Ejemplo n.º 1
0
 def __call__(self, seq, result=None):
     if result is None and self.working is None:
         self.setResultArray(len(seq))
     elif self.working is not None:
         if len(seq) != self.working.shape[0]:
             self.setResultArray(len(seq))
     
     result = self.working
     result.fill(0)
     if type(seq) != str:
         seq = ''.join(seq)
     
     return seq_to_symbols(seq, self.motifs, self.motif_length, result)
Ejemplo n.º 2
0
    def __call__(self, seq, result=None):
        if result is None and self.working is None:
            self.setResultArray(len(seq))
        elif self.working is not None:
            if len(seq) != self.working.shape[0]:
                self.setResultArray(len(seq))

        result = self.working
        result.fill(0)
        if type(seq) != str:
            seq = ''.join(seq)

        return seq_to_symbols(seq, self.motifs, self.motif_length, result)
Ejemplo n.º 3
0
def blockwise_bootstrap(signal, calc, block_size, num_reps, seq_to_symbols=None, num_stats=None):
    """returns observed statistic and the probability from the bootstrap
    test of observing more `power' by chance than that estimated from the
    observed signal
    
    Arguments:
        - signal: a series, can be a sequence object
        - calc: function to calculate the period power, e.g. ipdft, hybrid,
          auto_corr or any other statistic.
        - block_size: size of contiguous values for resampling
        - num_reps: number of randomly generated permutations
        - seq_to_symbols: function to convert a sequence to 1/0. If not
          provided, the raw data is used.
        - num_stats: the number of statistics being evaluated for each
          interation. Default to 1.
    """
    signal_length = len(signal)
    
    if seq_to_symbols is not None:
        dtype='c'
    else:
        dtype=None # let numpy guess
    
    signal = numpy.array(list(signal), dtype=dtype)
    
    if seq_to_symbols is not None:
        symbolic = seq_to_symbols(signal)
        data = symbolic
    else:
        data = signal
    
    obs_stat = calc(data)
    if seq_to_symbols is not None:
        if sum(symbolic) == 0:
            p = [numpy.array([1.0, 1.0, 1.0]), 1.0][num_stats == 1]
            
            return obs_stat, p
    
    if num_stats is None:
        try:
            num_stats = calc.getNumStats()
        except AttributeError:
            num_stats = 1
    
    if num_stats == 1:
        count = 0
    else:
        count = numpy.zeros(num_stats)
    
    for rep in range(num_reps):
        # get sample positions
        sampled_indices = sampled_places(block_size, signal_length)
        new_signal = signal.take(sampled_indices)
        if seq_to_symbols is not None:
            symbolic = seq_to_symbols(new_signal)
            data = symbolic
        else:
            data = new_signal
        sim_stat = calc(data)
        # count if > than observed
        if num_stats > 1:
            count[sim_stat >= obs_stat] += 1
        elif sim_stat >= obs_stat:
            count += 1
        
    return obs_stat, count / num_reps
Ejemplo n.º 4
0
def blockwise_bootstrap(signal,
                        calc,
                        block_size,
                        num_reps,
                        seq_to_symbols=None,
                        num_stats=None):
    """returns observed statistic and the probability from the bootstrap
    test of observing more `power' by chance than that estimated from the
    observed signal
    
    Arguments:
        - signal: a series, can be a sequence object
        - calc: function to calculate the period power, e.g. ipdft, hybrid,
          auto_corr or any other statistic.
        - block_size: size of contiguous values for resampling
        - num_reps: number of randomly generated permutations
        - seq_to_symbols: function to convert a sequence to 1/0. If not
          provided, the raw data is used.
        - num_stats: the number of statistics being evaluated for each
          interation. Default to 1.
    """
    signal_length = len(signal)

    if seq_to_symbols is not None:
        dtype = 'c'
    else:
        dtype = None  # let numpy guess

    signal = numpy.array(list(signal), dtype=dtype)

    if seq_to_symbols is not None:
        symbolic = seq_to_symbols(signal)
        data = symbolic
    else:
        data = signal

    obs_stat = calc(data)
    if seq_to_symbols is not None:
        if sum(symbolic) == 0:
            p = [numpy.array([1.0, 1.0, 1.0]), 1.0][num_stats == 1]

            return obs_stat, p

    if num_stats is None:
        try:
            num_stats = calc.getNumStats()
        except AttributeError:
            num_stats = 1

    if num_stats == 1:
        count = 0
    else:
        count = numpy.zeros(num_stats)

    for rep in range(num_reps):
        # get sample positions
        sampled_indices = sampled_places(block_size, signal_length)
        new_signal = signal.take(sampled_indices)
        if seq_to_symbols is not None:
            symbolic = seq_to_symbols(new_signal)
            data = symbolic
        else:
            data = new_signal
        sim_stat = calc(data)
        # count if > than observed
        if num_stats > 1:
            count[sim_stat >= obs_stat] += 1
        elif sim_stat >= obs_stat:
            count += 1

    return obs_stat, count / num_reps