Python poisson.pmf方法代碼示例

本文整理匯總了Python中scipy.stats.poisson.pmf方法的典型用法代碼示例。如果您正苦於以下問題：Python poisson.pmf方法的具體用法？Python poisson.pmf怎麽用？Python poisson.pmf使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類scipy.stats.poisson的用法示例。

在下文中一共展示了poisson.pmf方法的15個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: test_update_with_noise_coherent

# 需要導入模塊: from scipy.stats import poisson [as 別名]
# 或者: from scipy.stats.poisson import pmf [as 別名]
def test_update_with_noise_coherent(num_modes, parallel, monkeypatch):
    """ Test that adding noise on coherent states gives the same probabilities at some other coherent states"""

    if parallel: # set single-thread use in OpenMP
        monkeypatch.setenv("OMP_NUM_THREADS", "1")

    cutoff = 15
    nbar_vals = np.random.rand(num_modes)
    noise_dists = np.array([poisson.pmf(np.arange(cutoff), nbar) for nbar in nbar_vals])
    hbar = 2
    beta = np.random.rand(num_modes) + 1j * np.random.rand(num_modes)
    means = Means(np.concatenate((beta, beta.conj())), hbar=hbar)
    cov = hbar * np.identity(2 * num_modes) / 2
    cutoff = 10

    probs = probabilities(means, cov, cutoff, parallel=parallel, hbar=2)
    updated_probs = update_probabilities_with_noise(noise_dists, probs)
    beta_expected = np.sqrt(nbar_vals + np.abs(beta) ** 2)
    means_expected = Means(
        np.concatenate((beta_expected, beta_expected.conj())), hbar=hbar
    )
    expected = probabilities(means_expected, cov, cutoff, parallel=parallel, hbar=2)
    assert np.allclose(updated_probs, expected)

開發者ID:XanaduAI，項目名稱:thewalrus，代碼行數:25，代碼來源:test_quantum.py

示例2: test_update_with_noise_coherent_value_error

# 需要導入模塊: from scipy.stats import poisson [as 別名]
# 或者: from scipy.stats.poisson import pmf [as 別名]
def test_update_with_noise_coherent_value_error():
    """Tests the correct error is raised"""
    cutoff = 15
    num_modes = 3
    nbar_vals = np.random.rand(num_modes - 1)
    noise_dists = np.array([poisson.pmf(np.arange(cutoff), nbar) for nbar in nbar_vals])
    hbar = 2
    beta = np.random.rand(num_modes) + 1j * np.random.rand(num_modes)
    means = Means(np.concatenate((beta, beta.conj())), hbar=hbar)
    cov = hbar * np.identity(2 * num_modes) / 2
    cutoff = 10
    probs = probabilities(means, cov, cutoff, hbar=2)
    with pytest.raises(
        ValueError,
        match="The list of probability distributions probs_noise and the tensor of probabilities probs have incompatible dimensions.",
    ):
        update_probabilities_with_noise(noise_dists, probs)

開發者ID:XanaduAI，項目名稱:thewalrus，代碼行數:19，代碼來源:test_quantum.py

示例3: compute_window_score

# 需要導入模塊: from scipy.stats import poisson [as 別名]
# 或者: from scipy.stats.poisson import pmf [as 別名]
def compute_window_score(i, poisson_parameter):
    # type: (int, float) -> float

    # No enrichment; poisson param also average
    if i < poisson_parameter:
        return 0

    p_value = poisson.pmf(i, poisson_parameter)

    if p_value > 0:
        window_score = -log(p_value)
    else:
        # log of zero not defined
        window_score = 1000

    return window_score

開發者ID:biocore-ntnu，項目名稱:epic，代碼行數:18，代碼來源:compute_window_score.py

示例4: compute_enriched_threshold

# 需要導入模塊: from scipy.stats import poisson [as 別名]
# 或者: from scipy.stats.poisson import pmf [as 別名]
def compute_enriched_threshold(average_window_readcount):
    # type: (float) -> int
    """
    Computes the minimum number of tags required in window for an island to be enriched.
    """

    current_threshold, survival_function = 0, 1
    for current_threshold in count(start=0, step=1):
        survival_function -= poisson.pmf(current_threshold,
                                         average_window_readcount)
        if survival_function <= WINDOW_P_VALUE:
            break

    island_enriched_threshold = current_threshold + 1

    return island_enriched_threshold

開發者ID:biocore-ntnu，項目名稱:epic，代碼行數:18，代碼來源:compute_values_needed_for_recurrence.py

示例5: poisson_probability

# 需要導入模塊: from scipy.stats import poisson [as 別名]
# 或者: from scipy.stats.poisson import pmf [as 別名]
def poisson_probability(n, lam):
    global poisson_cache
    key = n * 10 + lam
    if key not in poisson_cache:
        poisson_cache[key] = poisson.pmf(n, lam)
    return poisson_cache[key]

開發者ID:ShangtongZhang，項目名稱:reinforcement-learning-an-introduction，代碼行數:8，代碼來源:car_rental.py