Related
I have the following data with the name 'Salaries.csv'. It looks like the following:[The dataset has some columns like Index(['yearID', 'teamID', 'lgID', 'salary', 'num_feat'], dtype='object'). Please note that the column num_feat I have added to the DataFrame.
I want to do a Seaborn pairplot for team 'ATL' to plot scatter plots among all numeric features in the data frame.
I have the following code :
import seaborn as sns
var_set = [
"yearID",
"teamID",
"lgID",
"playerID",
"salary"
]
head_set = []
head_set.extend(var_set)
head_set.append("num_feat")
df = pd.read_csv('Salaries.csv',index_col='playerID', header=None, names=head_set)
df['num_feat'] = 100 * np.random.random_sample(df.shape[0]). #Adding column num_feat
df_copy = df
cols_with_team_ATL = df_copy.loc[df_copy.teamID=="ATL", ]
# Create the default pairplot
pairplot_fig = sns.pairplot(cols_with_team_ATL, vars=['yearID', 'salary', 'num_feat'])
plt.subplots_adjust(top=0.9)
pairplot_fig.fig.suptitle("Scatter plots among all numeric features in the data frame for teamID = ATL", fontsize=18, alpha=0.9, weight='bold')
plt.show()
The same code runs perfectly on my friend's system but not on mine. It shows the following error in my system :
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
/var/folders/ch/6r9p7n0j3xg1l79lz1zdkvsh0000gq/T/ipykernel_97373/3735184261.py in <module>
25 # Create the default pairplot
26 print(df.columns)
---> 27 pairplot_fig = sns.pairplot(cols_with_team_ATL, vars=['yearID', 'salary', 'num_feat'])
28 plt.subplots_adjust(top=0.9)
29 pairplot_fig.fig.suptitle("Scatter plots among all numeric features in the data frame for teamID = ATL", fontsize=18, alpha=0.9, weight='bold')
~/USC/anaconda3/lib/python3.9/site-packages/seaborn/_decorators.py in inner_f(*args, **kwargs)
44 )
45 kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 46 return f(**kwargs)
47 return inner_f
48
~/USC/anaconda3/lib/python3.9/site-packages/seaborn/axisgrid.py in pairplot(data, hue, hue_order, palette, vars, x_vars, y_vars, kind, diag_kind, markers, height, aspect, corner, dropna, plot_kws, diag_kws, grid_kws, size)
2124 diag_kws.setdefault("legend", False)
2125 if diag_kind == "hist":
-> 2126 grid.map_diag(histplot, **diag_kws)
2127 elif diag_kind == "kde":
2128 diag_kws.setdefault("fill", True)
~/USC/anaconda3/lib/python3.9/site-packages/seaborn/axisgrid.py in map_diag(self, func, **kwargs)
1476 plot_kwargs.setdefault("hue_order", self._hue_order)
1477 plot_kwargs.setdefault("palette", self._orig_palette)
-> 1478 func(x=vector, **plot_kwargs)
1479 ax.legend_ = None
1480
~/USC/anaconda3/lib/python3.9/site-packages/seaborn/distributions.py in histplot(data, x, y, hue, weights, stat, bins, binwidth, binrange, discrete, cumulative, common_bins, common_norm, multiple, element, fill, shrink, kde, kde_kws, line_kws, thresh, pthresh, pmax, cbar, cbar_ax, cbar_kws, palette, hue_order, hue_norm, color, log_scale, legend, ax, **kwargs)
1460 if p.univariate:
1461
-> 1462 p.plot_univariate_histogram(
1463 multiple=multiple,
1464 element=element,
~/USC/anaconda3/lib/python3.9/site-packages/seaborn/distributions.py in plot_univariate_histogram(self, multiple, element, fill, common_norm, common_bins, shrink, kde, kde_kws, color, legend, line_kws, estimate_kws, **plot_kws)
426
427 # First pass through the data to compute the histograms
--> 428 for sub_vars, sub_data in self.iter_data("hue", from_comp_data=True):
429
430 # Prepare the relevant data
~/USC/anaconda3/lib/python3.9/site-packages/seaborn/_core.py in iter_data(self, grouping_vars, reverse, from_comp_data)
981
982 if from_comp_data:
--> 983 data = self.comp_data
984 else:
985 data = self.plot_data
~/USC/anaconda3/lib/python3.9/site-packages/seaborn/_core.py in comp_data(self)
1055 orig = self.plot_data[var].dropna()
1056 comp_col = pd.Series(index=orig.index, dtype=float, name=var)
-> 1057 comp_col.loc[orig.index] = pd.to_numeric(axis.convert_units(orig))
1058
1059 if axis.get_scale() == "log":
