Develop Reference

Dask IndexError: list index out of range

So i have folder called "data" say containing many CSV files
import dask.dataframe as dd
df = dd.read_csv('data/*.csv')
df.head()
df.column_1.mean().compute()
The above lines of code work perfectly and the dask.compute method does its job. But when i add the "include_path_column=True" parameter to the dd.read_cs() function call, i get the following error:
IndexError: list index out of range
When i expand the error i get
IndexError Traceback (most recent call last)
<ipython-input-129-4be67235bebb> in <module>
----> 1 df['H_hp'].mean().compute()
/anaconda/envs/azureml_py36/lib/python3.6/site-packages/dask/base.py in compute(self, **kwargs)
165 dask.base.compute
166 """
--> 167 (result,) = compute(self, traverse=False, **kwargs)
168 return result
169
/anaconda/envs/azureml_py36/lib/python3.6/site-packages/dask/base.py in compute(*args, **kwargs)
444 )
445
--> 446 dsk = collections_to_dsk(collections, optimize_graph, **kwargs)
447 keys, postcomputes = [], []
448 for x in collections:
/anaconda/envs/azureml_py36/lib/python3.6/site-packages/dask/base.py in collections_to_dsk(collections, optimize_graph, **kwargs)
216 dsk, keys = _extract_graph_and_keys(val)
217 groups[opt] = (dsk, keys)
--> 218 _opt = opt(dsk, keys, **kwargs)
219 _opt_list.append(_opt)
220
/anaconda/envs/azureml_py36/lib/python3.6/site-packages/dask/dataframe/optimize.py in optimize(dsk, keys, **kwargs)
19 dsk = fuse_roots(dsk, keys=flat_keys)
20
---> 21 dsk = ensure_dict(dsk)
22
23 if isinstance(keys, list):
/anaconda/envs/azureml_py36/lib/python3.6/site-packages/dask/utils.py in ensure_dict(d)
1030 dd_id = id(dd)
1031 if dd_id not in seen:
-> 1032 result.update(dd)
1033 seen.add(dd_id)
1034 return result
/anaconda/envs/azureml_py36/lib/python3.6/site-packages/dask/dataframe/io/csv.py in __getitem__(self, key)
80
81 if self.paths is not None:
---> 82 path_info = (self.colname, self.paths[i], self.paths)
83 else:
84 path_info = None
IndexError: list index out of range

getting a type error: str argument expected

The code is for matching using record linkage toolkit. When I am setting the comparison it is giving me the TypeError: str argument expected error.
I don't understand what is wrong with the code:
compare = recordlinkage.Compare()
compare.exact('Sex Global', 'Sex')
compare.exact('Age', 'Age (Yrs) at presentation')
compare.string('ADD_LINE_1', 'Address',
method='levenshtein',
threshold=0.7)
compare.string('CITY', 'City',
threshold=0.8)
compare.string('STATE_C', 'State',
threshold=0.85)
features = compare.compute(combinations, phhs_abnormal, hhsc_copy)
traceback:
TypeError Traceback (most recent call last)
<ipython-input-24-d84008a8ba19> in <module>
13 threshold=0.85)
14 features = compare.compute(combinations, phhs_abnormal,
---> 15 hhsc_copy)
~/.local/lib/python3.7/site-packages/recordlinkage/base.py in compute(self, pairs, x, x_link)
863
864 if self.n_jobs == 1:
--> 865 results = self._compute(pairs, x, x_link)
866 elif self.n_jobs > 1:
867 results = self._compute_parallel(
~/.local/lib/python3.7/site-packages/recordlinkage/base.py in _compute(self, pairs, x, x_link)
727 )
728
--> 729 result = feat._compute(data1, data2)
730 features.append((result, feat.label))
731
~/.local/lib/python3.7/site-packages/recordlinkage/base.py in _compute(self, left_on, right_on)
447 numpy.ndarray objects.
448 """
--> 449 result = self._compute_vectorized(*tuple(left_on + right_on))
450
451 return result
~/.local/lib/python3.7/site-packages/recordlinkage/compare.py in _compute_vectorized(self, s_left, s_right)
148 self.method))
149
--> 150 c = str_sim_alg(s_left, s_right)
151
152 if self.threshold is not None:
~/.local/lib/python3.7/site-packages/recordlinkage/algorithms/string.py in levenshtein_similarity(s1, s2)
62 raise err
63
---> 64 return conc.apply(levenshtein_apply)
65
66
/usr/local/lib/python3.7/dist-packages/pandas/core/series.py in apply(self, func, convert_dtype, args, **kwds)
4040 else:
4041 values = self.astype(object).values
-> 4042 mapped = lib.map_infer(values, f, convert=convert_dtype)
4043
4044 if len(mapped) and isinstance(mapped[0], Series):
pandas/_libs/lib.pyx in pandas._libs.lib.map_infer()
~/.local/lib/python3.7/site-packages/recordlinkage/algorithms/string.py in levenshtein_apply(x)
60 return np.nan
61 else:
---> 62 raise err
63
64 return conc.apply(levenshtein_apply)
~/.local/lib/python3.7/site-packages/recordlinkage/algorithms/string.py in levenshtein_apply(x)
54
55 try:
---> 56 return 1 - jellyfish.levenshtein_distance(x[0], x[1]) \
57 / np.max([len(x[0]), len(x[1])])
58 except Exception as err:
TypeError: str argument expected

