1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
|
# Copyright (c) 2017 Weitian LI <weitian@aaronly.me>
# MIT license
"""
Data structure/set utilities.
"""
import logging
from collections import Iterable
import pandas as pd
logger = logging.getLogger(__name__)
def _flatten_list(l):
"""
Flatten an arbitrarily nested list.
Credit
------
* Flatten (an irregular) list of lists
https://stackoverflow.com/a/2158532
"""
for el in l:
if isinstance(el, Iterable) and not isinstance(el, (str, bytes)):
yield from _flatten_list(el)
else:
yield el
def dictlist_to_dataframe(dictlist, keys=None):
"""
Convert the data in format of list of dictionaries to be a Pandas
DataFrame by flattening the dictionary keys into columns.
NOTE
----
If the item ``key`` of the dictionary has value of a list/vector,
then it is split into multiple columns named as ``key[0], key[1], ...``.
Parameters
----------
dictlist : list[dict]
The input data to be converted, is a list of dictionaries, with
each member dictionary has the same format/structure.
NOTE: The dictionary may have items with list/vector as the values,
but other more complex items (e.g., nested dictionary) is not
allowed and supported.
keys : list[str], optional
The list of dictionary items to be selected for conversion.
Default: convert all dictionary items.
Returns
-------
dataframe : `~pandas.DataFrame`
The converted Pandas DataFrame with columns be the dictionary
item keys.
"""
d0 = dictlist[0]
if keys is None:
keys = list(d0.keys())
logger.info("DataFrame conversion selected keys: {0}".format(keys))
columns = []
for k in keys:
v = d0[k]
if isinstance(v, Iterable) and not isinstance(v, (str, bytes)):
columns += ["%s[%d]" % (k, i) for i in range(len(v))]
else:
columns.append(k)
logger.info("DataFrame number of columns: %d" % len(columns))
logger.debug("DataFrame columns: {0}".format(columns))
data = []
for d in dictlist:
dv = [d[k] for k in keys]
dv2 = list(_flatten_list(dv))
data.append(dv2)
dataframe = pd.DataFrame(data, columns=columns)
return dataframe
|