~/USC/anaconda3/lib/python3.9/site-packages/pandas/core/indexing.py in __setitem__(self, key, value)
721
722 iloc = self if self.name == "iloc" else self.obj.iloc
--> 723 iloc._setitem_with_indexer(indexer, value, self.name)
724
725 def _validate_key(self, key, axis: int):
~/USC/anaconda3/lib/python3.9/site-packages/pandas/core/indexing.py in _setitem_with_indexer(self, indexer, value, name)
1730 self._setitem_with_indexer_split_path(indexer, value, name)
1731 else:
-> 1732 self._setitem_single_block(indexer, value, name)
1733
1734 def _setitem_with_indexer_split_path(self, indexer, value, name: str):
~/USC/anaconda3/lib/python3.9/site-packages/pandas/core/indexing.py in _setitem_single_block(self, indexer, value, name)
1966
1967 # actually do the set
-> 1968 self.obj._mgr = self.obj._mgr.setitem(indexer=indexer, value=value)
1969 self.obj._maybe_update_cacher(clear=True)
1970
~/USC/anaconda3/lib/python3.9/site-packages/pandas/core/internals/managers.py in setitem(self, indexer, value)
353
354 def setitem(self: T, indexer, value) -> T:
--> 355 return self.apply("setitem", indexer=indexer, value=value)
356
357 def putmask(self, mask, new, align: bool = True):
~/USC/anaconda3/lib/python3.9/site-packages/pandas/core/internals/managers.py in apply(self, f, align_keys, ignore_failures, **kwargs)
325 applied = b.apply(f, **kwargs)
326 else:
--> 327 applied = getattr(b, f)(**kwargs)
328 except (TypeError, NotImplementedError):
329 if not ignore_failures:
~/USC/anaconda3/lib/python3.9/site-packages/pandas/core/internals/blocks.py in setitem(self, indexer, value)
941
942 # length checking
--> 943 check_setitem_lengths(indexer, value, values)
944 exact_match = is_exact_shape_match(values, arr_value)
945
~/USC/anaconda3/lib/python3.9/site-packages/pandas/core/indexers.py in check_setitem_lengths(indexer, value, values)
174 and len(indexer[indexer]) == len(value)
175 ):
--> 176 raise ValueError(
177 "cannot set using a list-like indexer "
178 "with a different length than the value"
ValueError: cannot set using a list-like indexer with a different length than the value
Why is it not running particularly on my system? Is there any problem with the python version or Jupyter Notebook?
Please help.
I am using Koalas and I want to change the value of a column based on a condition.
In pandas I can do that using:
import pandas as pd
df_test = pd.DataFrame({
'a': [1,2,3]
,'b': ['one','two','three']})
df_test2 = pd.DataFrame({
'c': [2,1,3]
,'d': ['one','two','three']})
df_test.loc[df_test.a.isin(df_test2['c']),'b'] = 'four'
df_test.head()
a b
0 1 four
1 2 four
2 3 four
I am trying to use the same in Koalas, but I have this error:
---------------------------------------------------------------------------
PandasNotImplementedError Traceback (most recent call last)
<ipython-input-15-814219258adb> in <module>
5 new_loans['write_offs'] = 0
6
----> 7 new_loans.loc[(new_loans['ID'].isin(userinput_write_offs['id'])),'write_offs'] = 1
8 new_loans.loc[new_loans['write_offs']==1,'is_active'] = 0
9 new_loans = new_loans.sort_values(by = ['ZOHOID','Disb Date'])
/usr/local/lib/python3.7/dist-packages/databricks/koalas/base.py in isin(self, values)
894 )
895
--> 896 return self._with_new_scol(self.spark.column.isin(list(values)))
897
898 def isnull(self) -> Union["Series", "Index"]:
/usr/local/lib/python3.7/dist-packages/databricks/koalas/series.py in __iter__(self)
5871
5872 def __iter__(self):
-> 5873 return MissingPandasLikeSeries.__iter__(self)
5874
5875 if sys.version_info >= (3, 7):
/usr/local/lib/python3.7/dist-packages/databricks/koalas/missing/__init__.py in unsupported_function(*args, **kwargs)
21 def unsupported_function(*args, **kwargs):
22 raise PandasNotImplementedError(
---> 23 class_name=class_name, method_name=method_name, reason=reason
24 )
25
PandasNotImplementedError: The method `pd.Series.__iter__()` is not implemented. If you want to collect your data as an NumPy array, use 'to_numpy()' instead.
