如何用Python实现列表去重?

方式

## 1. 新建列表,如果新列表中不存在,则添加到新列表。 def unique(data):     new_list = []     for item in data:         if item not in new_list:             new_list.append(item)     return new_list   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("new_list + not in data:", unique(data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")  # result $ python -V Python 2.7.16 $ python unique.py  (&#39;for list + not in. data:&#39;, [&#39;a&#39;, 1, 2, &#39;b&#39;]) time:0.0441074371338 ms  ## 2. 新建列表。根据下标判断是否存在新列表中,如果新列表中不存在则添加到新列表。 def unique(data):     new_list = []     for i in range(len(data)):         if data[i] not in new_list:             new_list.append(data[i])     return new_list   ## 2.1 新建列表,使用列表推导来去重。是前一种的简写。 def unique(data):     new_list = []     [new_list.append(i) for i in data if not i in new_list]     return new_list  # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("for range + not in. data:", unique(data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 3. 通过index找不到该项,则追加到新列表中。index找不到会报错,因此放在异常处理里。 def unique(data):     new_list = []     for i in range(len(data)):         item = data[i]         try:             if (new_list.index(item) < 0):                 print(&#39;new_list:&#39;, new_list)         except ValueError:             new_list.append(item)     return new_list   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("list index + except:", unique(data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 4. 新建列表,两个循环。如果内循环与外循环项相同,且下标相同就添加到新列表,其余忽略 def unique(data):     new_list = []     for i in range(len(data)):         j = 0         while j <= i:             if data[i] == data[j]:                 if i == j:                     new_list.append(data[i])                 break             j += 1     return new_list  # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("new list + for. new_list:", unique(data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 5. 在原有列表上移除重复项目。自后往前遍历,逐个与前面项比较,如果值相同且下标相同,则移除当前项。 def unique(data):     l = len(data)     while (l > 0):         l -= 1         i = l         while i > 0:             i -= 1             if data[i] == data[l]:                 del data[l]                 break     return data  # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("one list while. last -> first result. data:", unique(data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 6. 在原有列表上移除重复项目。自前往后遍历,逐个与后面项比较,如果值相同且下标相同,则移除当前项。 def unique(data):     l = len(data)     i = 0     while i < l:         j = i + 1         while j < l:             if data[i] == data[j]:                 del data[j]                 l -= 1                 i -= 1                 break             j += 1         i += 1     return data   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("one list while. first -> last result. data:", unique(data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 7. 新建列表。遍历列表,利用index比较出现的位置,如果出现在第一次的位置则追加到新数组。 def unique(data):     new_list = []     for i in range(len(data)):         if i == data.index(data[i]):             new_list.append(data[i])     return new_list   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("for range + index. data:", unique(data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 8. 利用字典属性唯一性来实现去重复。 def unique(data):     obj = {}     for item in data:         obj[item] = item     return obj.values()   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("list + dict:", unique(data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 或者直接通过dict.fromkeys来实现 print("dict fromkeys:", dict.fromkeys(data).keys())  ## 9. 利用filter函数,即把不符合条件的过滤掉。这里filter不支持下标,因此需要借助外部列表存储不重复项 def uniq(item):     i = data.index(item)     if (item not in new_list):         new_list.append(item)         return True     return False def unique(item):     if obj.get(item) == None:         obj[item] = item         return True     return False   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() new_list = [] print(&#39;filter + list + not in: &#39;, filter(uniq, data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 10. 利用字典结合过滤来实现去重复。 def unique(item):     if obj.get(item) == None:         obj[item] = item         return True     return False   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() obj = {} print("filter + dict + get:", filter(unique, data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 11. 利用map来实现去重复。与map与filter类似,是一个高阶函数。可以针对其中项逐个修改操作。 ## 与filter不同map会保留原有项目,并不会删除,因此值可以改为None,然后再过滤掉。 def unique(item):     if item not in new_list:         new_list.append(item)         return item     return None   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] new_list = [] start_time = time.time()  print("list from Map:", filter(lambda item: item != None, map(unique, data))) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 12. 利用set数据结构里key的唯一性来去重复 data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] print("from Set:", list(set(data))) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 13. 提前排序,从后向前遍历,将当前项与前一项对比,如果重复则移除当前项 def unique(data):     data.sort()     l = len(data)     while (l > 0):         l -= 1         if (data[l] == data[l - 1]):             data.remove(data[l])     return data   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("sort + remove:", unique(data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 14. 提前排序,自前往后遍历,将当前项与后一项对比,如果重复则移除当前项 def unique(data):     """      in python 3: TypeError: &#39;<&#39; not supported between instances of &#39;int&#39; and &#39;str&#39;      need to keep the same Type of member in List     """     data.sort()     l = len(data) - 1     i = 0     while i < l:         if (data[i] == data[i + 1]):             del data[i]             i -= 1             l -= 1         i += 1     return data   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("sort+del ASE:", unique(data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 15. 利用reduce函数来去重复。reduce具有累计的作用,判断如果不在累计结果中出现,则追加到结果中。 import functools   def unique(data):     new_list = []      def foo(result, item):         if isinstance(result, list) == False:             result = [result]         return result if item in result else result + [item]      return functools.reduce(foo, data)   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("functools.reduce:", unique(data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 16. 利用递归调用来去重复。递归自后往前逐个调用,当长度为1时终止。 ## 当后一项与前任一项相同说明有重复,则删除当前项。相当于利用自我调用来替换循环 def recursion_unique(data, len):     if (len <= 1):         return data      l = len     last = l - 1     is_repeat = False      while (l > 1):         l -= 1         if (data[last] == data[l - 1]):             is_repeat = True             break      if (is_repeat):         del data[last]      return recursion_unique(data, len - 1)   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("recursion_unique:", recursion_unique(data, len(data))) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 17. 利用递归调用来去重复的另外一种方式。递归自后往前逐个调用,当长度为1时终止。 ## 与上一个递归不同,这里将不重复的项目作为结果拼接起来 def recursion_unique_new(data, len):     if (len <= 1):         return data      l = len     last = l - 1     is_repeat = False     while (l > 1):         l -= 1         if (data[last] == data[l - 1]):             is_repeat = True             break      if (is_repeat):         del data[last:]         result = []     else:         result = [data[last]]      return recursion_unique_new(data, len - 1) + result   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("recursion_unique_new:", recursion_unique_new(data, len(data))) print("time:" + str((time.time() - start_time) * 1000) + " ms")  ## 18. 利用numpy lib库. 需提前安装 `pip install numpy` import numpy as np   def unique(data):     res = np.array(data)     return list(np.unique(res))   # test data = [&#39;a&#39;, &#39;a&#39;, 1, 1, 2, 2, &#39;b&#39;, &#39;b&#39;, 2, 1] start_time = time.time() print("import numpy as np.unique:", unique(data)) print("time:" + str((time.time() - start_time) * 1000) + " ms")
Python如何实现列表去重复项

以上就是如何用Python实现列表去重?的详细内容,更多请关注其它相关文章!