How to display a sequence of numbers in column-major order?

Program description:
Find all the prime numbers between 1 and 4,027 and print them in a table which
"reads down", using as few rows as possible, and using as few sheets of paper
as possible. (This is because I have to print them out on paper to turn it in.) All numbers should be right-justified in their column. The height
of the columns should all be the same, except for perhaps the last column,
which might have a few blank entries towards its bottom row.
The plan for my first function is to find all prime numbers between the range above and put them in a list. Then I want my second function to display the list in a table that reads up to down.
2 23 59
3 29 61
5 31 67
7 37 71
11 41 73
13 43 79
17 47 83
19 53 89
ect...
This all I've been able to come up with myself:
def findPrimes(n):
""" Adds calculated prime numbers to a list. """
prime_list = list()
for number in range(1, n + 1):
prime = True
for i in range(2, number):
if(number % i == 0):
prime = False
if prime:
prime_list.append(number)
return prime_list
def displayPrimes():
pass
print(findPrimes(4027))
I'm not sure how to make a row/column display in Python. I remember using Java in my previous class and we had to use a for loop inside a for loop I believe. Do I have to do something similar to that?

Although I frequently don't answer questions where the original poster hasn't even made an attempt to solve the problem themselves, I decided to make an exception of yours—mostly because I found it an interesting (and surprisingly challenging) problem that required solving a number of somewhat tricky sub-problems.
I also optimized your find_primes() function slightly by taking advantage of some reatively well-know computational shortcuts for calculating them.
For testing and demo purposes, I made the tables only 15 rows high to force more than one page to be generated as shown in the output at the end.
from itertools import zip_longest
import locale
import math
locale.setlocale(locale.LC_ALL, '') # enable locale-specific formatting
def zip_discard(*iterables, _NULL=object()):
""" Like zip_longest() but doesn't fill out all rows to equal length.
https://stackoverflow.com/questions/38054593/zip-longest-without-fillvalue
"""
return [[entry for entry in iterable if entry is not _NULL]
for iterable in zip_longest(*iterables, fillvalue=_NULL)]
def grouper(n, seq):
""" Group elements in sequence into groups of "n" items. """
for i in range(0, len(seq), n):
yield seq[i:i+n]
def tabularize(width, height, numbers):
""" Print list of numbers in column-major tabular form given the dimensions
of the table in characters (rows and columns). Will create multiple
tables of required to display all numbers.
"""
# Determine number of chars needed to hold longest formatted numeric value
gap = 2 # including space between numbers
col_width = len('{:n}'.format(max(numbers))) + gap
# Determine number of columns that will fit within the table's width.
num_cols = width // col_width
chunk_size = num_cols * height # maximum numbers in each table
for i, chunk in enumerate(grouper(chunk_size, numbers), start=1):
print('---- Page {} ----'.format(i))
num_rows = int(math.ceil(len(chunk) / num_cols)) # rounded up
table = zip_discard(*grouper(num_rows, chunk))
for row in table:
print(''.join(('{:{width}n}'.format(num, width=col_width)
for num in row)))
