We Keep Coding

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")

impossible to read a csv file ith pyspark

I try to read a csv file using pyspark with this pyspark code :
tr_df = spark.read.csv("/data/file.csv",
header=True, inferSchema=True
)
tr_df.head(5)
But I get this error :
ValueError Traceback (most recent call last)
<ipython-input-53-03432bbf269d> in <module>
----> 1 tr_df.head(5)
~/anaconda3/envs/naboo-env/lib/python3.6/site-packages/pyspark/sql/dataframe.py
in head(self, n)
1250 rs = self.head(1)
1251 return rs[0] if rs else None
-> 1252 return self.take(n)
1253
1254 #ignore_unicode_prefix
~/anaconda3/envs/naboo-env/lib/python3.6/site-packages/pyspark/sql/dataframe.py
in take(self, num)
569 [Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
570 """
--> 571 return self.limit(num).collect()
572
573 #since(1.3)
~/anaconda3/envs/naboo-env/lib/python3.6/site-packages/pyspark/sql/dataframe.py
in collect(self)
532 with SCCallSiteSync(self._sc) as css:
533 sock_info = self._jdf.collectToPython()
--> 534 return list(_load_from_socket(sock_info, BatchedSerializer(PickleSerializer())))
535
536 #ignore_unicode_prefix
~/anaconda3/envs/naboo-env/lib/python3.6/site-packages/pyspark/serializers.py
in load_stream(self, stream)
145 while True:
146 try:
--> 147 yield self._read_with_length(stream)
148 except EOFError:
149 return
~/anaconda3/envs/naboo-env/lib/python3.6/site-packages/pyspark/serializers.py
in _read_with_length(self, stream)
170 if len(obj) < length:
171 raise EOFError
--> 172 return self.loads(obj)
173
174 def dumps(self, obj):
~/anaconda3/envs/naboo-env/lib/python3.6/site-packages/pyspark/serializers.py
in loads(self, obj, encoding)
578 if sys.version >= '3':
579 def loads(self, obj, encoding="bytes"):
--> 580 return pickle.loads(obj, encoding=encoding)
581 else:
582 def loads(self, obj, encoding=None):
~/anaconda3/envs/naboo-env/lib/python3.6/site-packages/pyspark/sql/types.py
in _parse_datatype_json_string(json_string)
867 >>> check_datatype(complex_maptype)
868 """
--> 869 return _parse_datatype_json_value(json.loads(json_string))
870
871
~/anaconda3/envs/naboo-env/lib/python3.6/site-packages/pyspark/sql/types.py
in _parse_datatype_json_value(json_value)
884 tpe = json_value["type"]
885 if tpe in _all_complex_types:
--> 886 return _all_complex_types[tpe].fromJson(json_value)
887 elif tpe == 'udt':
888 return UserDefinedType.fromJson(json_value)
~/anaconda3/envs/naboo-env/lib/python3.6/site-packages/pyspark/sql/types.py
in fromJson(cls, json)
575 #classmethod
576 def fromJson(cls, json):
--> 577 return StructType([StructField.fromJson(f) for f in json["fields"]])
578
579 def fieldNames(self):
~/anaconda3/envs/naboo-env/lib/python3.6/site-packages/pyspark/sql/types.py
in (.0)
575 #classmethod
576 def fromJson(cls, json):
--> 577 return StructType([StructField.fromJson(f) for f in json["fields"]])
578
579 def fieldNames(self):
~/anaconda3/envs/naboo-env/lib/python3.6/site-packages/pyspark/sql/types.py
in fromJson(cls, json)
432 def fromJson(cls, json):
433 return StructField(json["name"],
--> 434 _parse_datatype_json_value(json["type"]),
435 json["nullable"],
436 json["metadata"])
~/anaconda3/envs/naboo-env/lib/python3.6/site-packages/pyspark/sql/types.py
in _parse_datatype_json_value(json_value)
880 return DecimalType(int(m.group(1)), int(m.group(2)))
881 else:
--> 882 raise ValueError("Could not parse datatype: %s" % json_value)
883 else:
884 tpe = json_value["type"]
ValueError: Could not parse datatype: decimal(17,-24)
Can anyone help me to resolve this problem please?
Thanks

Seems there is a problem with datatype in one of your columns. Hence its throwing error. Remove inferSchema =True option while reading. After reading the data,try to analayze datatype and make any corrections if needed, then apply your own schema.

