Python collections.Counter.__init__() Examples

def __init__(self, freqdist, bins=None):
        """
        Use the expected likelihood estimate to create a probability
        distribution for the experiment used to generate ``freqdist``.

        :type freqdist: FreqDist
        :param freqdist: The frequency distribution that the
            probability estimates should be based on.
        :type bins: int
        :param bins: The number of sample values that can be generated
            by the experiment that is described by the probability
            distribution.  This value must be correctly set for the
            probabilities of the sample values to sum to one.  If
            ``bins`` is not specified, it defaults to ``freqdist.B()``.
        """
        LidstoneProbDist.__init__(self, freqdist, 0.5, bins) 

def test_equality_Set(self):
        class MySet(Set):
            def __init__(self, itr):
                self.contents = itr
            def __contains__(self, x):
                return x in self.contents
            def __iter__(self):
                return iter(self.contents)
            def __len__(self):
                return len([x for x in self.contents])
        s1 = MySet((1,))
        s2 = MySet((1, 2))
        s3 = MySet((3, 4))
        s4 = MySet((3, 4))
        self.assertTrue(s2 > s1)
        self.assertTrue(s1 < s2)
        self.assertFalse(s2 <= s1)
        self.assertFalse(s2 <= s3)
        self.assertFalse(s1 >= s2)
        self.assertEqual(s3, s4)
        self.assertNotEqual(s2, s3) 

def test_init(self):
        OrderedDict = self.OrderedDict
        with self.assertRaises(TypeError):
            OrderedDict([('a', 1), ('b', 2)], None)                                 # too many args
        pairs = [('a', 1), ('b', 2), ('c', 3), ('d', 4), ('e', 5)]
        self.assertEqual(sorted(OrderedDict(dict(pairs)).items()), pairs)           # dict input
        self.assertEqual(sorted(OrderedDict(**dict(pairs)).items()), pairs)         # kwds input
        self.assertEqual(list(OrderedDict(pairs).items()), pairs)                   # pairs input
        self.assertEqual(list(OrderedDict([('a', 1), ('b', 2), ('c', 9), ('d', 4)],
                                          c=3, e=5).items()), pairs)                # mixed input

        # make sure no positional args conflict with possible kwdargs
        self.assertEqual(list(OrderedDict(self=42).items()), [('self', 42)])
        self.assertEqual(list(OrderedDict(other=42).items()), [('other', 42)])
        self.assertRaises(TypeError, OrderedDict, 42)
        self.assertRaises(TypeError, OrderedDict, (), ())
        self.assertRaises(TypeError, OrderedDict.__init__)

        # Make sure that direct calls to __init__ do not clear previous contents
        d = OrderedDict([('a', 1), ('b', 2), ('c', 3), ('d', 44), ('e', 55)])
        d.__init__([('e', 5), ('f', 6)], g=7, d=4)
        self.assertEqual(list(d.items()),
            [('a', 1), ('b', 2), ('c', 3), ('d', 4), ('e', 5), ('f', 6), ('g', 7)]) 

def __init__(self, freqdist, bins=None):
        """
        :param freqdist: The frequency counts upon which to base the
            estimation.
        :type freqdist: FreqDist
        :param bins: The number of possible event types. This must be
            larger than the number of bins in the ``freqdist``. If None,
            then it's assumed to be equal to ``freqdist``.B() + 1
        :type bins: int
        """
        assert (
            bins is None or bins > freqdist.B()
        ), 'bins parameter must not be less than %d=freqdist.B()+1' % (freqdist.B() + 1)
        if bins is None:
            bins = freqdist.B() + 1
        self._freqdist = freqdist
        self._bins = bins
        r, nr = self._r_Nr()
        self.find_best_fit(r, nr)
        self._switch(r, nr)
        self._renormalize(r, nr) 

def __init__(self, prob_dist, samples, store_logs=True):
        """
        Creates the mutable probdist based on the given prob_dist and using
        the list of samples given. These values are stored as log
        probabilities if the store_logs flag is set.

