Cannot Load From HDF Data Store - python

I am using pandas 0.11.0 on Windows 64 Bit.
I have a datastore:
store = pandas.io.pytables.HDFStore( r"""C:\data.h5""" )
It has some data in it:
print(store)
<class 'pandas.io.pytables.HDFStore'>
File path: C:\data.h5
/region frame (shape->[30,2])
/sector frame (shape->[116,2])
When I try to load 'sector' from the store I get:
store['/sector']
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-24-7fea069742ed> in <module>()
----> 1 store['/sector']
C:\Anaconda\lib\site-packages\pandas\io\pytables.pyc in __getitem__(self, key)
236
237 def __getitem__(self, key):
--> 238 return self.get(key)
239
240 def __setitem__(self, key, value):
C:\Anaconda\lib\site-packages\pandas\io\pytables.pyc in get(self, key)
369 if group is None:
370 raise KeyError('No object named %s in the file' % key)
--> 371 return self._read_group(group)
372
373 def select(self, key, where=None, start=None, stop=None, columns=None, iterator=False, chunksize=None, **kwargs):
C:\Anaconda\lib\site-packages\pandas\io\pytables.pyc in _read_group(self, group, **kwargs)
876 s = self._create_storer(group)
877 s.infer_axes()
--> 878 return s.read(**kwargs)
879
880 class TableIterator(object):
C:\Anaconda\lib\site-packages\pandas\io\pytables.pyc in read(self, **kwargs)
1982 blocks = []
1983 for i in range(self.nblocks):
-> 1984 blk_items = self.read_index('block%d_items' % i)
1985 values = self.read_array('block%d_values' % i)
1986 blk = make_block(values, blk_items, items)
C:\Anaconda\lib\site-packages\pandas\io\pytables.pyc in read_index(self, key)
1615 return self.read_sparse_intindex(key)
1616 elif variety == 'regular':
-> 1617 _, index = self.read_index_node(getattr(self.group, key))
1618 return index
1619 else: # pragma: no cover
C:\Anaconda\lib\site-packages\pandas\io\pytables.pyc in read_index_node(self, node)
1733 **kwargs)
1734 else:
-> 1735 index = factory(_unconvert_index(data, kind), **kwargs)
1736
1737 index.name = name
TypeError: __new__() got an unexpected keyword argument 'freq'
What is this "freq" argument? And why is it stopping me from loading the data?

Related

FSSpec Error Handling in Python - Timeout Error

I am trying to get Terraclimate Data from Microsoft Planetary and facing time out error. Is there a possiblity of increasing the timeout time ? Please find the code below and the error I am facing. I am using fsspec and xarray for downloading spatial data from MS Planetary portal.
import fsspec
import xarray as xr
store = fsspec.get_mapper(asset.href)
data = xr.open_zarr(store, **asset.extra_fields["xarray:open_kwargs"])
clipped_data = data.sel(time=slice('2015-01-01','2019-12-31'),lon=slice(min_lon,max_lon),lat=slice(max_lat,min_lat))
parsed_data = clipped_data[['tmax', 'tmin', 'ppt', 'soil']]
lat_list = parsed_data['lat'].values.tolist()
lon_list = parsed_data['lon'].values.tolist()
filename = "Soil_Moisture_sample.csv"
for(i,j) in zip(lat_list,lon_list):
parsed_data[["soil","tmax","tmin","ppt"]].sel(lon=i, lat=j, method="nearest").to_dataframe().to_csv(filename,mode='a',index=False, header=False)
I am getting the following error
TimeoutError Traceback (most recent call last)
File ~\Anaconda3\envs\satellite\lib\site-packages\fsspec\asyn.py:53, in _runner(event, coro, result, timeout)
52 try:
---> 53 result[0] = await coro
54 except Exception as ex:
File ~\Anaconda3\envs\satellite\lib\site-packages\fsspec\asyn.py:423, in AsyncFileSystem._cat(self, path, recursive, on_error, batch_size, **kwargs)
422 if ex:
--> 423 raise ex
424 if (
425 len(paths) > 1
426 or isinstance(path, list)
427 or paths[0] != self._strip_protocol(path)
428 ):
File ~\Anaconda3\envs\satellite\lib\asyncio\tasks.py:455, in wait_for(fut, timeout, loop)
454 if timeout is None:
--> 455 return await fut
457 if timeout <= 0:
File ~\Anaconda3\envs\satellite\lib\site-packages\fsspec\implementations\http.py:221, in HTTPFileSystem._cat_file(self, url, start, end, **kwargs)
220 async with session.get(url, **kw) as r:
--> 221 out = await r.read()
222 self._raise_not_found_for_status(r, url)
File ~\Anaconda3\envs\satellite\lib\site-packages\aiohttp\client_reqrep.py:1036, in ClientResponse.read(self)
1035 try:
-> 1036 self._body = await self.content.read()
1037 for trace in self._traces:
File ~\Anaconda3\envs\satellite\lib\site-packages\aiohttp\streams.py:375, in StreamReader.read(self, n)
374 while True:
--> 375 block = await self.readany()
376 if not block:
File ~\Anaconda3\envs\satellite\lib\site-packages\aiohttp\streams.py:397, in StreamReader.readany(self)
396 while not self._buffer and not self._eof:
--> 397 await self._wait("readany")
399 return self._read_nowait(-1)
File ~\Anaconda3\envs\satellite\lib\site-packages\aiohttp\streams.py:304, in StreamReader._wait(self, func_name)
303 with self._timer:
--> 304 await waiter
305 else:
File ~\Anaconda3\envs\satellite\lib\site-packages\aiohttp\helpers.py:721, in TimerContext.__exit__(self, exc_type, exc_val, exc_tb)
720 if exc_type is asyncio.CancelledError and self._cancelled:
--> 721 raise asyncio.TimeoutError from None
722 return None
TimeoutError:
The above exception was the direct cause of the following exception:
FSTimeoutError Traceback (most recent call last)
Input In [62], in <cell line: 3>()
1 # Flood Region Point - Thiruvanthpuram
2 filename = "Soil_Moisture_sample.csv"
----> 3 parsed_data[["soil","tmax","tmin","ppt"]].sel(lon=8.520833, lat=76.4375, method="nearest").to_dataframe().to_csv(filename,mode='a',index=False, header=False)
File ~\Anaconda3\envs\satellite\lib\site-packages\xarray\core\dataset.py:5898, in Dataset.to_dataframe(self, dim_order)
5870 """Convert this dataset into a pandas.DataFrame.
5871
5872 Non-index variables in this dataset form the columns of the
(...)
5893
5894 """
5896 ordered_dims = self._normalize_dim_order(dim_order=dim_order)
-> 5898 return self._to_dataframe(ordered_dims=ordered_dims)
File ~\Anaconda3\envs\satellite\lib\site-packages\xarray\core\dataset.py:5862, in Dataset._to_dataframe(self, ordered_dims)
5860 def _to_dataframe(self, ordered_dims: Mapping[Any, int]):
5861 columns = [k for k in self.variables if k not in self.dims]
-> 5862 data = [
5863 self._variables[k].set_dims(ordered_dims).values.reshape(-1)
5864 for k in columns
5865 ]
5866 index = self.coords.to_index([*ordered_dims])
5867 return pd.DataFrame(dict(zip(columns, data)), index=index)
File ~\Anaconda3\envs\satellite\lib\site-packages\xarray\core\dataset.py:5863, in <listcomp>(.0)
5860 def _to_dataframe(self, ordered_dims: Mapping[Any, int]):
5861 columns = [k for k in self.variables if k not in self.dims]
5862 data = [
-> 5863 self._variables[k].set_dims(ordered_dims).values.reshape(-1)
5864 for k in columns
5865 ]
5866 index = self.coords.to_index([*ordered_dims])
5867 return pd.DataFrame(dict(zip(columns, data)), index=index)
File ~\Anaconda3\envs\satellite\lib\site-packages\xarray\core\variable.py:527, in Variable.values(self)
524 #property
525 def values(self):
526 """The variable's data as a numpy.ndarray"""
--> 527 return _as_array_or_item(self._data)
File ~\Anaconda3\envs\satellite\lib\site-packages\xarray\core\variable.py:267, in _as_array_or_item(data)
253 def _as_array_or_item(data):
254 """Return the given values as a numpy array, or as an individual item if
255 it's a 0d datetime64 or timedelta64 array.