How to print pandas dataframe containing some russian language

I am working on a following type of data.
itemid category subcategory title
1 10000010 Транспорт Автомобили с пробегом Toyota Sera, 1991
2 10000025 Услуги Предложения услуг Монтаж кровли
3 10000094 Личные вещи Одежда, обувь, аксессуары Костюм Steilmann
4 10000101 Транспорт Автомобили с пробегом Ford Focus, 2011
5 10000132 Транспорт Запчасти и аксессуары Турбина 3.0 Bar
6 10000152 Транспорт Автомобили с пробегом ВАЗ 2115 Samara, 2005
Now I run the following commands
import pandas as pd
trainingData = pd.read_table("train.tsv",nrows=10, header=0,encoding='utf-8')
trainingData['itemid'].head()
0 10000010
1 10000025
2 10000094
3 10000101
4 10000132
Name: itemid
Everything is good this point but when I do something like
trainingData['itemid','category'].head()
Error:
---------------------------------------------------------------------------
UnicodeDecodeError Traceback (most recent call last)
/home/vikram/Documents/Avito/ in ()
----> 1 trainingData[['itemid','category']].head()
/usr/lib/python2.7/dist-packages/IPython/core/displayhook.pyc in __call__(self, result)
236 self.start_displayhook()
237 self.write_output_prompt()
--> 238 format_dict = self.compute_format_data(result)
239 self.write_format_data(format_dict)
240 self.update_user_ns(result)
/usr/lib/python2.7/dist-packages/IPython/core/displayhook.pyc in compute_format_data(self, result)
148 MIME type representation of the object.
149 """
--> 150 return self.shell.display_formatter.format(result)
151
152 def write_format_data(self, format_dict):
/usr/lib/python2.7/dist-packages/IPython/core/formatters.pyc in format(self, obj, include, exclude)
124 continue
125 try:
--> 126 data = formatter(obj)
127 except:
128 # FIXME: log the exception
/usr/lib/python2.7/dist-packages/IPython/core/formatters.pyc in __call__(self, obj)
445 type_pprinters=self.type_printers,
446 deferred_pprinters=self.deferred_printers)
--> 447 printer.pretty(obj)
448 printer.flush()
449 return stream.getvalue()
/usr/lib/python2.7/dist-packages/IPython/lib/pretty.pyc in pretty(self, obj)
352 if callable(obj_class._repr_pretty_):
353 return obj_class._repr_pretty_(obj, self, cycle)
--> 354 return _default_pprint(obj, self, cycle)
355 finally:
356 self.end_group()
/usr/lib/python2.7/dist-packages/IPython/lib/pretty.pyc in _default_pprint(obj, p, cycle)
472 if getattr(klass, '__repr__', None) not in _baseclass_reprs:
473 # A user-provided repr.
--> 474 p.text(repr(obj))
475 return
476 p.begin_group(1, ' 456 self.to_string(buf=buf)
457 value = buf.getvalue()
458 if max([len(l) for l in value.split('\n')]) > terminal_width:
/usr/lib/pymodules/python2.7/pandas/core/frame.pyc in to_string(self, buf, columns, col_space, colSpace, header, index, na_rep, formatters, float_format, sparsify, nanRep, index_names, justify, force_unicode)
1024 index_names=index_names,
1025 header=header, index=index)
-> 1026 formatter.to_string(force_unicode=force_unicode)
1027
1028 if buf is None:
/usr/lib/pymodules/python2.7/pandas/core/format.pyc in to_string(self, force_unicode)
176 for i, c in enumerate(self.columns):
177 if self.header:
--> 178 fmt_values = self._format_col(c)
179 cheader = str_columns[i]
180 max_len = max(max(len(x) for x in fmt_values),
/usr/lib/pymodules/python2.7/pandas/core/format.pyc in _format_col(self, col)
217 float_format=self.float_format,
218 na_rep=self.na_rep,
--> 219 space=self.col_space)
220
221 def to_html(self):
/usr/lib/pymodules/python2.7/pandas/core/format.pyc in format_array(values, formatter, float_format, na_rep, digits, space, justify)
424 justify=justify)
425
--> 426 return fmt_obj.get_result()
427
428
/usr/lib/pymodules/python2.7/pandas/core/format.pyc in get_result(self)
471 fmt_values.append(float_format(v))
472 else:
--> 473 fmt_values.append(' %s' % _format(v))
474
475 return _make_fixed_width(fmt_values, self.justify)
/usr/lib/pymodules/python2.7/pandas/core/format.pyc in _format(x)
457 else:
458 # object dtype
--> 459 return '%s' % formatter(x)
460
461 vals = self.values
/usr/lib/pymodules/python2.7/pandas/core/common.pyc in _stringify(col)
503 def _stringify(col):
504 # unicode workaround
--> 505 return unicode(col)
506
507 def _maybe_make_list(obj):
UnicodeDecodeError: 'ascii' codec can't decode byte 0xd0 in position 0: ordinal not in range(128)
please help me "display" the data properly.