        :param prob_dist: the distribution from which to garner the
            probabilities
        :type prob_dist: ProbDist
        :param samples: the complete set of samples
        :type samples: sequence of any
        :param store_logs: whether to store the probabilities as logarithms
        :type store_logs: bool
        """
        self._samples = samples
        self._sample_dict = dict((samples[i], i) for i in range(len(samples)))
        self._data = array.array(str("d"), [0.0]) * len(samples)
        for i in range(len(samples)):
            if store_logs:
                self._data[i] = prob_dist.logprob(samples[i])
            else:
                self._data[i] = prob_dist.prob(samples[i])
        self._logs = store_logs 

def test_equality_Set(self):
        class MySet(Set):
            def __init__(self, itr):
                self.contents = itr
            def __contains__(self, x):
                return x in self.contents
            def __iter__(self):
                return iter(self.contents)
            def __len__(self):
                return len([x for x in self.contents])
        s1 = MySet((1,))
        s2 = MySet((1, 2))
        s3 = MySet((3, 4))
        s4 = MySet((3, 4))
        self.assertTrue(s2 > s1)
        self.assertTrue(s1 < s2)
        self.assertFalse(s2 <= s1)
        self.assertFalse(s2 <= s3)
        self.assertFalse(s1 >= s2)
        self.assertEqual(s3, s4)
        self.assertNotEqual(s2, s3) 

def __init__(self, freqdist, bins=None):
        """
        Use the Laplace estimate to create a probability distribution
        for the experiment used to generate ``freqdist``.

        :type freqdist: FreqDist
        :param freqdist: The frequency distribution that the
            probability estimates should be based on.
        :type bins: int
        :param bins: The number of sample values that can be generated
            by the experiment that is described by the probability
            distribution.  This value must be correctly set for the
            probabilities of the sample values to sum to one.  If
            ``bins`` is not specified, it defaults to ``freqdist.B()``.
        """
        LidstoneProbDist.__init__(self, freqdist, 1, bins) 

def test_equality_Set(self):
        class MySet(Set):
            def __init__(self, itr):
                self.contents = itr
            def __contains__(self, x):
                return x in self.contents
            def __iter__(self):
                return iter(self.contents)
            def __len__(self):
                return len([x for x in self.contents])
        s1 = MySet((1,))
        s2 = MySet((1, 2))
        s3 = MySet((3, 4))
        s4 = MySet((3, 4))
        self.assertTrue(s2 > s1)
        self.assertTrue(s1 < s2)
        self.assertFalse(s2 <= s1)
        self.assertFalse(s2 <= s3)
        self.assertFalse(s1 >= s2)
        self.assertEqual(s3, s4)
        self.assertNotEqual(s2, s3) 

def __init__(self, samples=None):
        """
        Construct a new frequency distribution.  If ``samples`` is
        given, then the frequency distribution will be initialized
        with the count of each object in ``samples``; otherwise, it
        will be initialized to be empty.

        In particular, ``FreqDist()`` returns an empty frequency
        distribution; and ``FreqDist(samples)`` first creates an empty
        frequency distribution, and then calls ``update`` with the
        list ``samples``.

        :param samples: The samples to initialize the frequency
            distribution with.
        :type samples: Sequence
        """
        Counter.__init__(self, samples)

        # Cached number of samples in this FreqDist
        self._N = None 

def __init__(self, **kwargs):
        """
        Initialize this object's probability.  This initializer should
        be called by subclass constructors.  ``prob`` should generally be
        the first argument for those constructors.

        :param prob: The probability associated with the object.
        :type prob: float
        :param logprob: The log of the probability associated with
            the object.
        :type logprob: float
        """
        if 'prob' in kwargs:
            if 'logprob' in kwargs:
                raise TypeError('Must specify either prob or logprob ' '(not both)')
            else:
                ProbabilisticMixIn.set_prob(self, kwargs['prob'])
        elif 'logprob' in kwargs:
            ProbabilisticMixIn.set_logprob(self, kwargs['logprob'])
        else:
            self.__prob = self.__logprob = None 

def __init__(self, samples):
        """
        Construct a new uniform probability distribution, that assigns
        equal probability to each sample in ``samples``.

