为 __main__ 创建循环

Question

我是 Python 新手，希望得到您的建议。

我有一个脚本，一次运行一个输入值，我希望它能够运行这些值的整个列表，而无需我一次输入一个值。我有一种预感，下面列出的主要方法需要一个“for 循环”。值是“gene_name”，所以有效地，我想输入一个脚本可以很好地运行的“gene_names”列表。

希望我的问题表述正确，谢谢！有问题的块似乎是

def get_probes_from_genes(gene_names)

   import json
   import urllib2
   import os
   import pandas as pd

   api_url = "http://api.brain-map.org/api/v2/data/query.json"

   def get_probes_from_genes(gene_names):
       if not isinstance(gene_names,list):
           gene_names = [gene_names]
       #in case there are white spaces in gene names
       gene_names = ["'%s'"%gene_name for gene_name in gene_names]**

       api_query = "?criteria=model::Probe"
       api_query= ",rma::criteria,[probe_type$eq'DNA']"
       api_query= ",products[abbreviation$eq'HumanMA']"
       api_query= ",gene[acronym$eq%s]"%(','.join(gene_names))
       api_query= ",rma::options[only$eq'probes.id','name']"

       data = json.load(urllib2.urlopen(api_url api_query))

       d = {probe['id']: probe['name'] for probe in data['msg']}

       if not d:
           raise Exception("Could not find any probes for %s gene. Check " \
           "http://help.brain-    map.org/download/attachments/2818165/HBA_ISH_GeneList.pdf?    version=1&modificationDate=1348783035873 " \
           "for list of available genes."%gene_name)

       return d

   def get_expression_values_from_probe_ids(probe_ids):
       if not isinstance(probe_ids,list):
           probe_ids = [probe_ids]
       #in case there are white spaces in gene names
       probe_ids = ["'%s'"%probe_id for probe_id in probe_ids]

       api_query = "?    criteria=service::human_microarray_expression[probes$in%s]"%    (','.join(probe_ids))
       data = json.load(urllib2.urlopen(api_url api_query))

       expression_values = [[float(expression_value) for expression_value in     data["msg"]["probes"][i]["expression_level"]] for i in range(len(probe_ids))]
       well_ids = [sample["sample"]["well"] for sample in data["msg"]    ["samples"]]
       donor_names = [sample["donor"]["name"] for sample in data["msg"]    ["samples"]]
       well_coordinates = [sample["sample"]["mri"] for sample in data["msg"]    ["samples"]]

       return expression_values, well_ids, well_coordinates, donor_names

   def get_mni_coordinates_from_wells(well_ids):
       package_directory = os.path.dirname(os.path.abspath(__file__))
       frame = pd.read_csv(os.path.join(package_directory, "data",     "corrected_mni_coordinates.csv"), header=0, index_col=0)

       return list(frame.ix[well_ids].itertuples(index=False))

   if __name__ == '__main__':
       probes_dict = get_probes_from_genes("SLC6A2")
       expression_values, well_ids, well_coordinates, donor_names =     get_expression_values_from_probe_ids(probes_dict.keys())
       print get_mni_coordinates_from_wells(well_ids)

Answer 1

哇，第一件事。 Python 不是 Java，所以请帮自己一个忙，使用漂亮的 """xxx\nyyy""" 字符串，用三引号表示多行。

 api_query = """?criteria=model::Probe"
             ,rma::criteria,[probe_type$eq'DNA']
             ...
             """

或类似的东西。你会得到输入的空格，所以你可能需要调整。

如果像建议的那样，您选择通过文件循环调用您的函数，您将需要尝试/排除您的 data-not-found 异常，或者您需要在不引发异常的情况下处理丢失的数据。我会选择自己返回一个空结果，让调用者担心如何处理它。

如果您确实选择引发异常，请创建自己的异常，而不是使用通用异常。这样您的代码就可以首先捕获您预期的异常。

class MyNoDataFoundException(Exception):
    pass

#replace your current raise code with...
if not d:
    raise MyNoDataFoundException(your message here)

关于捕获异常的说明，以接受的答案为起点：

if __name__ == '__main__':
    with open(r"/tmp/genes.txt","r") as f:
        for line in f.readlines():

            #keep track of your input data
            search_data = line.strip()
            try:
                probes_dict = get_probes_from_genes(search_data)
            except MyNoDataFoundException, e:
                #and do whatever you feel you need to do here...
                print "bummer about search_data:%s:\nexception:%s" % (search_data, e)

            expression_values, well_ids, well_coordinates, donor_names =     get_expression_values_from_probe_ids(probes_dict.keys())
            print get_mni_coordinates_from_wells(well_ids)

Answer 2

您可能想要创建一个带有基因名称的文件，然后读取文件的内容并在循环中调用您的函数。下面是一个例子

if __name__ == '__main__':
  with open(r"/tmp/genes.txt","r") as f:
      for line in f.readlines():
          probes_dict = get_probes_from_genes(line.strip())
          expression_values, well_ids, well_coordinates, donor_names =     get_expression_values_from_probe_ids(probes_dict.keys())
          print get_mni_coordinates_from_wells(well_ids)