256
(...)
265 TODO: remove this (replace with np.asarray) once these issues are fixed
266 """
--> 267 data = np.asarray(data)
268 if data.ndim == 0:
269 if data.dtype.kind == "M":
File ~\AppData\Roaming\Python\Python38\site-packages\dask\array\core.py:1696, in Array.__array__(self, dtype, **kwargs)
1695 def __array__(self, dtype=None, **kwargs):
-> 1696 x = self.compute()
1697 if dtype and x.dtype != dtype:
1698 x = x.astype(dtype)
File ~\AppData\Roaming\Python\Python38\site-packages\dask\base.py:315, in DaskMethodsMixin.compute(self, **kwargs)
291 def compute(self, **kwargs):
292 """Compute this dask collection
293
294 This turns a lazy Dask collection into its in-memory equivalent.
(...)
313 dask.base.compute
314 """
--> 315 (result,) = compute(self, traverse=False, **kwargs)
316 return result
File ~\AppData\Roaming\Python\Python38\site-packages\dask\base.py:600, in compute(traverse, optimize_graph, scheduler, get, *args, **kwargs)
597 keys.append(x.__dask_keys__())
598 postcomputes.append(x.__dask_postcompute__())
--> 600 results = schedule(dsk, keys, **kwargs)
601 return repack([f(r, *a) for r, (f, a) in zip(results, postcomputes)])
File ~\AppData\Roaming\Python\Python38\site-packages\dask\threaded.py:89, in get(dsk, keys, cache, num_workers, pool, **kwargs)
86 elif isinstance(pool, multiprocessing.pool.Pool):
87 pool = MultiprocessingPoolExecutor(pool)
---> 89 results = get_async(
90 pool.submit,
91 pool._max_workers,
92 dsk,
93 keys,
94 cache=cache,
95 get_id=_thread_get_id,
96 pack_exception=pack_exception,
97 **kwargs,
98 )
100 # Cleanup pools associated to dead threads
101 with pools_lock:
File ~\AppData\Roaming\Python\Python38\site-packages\dask\local.py:511, in get_async(submit, num_workers, dsk, result, cache, get_id, rerun_exceptions_locally, pack_exception, raise_exception, callbacks, dumps, loads, chunksize, **kwargs)
509 _execute_task(task, data) # Re-execute locally
510 else:
--> 511 raise_exception(exc, tb)
512 res, worker_id = loads(res_info)
513 state["cache"][key] = res
File ~\AppData\Roaming\Python\Python38\site-packages\dask\local.py:319, in reraise(exc, tb)
317 if exc.__traceback__ is not tb:
318 raise exc.with_traceback(tb)
--> 319 raise exc
File ~\AppData\Roaming\Python\Python38\site-packages\dask\local.py:224, in execute_task(key, task_info, dumps, loads, get_id, pack_exception)
222 try:
223 task, data = loads(task_info)
--> 224 result = _execute_task(task, data)
225 id = get_id()
226 result = dumps((result, id))
File ~\AppData\Roaming\Python\Python38\site-packages\dask\core.py:119, in _execute_task(arg, cache, dsk)
115 func, args = arg[0], arg[1:]
116 # Note: Don't assign the subtask results to a variable. numpy detects
117 # temporaries by their reference count and can execute certain
118 # operations in-place.
--> 119 return func(*(_execute_task(a, cache) for a in args))
120 elif not ishashable(arg):
121 return arg
File ~\AppData\Roaming\Python\Python38\site-packages\dask\array\core.py:128, in getter(a, b, asarray, lock)
123 # Below we special-case `np.matrix` to force a conversion to
124 # `np.ndarray` and preserve original Dask behavior for `getter`,
125 # as for all purposes `np.matrix` is array-like and thus
126 # `is_arraylike` evaluates to `True` in that case.
127 if asarray and (not is_arraylike(c) or isinstance(c, np.matrix)):
--> 128 c = np.asarray(c)
129 finally:
130 if lock:
File ~\Anaconda3\envs\satellite\lib\site-packages\xarray\core\indexing.py:459, in ImplicitToExplicitIndexingAdapter.__array__(self, dtype)
458 def __array__(self, dtype=None):
--> 459 return np.asarray(self.array, dtype=dtype)
File ~\Anaconda3\envs\satellite\lib\site-packages\xarray\core\indexing.py:623, in CopyOnWriteArray.__array__(self, dtype)
622 def __array__(self, dtype=None):
--> 623 return np.asarray(self.array, dtype=dtype)
File ~\Anaconda3\envs\satellite\lib\site-packages\xarray\core\indexing.py:524, in LazilyIndexedArray.__array__(self, dtype)
522 def __array__(self, dtype=None):
523 array = as_indexable(self.array)
--> 524 return np.asarray(array[self.key], dtype=None)
File ~\Anaconda3\envs\satellite\lib\site-packages\xarray\backends\zarr.py:76, in ZarrArrayWrapper.__getitem__(self, key)
74 array = self.get_array()
75 if isinstance(key, indexing.BasicIndexer):
---> 76 return array[key.tuple]
77 elif isinstance(key, indexing.VectorizedIndexer):
78 return array.vindex[
79 indexing._arrayize_vectorized_indexer(key, self.shape).tuple
80 ]
File ~\Anaconda3\envs\satellite\lib\site-packages\zarr\core.py:788, in Array.__getitem__(self, selection)
786 result = self.vindex[selection]
787 else:
--> 788 result = self.get_basic_selection(pure_selection, fields=fields)
789 return result
File ~\Anaconda3\envs\satellite\lib\site-packages\zarr\core.py:914, in Array.get_basic_selection(self, selection, out, fields)
911 return self._get_basic_selection_zd(selection=selection, out=out,
912 fields=fields)
913 else:
--> 914 return self._get_basic_selection_nd(selection=selection, out=out,
915 fields=fields)
File ~\Anaconda3\envs\satellite\lib\site-packages\zarr\core.py:957, in Array._get_basic_selection_nd(self, selection, out, fields)
951 def _get_basic_selection_nd(self, selection, out=None, fields=None):
952 # implementation of basic selection for array with at least one dimension
953
954 # setup indexer
955 indexer = BasicIndexer(selection, self)
--> 957 return self._get_selection(indexer=indexer, out=out, fields=fields)
File ~\Anaconda3\envs\satellite\lib\site-packages\zarr\core.py:1247, in Array._get_selection(self, indexer, out, fields)
1241 if not hasattr(self.chunk_store, "getitems") or \
1242 any(map(lambda x: x == 0, self.shape)):
1243 # sequentially get one key at a time from storage
1244 for chunk_coords, chunk_selection, out_selection in indexer:
1245
1246 # load chunk selection into output array
-> 1247 self._chunk_getitem(chunk_coords, chunk_selection, out, out_selection,
1248 drop_axes=indexer.drop_axes, fields=fields)
1249 else:
1250 # allow storage to get multiple items at once
1251 lchunk_coords, lchunk_selection, lout_selection = zip(*indexer)
File ~\Anaconda3\envs\satellite\lib\site-packages\zarr\core.py:1939, in Array._chunk_getitem(self, chunk_coords, chunk_selection, out, out_selection, drop_axes, fields)
1935 ckey = self._chunk_key(chunk_coords)
1937 try:
1938 # obtain compressed data for chunk
-> 1939 cdata = self.chunk_store[ckey]
1941 except KeyError:
1942 # chunk not initialized
1943 if self._fill_value is not None:
File ~\Anaconda3\envs\satellite\lib\site-packages\zarr\storage.py:717, in KVStore.__getitem__(self, key)
716 def __getitem__(self, key):
--> 717 return self._mutable_mapping[key]
File ~\Anaconda3\envs\satellite\lib\site-packages\fsspec\mapping.py:137, in FSMap.__getitem__(self, key, default)
135 k = self._key_to_str(key)
136 try:
--> 137 result = self.fs.cat(k)
138 except self.missing_exceptions:
139 if default is not None:
File ~\Anaconda3\envs\satellite\lib\site-packages\fsspec\asyn.py:111, in sync_wrapper.<locals>.wrapper(*args, **kwargs)
108 #functools.wraps(func)