def find_primes(n):
""" Create list of prime numbers from 1 to n. """
prime_list = []
for number in range(1, n+1):
for i in range(2, int(math.sqrt(number)) + 1):
if not number % i: # Evenly divisible?
break # Not prime.
else:
prime_list.append(number)
return prime_list
primes = find_primes(4027)
tabularize(80, 15, primes)
Output:
---- Page 1 ----
1 47 113 197 281 379 463 571 659 761 863
2 53 127 199 283 383 467 577 661 769 877
3 59 131 211 293 389 479 587 673 773 881
5 61 137 223 307 397 487 593 677 787 883
7 67 139 227 311 401 491 599 683 797 887
11 71 149 229 313 409 499 601 691 809 907
13 73 151 233 317 419 503 607 701 811 911
17 79 157 239 331 421 509 613 709 821 919
19 83 163 241 337 431 521 617 719 823 929
23 89 167 251 347 433 523 619 727 827 937
29 97 173 257 349 439 541 631 733 829 941
31 101 179 263 353 443 547 641 739 839 947
37 103 181 269 359 449 557 643 743 853 953
41 107 191 271 367 457 563 647 751 857 967
43 109 193 277 373 461 569 653 757 859 971
---- Page 2 ----
977 1,069 1,187 1,291 1,427 1,511 1,613 1,733 1,867 1,987 2,087
983 1,087 1,193 1,297 1,429 1,523 1,619 1,741 1,871 1,993 2,089
991 1,091 1,201 1,301 1,433 1,531 1,621 1,747 1,873 1,997 2,099
997 1,093 1,213 1,303 1,439 1,543 1,627 1,753 1,877 1,999 2,111
1,009 1,097 1,217 1,307 1,447 1,549 1,637 1,759 1,879 2,003 2,113
1,013 1,103 1,223 1,319 1,451 1,553 1,657 1,777 1,889 2,011 2,129
1,019 1,109 1,229 1,321 1,453 1,559 1,663 1,783 1,901 2,017 2,131
1,021 1,117 1,231 1,327 1,459 1,567 1,667 1,787 1,907 2,027 2,137
1,031 1,123 1,237 1,361 1,471 1,571 1,669 1,789 1,913 2,029 2,141
1,033 1,129 1,249 1,367 1,481 1,579 1,693 1,801 1,931 2,039 2,143
1,039 1,151 1,259 1,373 1,483 1,583 1,697 1,811 1,933 2,053 2,153
1,049 1,153 1,277 1,381 1,487 1,597 1,699 1,823 1,949 2,063 2,161
1,051 1,163 1,279 1,399 1,489 1,601 1,709 1,831 1,951 2,069 2,179
1,061 1,171 1,283 1,409 1,493 1,607 1,721 1,847 1,973 2,081 2,203
1,063 1,181 1,289 1,423 1,499 1,609 1,723 1,861 1,979 2,083 2,207
---- Page 3 ----
2,213 2,333 2,423 2,557 2,687 2,789 2,903 3,037 3,181 3,307 3,413
2,221 2,339 2,437 2,579 2,689 2,791 2,909 3,041 3,187 3,313 3,433
2,237 2,341 2,441 2,591 2,693 2,797 2,917 3,049 3,191 3,319 3,449
2,239 2,347 2,447 2,593 2,699 2,801 2,927 3,061 3,203 3,323 3,457
2,243 2,351 2,459 2,609 2,707 2,803 2,939 3,067 3,209 3,329 3,461
2,251 2,357 2,467 2,617 2,711 2,819 2,953 3,079 3,217 3,331 3,463
2,267 2,371 2,473 2,621 2,713 2,833 2,957 3,083 3,221 3,343 3,467
2,269 2,377 2,477 2,633 2,719 2,837 2,963 3,089 3,229 3,347 3,469
2,273 2,381 2,503 2,647 2,729 2,843 2,969 3,109 3,251 3,359 3,491
2,281 2,383 2,521 2,657 2,731 2,851 2,971 3,119 3,253 3,361 3,499
2,287 2,389 2,531 2,659 2,741 2,857 2,999 3,121 3,257 3,371 3,511
2,293 2,393 2,539 2,663 2,749 2,861 3,001 3,137 3,259 3,373 3,517
2,297 2,399 2,543 2,671 2,753 2,879 3,011 3,163 3,271 3,389 3,527
2,309 2,411 2,549 2,677 2,767 2,887 3,019 3,167 3,299 3,391 3,529
2,311 2,417 2,551 2,683 2,777 2,897 3,023 3,169 3,301 3,407 3,533
---- Page 4 ----
3,539 3,581 3,623 3,673 3,719 3,769 3,823 3,877 3,919 3,967 4,019
3,541 3,583 3,631 3,677 3,727 3,779 3,833 3,881 3,923 3,989 4,021
3,547 3,593 3,637 3,691 3,733 3,793 3,847 3,889 3,929 4,001 4,027
3,557 3,607 3,643 3,697 3,739 3,797 3,851 3,907 3,931 4,003
3,559 3,613 3,659 3,701 3,761 3,803 3,853 3,911 3,943 4,007
3,571 3,617 3,671 3,709 3,767 3,821 3,863 3,917 3,947 4,013

