H2O python rbind error - python

I have a 2000 rows data frame and I'm trying to slice the same data frame into two and combine them together.
t1 = test[:10, :]
t2 = test[20:, :]
temp = t1.rbind(t2)
temp.show()
Then I got this error:
---------------------------------------------------------------------------
EnvironmentError Traceback (most recent call last)
<ipython-input-37-8daeb3375743> in <module>()
2 t2 = test[20:, :]
3 temp = t1.rbind(t2)
----> 4 temp.show()
5 print len(temp)
6 print len(test)
/usr/local/lib/python2.7/dist-packages/h2o/frame.pyc in show(self, use_pandas)
383 print("This H2OFrame has been removed.")
384 return
--> 385 if not self._ex._cache.is_valid(): self._frame()._ex._cache.fill()
386 if H2ODisplay._in_ipy():
387 import IPython.display
/usr/local/lib/python2.7/dist-packages/h2o/frame.pyc in _frame(self, fill_cache)
423
424 def _frame(self, fill_cache=False):
--> 425 self._ex._eager_frame()
426 if fill_cache:
427 self._ex._cache.fill()
/usr/local/lib/python2.7/dist-packages/h2o/expr.pyc in _eager_frame(self)
67 if not self._cache.is_empty(): return self
68 if self._cache._id is not None: return self # Data already computed under ID, but not cached locally
---> 69 return self._eval_driver(True)
70
71 def _eager_scalar(self): # returns a scalar (or a list of scalars)
/usr/local/lib/python2.7/dist-packages/h2o/expr.pyc in _eval_driver(self, top)
81 def _eval_driver(self, top):
82 exec_str = self._do_it(top)
---> 83 res = ExprNode.rapids(exec_str)
84 if 'scalar' in res:
85 if isinstance(res['scalar'], list): self._cache._data = [float(x) for x in res['scalar']]
/usr/local/lib/python2.7/dist-packages/h2o/expr.pyc in rapids(expr)
163 The JSON response (as a python dictionary) of the Rapids execution
164 """
--> 165 return H2OConnection.post_json("Rapids", ast=expr,session_id=H2OConnection.session_id(), _rest_version=99)
166
167 class ASTId:
/usr/local/lib/python2.7/dist-packages/h2o/connection.pyc in post_json(url_suffix, file_upload_info, **kwargs)
515 if __H2OCONN__ is None:
516 raise ValueError("No h2o connection. Did you run `h2o.init()` ?")
--> 517 return __H2OCONN__._rest_json(url_suffix, "POST", file_upload_info, **kwargs)
518
519 def _rest_json(self, url_suffix, method, file_upload_info, **kwargs):
/usr/local/lib/python2.7/dist-packages/h2o/connection.pyc in _rest_json(self, url_suffix, method, file_upload_info, **kwargs)
518
519 def _rest_json(self, url_suffix, method, file_upload_info, **kwargs):
--> 520 raw_txt = self._do_raw_rest(url_suffix, method, file_upload_info, **kwargs)
521 return self._process_tables(raw_txt.json())
522
/usr/local/lib/python2.7/dist-packages/h2o/connection.pyc in _do_raw_rest(self, url_suffix, method, file_upload_info, **kwargs)
592 raise EnvironmentError(("h2o-py got an unexpected HTTP status code:\n {} {} (method = {}; url = {}). \n"+ \
593 "detailed error messages: {}")
--> 594 .format(http_result.status_code,http_result.reason,method,url,detailed_error_msgs))
595
596
EnvironmentError: h2o-py got an unexpected HTTP status code:
500 Server Error (method = POST; url = http://localhost:54321/99/Rapids).
detailed error messages: []
If I count rows (len(temp)), it works find. Also if I change the slicing index a little bit, it works find too. For example, if I change to this, it shows the data frame.
t1 = test[:10, :]
t2 = test[:5, :]
Do I miss something here? Thanks.

Unclear what happened without more information (logs would probably say why the rbind did not take).
What version are you using? I tried your code with iris on the bleeding edge and it all worked as expected.
By the way, rbind is typically going to be expensive, especially since what you're semantically after is a subset:
test[range(10) + range(20,test.nrow),:]
should also give you the desired subset (with caveat that you make the full list of row indices in python and pass it over REST to h2o).