How could I do the same operation in Koalas?
UPDATE
Following this question: Assign Koalas Column from Numpy Result I have done:
df_test.loc[df_test.a.isin(df_test2['c'].to_list()),'b'] = 'four'
But now I have this error:
---------------------------------------------------------------------------
PythonException Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/IPython/core/formatters.py in __call__(self, obj)
700 type_pprinters=self.type_printers,
701 deferred_pprinters=self.deferred_printers)
--> 702 printer.pretty(obj)
703 printer.flush()
704 return stream.getvalue()
/usr/local/lib/python3.7/dist-packages/IPython/lib/pretty.py in pretty(self, obj)
392 if cls is not object \
393 and callable(cls.__dict__.get('__repr__')):
--> 394 return _repr_pprint(obj, self, cycle)
395
396 return _default_pprint(obj, self, cycle)
/usr/local/lib/python3.7/dist-packages/IPython/lib/pretty.py in _repr_pprint(obj, p, cycle)
698 """A pprint that just redirects to the normal repr function."""
699 # Find newlines and replace them with p.break_()
--> 700 output = repr(obj)
701 lines = output.splitlines()
702 with p.group():
/usr/local/lib/python3.7/dist-packages/databricks/koalas/frame.py in __repr__(self)
10614 return self._to_internal_pandas().to_string()
10615
> 10616 pdf = self._get_or_create_repr_pandas_cache(max_display_count)
10617 pdf_length = len(pdf)
10618 pdf = pdf.iloc[:max_display_count]
/usr/local/lib/python3.7/dist-packages/databricks/koalas/frame.py in _get_or_create_repr_pandas_cache(self, n)
10606 def _get_or_create_repr_pandas_cache(self, n):
10607 if not hasattr(self, "_repr_pandas_cache") or n not in self._repr_pandas_cache:
> 10608 self._repr_pandas_cache = {n: self.head(n + 1)._to_internal_pandas()}
10609 return self._repr_pandas_cache[n]
10610
/usr/local/lib/python3.7/dist-packages/databricks/koalas/frame.py in _to_internal_pandas(self)
10602 This method is for internal use only.
10603 """
> 10604 return self._internal.to_pandas_frame
10605
10606 def _get_or_create_repr_pandas_cache(self, n):
/usr/local/lib/python3.7/dist-packages/databricks/koalas/utils.py in wrapped_lazy_property(self)
514 def wrapped_lazy_property(self):
515 if not hasattr(self, attr_name):
--> 516 setattr(self, attr_name, fn(self))
517 return getattr(self, attr_name)
518
/usr/local/lib/python3.7/dist-packages/databricks/koalas/internal.py in to_pandas_frame(self)
807 """ Return as pandas DataFrame. """
808 sdf = self.to_internal_spark_frame
--> 809 pdf = sdf.toPandas()
810 if len(pdf) == 0 and len(sdf.schema) > 0:
811 pdf = pdf.astype(
/usr/local/spark/python/pyspark/sql/pandas/conversion.py in toPandas(self)
136
137 # Below is toPandas without Arrow optimization.
