python - 无法从字典创建 pd.Series |类型错误 : 'values' is not ordered

Question

出于某种原因，我无法从该字典创建 pd.Series 对象。我和另一个非常相似的人一起做了。

注意:更新于 2018-June-04看起来这有一个 GitHub 问题: https://github.com/pandas-dev/pandas/issues/15457

pd.__version__
'0.23.0'


import pandas as pd
from numpy import array
import numpy as np

param_index = OrderedDict([((('criterion', 'gini'), ('max_features', 'log2'), ('min_samples_leaf', 1)), array([  0,  40,  80, 120, 160, 200])), ((('criterion', 'gini'), ('max_features', 'log2'), ('min_samples_leaf', 2)), array([  1,  41,  81, 121, 161, 201])), ((('criterion', 'gini'), ('max_features', 'log2'), ('min_samples_leaf', 3)), array([  2,  42,  82, 122, 162, 202])), ((('criterion', 'gini'), ('max_features', 'log2'), ('min_samples_leaf', 5)), array([  3,  43,  83, 123, 163, 203])), ((('criterion', 'gini'), ('max_features', 'log2'), ('min_samples_leaf', 8)), array([  4,  44,  84, 124, 164, 204])), ((('criterion', 'gini'), ('max_features', 'sqrt'), ('min_samples_leaf', 1)), array([  5,  45,  85, 125, 165, 205])), ((('criterion', 'gini'), ('max_features', 'sqrt'), ('min_samples_leaf', 2)), array([  6,  46,  86, 126, 166, 206])), ((('criterion', 'gini'), ('max_features', 'sqrt'), ('min_samples_leaf', 3)), array([  7,  47,  87, 127, 167, 207])), ((('criterion', 'gini'), ('max_features', 'sqrt'), ('min_samples_leaf', 5)), array([  8,  48,  88, 128, 168, 208])), ((('criterion', 'gini'), ('max_features', 'sqrt'), ('min_samples_leaf', 8)), array([  9,  49,  89, 129, 169, 209])), ((('criterion', 'gini'), ('max_features', None), ('min_samples_leaf', 1)), array([ 10,  50,  90, 130, 170, 210])), ((('criterion', 'gini'), ('max_features', None), ('min_samples_leaf', 2)), array([ 11,  51,  91, 131, 171, 211])), ((('criterion', 'gini'), ('max_features', None), ('min_samples_leaf', 3)), array([ 12,  52,  92, 132, 172, 212])), ((('criterion', 'gini'), ('max_features', None), ('min_samples_leaf', 5)), array([ 13,  53,  93, 133, 173, 213])), ((('criterion', 'gini'), ('max_features', None), ('min_samples_leaf', 8)), array([ 14,  54,  94, 134, 174, 214])), ((('criterion', 'gini'), ('max_features', 0.382), ('min_samples_leaf', 1)), array([ 15,  55,  95, 135, 175, 215])), ((('criterion', 'gini'), ('max_features', 0.382), ('min_samples_leaf', 2)), array([ 16,  56,  96, 136, 176, 216])), ((('criterion', 'gini'), ('max_features', 0.382), ('min_samples_leaf', 3)), array([ 17,  57,  97, 137, 177, 217])), ((('criterion', 'gini'), ('max_features', 0.382), ('min_samples_leaf', 5)), array([ 18,  58,  98, 138, 178, 218])), ((('criterion', 'gini'), ('max_features', 0.382), ('min_samples_leaf', 8)), array([ 19,  59,  99, 139, 179, 219])), ((('criterion', 'entropy'), ('max_features', 'log2'), ('min_samples_leaf', 1)), array([ 20,  60, 100, 140, 180, 220])), ((('criterion', 'entropy'), ('max_features', 'log2'), ('min_samples_leaf', 2)), array([ 21,  61, 101, 141, 181, 221])), ((('criterion', 'entropy'), ('max_features', 'log2'), ('min_samples_leaf', 3)), array([ 22,  62, 102, 142, 182, 222])), ((('criterion', 'entropy'), ('max_features', 'log2'), ('min_samples_leaf', 5)), array([ 23,  63, 103, 143, 183, 223])), ((('criterion', 'entropy'), ('max_features', 'log2'), ('min_samples_leaf', 8)), array([ 24,  64, 104, 144, 184, 224])), ((('criterion', 'entropy'), ('max_features', 'sqrt'), ('min_samples_leaf', 1)), array([ 25,  65, 105, 145, 185, 225])), ((('criterion', 'entropy'), ('max_features', 'sqrt'), ('min_samples_leaf', 2)), array([ 26,  66, 106, 146, 186, 226])), ((('criterion', 'entropy'), ('max_features', 'sqrt'), ('min_samples_leaf', 3)), array([ 27,  67, 107, 147, 187, 227])), ((('criterion', 'entropy'), ('max_features', 'sqrt'), ('min_samples_leaf', 5)), array([ 28,  68, 108, 148, 188, 228])), ((('criterion', 'entropy'), ('max_features', 'sqrt'), ('min_samples_leaf', 8)), array([ 29,  69, 109, 149, 189, 229])), ((('criterion', 'entropy'), ('max_features', None), ('min_samples_leaf', 1)), array([ 30,  70, 110, 150, 190, 230])), ((('criterion', 'entropy'), ('max_features', None), ('min_samples_leaf', 2)), array([ 31,  71, 111, 151, 191, 231])), ((('criterion', 'entropy'), ('max_features', None), ('min_samples_leaf', 3)), array([ 32,  72, 112, 152, 192, 232])), ((('criterion', 'entropy'), ('max_features', None), ('min_samples_leaf', 5)), array([ 33,  73, 113, 153, 193, 233])), ((('criterion', 'entropy'), ('max_features', None), ('min_samples_leaf', 8)), array([ 34,  74, 114, 154, 194, 234])), ((('criterion', 'entropy'), ('max_features', 0.382), ('min_samples_leaf', 1)), array([ 35,  75, 115, 155, 195, 235])), ((('criterion', 'entropy'), ('max_features', 0.382), ('min_samples_leaf', 2)), array([ 36,  76, 116, 156, 196, 236])), ((('criterion', 'entropy'), ('max_features', 0.382), ('min_samples_leaf', 3)), array([ 37,  77, 117, 157, 197, 237])), ((('criterion', 'entropy'), ('max_features', 0.382), ('min_samples_leaf', 5)), array([ 38,  78, 118, 158, 198, 238])), ((('criterion', 'entropy'), ('max_features', 0.382), ('min_samples_leaf', 8)), array([ 39,  79, 119, 159, 199, 239]))])