109 def wrapper(*args, **kwargs):
110 self = obj or args[0]
--> 111 return sync(self.loop, func, *args, **kwargs)
File ~\Anaconda3\envs\satellite\lib\site-packages\fsspec\asyn.py:94, in sync(loop, func, timeout, *args, **kwargs)
91 return_result = result[0]
92 if isinstance(return_result, asyncio.TimeoutError):
93 # suppress asyncio.TimeoutError, raise FSTimeoutError
---> 94 raise FSTimeoutError from return_result
95 elif isinstance(return_result, BaseException):
96 raise return_result
FSTimeoutError:
In the line:
store = fsspec.get_mapper(asset.href)
You can pass extra arguments to the fsspec backend, in this case HTTP, see fsspec.implementations.http.HTTPFileSystem. In this case, client_kwargs get passed to aiohttp.ClientSession, and include an optional timeout argument. Your call may look something like
from aiohttp import ClientTimeout
store = get_mapper(asset.href, client_kwargs={"timeout": ClientTimeout(total=5000, connect=1000)})

GeoDataFrame Value Error: 'data' should be a 1-dimensional array of geometry objects'

I want to quantify some geolocations with osmnx using the nearest_edges-function. I get a value error message when running this code and don't know what I'm doing wrong:
# project graph and points
G_proj = ox.project_graph(G)
gdf_loc_p = gdf_loc["geometry"].to_crs(G_proj.graph["crs"])
ne, d = ox.nearest_edges(
G_proj, X=gdf_loc_p.x.values, Y=gdf_loc_p.y.values, return_dist=True
)
# reindex points based on results from nearest_edges
gdf_loc = (
gdf_loc.set_index(pd.MultiIndex.from_tuples(ne, names=["u", "v", "key"]))
.assign(distance=d)
.sort_index()
)
# join geometry from edges back to points
# aggregate so have number of accidents on each edge
gdf_bad_roads = (
gdf_edges.join(gdf_loc, rsuffix="_loc", how="inner")
.groupby(["u", "v", "key"])
.agg(geometry = ("geometry", "first"), number=("osmid", "size"))
.set_crs(gdf_edges.crs)
)
When running it tells me in the line .agg(geometry)# we require a list, but not a 'str' and from there on couple more issues leading to a value error data' should be a 1-dimensional array of geometry objects. I attached the whole Traceback. Thanks for your help!
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
/var/folders/jy/1f2tlvb965g30zhw9q3cvdw07r5rb_/T/ipykernel_82991/3621029527.py in <module>
2 # aggregate so have number of accidents on each edge
3 gdf_bad_roads = (
----> 4 gdf_edges.join(gdf_loc, rsuffix="_loc", how="inner")
5 .groupby(["u", "v", "key"])
6 .agg(geometry = ("geometry", "first"), number=("osmid", "size"))
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/core/groupby/generic.py in aggregate(self, func, engine, engine_kwargs, *args, **kwargs)
977
978 op = GroupByApply(self, func, args, kwargs)
--> 979 result = op.agg()
980 if not is_dict_like(func) and result is not None:
981 return result
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/core/apply.py in agg(self)
159
160 if is_dict_like(arg):
--> 161 return self.agg_dict_like()
162 elif is_list_like(arg):
163 # we require a list, but not a 'str'
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/core/apply.py in agg_dict_like(self)
457
458 axis = 0 if isinstance(obj, ABCSeries) else 1
--> 459 result = concat(
460 {k: results[k] for k in keys_to_use}, axis=axis, keys=keys_to_use
461 )
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/util/_decorators.py in wrapper(*args, **kwargs)
309 stacklevel=stacklevel,
310 )
--> 311 return func(*args, **kwargs)
312
313 return wrapper
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/core/reshape/concat.py in concat(objs, axis, join, ignore_index, keys, levels, names, verify_integrity, sort, copy)
305 )
306
--> 307 return op.get_result()
308
309
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/core/reshape/concat.py in get_result(self)
537
538 cons = sample._constructor
--> 539 return cons(new_data).__finalize__(self, method="concat")
540
541 def _get_result_dim(self) -> int:
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/geopandas/geodataframe.py in __init__(self, data, geometry, crs, *args, **kwargs)
155 try:
156 if (
--> 157 hasattr(self["geometry"].values, "crs")
158 and self["geometry"].values.crs
159 and crs
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/geopandas/geodataframe.py in __getitem__(self, key)
1325 GeoDataFrame.
1326 """
-> 1327 result = super().__getitem__(key)
1328 geo_col = self._geometry_column_name
1329 if isinstance(result, Series) and isinstance(result.dtype, GeometryDtype):
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/core/frame.py in __getitem__(self, key)
3424 if self.columns.is_unique and key in self.columns:
3425 if isinstance(self.columns, MultiIndex):
-> 3426 return self._getitem_multilevel(key)
3427 return self._get_item_cache(key)
3428
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/core/frame.py in _getitem_multilevel(self, key)
3511 result_columns = maybe_droplevels(new_columns, key)
3512 if self._is_mixed_type:
-> 3513 result = self.reindex(columns=new_columns)
3514 result.columns = result_columns
3515 else:
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/util/_decorators.py in wrapper(*args, **kwargs)
322 #wraps(func)
323 def wrapper(*args, **kwargs) -> Callable[..., Any]:
--> 324 return func(*args, **kwargs)
325
326 kind = inspect.Parameter.POSITIONAL_OR_KEYWORD
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/core/frame.py in reindex(self, *args, **kwargs)
4770 kwargs.pop("axis", None)
4771 kwargs.pop("labels", None)
-> 4772 return super().reindex(**kwargs)
4773
4774 #deprecate_nonkeyword_arguments(version=None, allowed_args=["self", "labels"])
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/core/generic.py in reindex(self, *args, **kwargs)
4816
4817 # perform the reindex on the axes
-> 4818 return self._reindex_axes(
4819 axes, level, limit, tolerance, method, fill_value, copy
4820 ).__finalize__(self, method="reindex")
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/core/frame.py in _reindex_axes(self, axes, level, limit, tolerance, method, fill_value, copy)
4589 columns = axes["columns"]
4590 if columns is not None:
-> 4591 frame = frame._reindex_columns(
4592 columns, method, copy, level, fill_value, limit, tolerance
4593 )
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/core/frame.py in _reindex_columns(self, new_columns, method, copy, level, fill_value, limit, tolerance)
4634 new_columns, method=method, level=level, limit=limit, tolerance=tolerance
4635 )
-> 4636 return self._reindex_with_indexers(
4637 {1: [new_columns, indexer]},
4638 copy=copy,
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/pandas/core/generic.py in _reindex_with_indexers(self, reindexers, fill_value, copy, allow_dups)
4895 new_data = new_data.copy()
4896
-> 4897 return self._constructor(new_data).__finalize__(self)
4898
4899 def filter(
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/geopandas/geodataframe.py in __init__(self, data, geometry, crs, *args, **kwargs)
162 _crs_mismatch_warning()
163 # TODO: raise error in 0.9 or 0.10.