I had the same issue caused by IPython, which could not display non-ASCII text returned by the Pandas head() function. It turned out that the default encoding for Python was set to 'ascii' on my machine. You can check this with
import sys
sys.getdefaultencoding()
The solution was to re-set the default encoding to UTF-8:
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
After this, IPython displayed Pandas data frames with non-ASCII characters correctly.
Note that the reload call is necessary to make the setdefaultencoding function available. Without it you'll get the error:
AttributeError: 'module' object has no attribute 'setdefaultencoding'

Pandas duplicate datetimeindex entries lead to odd exception

Let's take the following contrived example where I create a DataFrame and then make a DatetimeIndex using a column with duplicate entries. I then place this DataFrame into a Panel and then attempt to iterate over the major axis.
import pandas as pd
import datetime as dt
a = [1371215933513120, 1371215933513121, 1371215933513122, 1371215933513122]
b = [1,2,3,4]
df = pd.DataFrame({'a':a, 'b':b, 'c':[dt.datetime.fromtimestamp(t/1000000.) for t in a]})
df.index=pd.DatetimeIndex(df['c'])
d = OrderedDict()
d['x'] = df
p = pd.Panel(d)
for y in p.major_axis:
print y
print p.major_xs(y)
This leads to the following output:
2013-06-14 15:18:53.513120
x
a 1371215933513120
b 1
c 2013-06-14 15:18:53.513120
2013-06-14 15:18:53.513121
x
a 1371215933513121
b 2
c 2013-06-14 15:18:53.513121
2013-06-14 15:18:53.513122
Followed by a rather cryptic (to me) error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-35-045aaae5a074> in <module>()
13 for y in p.major_axis:
14 print y
---> 15 print p.major_xs(y)
/usr/local/lib/python2.7/dist-packages/pandas-0.11.0-py2.7-linux-x86_64.egg/pandas/core/frame.py in __str__(self)
667 if py3compat.PY3:
668 return self.__unicode__()
--> 669 return self.__bytes__()
670
671 def __bytes__(self):
/usr/local/lib/python2.7/dist-packages/pandas-0.11.0-py2.7-linux-x86_64.egg/pandas/core/frame.py in __bytes__(self)
677 """
678 encoding = com.get_option("display.encoding")
--> 679 return self.__unicode__().encode(encoding, 'replace')
680
681 def __unicode__(self):
/usr/local/lib/python2.7/dist-packages/pandas-0.11.0-py2.7-linux-x86_64.egg/pandas/core/frame.py in __unicode__(self)
692 # This needs to compute the entire repr
693 # so don't do it unless rownum is bounded
--> 694 fits_horizontal = self._repr_fits_horizontal_()
695
696 if fits_vertical and fits_horizontal:
/usr/local/lib/python2.7/dist-packages/pandas-0.11.0-py2.7-linux-x86_64.egg/pandas/core/frame.py in _repr_fits_horizontal_(self)
652 d=d.iloc[:min(max_rows, height,len(d))]
653
--> 654 d.to_string(buf=buf)