Related

Brightway2: LCA scores & calculations

My problem is about getting emissions results of my functional unit from a ecoinvent excel spreadsheet format.
I managed to get activities/process impacts thanks to ca.annotated_top_processes(lca) or lca.top_activities()but emissions/biosphere flows can't be displayed but through ca.hinton_matrix(lca, rows=10, cols=10). How can I get specific scores ?
Here's the situation:
import brightway2 as bw
from stats_arrays import *
import bw2analyzer as bwa
projects.set_current("excel_import_verif1")
bw.databases
db = bw.Database('IoTBOLLCA') #Excel spreadsheet
CC = [method for method in bw.methods if "('ReCiPe Midpoint (H) V1.13', 'climate change', 'GWP100')" in str(method)][0]
FU = [i for i in db if 'FU' in i['name']][0]
lca = bw.LCA({FU:1},CC)
lca.lci()
lca.lcia()
lca.score
ca = bwa.ContributionAnalysis()
lca.top_emissions()
and I get this error
TypeError Traceback (most recent call last)
File ~\Anaconda3\envs\bw2\lib\site-packages\scipy\sparse\_sputils.py:208, in isintlike(x)
207 try:
--> 208 operator.index(x)
209 except (TypeError, ValueError):
TypeError: 'numpy.float64' object cannot be interpreted as an integer
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
Input In [28], in <cell line: 1>()
----> 1 lca.top_emissions()
File ~\Anaconda3\envs\bw2\lib\site-packages\bw2calc\lca.py:575, in LCA.top_emissions(self, **kwargs)
573 except ImportError:
574 raise ImportError("`bw2analyzer` is not installed")
--> 575 return ContributionAnalysis().annotated_top_emissions(self, **kwargs)
File ~\Anaconda3\envs\bw2\lib\site-packages\bw2analyzer\contribution.py:152, in ContributionAnalysis.annotated_top_emissions(self, lca, names, **kwargs)
146 """Get list of most damaging biosphere flows in an LCA, sorted by ``abs(direct impact)``.
147
148 Returns a list of tuples: ``(lca score, inventory amount, activity)``. If ``names`` is False, they returns the process key as the last element.
149
150 """
151 ra, rp, rb = lca.reverse_dict()
--> 152 results = [
153 (score, lca.inventory[index, :].sum(), rb[index])
154 for score, index in self.top_emissions(
155 lca.characterized_inventory, **kwargs
156 )
157 ]
158 if names:
159 results = [(x[0], x[1], get_activity(x[2])) for x in results]
File ~\Anaconda3\envs\bw2\lib\site-packages\bw2analyzer\contribution.py:153, in <listcomp>(.0)
146 """Get list of most damaging biosphere flows in an LCA, sorted by ``abs(direct impact)``.
147
148 Returns a list of tuples: ``(lca score, inventory amount, activity)``. If ``names`` is False, they returns the process key as the last element.
149
150 """
151 ra, rp, rb = lca.reverse_dict()
152 results = [
--> 153 (score, lca.inventory[index, :].sum(), rb[index])
154 for score, index in self.top_emissions(
155 lca.characterized_inventory, **kwargs
156 )
157 ]
158 if names:
159 results = [(x[0], x[1], get_activity(x[2])) for x in results]
File ~\Anaconda3\envs\bw2\lib\site-packages\scipy\sparse\_index.py:47, in IndexMixin.__getitem__(self, key)
46 def __getitem__(self, key):
---> 47 row, col = self._validate_indices(key)
49 # Dispatch to specialized methods.
50 if isinstance(row, INT_TYPES):
File ~\Anaconda3\envs\bw2\lib\site-packages\scipy\sparse\_index.py:152, in IndexMixin._validate_indices(self, key)
149 M, N = self.shape
150 row, col = _unpack_index(key)
--> 152 if isintlike(row):
153 row = int(row)
154 if row < -M or row >= M:
File ~\Anaconda3\envs\bw2\lib\site-packages\scipy\sparse\_sputils.py:216, in isintlike(x)
214 if loose_int:
215 msg = "Inexact indices into sparse matrices are not allowed"
--> 216 raise ValueError(msg)
217 return loose_int
218 return True
ValueError: Inexact indices into sparse matrices are not allowed
This is an error as of Scipy version 1.9; for now, you can force a downgrade to Scipy 1.8.something.
This has been noted as an issue, but the focus for BW development is in other areas currently.