--> 164 self["geometry"] = _ensure_geometry(self["geometry"].values, crs)
165 except TypeError:
166 pass
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/geopandas/geodataframe.py in _ensure_geometry(data, crs)
44 return GeoSeries(out, index=data.index, name=data.name)
45 else:
---> 46 out = from_shapely(data, crs=crs)
47 return out
48
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/geopandas/array.py in from_shapely(data, crs)
149
150 """
--> 151 return GeometryArray(vectorized.from_shapely(data), crs=crs)
152
153
~/opt/anaconda3/envs/pyproj_env/lib/python3.10/site-packages/geopandas/array.py in __init__(self, data, crs)
278 )
279 elif not data.ndim == 1:
--> 280 raise ValueError(
281 "'data' should be a 1-dimensional array of geometry objects."
282 )
ValueError: 'data' should be a 1-dimensional array of geometry objects.
Edit: thank you! Unfortunately it doesnt work. I downgraded Python to 3.9 (and upgraded Panda to 1.4 but have same issue). I added the Traceback of the other code as well.
----
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Input In [4], in <cell line: 4>()
2 gdf_bad_roads = gdf_edges.join(gdf_loc, rsuffix="_loc", how="inner")
3 # aggregate so have number of accidents on each edge
----> 4 gdf_bad_roads_agg = gdf_bad_roads.groupby(["u", "v", "key"]).agg(
5 geometry=("geometry", "first"), number=("osmid", "size")
6 ).set_crs(gdf_edges.crs)
8 print(f"""
9 pandas: {pd.__version__}
10 geopandas: {gpd.__version__}
11 osmnx: {ox.__version__}""")
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/core/groupby/generic.py:869, in DataFrameGroupBy.aggregate(self, func, engine, engine_kwargs, *args, **kwargs)
866 func = maybe_mangle_lambdas(func)
868 op = GroupByApply(self, func, args, kwargs)
--> 869 result = op.agg()
870 if not is_dict_like(func) and result is not None:
871 return result
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/core/apply.py:168, in Apply.agg(self)
165 return self.apply_str()
167 if is_dict_like(arg):
--> 168 return self.agg_dict_like()
169 elif is_list_like(arg):
170 # we require a list, but not a 'str'
171 return self.agg_list_like()
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/core/apply.py:498, in Apply.agg_dict_like(self)
495 keys_to_use = ktu
497 axis = 0 if isinstance(obj, ABCSeries) else 1
--> 498 result = concat(
499 {k: results[k] for k in keys_to_use}, axis=axis, keys=keys_to_use
500 )
501 elif any(is_ndframe):
502 # There is a mix of NDFrames and scalars
503 raise ValueError(
504 "cannot perform both aggregation "
505 "and transformation operations "
506 "simultaneously"
507 )
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/util/_decorators.py:311, in deprecate_nonkeyword_arguments.<locals>.decorate.<locals>.wrapper(*args, **kwargs)
305 if len(args) > num_allow_args:
306 warnings.warn(
307 msg.format(arguments=arguments),
308 FutureWarning,
309 stacklevel=stacklevel,
310 )
--> 311 return func(*args, **kwargs)
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/core/reshape/concat.py:359, in concat(objs, axis, join, ignore_index, keys, levels, names, verify_integrity, sort, copy)
155 """
156 Concatenate pandas objects along a particular axis with optional set logic
157 along the other axes.
(...)
344 ValueError: Indexes have overlapping values: ['a']
345 """
346 op = _Concatenator(
347 objs,
348 axis=axis,
(...)
356 sort=sort,
357 )
--> 359 return op.get_result()
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/core/reshape/concat.py:599, in _Concatenator.get_result(self)
596 new_data._consolidate_inplace()
598 cons = sample._constructor
--> 599 return cons(new_data).__finalize__(self, method="concat")
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/geopandas/geodataframe.py:157, in GeoDataFrame.__init__(self, data, geometry, crs, *args, **kwargs)
154 index = self.index
155 try:
156 if (
--> 157 hasattr(self["geometry"].values, "crs")
158 and self["geometry"].values.crs
159 and crs
160 and not self["geometry"].values.crs == crs
161 ):
162 _crs_mismatch_warning()
163 # TODO: raise error in 0.9 or 0.10.
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/geopandas/geodataframe.py:1327, in GeoDataFrame.__getitem__(self, key)
1321 def __getitem__(self, key):
1322 """
1323 If the result is a column containing only 'geometry', return a
1324 GeoSeries. If it's a DataFrame with a 'geometry' column, return a
1325 GeoDataFrame.
1326 """
-> 1327 result = super().__getitem__(key)
1328 geo_col = self._geometry_column_name
1329 if isinstance(result, Series) and isinstance(result.dtype, GeometryDtype):
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/core/frame.py:3473, in DataFrame.__getitem__(self, key)
3471 if self.columns.is_unique and key in self.columns:
3472 if isinstance(self.columns, MultiIndex):
-> 3473 return self._getitem_multilevel(key)
3474 return self._get_item_cache(key)
3476 # Do we have a slicer (on rows)?
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/core/frame.py:3560, in DataFrame._getitem_multilevel(self, key)
3558 result_columns = maybe_droplevels(new_columns, key)
3559 if self._is_mixed_type:
-> 3560 result = self.reindex(columns=new_columns)
3561 result.columns = result_columns
3562 else:
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/util/_decorators.py:324, in rewrite_axis_style_signature.<locals>.decorate.<locals>.wrapper(*args, **kwargs)
322 #wraps(func)
323 def wrapper(*args, **kwargs) -> Callable[..., Any]:
--> 324 return func(*args, **kwargs)
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/core/frame.py:4798, in DataFrame.reindex(self, *args, **kwargs)
4796 kwargs.pop("axis", None)
4797 kwargs.pop("labels", None)
-> 4798 return super().reindex(**kwargs)
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/core/generic.py:4974, in NDFrame.reindex(self, *args, **kwargs)
4971 return self._reindex_multi(axes, copy, fill_value)
4973 # perform the reindex on the axes
-> 4974 return self._reindex_axes(
4975 axes, level, limit, tolerance, method, fill_value, copy
4976 ).__finalize__(self, method="reindex")
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/core/frame.py:4611, in DataFrame._reindex_axes(self, axes, level, limit, tolerance, method, fill_value, copy)
4609 columns = axes["columns"]
4610 if columns is not None:
-> 4611 frame = frame._reindex_columns(
4612 columns, method, copy, level, fill_value, limit, tolerance
4613 )
4615 index = axes["index"]
4616 if index is not None:
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/core/frame.py:4656, in DataFrame._reindex_columns(self, new_columns, method, copy, level, fill_value, limit, tolerance)
4643 def _reindex_columns(
4644 self,
4645 new_columns,
(...)
4651 tolerance=None,
4652 ):
4653 new_columns, indexer = self.columns.reindex(
4654 new_columns, method=method, level=level, limit=limit, tolerance=tolerance
4655 )
-> 4656 return self._reindex_with_indexers(
4657 {1: [new_columns, indexer]},
4658 copy=copy,
4659 fill_value=fill_value,
4660 allow_dups=False,
4661 )
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/pandas/core/generic.py:5054, in NDFrame._reindex_with_indexers(self, reindexers, fill_value, copy, allow_dups)
5051 if copy and new_data is self._mgr:
5052 new_data = new_data.copy()
-> 5054 return self._constructor(new_data).__finalize__(self)
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/geopandas/geodataframe.py:164, in GeoDataFrame.__init__(self, data, geometry, crs, *args, **kwargs)
162 _crs_mismatch_warning()
163 # TODO: raise error in 0.9 or 0.10.
--> 164 self["geometry"] = _ensure_geometry(self["geometry"].values, crs)
165 except TypeError:
166 pass
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/geopandas/geodataframe.py:46, in _ensure_geometry(data, crs)
44 return GeoSeries(out, index=data.index, name=data.name)
45 else:
---> 46 out = from_shapely(data, crs=crs)
47 return out
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/geopandas/array.py:151, in from_shapely(data, crs)
135 def from_shapely(data, crs=None):
136 """
137 Convert a list or array of shapely objects to a GeometryArray.
138
(...)
