Module dist

Discrete probability distributions

Classes
	DDist Discrete distribution represented as a dictionary.
	MixtureDist A mixture of two probabability distributions, d1 and d2, with mixture parameter p.

Functions

JDist(PA, PBgA)
Create a joint distribution on P(A, B) (in that order), represented as a DDist

bayesEvidence(PA, PBgA, b)
Returns: P(A | b)

totalProbability(PA, PBgA)
Returns: P(B) using the law of total probability.

DeltaDist(v)
Distribution with all of its probability mass on value v

UniformDist(elts)
Uniform distribution over a given finite set of elts

triangleDist(peak, halfWidth, lo=None, hi=None)
Construct and return a DDist over integers.

squareDist(lo, hi, loLimit=None, hiLimit=None)
Construct and return a DDist over integers.

removeElt(items, i)
non-destructively remove the element at index i from a list; returns a copy; if the result is a list of length 1, just return the element

incrDictEntry(d, k, v)
If dictionary d has key k, then increment d[k] by v.

Variables
	__package__ = `None`

Function Details

JDist(PA, PBgA)

Create a joint distribution on P(A, B) (in that order), represented as a DDist

Parameters:

PA - a DDist on some random var A
PBgA - a conditional probability distribution specifying P(B | A) (that is, a function from elements of A to DDist on B)

bayesEvidence(PA, PBgA, b)

Parameters:

PBgA - conditional distribution over B given A (function from values of a to DDist over B)
PA - prior on A
b - evidence value for B = b

Returns:

P(A | b)

totalProbability(PA, PBgA)

Parameters:

PBgA - conditional distribution over B given A (function from values of a to DDist over B)
PA - distribution over A (object of type DiscreteDist)

Returns:

P(B) using the law of total probability. self represents P(B | A); P(A) is the argument to the method; we compute and return P(B) as sum_a P(B | a) P(a)

UniformDist(elts)

Uniform distribution over a given finite set of elts

Parameters:

elts - list of any kind of item

triangleDist(peak, halfWidth, lo=None, hi=None)

Construct and return a DDist over integers. The distribution will have its peak at index peak and fall off linearly from there, reaching 0 at an index halfWidth on either side of peak. Any probability mass that would be below lo or above hi is assigned to lo or hi

squareDist(lo, hi, loLimit=None, hiLimit=None)

Construct and return a DDist over integers. The distribution will have a uniform distribution on integers from lo to hi-1 (inclusive). Any probability mass that would be below lo or above hi is assigned to lo or hi.

incrDictEntry(d, k, v)

If dictionary d has key k, then increment d[k] by v. Else set d[k] = v.

Parameters:

d - dictionary
k - legal dictionary key (doesn't have to be in d)
v - numeric value