How to fix BulkIndexError when inserting large file of over 500mb into Elasticsearch

I am trying to insert data of size 589MB CSV format into elasticsearch, but am getting BulkIndexError how can I fix this.
Here is the sample code I try to make use of to insert the data into elasticsearch...
# Read the sample datasets
import pandas as pd
df = pd.read_csv(r'C:\Users\HOPE\Desktop\Data Science\Machine Learning\NLP\Covid NLP\Covid QA Project\FINAL_CORD_DATA.csv')
df.head()
from haystack.document_store.elasticsearch import ElasticsearchDocumentStore
document_store = ElasticsearchDocumentStore(host="localhost", username="", password="", index="document")
# Convert files to dicts
dicts = df.to_dict('records')
final_dicts = []
for each in dicts:
tmp = {}
tmp['text'] = each.pop('body_text')
tmp['meta'] = each
final_dicts.append(tmp)
document_store.write_documents(final_dicts)
here is the error I get after running the last code
BulkIndexError Traceback (most recent call last)
<ipython-input-6-ca13005a46cd> in <module>
6 final_dicts.append(tmp)
7
----> 8 document_store.write_documents(final_dicts)
~\Anaconda3\envs\ml\lib\site-packages\haystack\document_store\elasticsearch.py in write_documents(self, documents, index, batch_size)
302 # Pass batch_size number of documents to bulk
303 if len(documents_to_index) % batch_size == 0:
--> 304 bulk(self.client, documents_to_index, request_timeout=300, refresh=self.refresh_type)
305 documents_to_index = []
306
~\Anaconda3\envs\ml\lib\site-packages\elasticsearch\helpers\actions.py in bulk(client, actions, stats_only, *args, **kwargs)
388 # make streaming_bulk yield successful results so we can count them
389 kwargs["yield_ok"] = True
--> 390 for ok, item in streaming_bulk(client, actions, *args, **kwargs):
391 # go through request-response pairs and detect failures
392 if not ok:
~\Anaconda3\envs\ml\lib\site-packages\elasticsearch\helpers\actions.py in streaming_bulk(client, actions, chunk_size, max_chunk_bytes, raise_on_error, expand_action_callback, raise_on_exception, max_retries, initial_backoff, max_backoff, yield_ok, *args, **kwargs)
309
310 try:
--> 311 for data, (ok, info) in zip(
312 bulk_data,
313 _process_bulk_chunk(
~\Anaconda3\envs\ml\lib\site-packages\elasticsearch\helpers\actions.py in _process_bulk_chunk(client, bulk_actions, bulk_data, raise_on_exception, raise_on_error, *args, **kwargs)
245 resp=resp, bulk_data=bulk_data, raise_on_error=raise_on_error
246 )
--> 247 for item in gen:
248 yield item
249
~\Anaconda3\envs\ml\lib\site-packages\elasticsearch\helpers\actions.py in _process_bulk_chunk_success(resp, bulk_data, raise_on_error)
186
187 if errors:
--> 188 raise BulkIndexError("%i document(s) failed to index." % len(errors), errors)
189
190