pd.Series(list(param_index.values()), index=param_index.keys())


---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/algorithms.py in factorize(values, sort, order, na_sentinel, size_hint)
    634         try:
--> 635             order = uniques.argsort()
    636             order2 = order.argsort()

TypeError: '<' not supported between instances of 'NoneType' and 'str'

During handling of the above exception, another exception occurred:

TypeError                                 Traceback (most recent call last)
~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/sorting.py in safe_sort(values, labels, na_sentinel, assume_unique)
    445         try:
--> 446             sorter = values.argsort()
    447             ordered = values.take(sorter)

TypeError: '<' not supported between instances of 'NoneType' and 'str'

During handling of the above exception, another exception occurred:

TypeError                                 Traceback (most recent call last)
~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/arrays/categorical.py in __init__(self, values, categories, ordered, dtype, fastpath)
    344             try:
--> 345                 codes, categories = factorize(values, sort=True)
    346             except TypeError:

~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/util/_decorators.py in wrapper(*args, **kwargs)
    176                     kwargs[new_arg_name] = new_arg_value
--> 177             return func(*args, **kwargs)
    178         return wrapper

~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/algorithms.py in factorize(values, sort, order, na_sentinel, size_hint)
    642                                         na_sentinel=na_sentinel,
--> 643                                         assume_unique=True)
    644 

~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/sorting.py in safe_sort(values, labels, na_sentinel, assume_unique)
    449             # try this anyway
--> 450             ordered = sort_mixed(values)
    451 

~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/sorting.py in sort_mixed(values)
    435                            dtype=bool)
--> 436         nums = np.sort(values[~str_pos])
    437         strs = np.sort(values[str_pos])

~/anaconda/envs/python3/lib/python3.6/site-packages/numpy/core/fromnumeric.py in sort(a, axis, kind, order)
    846         a = asanyarray(a).copy(order="K")
--> 847     a.sort(axis=axis, kind=kind, order=order)
    848     return a

TypeError: '<' not supported between instances of 'NoneType' and 'str'

During handling of the above exception, another exception occurred:

