Python scipy.stats 模块，itemfreq() 实例源码

def compute_histogram(data, labels):
    histogram = itemfreq(sorted(data))
    for label in labels:
        if label not in histogram[:,0]:
            histogram = np.vstack((histogram,
                                   np.array([[label, 0]], dtype=object)))
    histogram = histogram[histogram[:,0].argsort()]
    return histogram

# compute histograms

def compute_histogram(data, labels):
    histogram = dict(itemfreq(data))
    for label in labels:
        if label not in histogram:
            histogram[label] = .0
    return histogram

def compute_histogram(data, labels):
    histogram = itemfreq(sorted(data))
    for label in labels:
        if label not in histogram[:,0]:
            histogram = np.vstack((histogram,
                                   np.array([[label, 0]], dtype=object)))
    histogram = histogram[histogram[:,0].argsort()]
    return histogram

# compute histograms

def compute_histogram(data, labels):
    histogram = dict(itemfreq(data))
    for label in labels:
        if label not in histogram:
            histogram[label] = .0
    return histogram

def boc_term_vectors(word_list):
    word_list = [word.lower() for word in word_list]
    unique_chars = np.unique(
                        np.hstack([list(word) 
                        for word in word_list]))
    word_list_term_counts = [{char: count for char, count in itemfreq(list(word))}
                             for word in word_list]

    boc_vectors = [np.array([int(word_term_counts.get(char, 0)) 
                            for char in unique_chars])
                   for word_term_counts in word_list_term_counts]
    return list(unique_chars), boc_vectors

def _calculate_leaf_value(self, targets):
        """Find optimal value for leaf."""
        if self.loss is not None:
            # Gradient boosting
            self.outcome = self.loss.approximate(targets['actual'], targets['y_pred'])
        else:
            # Random Forest
            if self.regression:
                # Mean value for regression task
                self.outcome = np.mean(targets['y'])
            else:
                # Probability for classification task
                self.outcome = stats.itemfreq(targets['y'])[:, 1] / float(targets['y'].shape[0])

def calc_class_entropy(y):
    class_counts = stats.itemfreq(y)[:, 1]
    return stats.entropy(class_counts, base=2)

def cudatest_hist():
    # src1 = np.arange(n, dtype=np.float32)
    src1 = np.random.randint(BIN_COUNT,size=n).astype(np.float32)
    histogram = np.zeros(BIN_COUNT, dtype=np.int32)

    print(src1)
    stream = cuda.stream()  # use stream to trigger async memory transfer
    ts = timer()

    # Controll the iterations
    count = 1
    for i in range(count):
        with stream.auto_synchronize():
            # ts = timer()
            d_src1 = cuda.to_device(src1, stream=stream)
            d_hist = cuda.to_device(histogram, stream=stream)
            # gpu_1d_stencil[bpg, tpb, stream](d_src1)
            gpu_histogram[bpg, tpb, stream](d_src1,d_hist)
            d_src1.copy_to_host(src1, stream=stream)
            d_hist.copy_to_host(histogram, stream=stream)

    te = timer()
    print('pinned ',count," : ", te - ts)
    print(histogram)
    # Taking histogram on origional data.
    # This histogram will contain few more frequency due to the padding we add in the orional data.
    # in kernel code.
    hist = src1.astype(np.int64)
    x = itemfreq(hist.ravel())
    hist = x#[:, 1]/sum(x[:, 1])
    print(hist)


# cudatest_stencil()