        :param samples: The samples that should be given uniform
            probability.
        :type samples: list
        :raise ValueError: If ``samples`` is empty.
        """
        if len(samples) == 0:
            raise ValueError(
                'A Uniform probability distribution must ' + 'have at least one sample.'
            )
        self._sampleset = set(samples)
        self._prob = 1.0 / len(self._sampleset)
        self._samples = list(self._sampleset) 

def __init__(self, *args, **kwds):
        self.called = False
        Counter.__init__(self, *args, **kwds) 

def __init__(self, it=()):
        self.data = set(it) 

def test_init(self):
        self.assertEqual(list(Counter(self=42).items()), [('self', 42)])
        self.assertEqual(list(Counter(iterable=42).items()), [('iterable', 42)])
        self.assertEqual(list(Counter(iterable=None).items()), [('iterable', None)])
        self.assertRaises(TypeError, Counter, 42)
        self.assertRaises(TypeError, Counter, (), ())
        self.assertRaises(TypeError, Counter.__init__) 

def __init__(self, freqdist, bins=None, discount=0.75):
        """
        :param freqdist: The trigram frequency distribution upon which to base
            the estimation
        :type freqdist: FreqDist
        :param bins: Included for compatibility with nltk.tag.hmm
        :type bins: int or float
        :param discount: The discount applied when retrieving counts of
            trigrams
        :type discount: float (preferred, but can be set to int)
        """

        if not bins:
            self._bins = freqdist.B()
        else:
            self._bins = bins
        self._D = discount

        # cache for probability calculation
        self._cache = {}

        # internal bigram and trigram frequency distributions
        self._bigrams = defaultdict(int)
        self._trigrams = freqdist

        # helper dictionaries used to calculate probabilities
        self._wordtypes_after = defaultdict(float)
        self._trigrams_contain = defaultdict(float)
        self._wordtypes_before = defaultdict(float)
        for w0, w1, w2 in freqdist:
            self._bigrams[(w0, w1)] += freqdist[(w0, w1, w2)]
            self._wordtypes_after[(w0, w1)] += 1
            self._trigrams_contain[w1] += 1
            self._wordtypes_before[(w1, w2)] += 1 

def test_Sequence_mixins(self):
        class SequenceSubclass(Sequence):
            def __init__(self, seq=()):
                self.seq = seq

            def __getitem__(self, index):
                return self.seq[index]

            def __len__(self):
                return len(self.seq)

        # Compare Sequence.index() behavior to (list|str).index() behavior
        def assert_index_same(seq1, seq2, index_args):
            try:
                expected = seq1.index(*index_args)
            except ValueError:
                with self.assertRaises(ValueError):
                    seq2.index(*index_args)
            else:
                actual = seq2.index(*index_args)
                self.assertEqual(
                    actual, expected, '%r.index%s' % (seq1, index_args))

        for ty in list, str:
            nativeseq = ty('abracadabra')
            indexes = [-10000, -9999] + list(range(-3, len(nativeseq) + 3))
            seqseq = SequenceSubclass(nativeseq)
            for letter in set(nativeseq) | {'z'}:
                assert_index_same(nativeseq, seqseq, (letter,))
                for start in range(-3, len(nativeseq) + 3):
                    assert_index_same(nativeseq, seqseq, (letter, start))
                    for stop in range(-3, len(nativeseq) + 3):
                        assert_index_same(
                            nativeseq, seqseq, (letter, start, stop)) 

def test_issue26915(self):
        # Container membership test should check identity first
        class CustomEqualObject:
            def __eq__(self, other):
                return False
        class CustomSequence(Sequence):
            def __init__(self, seq):
                self._seq = seq
            def __getitem__(self, index):
                return self._seq[index]
            def __len__(self):
                return len(self._seq)