655 value = buf.getvalue()
656 repr_width = max([len(l) for l in value.split('\n')])
/usr/local/lib/python2.7/dist-packages/pandas-0.11.0-py2.7-linux-x86_64.egg/pandas/core/frame.py in to_string(self, buf, columns, col_space, colSpace, header, index, na_rep, formatters, float_format, sparsify, nanRep, index_names, justify, force_unicode, line_width)
1489 header=header, index=index,
1490 line_width=line_width)
-> 1491 formatter.to_string()
1492
1493 if buf is None:
/usr/local/lib/python2.7/dist-packages/pandas-0.11.0-py2.7-linux-x86_64.egg/pandas/core/format.py in to_string(self, force_unicode)
312 text = info_line
313 else:
--> 314 strcols = self._to_str_columns()
315 if self.line_width is None:
316 text = adjoin(1, *strcols)
/usr/local/lib/python2.7/dist-packages/pandas-0.11.0-py2.7-linux-x86_64.egg/pandas/core/format.py in _to_str_columns(self)
265 for i, c in enumerate(self.columns):
266 if self.header:
--> 267 fmt_values = self._format_col(i)
268 cheader = str_columns[i]
269
/usr/local/lib/python2.7/dist-packages/pandas-0.11.0-py2.7-linux-x86_64.egg/pandas/core/format.py in _format_col(self, i)
403 float_format=self.float_format,
404 na_rep=self.na_rep,
--> 405 space=self.col_space)
406
407 def to_html(self, classes=None):
/usr/local/lib/python2.7/dist-packages/pandas-0.11.0-py2.7-linux-x86_64.egg/pandas/core/format.py in format_array(values, formatter, float_format, na_rep, digits, space, justify)
1319 justify=justify)
1320
-> 1321 return fmt_obj.get_result()
1322
1323
/usr/local/lib/python2.7/dist-packages/pandas-0.11.0-py2.7-linux-x86_64.egg/pandas/core/format.py in get_result(self)
1335
1336 def get_result(self):
-> 1337 fmt_values = self._format_strings()
1338 return _make_fixed_width(fmt_values, self.justify)
1339
/usr/local/lib/python2.7/dist-packages/pandas-0.11.0-py2.7-linux-x86_64.egg/pandas/core/format.py in _format_strings(self)
1362
1363 print "vals:", vals
-> 1364 is_float = lib.map_infer(vals, com.is_float) & notnull(vals)
1365 leading_space = is_float.any()
1366
ValueError: operands could not be broadcast together with shapes (2) (2,3)
Now, having explained that I'm creating an index with duplicate entries, the source of the error is clear. Without having known that, however, it would have been more difficult (again, for a novice like me) to figure out why this Exception was popping up.
This leads me to a few questions.
Is this really the expected behavior of pandas? Is it forbidden to create an index with duplicate entries, or is it just forbidden to iterate over them?
If it's forbidden to create such an index, then shouldn't an exception be raised when initially creating it?
If the iteration is somehow incorrect, shouldn't the error be more informative?
Am I doing something wrong?