TypeError                                 Traceback (most recent call last)
<ipython-input-72-1f46691300f8> in <module>()
      1 param_index = OrderedDict([((('criterion', 'gini'), ('max_features', 'log2'), ('min_samples_leaf', 1)), array([  0,  40,  80, 120, 160, 200])), ((('criterion', 'gini'), ('max_features', 'log2'), ('min_samples_leaf', 2)), array([  1,  41,  81, 121, 161, 201])), ((('criterion', 'gini'), ('max_features', 'log2'), ('min_samples_leaf', 3)), array([  2,  42,  82, 122, 162, 202])), ((('criterion', 'gini'), ('max_features', 'log2'), ('min_samples_leaf', 5)), array([  3,  43,  83, 123, 163, 203])), ((('criterion', 'gini'), ('max_features', 'log2'), ('min_samples_leaf', 8)), array([  4,  44,  84, 124, 164, 204])), ((('criterion', 'gini'), ('max_features', 'sqrt'), ('min_samples_leaf', 1)), array([  5,  45,  85, 125, 165, 205])), ((('criterion', 'gini'), ('max_features', 'sqrt'), ('min_samples_leaf', 2)), array([  6,  46,  86, 126, 166, 206])), ((('criterion', 'gini'), ('max_features', 'sqrt'), ('min_samples_leaf', 3)), array([  7,  47,  87, 127, 167, 207])), ((('criterion', 'gini'), ('max_features', 'sqrt'), ('min_samples_leaf', 5)), array([  8,  48,  88, 128, 168, 208])), ((('criterion', 'gini'), ('max_features', 'sqrt'), ('min_samples_leaf', 8)), array([  9,  49,  89, 129, 169, 209])), ((('criterion', 'gini'), ('max_features', None), ('min_samples_leaf', 1)), array([ 10,  50,  90, 130, 170, 210])), ((('criterion', 'gini'), ('max_features', None), ('min_samples_leaf', 2)), array([ 11,  51,  91, 131, 171, 211])), ((('criterion', 'gini'), ('max_features', None), ('min_samples_leaf', 3)), array([ 12,  52,  92, 132, 172, 212])), ((('criterion', 'gini'), ('max_features', None), ('min_samples_leaf', 5)), array([ 13,  53,  93, 133, 173, 213])), ((('criterion', 'gini'), ('max_features', None), ('min_samples_leaf', 8)), array([ 14,  54,  94, 134, 174, 214])), ((('criterion', 'gini'), ('max_features', 0.382), ('min_samples_leaf', 1)), array([ 15,  55,  95, 135, 175, 215])), ((('criterion', 'gini'), ('max_features', 0.382), ('min_samples_leaf', 2)), array([ 16,  56,  96, 136, 176, 216])), ((('criterion', 'gini'), ('max_features', 0.382), ('min_samples_leaf', 3)), array([ 17,  57,  97, 137, 177, 217])), ((('criterion', 'gini'), ('max_features', 0.382), ('min_samples_leaf', 5)), array([ 18,  58,  98, 138, 178, 218])), ((('criterion', 'gini'), ('max_features', 0.382), ('min_samples_leaf', 8)), array([ 19,  59,  99, 139, 179, 219])), ((('criterion', 'entropy'), ('max_features', 'log2'), ('min_samples_leaf', 1)), array([ 20,  60, 100, 140, 180, 220])), ((('criterion', 'entropy'), ('max_features', 'log2'), ('min_samples_leaf', 2)), array([ 21,  61, 101, 141, 181, 221])), ((('criterion', 'entropy'), ('max_features', 'log2'), ('min_samples_leaf', 3)), array([ 22,  62, 102, 142, 182, 222])), ((('criterion', 'entropy'), ('max_features', 'log2'), ('min_samples_leaf', 5)), array([ 23,  63, 103, 143, 183, 223])), ((('criterion', 'entropy'), ('max_features', 'log2'), ('min_samples_leaf', 8)), array([ 24,  64, 104, 144, 184, 224])), ((('criterion', 'entropy'), ('max_features', 'sqrt'), ('min_samples_leaf', 1)), array([ 25,  65, 105, 145, 185, 225])), ((('criterion', 'entropy'), ('max_features', 'sqrt'), ('min_samples_leaf', 2)), array([ 26,  66, 106, 146, 186, 226])), ((('criterion', 'entropy'), ('max_features', 'sqrt'), ('min_samples_leaf', 3)), array([ 27,  67, 107, 147, 187, 227])), ((('criterion', 'entropy'), ('max_features', 'sqrt'), ('min_samples_leaf', 5)), array([ 28,  68, 108, 148, 188, 228])), ((('criterion', 'entropy'), ('max_features', 'sqrt'), ('min_samples_leaf', 8)), array([ 29,  69, 109, 149, 189, 229])), ((('criterion', 'entropy'), ('max_features', None), ('min_samples_leaf', 1)), array([ 30,  70, 110, 150, 190, 230])), ((('criterion', 'entropy'), ('max_features', None), ('min_samples_leaf', 2)), array([ 31,  71, 111, 151, 191, 231])), ((('criterion', 'entropy'), ('max_features', None), ('min_samples_leaf', 3)), array([ 32,  72, 112, 152, 192, 232])), ((('criterion', 'entropy'), ('max_features', None), ('min_samples_leaf', 5)), array([ 33,  73, 113, 153, 193, 233])), ((('criterion', 'entropy'), ('max_features', None), ('min_samples_leaf', 8)), array([ 34,  74, 114, 154, 194, 234])), ((('criterion', 'entropy'), ('max_features', 0.382), ('min_samples_leaf', 1)), array([ 35,  75, 115, 155, 195, 235])), ((('criterion', 'entropy'), ('max_features', 0.382), ('min_samples_leaf', 2)), array([ 36,  76, 116, 156, 196, 236])), ((('criterion', 'entropy'), ('max_features', 0.382), ('min_samples_leaf', 3)), array([ 37,  77, 117, 157, 197, 237])), ((('criterion', 'entropy'), ('max_features', 0.382), ('min_samples_leaf', 5)), array([ 38,  78, 118, 158, 198, 238])), ((('criterion', 'entropy'), ('max_features', 0.382), ('min_samples_leaf', 8)), array([ 39,  79, 119, 159, 199, 239]))])
----> 2 pd.Series(list(param_index.values()), index=param_index.keys())

