这个问题源于Run a function on each element in a dataframe column of lists,它回答了一个问题,在这个问题中,我有几个函数在列表列中的每个元素上运行,并生成一个分数(func_results
),如下所示:
col1 col2 func_results
0 MAX [MAX, amx, akd] [('MAX',1.0),('amx',0.89),('akd',0.56)]
1 Sam ['Sam','sammy','samsam'] [('Sam',1.0),('sammy',0.91), ('samsam',0.88)]
2 Larry ['lar','lair','larrylamo'] [('lar',0.91),('larrylamo',0.91), ('lair',0.83)]
此^df的可执行代码-您需要首先从下面运行所有函数:
data = {'col1': ['MAX', 'Sam', 'Larry'],
'col2': ["['MAX', 'amx', 'akd']", "['Sam','sammy','samsam']", "['lar','lair','larrylamo']"],
# 'func_results': ["[('MAX',1.0),('amx',0.89),('akd',0.56)]", "[('Sam',1.0),('sammy',0.91), ('samsam',0.88)]", "[('lar',0.91),('larrylamo',0.91), ('lair',0.83)]"]
}
# df1 = pd.DataFrame (data, columns = ['col1','col2','func_results'])
df1 = pd.DataFrame (data, columns = ['col1','col2'])
df1['col2'] = df1.col2.apply(literal_eval)
df1['func_results'] = df1.agg(lambda x: get_top_matches(*x), axis=1)
df1
现在,当col2
不包含任何列表,而每行只包含一个字符串时,我需要运行相同的函数集,就像这样df:
col1 col2
0 abc co AAP akj
1 kdj fuj ddd
2 bac ADO asd
此df的可执行文件:
data = {'col1': ['abc co', 'kdj', 'bac'],
'col2': ['AAP akj', 'fuj ddd', 'ADO asd']
}
df3 = pd.DataFrame (data, columns = ['col1','col2'])
df3
功能:
#jaro version
def sort_token_alphabetically(word):
token = re.split('[,. ]', word)
sorted_token = sorted(token)
return ' '.join(sorted_token)
def get_jaro_distance(first, second, winkler=True, winkler_ajustment=True,
scaling=0.1, sort_tokens=True):
"""
:param first: word to calculate distance for
:param second: word to calculate distance with
:param winkler: same as winkler_ajustment
:param winkler_ajustment: add an adjustment factor to the Jaro of the distance
:param scaling: scaling factor for the Winkler adjustment
:return: Jaro distance adjusted (or not)
"""
if sort_tokens:
first = sort_token_alphabetically(first)
second = sort_token_alphabetically(second)
if not first or not second:
raise JaroDistanceException(
"Cannot calculate distance from NoneType ({0}, {1})".format(
first.__class__.__name__,
second.__class__.__name__))
jaro = _score(first, second)
cl = min(len(_get_prefix(first, second)), 4)
if all([winkler, winkler_ajustment]): # 0.1 as scaling factor
return round((jaro + (scaling * cl * (1.0 - jaro))) * 100.0) / 100.0
return jaro
def _score(first, second):
shorter, longer = first.lower(), second.lower()
if len(first) > len(second):
longer, shorter = shorter, longer
m1 = _get_matching_characters(shorter, longer)
m2 = _get_matching_characters(longer, shorter)
if len(m1) == 0 or len(m2) == 0:
return 0.0
return (float(len(m1)) / len(shorter) +
float(len(m2)) / len(longer) +
float(len(m1) - _transpositions(m1, m2)) / len(m1)) / 3.0
def _get_diff_index(first, second):
if first == second:
pass
if not first or not second:
return 0
max_len = min(len(first), len(second))
for i in range(0, max_len):
if not first[i] == second[i]:
return i
return max_len
def _get_prefix(first, second):
if not first or not second:
return ""
index = _get_diff_index(first, second)
if index == -1:
return first
elif index == 0:
return ""
else:
return first[0:index]
def _get_matching_characters(first, second):
common = []
limit = math.floor(min(len(first), len(second)) / 2)
for i, l in enumerate(first):
left, right = int(max(0, i - limit)), int(
min(i + limit + 1, len(second)))
if l in second[left:right]:
common.append(l)
second = second[0:second.index(l)] + '*' + second[
second.index(l) + 1:]
return ''.join(common)
def _transpositions(first, second):
return math.floor(
len([(f, s) for f, s in zip(first, second) if not f == s]) / 2.0)
def get_top_matches(reference, value_list, max_results=None):
scores = []
if not max_results:
max_results = len(value_list)
for val in value_list:
score_sorted = get_jaro_distance(reference, val)
score_unsorted = get_jaro_distance(reference, val, sort_tokens=False)
scores.append((val, max(score_sorted, score_unsorted)))
scores.sort(key=lambda x: x[1], reverse=True)
return scores[:max_results]
class JaroDistanceException(Exception):
def __init__(self, message):
super(Exception, self).__init__(message)
我只是想让它在col2
不是列表,而是每行一个字符串时运行,并在df中生成一个func_results
列
有什么想法吗
如果需要将
col2
作为一个字符串的列表,则需要将col2
的每个单元格包装到列表中,并调用get_top_matches
,如下所示:相关问题 更多 >
编程相关推荐