149
150 """
--> 151 return GeometryArray(vectorized.from_shapely(data), crs=crs)
File ~/opt/anaconda3/envs/pyproj_env/lib/python3.9/site-packages/geopandas/array.py:280, in GeometryArray.__init__(self, data, crs)
275 raise TypeError(
276 "'data' should be array of geometry objects. Use from_shapely, "
277 "from_wkb, from_wkt functions to construct a GeometryArray."
278 )
279 elif not data.ndim == 1:
--> 280 raise ValueError(
281 "'data' should be a 1-dimensional array of geometry objects."
282 )
283 self.data = data
285 self._crs = None
ValueError: 'data' should be a 1-dimensional array of geometry objects.
pandas: 1.4.1
geopandas: 0.10.2
osmnx: 1.1.2
have changed this to a MWE
have separated out join() and groupby() / agg()
have included versions
one difference I can see - python 3.9 vs 3.10
import osmnx as ox
import geopandas as gpd
import pandas as pd
import io
df = pd.read_csv(
io.StringIO(
"""AccidentUID,AccidentLocation_CHLV95_E,AccidentLocation_CHLV95_N
99BA5D383B96D02AE0430A865E33D02A,2663985,1213215
9B25C4871C909022E0430A865E339022,2666153,1211303
9B71AB601D948092E0430A865E338092,2666168,1211785
9C985CF7710A60C0E0430A865E3360C0,2663991,1213203
9EA9548660AB3002E0430A865E333002,2666231,1210786
9B2E8B25D5C29094E0430A865E339094,2666728,1210404
9C87C10FB73A905EE0430A865E33905E,2666220,1211811
9E30F39D35CA1058E0430A865E331058,2664599,1212960
9BC2EA43E0BFC068E0430A865E33C068,2665533,1212617
9C0BB9332AB30044E0430A865E330044,2666852,1211964"""
)
)
gdf_loc = gpd.GeoDataFrame(
data=df,
geometry=gpd.points_from_xy(
df["AccidentLocation_CHLV95_E"], df["AccidentLocation_CHLV95_N"]
),
crs="EPSG:2056",
).to_crs("epsg:4326")
# get OSM data for investigated location
G = ox.graph_from_place("Luzern, Switzerland", network_type="drive")
G_proj = ox.project_graph(G)
gdf_nodes, gdf_edges = ox.utils_graph.graph_to_gdfs(G_proj)
# project graph and points
gdf_loc_p = gdf_loc["geometry"].to_crs(G_proj.graph["crs"])
ne, d = ox.nearest_edges(
G_proj, X=gdf_loc_p.x.values, Y=gdf_loc_p.y.values, return_dist=True
)
# reindex points based on results from nearest_edges
gdf_loc = (
gdf_loc.set_index(pd.MultiIndex.from_tuples(ne, names=["u", "v", "key"]))
.assign(distance=d)
.sort_index()
)
# join geometry from edges back to points
gdf_bad_roads = gdf_edges.join(gdf_loc, rsuffix="_loc", how="inner")
# aggregate so have number of accidents on each edge
gdf_bad_roads_agg = gdf_bad_roads.groupby(["u", "v", "key"]).agg(
geometry=("geometry", "first"), number=("osmid", "size")
).set_crs(gdf_edges.crs)
print(f"""
pandas: {pd.__version__}
geopandas: {gpd.__version__}
osmnx: {ox.__version__}""")
pandas: 1.4.0
geopandas: 0.10.2
osmnx: 1.1.2
Alternative aggregate syntax. Has been confirmed both work
hence conclusion is that named aggregations are failing. Possibly should be raised as an issue on pandas, but is not failing on all environments
groupby()/apply() is doing a first on shared edges and also necessary to set CRS again
dissolve() is doing a unary union on geometries. Conceptually should be the same, but is giving slightly different geometry. (A unary union of identical geometries IMHO is an instance of one of the geometries)
gdf_bad_roads.groupby(["u", "v", "key"]).agg({"geometry":"first", "AccidentUID":"size"}).set_crs(gdf_edges.crs).explore(color="blue")
gdf_bad_roads.dissolve(["u", "v", "key"], aggfunc={"AccidentUID":"size"}).explore(color="blue")

Numpy - Length of values (1191) does not match length of index (1250)

would appreciate any help with this, I'm getting and error of
ValueError: Length of values (1191) does not match length of index (1250).
I don't understand where Numpy is getting the length of 1191 from ?, I've created a Dataframe of 1250, and I'm trying to assign future['floor'] to it based on conditions, future['cap'] works fine, but that is Pandas, whereas 'Floor' is using NP, but I don't understand why NP would cause this error. Thanks for your help. Gav
future = m.make_future_dataframe(periods=1250,freq='D', include_history=False)
conditions = [
g['Operator'] == 100151,
g['Operator'] == 20137,
g['Operator'] == 20147,
]
values = [
g['y'].mean()/2,
g['y'].mean()/2,
g['y'].mean()/2
]
future['floor'] = np.select(conditions,values)
future['cap'] = max(g['y'])*1.25
forecast = m.predict(future)
ValueError Traceback (most recent call last)
<ipython-input-184-a698f789f6b3> in <module>
----> 1 fout = df.groupby('Operator').apply(forecast_data)
~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, func, *args, **kwargs)
892 with option_context("mode.chained_assignment", None):
893 try:
--> 894 result = self._python_apply_general(f, self._selected_obj)
895 except TypeError:
896 # gh-20949
~\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _python_apply_general(self, f, data)
926 data after applying f
927 """
--> 928 keys, values, mutated = self.grouper.apply(f, data, self.axis)
929
930 return self._wrap_applied_output(
~\Anaconda3\lib\site-packages\pandas\core\groupby\ops.py in apply(self, f, data, axis)
236 # group might be modified
237 group_axes = group.axes
--> 238 res = f(group)
239 if not _is_indexed_like(res, group_axes, axis):
240 mutated = True
<ipython-input-183-f88148e0e94e> in forecast_data(g)
42 g['y'].mean()/2
43 ]
---> 44 future['floor'] = np.select(conditions,values)
45 future['cap'] = max(g['y'])*1.25
46 forecast = m.predict(future)
~\Anaconda3\lib\site-packages\pandas\core\frame.py in __setitem__(self, key, value)
3161 else:
3162 # set column
-> 3163 self._set_item(key, value)
3164
3165 def _setitem_slice(self, key: slice, value):
~\Anaconda3\lib\site-packages\pandas\core\frame.py in _set_item(self, key, value)
3240 """
3241 self._ensure_valid_index(value)
-> 3242 value = self._sanitize_column(key, value)
3243 NDFrame._set_item(self, key, value)
3244
~\Anaconda3\lib\site-packages\pandas\core\frame.py in _sanitize_column(self, key, value, broadcast)
3897
3898 # turn me into an ndarray
-> 3899 value = sanitize_index(value, self.index)
3900 if not isinstance(value, (np.ndarray, Index)):
3901 if isinstance(value, list) and len(value) > 0:
~\Anaconda3\lib\site-packages\pandas\core\internals\construction.py in sanitize_index(data, index)
749 """
750 if len(data) != len(index):
--> 751 raise ValueError(
752 "Length of values "
753 f"({len(data)}) "
ValueError: Length of values (1191) does not match length of index (1250)

Python/Numba: Trouble creating custom type using Numba Extension API

I am trying to create a custom Numba Type. I am having issues boxing and unboxing Numba Numpy Arrays to a Native Numpy Arrays.
I have searched online for similar issues and followed the documentation example to the best of my ability. (https://numba.pydata.org/numba-doc/latest/extending/interval-example.html).
I have tried to interpret (https://github.com/numba/numba/blob/master/numba/targets/boxing.py) but it is quite difficult. Therefore, I think I might be doing something small wrong.