        nan = float('nan')
        obj = CustomEqualObject()
        seq = CustomSequence([nan, obj, nan])
        containers = [
            seq,
            ItemsView({1: nan, 2: obj}),
            ValuesView({1: nan, 2: obj})
        ]
        for container in containers:
            for elem in container:
                self.assertIn(elem, container)
        self.assertEqual(seq.index(nan), 0)
        self.assertEqual(seq.index(obj), 1)
        self.assertEqual(seq.count(nan), 2)
        self.assertEqual(seq.count(obj), 1) 

def test_issue_4920(self):
        # MutableSet.pop() method did not work
        class MySet(MutableSet):
            __slots__=['__s']
            def __init__(self,items=None):
                if items is None:
                    items=[]
                self.__s=set(items)
            def __contains__(self,v):
                return v in self.__s
            def __iter__(self):
                return iter(self.__s)
            def __len__(self):
                return len(self.__s)
            def add(self,v):
                result=v not in self.__s
                self.__s.add(v)
                return result
            def discard(self,v):
                result=v in self.__s
                self.__s.discard(v)
                return result
            def __repr__(self):
                return "MySet(%s)" % repr(list(self))
        s = MySet([5,43,2,1])
        self.assertEqual(s.pop(), 1) 

def test_isdisjoint_Set(self):
        class MySet(Set):
            def __init__(self, itr):
                self.contents = itr
            def __contains__(self, x):
                return x in self.contents
            def __iter__(self):
                return iter(self.contents)
            def __len__(self):
                return len([x for x in self.contents])
        s1 = MySet((1, 2, 3))
        s2 = MySet((4, 5, 6))
        s3 = MySet((1, 5, 6))
        self.assertTrue(s1.isdisjoint(s2))
        self.assertFalse(s1.isdisjoint(s3)) 

def test_hash_Set(self):
        class OneTwoThreeSet(Set):
            def __init__(self):
                self.contents = [1, 2, 3]
            def __contains__(self, x):
                return x in self.contents
            def __len__(self):
                return len(self.contents)
            def __iter__(self):
                return iter(self.contents)
            def __hash__(self):
                return self._hash()
        a, b = OneTwoThreeSet(), OneTwoThreeSet()
        self.assertTrue(hash(a) == hash(b)) 

def validate_comparison(self, instance):
        ops = ['lt', 'gt', 'le', 'ge', 'ne', 'or', 'and', 'xor', 'sub']
        operators = {}
        for op in ops:
            name = '__' + op + '__'
            operators[name] = getattr(operator, name)

        class Other:
            def __init__(self):
                self.right_side = False
            def __eq__(self, other):
                self.right_side = True
                return True
            __lt__ = __eq__
            __gt__ = __eq__
            __le__ = __eq__
            __ge__ = __eq__
            __ne__ = __eq__
            __ror__ = __eq__
            __rand__ = __eq__
            __rxor__ = __eq__
            __rsub__ = __eq__

        for name, op in operators.items():
            if not hasattr(instance, name):
                continue
            other = Other()
            op(instance, other)
            self.assertTrue(other.right_side,'Right side not called for %s.%s'
                            % (type(instance), name)) 

def __init__(self, prob_dict=None, log=False, normalize=False):
        """
        Construct a new probability distribution from the given
        dictionary, which maps values to probabilities (or to log
        probabilities, if ``log`` is true).  If ``normalize`` is
        true, then the probability values are scaled by a constant
        factor such that they sum to 1.

        If called without arguments, the resulting probability
        distribution assigns zero probability to all values.
        """

        self._prob_dict = prob_dict.copy() if prob_dict is not None else {}
        self._log = log

