Exemple #1
0
    def get_keys_multiproc(
        cls,
        lookup,
        loc_df,
        success_only=False,
        num_cores=-1,
        num_partitions=-1
    ):
        """
        Used for CPU bound lookup operations, Depends on a method

        `process_locations_multiproc(dataframe)`

        where single_row is a pandas series from a location Pandas DataFrame
        and returns a list of dicts holding the lookup results for that single row
        """
        pool_count = num_cores if num_cores > 0 else cpu_count()
        part_count = num_partitions if num_partitions > 0 else min(pool_count * 2, len(loc_df))
        locations = np.array_split(loc_df, part_count)

        pool = Pool(pool_count)
        results = pool.map(lookup.process_locations_multiproc, locations)
        lookup_results = sum([r for r in results if r], [])
        pool.terminate()
        return lookup_results
Exemple #2
0
    def searchDarkWeb(self, query, include=None, exclude=None):
        ''' Gets data from search engines specified '''
        if include:
            final = [a for a in include if a in self.sites]
        elif exclude:
            final = [a for a in self.sites if a not in exclude]
        else:
            final = list(self.sites.keys())

        self.query = query
        pool = Pool(processes=len(final))
        data = pool.map(self.search, final)
        resultList = [d for dat in data for d in dat]
        pool.close()

        ind = Indexer()
        for i in resultList:
            ind.join(i)
        return ind.results()
Exemple #3
0
def _scan_match(sample_ui_list, path_list, comp_func, weight_list=None, threshold=0.6, pool_size=12):
    """
    :param sample_ui_list: output after process_csv()
    :param path_list: relative or absolute path list of csv files
    :param comp_func: compare function
    :param weight_list: ui weight mask
    :param threshold: threshold,超过一定的阈值才会被计算成相同组件
    :param pool_size: 并行池大小
    :return: best match path name
    """
    pool = Pool(processes=pool_size)

    arg_list = []
    for j in range(len(path_list)):
        arg_list.append((j + 1, path_list[j], sample_ui_list, comp_func, weight_list, threshold))
    score_list = pool.map(_single_scan_helper, arg_list)
    pool.close()
    pool.join()

    # return sorted path^score^score_distribution_list list
    return sorted(score_list, key=lambda k: k[1], reverse=True)
def main():
    p = Pool(5)
    A = []
    for i in range(0, 100):
        A.append(i)
    print(p.map(f, A))