Below is my current attempt at including a Numpy array in my custom type.
import numpy as np
from numba import types, cgutils
from numba.extending import typeof_impl, type_callable, models
from numba.extending import register_model, make_attribute_wrapper, overload_attribute
from numba.extending import lower_builtin, unbox, NativeValue, box
class BMatrix(object):
"""
A empty wrapper for a Binary Matrix
"""
def __init__(self, m, n, row_index):#, col_index):
self.m = m
self.n = n
self.row_index = row_index
# self.col_i = col_index
def __repr__(self):
return 'BMatrix(%d, %d)' % (self.m, self.n)
#property
def shape(self):
return (self.m, self.n)
class BMatrixType(types.Type):
def __init__(self):
super(BMatrixType, self).__init__(name='BMatrix')
bmatrix_type = BMatrixType()
#typeof_impl.register(BMatrix)
def typeof_index(val, c):
return bmatrix_type
#type_callable(BMatrix)
def type_bmatrix(context):
def typer(m, n, row_index):
if (isinstance(m, types.Integer)
and isinstance(n, types.Integer)
and isinstance(row_index, nb.types.Array)):
# and isinstance(col_index, nb.types.Array)):
return bmatrix_type
return typer
#register_model(BMatrixType)
class BMatrixModel(models.StructModel):
def __init__(self, dmm, fe_type):
members = [
('m', types.int64),
('n', types.int64),
('row_index', types.Array(types.int64, 1, 'C'))
]
models.StructModel.__init__(self, dmm, fe_type, members)
make_attribute_wrapper(BMatrixType, 'm', 'm')
make_attribute_wrapper(BMatrixType, 'n', 'n')
make_attribute_wrapper(BMatrixType, 'row_index', 'row_index')
#overload_attribute(BMatrixType, "shape")
def get_shape(bmatrix):
def getter(bmatrix):
return (bmatrix.m, bmatrix.n)
return getter
#lower_builtin(BMatrix, types.Integer, types.Integer, types.Array) #nb.types.Array, #nb.types.Array)
def impl_bmatrix(context, builder, sig, args):
typ = sig.return_type
m, n, row_index = args
bmatrix = cgutils.create_struct_proxy(typ)(context, builder)
bmatrix.m = m
bmatrix.n = n
bmatrix.row_index = row_index
return bmatrix._getvalue()
#unbox(BMatrixType)
def unbox_bmatrix(typ, obj, c):
"""
Convert a BMatrixType object to a native interval structure.
"""
m_obj = c.pyapi.object_getattr_string(obj, "m")
n_obj = c.pyapi.object_getattr_string(obj, "n")
row_index_obj = c.pyapi.object_getattr_string(obj, "row_index")
BMatrix = cgutils.create_struct_proxy(typ)(c.context, c.builder)
BMatrix.m = c.pyapi.long_as_longlong(m_obj)
BMatrix.n = c.pyapi.long_as_longlong(n_obj)
BMatrix.row_index = nb.targets.boxing.unbox_array(types.Array(types.int64, 1, 'C'),
row_index_obj, c)
c.pyapi.decref(m_obj)
c.pyapi.decref(n_obj)
c.pyapi.decref(row_index_obj)
is_error = cgutils.is_not_null(c.builder, c.pyapi.err_occurred())
return NativeValue(BMatrix._getvalue(), is_error=is_error)
#box(BMatrixType)
def box_bmatrix(typ, val, c):
"""
Convert a native bmatrix structure to an BMatrix object.
"""
Bmatrix = cgutils.create_struct_proxy(typ)(c.context, c.builder, value=val)
m_obj = c.pyapi.long_from_longlong(Bmatrix.m)
n_obj = c.pyapi.long_from_longlong(Bmatrix.n)
row_index_obj = nb.targets.boxing.box_array(types.Array(types.int64, 1, 'C'),
Bmatrix.row_index, c)
class_obj = c.pyapi.unserialize(c.pyapi.serialize_object(Bmatrix))
res = c.pyapi.call_function_objargs(class_obj, (m_obj, n_obj))
c.pyapi.decref(m_obj)
c.pyapi.decref(n_obj)
c.pyapi.decref(row_index_obj)
c.pyapi.decref(class_obj)
return res
Test Cases (The error Tracebacks are absolutely massive for test_2 and test_3).
#nb.jit(nopython=True)
def test_1(): #Runs
x = BMatrix(10, 10, np.array([10,10,10]))
def test_2(): #Errors
x = BMatrix(10, 10, np.array([10,10,10]))
#nb.jit(nopython=True)
def _test_2(y):
return y
return _test_2(x)
#nb.jit(nopython=True)
def test_3(): #Errors
return BMatrix(10, 10, np.array([10,10,10]))
#nb.jit(nopython=True)
def test_4():
return BMatrix(10, 10, np.array([10,10,10])).row_index
These are the error when I run the test cases
test_1() #Runs
test_2()
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-52-0f6d1bdba40b> in <module>
----> 1 test_2()
<ipython-input-51-60141c9792c1> in test_2()
9 return y
10
---> 11 return _test_2(x)
12 #nb.jit(nopython=True)
13 def test_3():
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in _compile_for_args(self, *args, **kws)
368 e.patch_message(''.join(e.args) + help_msg)
369 # ignore the FULL_TRACEBACKS config, this needs reporting!
--> 370 raise e
371
372 def inspect_llvm(self, signature=None):
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in _compile_for_args(self, *args, **kws)
325 argtypes.append(self.typeof_pyval(a))
326 try:
--> 327 return self.compile(tuple(argtypes))
328 except errors.TypingError as e:
329 # Intercept typing error that may be due to an argument
//anaconda3/lib/python3.7/site-packages/numba/compiler_lock.py in _acquire_compile_lock(*args, **kwargs)
30 def _acquire_compile_lock(*args, **kwargs):
31 with self:
---> 32 return func(*args, **kwargs)
33 return _acquire_compile_lock
34
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in compile(self, sig)
657
658 self._cache_misses[sig] += 1
--> 659 cres = self._compiler.compile(args, return_type)
660 self.add_overload(cres)
661 self._cache.save_overload(sig, cres)
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in compile(self, args, return_type)
81 args=args, return_type=return_type,
82 flags=flags, locals=self.locals,
---> 83 pipeline_class=self.pipeline_class)
84 # Check typing error if object mode is used
85 if cres.typing_error is not None and not flags.enable_pyobject:
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in compile_extra(typingctx, targetctx, func, args, return_type, flags, locals, library, pipeline_class)
953 pipeline = pipeline_class(typingctx, targetctx, library,
954 args, return_type, flags, locals)
--> 955 return pipeline.compile_extra(func)
956
957
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in compile_extra(self, func)
375 self.lifted = ()
376 self.lifted_from = None
--> 377 return self._compile_bytecode()
378
379 def compile_ir(self, func_ir, lifted=(), lifted_from=None):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in _compile_bytecode(self)
884 """
885 assert self.func_ir is None
--> 886 return self._compile_core()
887
888 def _compile_ir(self):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in _compile_core(self)
871 self.define_pipelines(pm)
872 pm.finalize()
--> 873 res = pm.run(self.status)
874 if res is not None:
875 # Early pipeline completion
//anaconda3/lib/python3.7/site-packages/numba/compiler_lock.py in _acquire_compile_lock(*args, **kwargs)
30 def _acquire_compile_lock(*args, **kwargs):
31 with self:
---> 32 return func(*args, **kwargs)
33 return _acquire_compile_lock
34
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in run(self, status)
252 # No more fallback pipelines?