Possible bug with `xarray.Dataset.groupby()`?

I'm using Xarray version 0.8.0, Python 3.5.1, on Mac OS X El Capitan 10.11.6.
The following code works as expected.
id_data_array = xarray.DataArray([280, 306, 280], coords={"index": range(3)})
random = numpy.random.rand(3)
score_data_array = xarray.DataArray(random, coords={"index": range(3)})
score_dataset = xarray.Dataset({"id": id_data_array, "score": score_data_array})
print(score_dataset)
print("======")
print(score_dataset.groupby("id").count())
Output:
<xarray.Dataset>
Dimensions: (index: 3)
Coordinates:
* index (index) int64 0 1 2
Data variables:
id (index) int64 280 306 280
score (index) float64 0.8358 0.7536 0.9495
======
<xarray.Dataset>
Dimensions: (id: 2)
Coordinates:
* id (id) int64 280 306
Data variables:
score (id) int64 2 1
In [ ]:
However, if I change just one little thing, to make the elements of id_data_array all distinct, then there is an error.
Code:
id_data_array = xarray.DataArray([280, 306, 120], coords={"index": range(3)})
random = numpy.random.rand(3)
score_data_array = xarray.DataArray(random, coords={"index": range(3)})
score_dataset = xarray.Dataset({"id": id_data_array, "score": score_data_array})
print(score_dataset)
print("======")
print(score_dataset.groupby("id").count())
Output:
<xarray.Dataset>
Dimensions: (index: 3)
Coordinates:
* index (index) int64 0 1 2
Data variables:
id (index) int64 280 306 120
score (index) float64 0.1353 0.0437 0.1687
======
---------------------------------------------------------------------------
InvalidIndexError Traceback (most recent call last)
<ipython-input-92-cc412270ba2e> in <module>()
5 print(score_dataset)
6 print("======")
----> 7 print(score_dataset.groupby("id").count())
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/common.py in wrapped_func(self, dim, keep_attrs, **kwargs)
44 return self.reduce(func, dim, keep_attrs,
45 numeric_only=numeric_only, allow_lazy=True,
---> 46 **kwargs)
47 return wrapped_func
48
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/groupby.py in reduce(self, func, dim, keep_attrs, **kwargs)
605 def reduce_dataset(ds):
606 return ds.reduce(func, dim, keep_attrs, **kwargs)
--> 607 return self.apply(reduce_dataset)
608
609 def assign(self, **kwargs):
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/groupby.py in apply(self, func, **kwargs)
562 kwargs.pop('shortcut', None) # ignore shortcut if set (for now)
563 applied = (func(ds, **kwargs) for ds in self._iter_grouped())
--> 564 combined = self._concat(applied)
565 result = self._maybe_restore_empty_groups(combined)
566 return result
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/groupby.py in _concat(self, applied)
570 concat_dim, positions = self._infer_concat_args(applied_example)
571
--> 572 combined = concat(applied, concat_dim)
573 reordered = _maybe_reorder(combined, concat_dim, positions)
574 return reordered
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/combine.py in concat(objs, dim, data_vars, coords, compat, positions, indexers, mode, concat_over)
114 raise TypeError('can only concatenate xarray Dataset and DataArray '
115 'objects, got %s' % type(first_obj))
--> 116 return f(objs, dim, data_vars, coords, compat, positions)
117
118