Overriding * imports globally for jupyter

I'm running jupyter lab on windows and fastai.vision.utils.verify_images(fns) is giving me problems because it calls fastcore.parallel.parallel with default n_workers=8. There are many ways around it, but I was trying to figure out a code block that I could slap in any notebook and have it so all underlying calls to parallel will run with n_workers=1.
I tried the following cell:
import fastcore
import sys
_fastcore = fastcore
_parallel = lambda *args, **kwargs: fastcore.parallel.parallel(*args, **kwargs, n_workers=1)
_fastcore.parallel.parallel = _parallel
sys.modules['fastcore'] = _fastcore
fastcore.parallel.parallel
printing
<function __main__.<lambda>(*args, **kwargs)>
but when I try running verify_images it still fails as if the patch never happened
---------------------------------------------------------------------------
BrokenProcessPool Traceback (most recent call last)
<ipython-input-37-f1773f2c9e62> in <module>
3 # from mock import patch
4 # with patch('fastcore.parallel.parallel') as _parallel:
----> 5 failed = verify_images(fns)
6 # failed = L(fns[i] for i,o in enumerate(_parallel(verify_image, fns)) if not o)
7 failed
~\anaconda3\lib\site-packages\fastai\vision\utils.py in verify_images(fns)
59 def verify_images(fns):
60 "Find images in `fns` that can't be opened"
---> 61 return L(fns[i] for i,o in enumerate(parallel(verify_image, fns)) if not o)
62
63 # Cell
~\anaconda3\lib\site-packages\fastcore\parallel.py in parallel(f, items, n_workers, total, progress, pause, threadpool, timeout, chunksize, *args, **kwargs)
121 if total is None: total = len(items)
122 r = progress_bar(r, total=total, leave=False)
--> 123 return L(r)
124
125 # Cell
~\anaconda3\lib\site-packages\fastcore\foundation.py in __call__(cls, x, *args, **kwargs)
95 def __call__(cls, x=None, *args, **kwargs):
96 if not args and not kwargs and x is not None and isinstance(x,cls): return x
---> 97 return super().__call__(x, *args, **kwargs)
98
99 # Cell
~\anaconda3\lib\site-packages\fastcore\foundation.py in __init__(self, items, use_list, match, *rest)
103 def __init__(self, items=None, *rest, use_list=False, match=None):
104 if (use_list is not None) or not is_array(items):
--> 105 items = listify(items, *rest, use_list=use_list, match=match)
106 super().__init__(items)
107
~\anaconda3\lib\site-packages\fastcore\basics.py in listify(o, use_list, match, *rest)
54 elif isinstance(o, list): res = o
55 elif isinstance(o, str) or is_array(o): res = [o]
---> 56 elif is_iter(o): res = list(o)
57 else: res = [o]
58 if match is not None:
~\anaconda3\lib\concurrent\futures\process.py in _chain_from_iterable_of_lists(iterable)
482 careful not to keep references to yielded objects.
483 """
--> 484 for element in iterable:
485 element.reverse()
486 while element:
~\anaconda3\lib\concurrent\futures\_base.py in result_iterator()
609 # Careful not to keep a reference to the popped future
610 if timeout is None:
--> 611 yield fs.pop().result()
612 else:
613 yield fs.pop().result(end_time - time.monotonic())
~\anaconda3\lib\concurrent\futures\_base.py in result(self, timeout)
437 raise CancelledError()
438 elif self._state == FINISHED:
--> 439 return self.__get_result()
440 else:
441 raise TimeoutError()
~\anaconda3\lib\concurrent\futures\_base.py in __get_result(self)
386 def __get_result(self):
387 if self._exception:
--> 388 raise self._exception
389 else:
390 return self._result
BrokenProcessPool: A process in the process pool was terminated abruptly while the future was running or pending.
I suspect it has to do with fastai.vision.utils using * imports for fastcore. Is there a way to achieve what I want?
Since the parallel function has already been imported into the fastai.vision.utils module, the correct way is to monkeypatch that module rather than fastcore.parallel:
... # your code for custom `parallel` function goes here
import fastai.vision.utils
fastai.vision.utils.parallel = _parallel # assign your custom function here