253 if is_final_pipeline:
--> 254 raise patched_exception
255 # Go to next fallback pipeline
256 else:
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in run(self, status)
243 try:
244 event("-- %s" % stage_name)
--> 245 stage()
246 except _EarlyPipelineCompletion as e:
247 return e.result
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in stage_nopython_backend(self)
745 """
746 lowerfn = self.backend_nopython_mode
--> 747 self._backend(lowerfn, objectmode=False)
748
749 def stage_compile_interp_mode(self):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in _backend(self, lowerfn, objectmode)
685 self.library.enable_object_caching()
686
--> 687 lowered = lowerfn()
688 signature = typing.signature(self.return_type, *self.args)
689 self.cr = compile_result(
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in backend_nopython_mode(self)
672 self.calltypes,
673 self.flags,
--> 674 self.metadata)
675
676 def _backend(self, lowerfn, objectmode):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in native_lowering_stage(targetctx, library, interp, typemap, restype, calltypes, flags, metadata)
1124 lower.lower()
1125 if not flags.no_cpython_wrapper:
-> 1126 lower.create_cpython_wrapper(flags.release_gil)
1127 env = lower.env
1128 call_helper = lower.call_helper
//anaconda3/lib/python3.7/site-packages/numba/lowering.py in create_cpython_wrapper(self, release_gil)
269 self.context.create_cpython_wrapper(self.library, self.fndesc,
270 self.env, self.call_helper,
--> 271 release_gil=release_gil)
272
273 def setup_function(self, fndesc):
//anaconda3/lib/python3.7/site-packages/numba/targets/cpu.py in create_cpython_wrapper(self, library, fndesc, env, call_helper, release_gil)
155 fndesc, env, call_helper=call_helper,
156 release_gil=release_gil)
--> 157 builder.build()
158 library.add_ir_module(wrapper_module)
159
//anaconda3/lib/python3.7/site-packages/numba/callwrapper.py in build(self)
120
121 api = self.context.get_python_api(builder)
--> 122 self.build_wrapper(api, builder, closure, args, kws)
123
124 return wrapper, api
//anaconda3/lib/python3.7/site-packages/numba/callwrapper.py in build_wrapper(self, api, builder, closure, args, kws)
153 innerargs.append(None)
154 else:
--> 155 val = cleanup_manager.add_arg(builder.load(obj), ty)
156 innerargs.append(val)
157
//anaconda3/lib/python3.7/site-packages/numba/callwrapper.py in add_arg(self, obj, ty)
30 """
31 # Unbox argument
---> 32 native = self.api.to_native_value(ty, obj)
33
34 # If an error occurred, go to the cleanup block for the previous argument.
//anaconda3/lib/python3.7/site-packages/numba/pythonapi.py in to_native_value(self, typ, obj)
1423 impl = _unboxers.lookup(typ.__class__, unbox_unsupported)
1424 c = _UnboxContext(self.context, self.builder, self)
-> 1425 return impl(typ, obj, c)
1426
1427 def from_native_return(self, typ, val, env_manager):
<ipython-input-45-d8ac5afde794> in unbox_bmatrix(typ, obj, c)
85 BMatrix.n = c.pyapi.long_as_longlong(n_obj)
86 BMatrix.row_index = nb.targets.boxing.unbox_array(types.Array(types.int64, 1, 'C'),
---> 87 row_index_obj, c)
88 c.pyapi.decref(m_obj)
89 c.pyapi.decref(n_obj)
//anaconda3/lib/python3.7/site-packages/numba/cgutils.py in __setattr__(self, field, value)
162 if field.startswith('_'):
163 return super(_StructProxy, self).__setattr__(field, value)
--> 164 self[self._datamodel.get_field_position(field)] = value
165
166 def __getitem__(self, index):
//anaconda3/lib/python3.7/site-packages/numba/cgutils.py in __setitem__(self, index, value)
177 ptr = self._get_ptr_by_index(index)
178 value = self._cast_member_from_value(index, value)
--> 179 if value.type != ptr.type.pointee:
180 if (is_pointer(value.type) and is_pointer(ptr.type.pointee)
181 and value.type.pointee == ptr.type.pointee.pointee):
AttributeError: Failed in nopython mode pipeline (step: nopython mode backend)
'NativeValue' object has no attribute 'type'
test_3()
KeyError Traceback (most recent call last)
//anaconda3/lib/python3.7/site-packages/numba/pythonapi.py in serialize_object(self, obj)
1403 try:
-> 1404 gv = self.module.__serialized[obj]
1405 except KeyError:
KeyError: <numba.cgutils.ValueStructProxy_BMatrix object at 0x11e693f28>
During handling of the above exception, another exception occurred:
PicklingError Traceback (most recent call last)
<ipython-input-53-8d78c7c0acee> in <module>
----> 1 test_3()
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in _compile_for_args(self, *args, **kws)
368 e.patch_message(''.join(e.args) + help_msg)
369 # ignore the FULL_TRACEBACKS config, this needs reporting!
--> 370 raise e
371
372 def inspect_llvm(self, signature=None):
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in _compile_for_args(self, *args, **kws)
325 argtypes.append(self.typeof_pyval(a))
326 try:
--> 327 return self.compile(tuple(argtypes))
328 except errors.TypingError as e:
329 # Intercept typing error that may be due to an argument
//anaconda3/lib/python3.7/site-packages/numba/compiler_lock.py in _acquire_compile_lock(*args, **kwargs)
30 def _acquire_compile_lock(*args, **kwargs):
31 with self:
---> 32 return func(*args, **kwargs)
33 return _acquire_compile_lock
34
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in compile(self, sig)
657
658 self._cache_misses[sig] += 1
--> 659 cres = self._compiler.compile(args, return_type)
660 self.add_overload(cres)
661 self._cache.save_overload(sig, cres)
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in compile(self, args, return_type)
81 args=args, return_type=return_type,
82 flags=flags, locals=self.locals,
---> 83 pipeline_class=self.pipeline_class)
84 # Check typing error if object mode is used
85 if cres.typing_error is not None and not flags.enable_pyobject:
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in compile_extra(typingctx, targetctx, func, args, return_type, flags, locals, library, pipeline_class)
953 pipeline = pipeline_class(typingctx, targetctx, library,
954 args, return_type, flags, locals)
--> 955 return pipeline.compile_extra(func)
956
957
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in compile_extra(self, func)
375 self.lifted = ()
376 self.lifted_from = None
--> 377 return self._compile_bytecode()
378
379 def compile_ir(self, func_ir, lifted=(), lifted_from=None):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in _compile_bytecode(self)
884 """
885 assert self.func_ir is None
--> 886 return self._compile_core()
887
888 def _compile_ir(self):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in _compile_core(self)
871 self.define_pipelines(pm)
872 pm.finalize()
--> 873 res = pm.run(self.status)
874 if res is not None:
875 # Early pipeline completion
//anaconda3/lib/python3.7/site-packages/numba/compiler_lock.py in _acquire_compile_lock(*args, **kwargs)
30 def _acquire_compile_lock(*args, **kwargs):
31 with self:
---> 32 return func(*args, **kwargs)
33 return _acquire_compile_lock
34
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in run(self, status)
252 # No more fallback pipelines?