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/combine.py in _dataset_concat(datasets, dim, data_vars, coords, compat, positions)
276 if coord is not None:
277 # add concat dimension last to ensure that its in the final Dataset
--> 278 result[coord.name] = coord
279
280 return result
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/dataset.py in __setitem__(self, key, value)
536 raise NotImplementedError('cannot yet use a dictionary as a key '
537 'to set Dataset values')
--> 538 self.update({key: value})
539
540 def __delitem__(self, key):
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/dataset.py in update(self, other, inplace)
1434 dataset.
1435 """
-> 1436 variables, coord_names, dims = dataset_update_method(self, other)
1437
1438 return self._replace_vars_and_dims(variables, coord_names, dims,
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/merge.py in dataset_update_method(dataset, other)
490 priority_arg = 1
491 indexes = dataset.indexes
--> 492 return merge_core(objs, priority_arg=priority_arg, indexes=indexes)
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/merge.py in merge_core(objs, compat, join, priority_arg, explicit_coords, indexes)
371
372 coerced = coerce_pandas_values(objs)
--> 373 aligned = deep_align(coerced, join=join, copy=False, indexes=indexes)
374 expanded = expand_variable_dicts(aligned)
375
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/alignment.py in deep_align(list_of_variable_maps, join, copy, indexes)
146 out.append(variables)
147
--> 148 aligned = partial_align(*targets, join=join, copy=copy, indexes=indexes)
149
150 for key, aligned_obj in zip(keys, aligned):
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/alignment.py in partial_align(*objects, **kwargs)
109 valid_indexers = dict((k, v) for k, v in joined_indexes.items()
110 if k in obj.dims)
--> 111 result.append(obj.reindex(copy=copy, **valid_indexers))
112 return tuple(result)
113
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/dataset.py in reindex(self, indexers, method, tolerance, copy, **kw_indexers)
1216
1217 variables = alignment.reindex_variables(
-> 1218 self.variables, self.indexes, indexers, method, tolerance, copy=copy)
1219 return self._replace_vars_and_dims(variables)
1220
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/alignment.py in reindex_variables(variables, indexes, indexers, method, tolerance, copy)
218 target = utils.safe_cast_to_index(indexers[name])
219 indexer = index.get_indexer(target, method=method,
--> 220 **get_indexer_kwargs)
221
222 to_shape[name] = len(target)
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/pandas/indexes/base.py in get_indexer(self, target, method, limit, tolerance)
2080
2081 if not self.is_unique:
-> 2082 raise InvalidIndexError('Reindexing only valid with uniquely'
2083 ' valued Index objects')
2084
InvalidIndexError: Reindexing only valid with uniquely valued Index objects
To me this seems buggy because if this is the desired behaviour then it would be very strange. Surely, we should include the case when all the elements of the DataArray we're grouping by are distinct?
Update
I've now uninstalled and reinstalled Xarray. The new Xarray is version 0.8.1, and it seems to work fine. So it may indeed be a bug in Xarray 0.8.0.