        # Normalize the distribution, if requested.
        if normalize:
            if len(prob_dict) == 0:
                raise ValueError(
                    'A DictionaryProbDist must have at least one sample '
                    + 'before it can be normalized.'
                )
            if log:
                value_sum = sum_logs(list(self._prob_dict.values()))
                if value_sum <= _NINF:
                    logp = math.log(1.0 / len(prob_dict), 2)
                    for x in prob_dict:
                        self._prob_dict[x] = logp
                else:
                    for (x, p) in self._prob_dict.items():
                        self._prob_dict[x] -= value_sum
            else:
                value_sum = sum(self._prob_dict.values())
                if value_sum == 0:
                    p = 1.0 / len(prob_dict)
                    for x in prob_dict:
                        self._prob_dict[x] = p
                else:
                    norm_factor = 1.0 / value_sum
                    for (x, p) in self._prob_dict.items():
                        self._prob_dict[x] *= norm_factor 

def __init__(self, samples):
        if len(samples) == 0:
            raise ValueError(
                'A probability distribution must ' + 'have at least one sample.'
            )
        self._probs = self.unirand(samples)
        self._samples = list(self._probs.keys()) 

def __init__(self):
        """
        Classes inheriting from ProbDistI should implement __init__.
        """ 

def test_init(self):
        self.assertEqual(list(Counter(self=42).items()), [('self', 42)])
        self.assertEqual(list(Counter(iterable=42).items()), [('iterable', 42)])
        self.assertEqual(list(Counter(iterable=None).items()), [('iterable', None)])
        self.assertRaises(TypeError, Counter, 42)
        self.assertRaises(TypeError, Counter, (), ())
        self.assertRaises(TypeError, Counter.__init__) 

def __init__(self, *args, **kwds):
        self.called = False
        Counter.__init__(self, *args, **kwds) 

def __init__(self, *args, **kwds):
        self.called = False
        Counter.__init__(self, *args, **kwds) 

def test_Sequence_mixins(self):
        class SequenceSubclass(Sequence):
            def __init__(self, seq=()):
                self.seq = seq

            def __getitem__(self, index):
                return self.seq[index]

            def __len__(self):
                return len(self.seq)

        # Compare Sequence.index() behavior to (list|str).index() behavior
        def assert_index_same(seq1, seq2, index_args):
            try:
                expected = seq1.index(*index_args)
            except ValueError:
                with self.assertRaises(ValueError):
                    seq2.index(*index_args)
            else:
                actual = seq2.index(*index_args)
                self.assertEqual(
                    actual, expected, '%r.index%s' % (seq1, index_args))

        for ty in list, str:
            nativeseq = ty('abracadabra')
            indexes = [-10000, -9999] + list(range(-3, len(nativeseq) + 3))
            seqseq = SequenceSubclass(nativeseq)
            for letter in set(nativeseq) | {'z'}:
                assert_index_same(nativeseq, seqseq, (letter,))
                for start in range(-3, len(nativeseq) + 3):
                    assert_index_same(nativeseq, seqseq, (letter, start))
                    for stop in range(-3, len(nativeseq) + 3):
                        assert_index_same(
                            nativeseq, seqseq, (letter, start, stop)) 

def test_issue_4920(self):
        # MutableSet.pop() method did not work
        class MySet(MutableSet):
            __slots__=['__s']
            def __init__(self,items=None):
                if items is None:
                    items=[]
                self.__s=set(items)
            def __contains__(self,v):
                return v in self.__s
            def __iter__(self):
                return iter(self.__s)
            def __len__(self):
                return len(self.__s)
            def add(self,v):
                result=v not in self.__s
                self.__s.add(v)
                return result
            def discard(self,v):
                result=v in self.__s
                self.__s.discard(v)
                return result
            def __repr__(self):
                return "MySet(%s)" % repr(list(self))
        s = MySet([5,43,2,1])
        self.assertEqual(s.pop(), 1) 

def test_isdisjoint_Set(self):
        class MySet(Set):
            def __init__(self, itr):
                self.contents = itr
            def __contains__(self, x):
                return x in self.contents
            def __iter__(self):
                return iter(self.contents)
            def __len__(self):
                return len([x for x in self.contents])
        s1 = MySet((1, 2, 3))
        s2 = MySet((4, 5, 6))
        s3 = MySet((1, 5, 6))
        self.assertTrue(s1.isdisjoint(s2))
        self.assertFalse(s1.isdisjoint(s3))