~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/series.py in __init__(self, data, index, dtype, name, copy, fastpath)
    180 
    181             if index is not None:
--> 182                 index = _ensure_index(index)
    183 
    184             if data is None:

~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/indexes/base.py in _ensure_index(index_like, copy)
   4955             index_like = copy(index_like)
   4956 
-> 4957     return Index(index_like)
   4958 
   4959 

~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/indexes/base.py in __new__(cls, data, dtype, copy, name, fastpath, tupleize_cols, **kwargs)
    433                     from .multi import MultiIndex
    434                     return MultiIndex.from_tuples(
--> 435                         data, names=name or kwargs.get('names'))
    436             # other iterable of some kind
    437             subarr = com._asarray_tuplesafe(data, dtype=object)

~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/indexes/multi.py in from_tuples(cls, tuples, sortorder, names)
   1354             arrays = lzip(*tuples)
   1355 
-> 1356         return MultiIndex.from_arrays(arrays, sortorder=sortorder, names=names)
   1357 
   1358     @classmethod

~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/indexes/multi.py in from_arrays(cls, arrays, sortorder, names)
   1298         from pandas.core.arrays.categorical import _factorize_from_iterables
   1299 
-> 1300         labels, levels = _factorize_from_iterables(arrays)
   1301         if names is None:
   1302             names = [getattr(arr, "name", None) for arr in arrays]

~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/arrays/categorical.py in _factorize_from_iterables(iterables)
   2541         # For consistency, it should return a list of 2 lists.
   2542         return [[], []]
-> 2543     return map(list, lzip(*[_factorize_from_iterable(it) for it in iterables]))

~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/arrays/categorical.py in <listcomp>(.0)
   2541         # For consistency, it should return a list of 2 lists.
   2542         return [[], []]
-> 2543     return map(list, lzip(*[_factorize_from_iterable(it) for it in iterables]))

~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/arrays/categorical.py in _factorize_from_iterable(values)
   2513         codes = values.codes
   2514     else:
-> 2515         cat = Categorical(values, ordered=True)
   2516         categories = cat.categories
   2517         codes = cat.codes

~/anaconda/envs/python3/lib/python3.6/site-packages/pandas/core/arrays/categorical.py in __init__(self, values, categories, ordered, dtype, fastpath)
    349                     # raise, as we don't have a sortable data structure and so
    350                     # the user should give us one by specifying categories
--> 351                     raise TypeError("'values' is not ordered, please "
    352                                     "explicitly specify the categories order "
    353                                     "by passing in a categories argument.")

TypeError: 'values' is not ordered, please explicitly specify the categories order by passing in a categories argument.

Answer 1

我认为您只需要展平索引列表即可。

In [1]: s = pd.Series(data=param_index.values(), index=[x[0] for x in param_index.keys()])
In [2]: s.head()
Out[2]:
    (criterion, gini)    [0, 40, 80, 120, 160, 200]
    (criterion, gini)    [1, 41, 81, 121, 161, 201]
    (criterion, gini)    [2, 42, 82, 122, 162, 202]
    (criterion, gini)    [3, 43, 83, 123, 163, 203]
    (criterion, gini)    [4, 44, 84, 124, 164, 204]
    dtype: object