(Memory) Problem when accessing Dask type arrays

I need to load some meteorological data to analyze several months but such data is stored in files that cover only one day so I need to acces many files at once.
I am following some pre-given instruction that told me to create a memory partition in my computer.
from datetime import datetime, timedelta
import dask.array as da
from dask.distributed import Client, LocalCluster
import xarray
try:
client
except NameError:
client = Client(n_workers=1, threads_per_worker=4, memory_limit='2GB')
else:
print("Client already exists")
After this, I create an array dates that goes from 1st June to 1st October and that is need in "files" to get the link to the meteorological data.
dates=[datetime(2019,6,1) + timedelta(days=i) for i in range(3*30)]
files= [date.strftime('http://mandeo.meteogalicia.es/thredds/dodsC/modelos/WRF_HIST/d03/%Y/%m/wrf_arw_det_history_d03_%Y%m%d_0000.nc4') for date in dates]
My issue starts when I try to unzip all that data as
multi = xarray.open_mfdataset(files, preprocess= lambda a : a.isel(time=slice(0,24)))
It raises the error:
KeyError Traceback (most recent call last)
~\Nueva carpeta\lib\site-packages\xarray\backends\file_manager.py in _acquire_with_cache_info(self, needs_lock)
197 try:
--> 198 file = self._cache[self._key]
199 except KeyError:
~\Nueva carpeta\lib\site-packages\xarray\backends\lru_cache.py in __getitem__(self, key)
52 with self._lock:
---> 53 value = self._cache[key]
54 self._cache.move_to_end(key)
KeyError: [<class 'netCDF4._netCDF4.Dataset'>, ('http://mandeo.meteogalicia.es/thredds/dodsC/modelos/WRF_HIST/d03/2019/06/wrf_arw_det_history_d03_20190626_0000.nc4',), 'r', (('clobber', True), ('diskless', False), ('format', 'NETCDF4'), ('persist', False))]
During handling of the above exception, another exception occurred:
OSError Traceback (most recent call last)
<ipython-input-19-c3d0f4a8cc26> in <module>
----> 1 multi = xarray.open_mfdataset(files, preprocess= lambda a : a.isel(time=slice(0,24)))
~\Nueva carpeta\lib\site-packages\xarray\backends\api.py in open_mfdataset(paths, chunks, concat_dim, compat, preprocess, engine, lock, data_vars, coords, combine, autoclose, parallel, join, attrs_file, **kwargs)
916 getattr_ = getattr
917
--> 918 datasets = [open_(p, **open_kwargs) for p in paths]
919 file_objs = [getattr_(ds, "_file_obj") for ds in datasets]
920 if preprocess is not None:
~\Nueva carpeta\lib\site-packages\xarray\backends\api.py in <listcomp>(.0)
916 getattr_ = getattr
917
--> 918 datasets = [open_(p, **open_kwargs) for p in paths]
919 file_objs = [getattr_(ds, "_file_obj") for ds in datasets]
920 if preprocess is not None:
~\Nueva carpeta\lib\site-packages\xarray\backends\api.py in open_dataset(filename_or_obj, group, decode_cf, mask_and_scale, decode_times, autoclose, concat_characters, decode_coords, engine, chunks, lock, cache, drop_variables, backend_kwargs, use_cftime, decode_timedelta)
507 if engine == "netcdf4":
508 store = backends.NetCDF4DataStore.open(
--> 509 filename_or_obj, group=group, lock=lock, **backend_kwargs
510 )
511 elif engine == "scipy":
~\Nueva carpeta\lib\site-packages\xarray\backends\netCDF4_.py in open(cls, filename, mode, format, group, clobber, diskless, persist, lock, lock_maker, autoclose)
356 netCDF4.Dataset, filename, mode=mode, kwargs=kwargs
357 )
--> 358 return cls(manager, group=group, mode=mode, lock=lock, autoclose=autoclose)
359
360 def _acquire(self, needs_lock=True):
~\Nueva carpeta\lib\site-packages\xarray\backends\netCDF4_.py in __init__(self, manager, group, mode, lock, autoclose)
312 self._group = group
313 self._mode = mode
--> 314 self.format = self.ds.data_model
315 self._filename = self.ds.filepath()
316 self.is_remote = is_remote_uri(self._filename)
~\Nueva carpeta\lib\site-packages\xarray\backends\netCDF4_.py in ds(self)
365 #property
366 def ds(self):
--> 367 return self._acquire()
368
369 def open_store_variable(self, name, var):
~\Nueva carpeta\lib\site-packages\xarray\backends\netCDF4_.py in _acquire(self, needs_lock)
359
360 def _acquire(self, needs_lock=True):
--> 361 with self._manager.acquire_context(needs_lock) as root:
362 ds = _nc4_require_group(root, self._group, self._mode)
363 return ds
~\Nueva carpeta\lib\contextlib.py in __enter__(self)
110 del self.args, self.kwds, self.func
111 try:
--> 112 return next(self.gen)
113 except StopIteration:
114 raise RuntimeError("generator didn't yield") from None
~\Nueva carpeta\lib\site-packages\xarray\backends\file_manager.py in acquire_context(self, needs_lock)
184 def acquire_context(self, needs_lock=True):
185 """Context manager for acquiring a file."""
--> 186 file, cached = self._acquire_with_cache_info(needs_lock)
187 try:
188 yield file
~\Nueva carpeta\lib\site-packages\xarray\backends\file_manager.py in _acquire_with_cache_info(self, needs_lock)
202 kwargs = kwargs.copy()
203 kwargs["mode"] = self._mode
--> 204 file = self._opener(*self._args, **kwargs)
205 if self._mode == "w":
206 # ensure file doesn't get overriden when opened again
netCDF4\_netCDF4.pyx in netCDF4._netCDF4.Dataset.__init__()
netCDF4\_netCDF4.pyx in netCDF4._netCDF4._ensure_nc_success()
OSError: [Errno -37] NetCDF: Write to read only: b'http://mandeo.meteogalicia.es/thredds/dodsC/modelos/WRF_HIST/d03/2019/06/wrf_arw_det_history_d03_20190626_0000.nc4'
Does anyone know why this error occurs?