--> 138 pdf = pd.DataFrame.from_records(self.collect(), columns=self.columns)
139 column_counter = Counter(self.columns)
140
/usr/local/spark/python/pyspark/sql/dataframe.py in collect(self)
594 """
595 with SCCallSiteSync(self._sc) as css:
--> 596 sock_info = self._jdf.collectToPython()
597 return list(_load_from_socket(sock_info, BatchedSerializer(PickleSerializer())))
598
/usr/local/lib/python3.7/dist-packages/py4j/java_gateway.py in __call__(self, *args)
1303 answer = self.gateway_client.send_command(command)
1304 return_value = get_return_value(
-> 1305 answer, self.gateway_client, self.target_id, self.name)
1306
1307 for temp_arg in temp_args:
/usr/local/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
132 # Hide where the exception came from that shows a non-Pythonic
133 # JVM exception message.
--> 134 raise_from(converted)
135 else:
136 raise
/usr/local/spark/python/pyspark/sql/utils.py in raise_from(e)
PythonException:
An exception was thrown from the Python worker. Please see the stack trace below.
Traceback (most recent call last):
File "/opt/spark/python/lib/pyspark.zip/pyspark/worker.py", line 589, in main
func, profiler, deserializer, serializer = read_udfs(pickleSer, infile, eval_type)
File "/opt/spark/python/lib/pyspark.zip/pyspark/worker.py", line 447, in read_udfs
udfs.append(read_single_udf(pickleSer, infile, eval_type, runner_conf, udf_index=i))
File "/opt/spark/python/lib/pyspark.zip/pyspark/worker.py", line 254, in read_single_udf
f, return_type = read_command(pickleSer, infile)
File "/opt/spark/python/lib/pyspark.zip/pyspark/worker.py", line 74, in read_command
command = serializer._read_with_length(file)
File "/opt/spark/python/lib/pyspark.zip/pyspark/serializers.py", line 172, in _read_with_length
return self.loads(obj)
File "/opt/spark/python/lib/pyspark.zip/pyspark/serializers.py", line 458, in loads
return pickle.loads(obj, encoding=encoding)
File "/opt/spark/python/lib/pyspark.zip/pyspark/cloudpickle.py", line 1110, in subimport
__import__(name)
ModuleNotFoundError: No module named 'pandas'
Why is trying to use pandas?
Koalas package exposes Pandas Like APIs on high level for the users but under the hood implementation is done using PySpark APIs.
I observed that within the stack track log you have pasted, a pandas dataframe is being created from sdf spark Dataframe using toPandas() method and assigned to pdf.
In the implementation of toPandas() function, pandas and numpy are being imported.
check line numbers 809 & 138.
/usr/local/lib/python3.7/dist-packages/databricks/koalas/internal.py in to_pandas_frame(self)
807 """ Return as pandas DataFrame. """
808 sdf = self.to_internal_spark_frame
--> 809 pdf = sdf.toPandas()
810 if len(pdf) == 0 and len(sdf.schema) > 0:
811 pdf = pdf.astype(
/usr/local/spark/python/pyspark/sql/pandas/conversion.py in toPandas(self)
136
137 # Below is toPandas without Arrow optimization.
--> 138 pdf = pd.DataFrame.from_records(self.collect(), columns=self.columns)
139 column_counter = Counter(self.columns)
140
/usr/local/spark/python/pyspark/sql/dataframe.py in collect(self)
594 """
595 with SCCallSiteSync(self._sc) as css:
--> 596 sock_info = self._jdf.collectToPython()
597 return list(_load_from_socket(sock_info, BatchedSerializer(PickleSerializer())))
598
you can check out the implementation of toPandas() function at the following link:
https://github.com/apache/spark/blob/master/python/pyspark/sql/pandas/conversion.py
I have the following problem. My data is a huge dataframe, looking like this (this is the head of the dataframe)
import pandas
import dask.dataframe as dd
data = dd.read_csv(data_path)
data.persist()
print(data.head())
Gitter_ID_100m x_mp_100m y_mp_100m Einwohner
0 100mN26840E43341 4334150 2684050 -1
1 100mN26840E43342 4334250 2684050 -1
2 100mN26840E43343 4334350 2684050 -1
3 100mN26840E43344 4334450 2684050 -1
