"precommit format with github style"

python/paddle/v2/dataset/mq2007.py

@@ -23,7 +23,6 @@ http://research.microsoft.com/en-us/um/beijing/projects/letor/LETOR4.0/Data/MQ20
 
 """
 
-
 import os
 import random
 import functools
@@ -31,7 +30,6 @@ import rarfile
 from common import download
 import numpy as np
 
-
 # URL = "http://research.microsoft.com/en-us/um/beijing/projects/letor/LETOR4.0/Data/MQ2007.rar"
 URL = "http://www.bigdatalab.ac.cn/benchmark/upload/download_source/7b6dbbe2-842c-11e4-a536-bcaec51b9163_MQ2007.rar"
 MD5 = "7be1640ae95c6408dab0ae7207bdc706"
@@ -63,8 +61,12 @@ class Query(object):
   description : string
     comment section in query doc pair data
   """
-  def __init__(self, query_id=-1, relevance_score=-1,
-               feature_vector=None, description=""):
+
+    def __init__(self,
+                 query_id=-1,
+                 relevance_score=-1,
+                 feature_vector=None,
+                 description=""):
         self.query_id = query_id
         self.relevance_score = relevance_score
         if feature_vector is None:
@@ -74,7 +76,8 @@ class Query(object):
         self.description = description
 
     def __str__(self):
-    string = "%s %s %s" %(str(self.relevance_score), str(self.query_id), " ".join(str(f) for f in self.feature_vector))
+        string = "%s %s %s" % (str(self.relevance_score), str(self.query_id),
+                               " ".join(str(f) for f in self.feature_vector))
         return string
 
     # @classmethod
@@ -84,9 +87,10 @@ class Query(object):
     """
         comment_position = text.find('#')
         line = text[:comment_position].strip()
-    self.description = text[comment_position+1:].strip()
+        self.description = text[comment_position + 1:].strip()
         parts = line.split()
-    assert(len(parts) == 48), "expect 48 space split parts, get %d" %(len(parts))
+        assert (len(parts) == 48), "expect 48 space split parts, get %d" % (
+            len(parts))
         # format : 0 qid:10 1:0.000272 2:0.000000 .... 
         self.relevance_score = int(parts[0])
         self.query_id = int(parts[1].split(':')[1])
@@ -95,10 +99,12 @@ class Query(object):
             self.feature_vector.append(float(pair[1]))
         return self
 
+
 class QueryList(object):
     """
   group query into list, every item in list is a Query
   """
+
     def __init__(self, querylist=None):
         self.query_id = -1
         if querylist is None:
@@ -122,7 +128,7 @@ class QueryList(object):
     def _correct_ranking_(self):
         if self.querylist is None:
             return
-    self.querylist.sort(key=lambda x:x.relevance_score, reverse=True)
+        self.querylist.sort(key=lambda x: x.relevance_score, reverse=True)
 
     def _add_query(self, query):
         if self.query_id == -1:
@@ -133,7 +139,6 @@ class QueryList(object):
         self.querylist.append(query)
 
 
-
 def gen_pair(querylist, partial_order="full"):
     """
   gen pair for pair-wise learning to rank algorithm
@@ -157,23 +162,29 @@ def gen_pair(querylist, partial_order="full"):
         for i, query_left in enumerate(querylist):
             for j, query_right in enumerate(querylist):
                 if query_left.relevance_score > query_right.relevance_score:
-          yield 1, np.array(query_left.feature_vector), np.array(query_right.feature_vector)
+                    yield 1, np.array(query_left.feature_vector), np.array(
+                        query_right.feature_vector)
                 else:
-          yield 1, np.array(query_left.feature_vector), np.array(query_right.feature_vector)
+                    yield 1, np.array(query_left.feature_vector), np.array(
+                        query_right.feature_vector)
 
     elif partial_order == "neighbour":
         # C(n)
         k = 0
-    while k < len(querylist)-1:
+        while k < len(querylist) - 1:
             query_left = querylist[k]
-      query_right = querylist[k+1]
+            query_right = querylist[k + 1]
             if query_left.relevance_score > query_right.relevance_score:
-        yield 1, np.array(query_left.feature_vector), np.array(query_right.feature_vector)
+                yield 1, np.array(query_left.feature_vector), np.array(
+                    query_right.feature_vector)
             else:
-        yield 1, np.array(query_left.feature_vector), np.array(query_right.feature_vector)
+                yield 1, np.array(query_left.feature_vector), np.array(
+                    query_right.feature_vector)
             k += 1
     else:
-    raise ValueError("unsupport parameter of partial_order, Only can be neighbour or full")
+        raise ValueError(
+            "unsupport parameter of partial_order, Only can be neighbour or full"
+        )
 
 
 def gen_list(querylist):
@@ -190,19 +201,17 @@ def gen_list(querylist):
   """
     if not isinstance(querylist, QueryList):
         querylist = QueryList(querylist)
-  querylist._correct_ranking_()
+    # querylist._correct_ranking_()
     relevance_score_list = [query.relevance_score for query in querylist]
     feature_vector_list = [query.feature_vector for query in querylist]
-  # yield np.array(relevance_score_list).T, np.array(feature_vector_list)
-  for i in range(len(querylist)):
-    yield relevance_score_list[i], np.array(feature_vector_list[i])
+    yield np.array(relevance_score_list).T, np.array(feature_vector_list)
 
 
 def load_from_text(filepath, shuffle=True, fill_missing=-1):
     """
   parse data file into querys
   """
-  prev_query_id = -1;
+    prev_query_id = -1
     querylists = []
     querylist = None
     fn = __initialize_meta_info__()
@@ -235,23 +244,27 @@ def __reader__(filepath, format="pairwise", shuffle=True, fill_missing=-1):
     label query_left, query_right  # format = "pairwise"
     label querylist # format = "listwise"
   """
-  querylists = load_from_text(filepath, shuffle=shuffle, fill_missing=fill_missing)
+    querylists = load_from_text(
+        filepath, shuffle=shuffle, fill_missing=fill_missing)
     for querylist in querylists:
         if format == "pairwise":
             for pair in gen_pair(querylist):
                 yield pair
         elif format == "listwise":
-      # yield next(gen_list(querylist))
-      for instance in gen_list(querylist):
-        yield instance
+            yield next(gen_list(querylist))
+
 
-train = functools.partial(__reader__,filepath="MQ2007/MQ2007/Fold1/train.txt")
+train = functools.partial(__reader__, filepath="MQ2007/MQ2007/Fold1/train.txt")
 test = functools.partial(__reader__, filepath="MQ2007/MQ2007/Fold1/test.txt")
 
 
 def fetch():
     return download(URL, "MQ2007", MD5)
 
+
 if __name__ == "__main__":
     fetch()
-
+    for i, (score,
+            samples) in enumerate(train(
+                format="listwise", shuffle=False)):
+        np.savetxt("query_%d" % (i), score, fmt="%.2f")