MixedLM usage for model fit

I want fit my sample data to mixed panel regression using MixedLM however for my input sm.MixedLM.from_formula("TOTCOST~YEAR",dat,groups=dat["NI"]) I am facing the following error:
ValueError Traceback (most recent call last)
<ipython-input-40-38fa54e8b448> in <module>()
----> 1 sm.MixedLM.from_formula("TOTCOST~YEAR",dat,groups=dat["NI"])
C:\Users\Harshita Jaiswal\Anaconda2\lib\site-packages\statsmodels\regression\mixed_linear_model.pyc in from_formula(cls, formula, data, re_formula, subset, *args, **kwargs)
651 subset=None,
652 exog_re=exog_re,
--> 653 *args, **kwargs)
654
655 # expand re names to account for pairs of RE
C:\Users\Harshita Jaiswal\Anaconda2\lib\site-packages\statsmodels\base\model.pyc in from_formula(cls, formula, data, subset, *args, **kwargs)
145 (endog, exog), missing_idx = handle_formula_data(data, None, formula,
146 depth=eval_env,
--> 147 missing=missing)
148 kwargs.update({'missing_idx': missing_idx,
149 'missing': missing})
C:\Users\Harshita Jaiswal\Anaconda2\lib\site-packages\statsmodels\formula\formulatools.pyc in handle_formula_data(Y, X, formula, depth, missing)
63 if data_util._is_using_pandas(Y, None):
64 result = dmatrices(formula, Y, depth, return_type='dataframe',
---> 65 NA_action=na_action)
66 else:
67 result = dmatrices(formula, Y, depth, return_type='dataframe',
C:\Users\Harshita Jaiswal\Anaconda2\lib\site-packages\patsy\highlevel.pyc in dmatrices(formula_like, data, eval_env, NA_action, return_type)
295 eval_env = EvalEnvironment.capture(eval_env, reference=1)
296 (lhs, rhs) = _do_highlevel_design(formula_like, data, eval_env,
--> 297 NA_action, return_type)
298 if lhs.shape[1] == 0:
299 raise PatsyError("model is missing required outcome variables")
C:\Users\Harshita Jaiswal\Anaconda2\lib\site-packages\patsy\highlevel.pyc in _do_highlevel_design(formula_like, data, eval_env, NA_action, return_type)
150 return iter([data])
151 design_infos = _try_incr_builders(formula_like, data_iter_maker, eval_env,
--> 152 NA_action)
153 if design_infos is not None:
154 return build_design_matrices(design_infos, data,
C:\Users\Harshita Jaiswal\Anaconda2\lib\site-packages\patsy\highlevel.pyc in _try_incr_builders(formula_like, data_iter_maker, eval_env, NA_action)
55 data_iter_maker,
56 eval_env,
---> 57 NA_action)
58 else:
59 return None
C:\Users\Harshita Jaiswal\Anaconda2\lib\site-packages\patsy\build.pyc in design_matrix_builders(termlists, data_iter_maker, eval_env, NA_action)
704 factor_states[factor],
705 num_columns=num_column_counts[factor],
--> 706 categories=None)
707 else:
708 assert factor in cat_levels_contrasts
C:\Users\Harshita Jaiswal\Anaconda2\lib\site-packages\patsy\design_info.pyc in __init__(self, factor, type, state, num_columns, categories)
86 if self.type == "numerical":
87 if not isinstance(num_columns, int):
---> 88 raise ValueError("For numerical factors, num_columns "
89 "must be an int")
90 if categories is not None:
ValueError: For numerical factors, num_columns must be an int
Any help will be appreciated. Thank you