ince_mi_dist_cont(X, Y, n_bins=None, **kwargs):`
`     """wraps pyentropy's grandiose object initialisation and quantisation`
`     `
`     if no n_bins is given, we choose the maximimum statistically valid number`
`     by the cochrane criterion, and leave it be. This will give good results in`
`-    all except particularly pathological cases. (bins will be approximately equal occupancy)`
`+    all except particularly pathological cases. (bins will be approximately`
`+    equal occupancy)`
`     """`
`     kwargs.setdefault('method', 'qe')`
`     kwargs.setdefault('sampling', 'kt')`