253 if is_final_pipeline:
--> 254 raise patched_exception
255 # Go to next fallback pipeline
256 else:
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in run(self, status)
243 try:
244 event("-- %s" % stage_name)
--> 245 stage()
246 except _EarlyPipelineCompletion as e:
247 return e.result
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in stage_nopython_backend(self)
745 """
746 lowerfn = self.backend_nopython_mode
--> 747 self._backend(lowerfn, objectmode=False)
748
749 def stage_compile_interp_mode(self):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in _backend(self, lowerfn, objectmode)
685 self.library.enable_object_caching()
686
--> 687 lowered = lowerfn()
688 signature = typing.signature(self.return_type, *self.args)
689 self.cr = compile_result(
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in backend_nopython_mode(self)
672 self.calltypes,
673 self.flags,
--> 674 self.metadata)
675
676 def _backend(self, lowerfn, objectmode):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in native_lowering_stage(targetctx, library, interp, typemap, restype, calltypes, flags, metadata)
1124 lower.lower()
1125 if not flags.no_cpython_wrapper:
-> 1126 lower.create_cpython_wrapper(flags.release_gil)
1127 env = lower.env
1128 call_helper = lower.call_helper
//anaconda3/lib/python3.7/site-packages/numba/lowering.py in create_cpython_wrapper(self, release_gil)
269 self.context.create_cpython_wrapper(self.library, self.fndesc,
270 self.env, self.call_helper,
--> 271 release_gil=release_gil)
272
273 def setup_function(self, fndesc):
//anaconda3/lib/python3.7/site-packages/numba/targets/cpu.py in create_cpython_wrapper(self, library, fndesc, env, call_helper, release_gil)
155 fndesc, env, call_helper=call_helper,
156 release_gil=release_gil)
--> 157 builder.build()
158 library.add_ir_module(wrapper_module)
159
//anaconda3/lib/python3.7/site-packages/numba/callwrapper.py in build(self)
120
121 api = self.context.get_python_api(builder)
--> 122 self.build_wrapper(api, builder, closure, args, kws)
123
124 return wrapper, api
//anaconda3/lib/python3.7/site-packages/numba/callwrapper.py in build_wrapper(self, api, builder, closure, args, kws)
174
175 retty = self._simplified_return_type()
--> 176 obj = api.from_native_return(retty, retval, env_manager)
177 builder.ret(obj)
178
//anaconda3/lib/python3.7/site-packages/numba/pythonapi.py in from_native_return(self, typ, val, env_manager)
1429 "prevented the return of " \
1430 "optional value"
-> 1431 out = self.from_native_value(typ, val, env_manager)
1432 return out
1433
//anaconda3/lib/python3.7/site-packages/numba/pythonapi.py in from_native_value(self, typ, val, env_manager)
1443
1444 c = _BoxContext(self.context, self.builder, self, env_manager)
-> 1445 return impl(typ, val, c)
1446
1447 def reflect_native_value(self, typ, val, env_manager=None):
<ipython-input-45-d8ac5afde794> in box_bmatrix(typ, val, c)
104 Bmatrix.row_index, c)
105
--> 106 class_obj = c.pyapi.unserialize(c.pyapi.serialize_object(Bmatrix))
107 res = c.pyapi.call_function_objargs(class_obj, (m_obj, n_obj))
108 c.pyapi.decref(m_obj)
//anaconda3/lib/python3.7/site-packages/numba/pythonapi.py in serialize_object(self, obj)
1404 gv = self.module.__serialized[obj]
1405 except KeyError:
-> 1406 struct = self.serialize_uncached(obj)
1407 name = ".const.picklebuf.%s" % (id(obj) if config.DIFF_IR == 0 else "DIFF_IR")
1408 gv = self.context.insert_unique_const(self.module, name, struct)
//anaconda3/lib/python3.7/site-packages/numba/pythonapi.py in serialize_uncached(self, obj)
1383 """
1384 # First make the array constant
-> 1385 data = pickle.dumps(obj, protocol=-1)
1386 assert len(data) < 2**31
1387 name = ".const.pickledata.%s" % (id(obj) if config.DIFF_IR == 0 else "DIFF_IR")
PicklingError: Failed in nopython mode pipeline (step: nopython mode backend)
Can't pickle <class 'numba.cgutils.ValueStructProxy_BMatrix'>: attribute lookup ValueStructProxy_BMatrix on numba.cgutils failed
test_4() #Runs Wrong
array([-2387225703656530210, -2387225703656530210, -2387225703656530210])
unbox_array returns a NativeValue. Inside NativeValue is the actual value which is what you want to assign to row_index. So, just add ".value" to the end of the following line to extract the value from the NativeValue.
BMatrix.row_index = nb.targets.boxing.unbox_array(types.Array(types.int64, 1, 'C'), row_index_obj, c)

TypeError: unhashable type: 'numpy.ndarray' with Pandas after importing data from MYSQL

I ran the same program on two different data sources (a CSV file & MYSQL database), CSV import runs fine but MYSQL import throws the numpy type error:
I'm guessing issue may lie with these 2 points:
1. Data import issues - INT, TEXT etc? I'm using VARCHAR for the data.
2. Issue with how matplotlib works with Panda dataframes?
I'm new so please treat me as one :)
import pandas as pd
import numpy as np
import matplotlib.pyplot as pp
import seaborn
from sqlalchemy import create_engine
import pymysql
engine = create_engine("mysql+pymysql://root:root#127.0.0.1:3306/babynames",echo=False)
names = pd.read_sql_query('select * from BABYNAMES',engine)
names_indexed = names.set_index(['gender','name','year']).sort_index()
def plotname(gender, name):
data = names_indexed.loc[gender, name]
pp.plot(data.index, data.values)
plotname('F','Nancy')
Error code:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-32-9d981bcf8365> in <module>()
----> 1 plotname('F','Nancy')
<ipython-input-31-85c728659ad0> in plotname(gender, name)
1 def plotname(gender, name):
2 data = allyears_indexed.loc[gender, name]
----> 3 pp.plot(data.index, data.values)
~/anaconda3/lib/python3.7/site-packages/matplotlib/pyplot.py in plot(*args, **kwargs)
3361 mplDeprecation)
3362 try:
-> 3363 ret = ax.plot(*args, **kwargs)
3364 finally:
3365 ax._hold = washold
~/anaconda3/lib/python3.7/site-packages/matplotlib/__init__.py in inner(ax, *args, **kwargs)
1865 "the Matplotlib list!)" % (label_namer, func.__name__),
1866 RuntimeWarning, stacklevel=2)
-> 1867 return func(ax, *args, **kwargs)
1868
1869 inner.__doc__ = _add_data_doc(inner.__doc__,
~/anaconda3/lib/python3.7/site-packages/matplotlib/axes/_axes.py in plot(self, *args, **kwargs)
1526 kwargs = cbook.normalize_kwargs(kwargs, _alias_map)
1527
-> 1528 for line in self._get_lines(*args, **kwargs):
1529 self.add_line(line)
1530 lines.append(line)
~/anaconda3/lib/python3.7/site-packages/matplotlib/axes/_base.py in _grab_next_args(self, *args, **kwargs)
404 this += args[0],
405 args = args[1:]
--> 406 for seg in self._plot_args(this, kwargs):
407 yield seg
408
~/anaconda3/lib/python3.7/site-packages/matplotlib/axes/_base.py in _plot_args(self, tup, kwargs)
381 x, y = index_of(tup[-1])
382
--> 383 x, y = self._xy_from_xy(x, y)
384
385 if self.command == 'plot':
~/anaconda3/lib/python3.7/site-packages/matplotlib/axes/_base.py in _xy_from_xy(self, x, y)
214 if self.axes.xaxis is not None and self.axes.yaxis is not None:
215 bx = self.axes.xaxis.update_units(x)
--> 216 by = self.axes.yaxis.update_units(y)
217
218 if self.command != 'plot':
~/anaconda3/lib/python3.7/site-packages/matplotlib/axis.py in update_units(self, data)
1467 neednew = self.converter != converter
1468 self.converter = converter
-> 1469 default = self.converter.default_units(data, self)
1470 if default is not None and self.units is None:
1471 self.set_units(default)
~/anaconda3/lib/python3.7/site-packages/matplotlib/category.py in default_units(data, axis)
113 # default_units->axis_info->convert
114 if axis.units is None:
--> 115 axis.set_units(UnitData(data))
116 else:
117 axis.units.update(data)
~/anaconda3/lib/python3.7/site-packages/matplotlib/category.py in __init__(self, data)
180 self._counter = itertools.count(start=0)
181 if data is not None:
--> 182 self.update(data)
183
184 def update(self, data):
~/anaconda3/lib/python3.7/site-packages/matplotlib/category.py in update(self, data)
197 data = np.atleast_1d(np.array(data, dtype=object))
198
--> 199 for val in OrderedDict.fromkeys(data):
200 if not isinstance(val, VALID_TYPES):
201 raise TypeError("{val!r} is not a string".format(val=val))
TypeError: unhashable type: 'numpy.ndarray'
I was right, the issue was with the data types. I created a new table replacing VARCHAR for INT and then used the same code from above and the program worked perfectly.

Categories