NameError: name 'onset_to_death' is not defined. Works in Py2 but not Py3

I'm taking an online python course (EpiSkills, which uses the Jupyter notebook) that was written in Python 2.7, and I'm on Python 3.6.4 so I have run into a few compatibility issues along the way. Most of the time I've been able to stumble through, but can't figure out this one, so was hoping someone might be able to help.
I start with the following packages:
import pandas as pd
import epipy
import seaborn as sns
%pylab inline
import statsmodels.api as sm
from scipy import stats
import numpy as np
And use the following code to create a pandas series and model:
multivar_model = sm.formula.glm('age ~ onset_to_hospital + onset_to_death +
data=my_data).fit()
new_data = pd.Series([6, 8, 'male'], index=['onset_to_hospital', 'onset_to_death', 'sex'])
When I try to use this to the following code, I throw the error that I've attached:
multivar_model.predict(new_data)
NameError part1
NameError part2
The intended output is meant to be this:
array([ 60.6497459])
I know that a lot of NameErrors are because something has been specified in the local, not global, environment but I'm unsure how to correct it in this instance. Any help is much appreciated.
Thanks!
C
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\compat.py in call_and_wrap_exc(msg, origin, f, *args, **kwargs)
116 try:
--> 117 return f(*args, **kwargs)
118 except Exception as e:
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\eval.py in eval(self, expr, source_name, inner_namespace)
165 return eval(code, {}, VarLookupDict([inner_namespace]
--> 166 + self._namespaces))
167
<string> in <module>()
NameError: name 'onset_to_death' is not defined
The above exception was the direct cause of the following exception:
PatsyError Traceback (most recent call last)
<ipython-input-79-e0364e267da7> in <module>()
----> 1 multivar_model.predict(new_data)
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\statsmodels\base\model.py in predict(self, exog, transform, *args, **kwargs)
774 exog_index = exog.index
775 exog = dmatrix(self.model.data.design_info.builder,
--> 776 exog, return_type="dataframe")
777 if len(exog) < len(exog_index):
778 # missing values, rows have been dropped
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\highlevel.py in dmatrix(formula_like, data, eval_env, NA_action, return_type)
289 eval_env = EvalEnvironment.capture(eval_env, reference=1)
290 (lhs, rhs) = _do_highlevel_design(formula_like, data, eval_env,
--> 291 NA_action, return_type)
292 if lhs.shape[1] != 0:
293 raise PatsyError("encountered outcome variables for a model "
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\highlevel.py in _do_highlevel_design(formula_like, data, eval_env, NA_action, return_type)
167 return build_design_matrices(design_infos, data,
168 NA_action=NA_action,
--> 169 return_type=return_type)
170 else:
171 # No builders, but maybe we can still get matrices
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\build.py in build_design_matrices(design_infos, data, NA_action, return_type, dtype)
886 for factor_info in six.itervalues(design_info.factor_infos):
887 if factor_info not in factor_info_to_values:
--> 888 value, is_NA = _eval_factor(factor_info, data, NA_action)
889 factor_info_to_isNAs[factor_info] = is_NA
890 # value may now be a Series, DataFrame, or ndarray
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\build.py in _eval_factor(factor_info, data, NA_action)
61 def _eval_factor(factor_info, data, NA_action):
62 factor = factor_info.factor
---> 63 result = factor.eval(factor_info.state, data)
64 # Returns either a 2d ndarray, or a DataFrame, plus is_NA mask
65 if factor_info.type == "numerical":
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\eval.py in eval(self, memorize_state, data)
564 return self._eval(memorize_state["eval_code"],
565 memorize_state,
--> 566 data)
567
568 __getstate__ = no_pickling
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\eval.py in _eval(self, code, memorize_state, data)
549 memorize_state["eval_env"].eval,
550 code,
--> 551 inner_namespace=inner_namespace)
552
553 def memorize_chunk(self, state, which_pass, data):
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\compat.py in call_and_wrap_exc(msg, origin, f, *args, **kwargs)
122 origin)
123 # Use 'exec' to hide this syntax from the Python 2 parser:
--> 124 exec("raise new_exc from e")
125 else:
126 # In python 2, we just let the original exception escape -- better
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\compat.py in <module>()
PatsyError: Error evaluating factor: NameError: name 'onset_to_death' is not defined
age ~ onset_to_hospital + onset_to_death + sex
^^^^^^^^^^^^^^

Categories