4 100mN26840E43345 4334550 2684050 -1
I am using Dask to handle it. I now want to create a new column where the 'x_mp_100m' and 'y_mp_100m' are converted into a Shapely Point. For a single row, it would look like this:
from shapely.geometry import Point
test_df = data.head(1)
test_df = test_df.assign(geom=lambda k: Point(k.x_mp_100m,k.y_mp_100m))
print(test_df)
Gitter_ID_100m x_mp_100m y_mp_100m Einwohner geom
0 100mN26840E43341 4334150 2684050 -1 POINT (4334150 2684050)
I already tried the following code with Dask:
data_out = data.map_partitions(lambda df: df.assign(geom= lambda k: Point(k.x_mp_100m,k.y_mp_100m)), meta=pd.DataFrame)
When doing that, I get the following error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-17-b8de11d9b9b3> in <module>
----> 1 data_out.compute()
~\AppData\Local\Continuum\anaconda3\lib\site-packages\dask\base.py in compute(self, **kwargs)
154 dask.base.compute
155 """
--> 156 (result,) = compute(self, traverse=False, **kwargs)
157 return result
158
~\AppData\Local\Continuum\anaconda3\lib\site-packages\dask\base.py in compute(*args, **kwargs)
395 keys = [x.__dask_keys__() for x in collections]
396 postcomputes = [x.__dask_postcompute__() for x in collections]
--> 397 results = schedule(dsk, keys, **kwargs)
398 return repack([f(r, *a) for r, (f, a) in zip(results, postcomputes)])
399
~\AppData\Local\Continuum\anaconda3\lib\site-packages\distributed\client.py in get(self, dsk, keys, restrictions, loose_restrictions, resources, sync, asynchronous, direct, retries, priority, fifo_timeout, actors, **kwargs)
2319 try:
2320 results = self.gather(packed, asynchronous=asynchronous,
-> 2321 direct=direct)
2322 finally:
2323 for f in futures.values():
~\AppData\Local\Continuum\anaconda3\lib\site-packages\distributed\client.py in gather(self, futures, errors, maxsize, direct, asynchronous)
1653 return self.sync(self._gather, futures, errors=errors,
1654 direct=direct, local_worker=local_worker,
-> 1655 asynchronous=asynchronous)
1656
1657 #gen.coroutine
~\AppData\Local\Continuum\anaconda3\lib\site-packages\distributed\client.py in sync(self, func, *args, **kwargs)
671 return future
672 else:
--> 673 return sync(self.loop, func, *args, **kwargs)
674
675 def __repr__(self):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\distributed\utils.py in sync(loop, func, *args, **kwargs)
275 e.wait(10)
276 if error[0]:
--> 277 six.reraise(*error[0])
278 else:
279 return result[0]
~\AppData\Local\Continuum\anaconda3\lib\site-packages\six.py in reraise(tp, value, tb)
691 if value.__traceback__ is not tb:
692 raise value.with_traceback(tb)
--> 693 raise value
694 finally:
695 value = None
~\AppData\Local\Continuum\anaconda3\lib\site-packages\distributed\utils.py in f()
260 if timeout is not None:
261 future = gen.with_timeout(timedelta(seconds=timeout), future)
--> 262 result[0] = yield future
263 except Exception as exc:
264 error[0] = sys.exc_info()
~\AppData\Local\Continuum\anaconda3\lib\site-packages\tornado\gen.py in run(self)
1131
1132 try:
-> 1133 value = future.result()
1134 except Exception:
1135 self.had_exception = True
~\AppData\Local\Continuum\anaconda3\lib\site-packages\tornado\gen.py in run(self)
1139 if exc_info is not None:
1140 try:
-> 1141 yielded = self.gen.throw(*exc_info)
1142 finally:
1143 # Break up a reference to itself
~\AppData\Local\Continuum\anaconda3\lib\site-packages\distributed\client.py in _gather(self, futures, errors, direct, local_worker)
1498 six.reraise(type(exception),
1499 exception,
-> 1500 traceback)
1501 if errors == 'skip':
1502 bad_keys.add(key)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\six.py in reraise(tp, value, tb)
690 value = tp()
691 if value.__traceback__ is not tb:
--> 692 raise value.with_traceback(tb)
693 raise value
694 finally:
~\AppData\Local\Continuum\anaconda3\lib\site-packages\dask\dataframe\core.py in apply_and_enforce()
3682
3683 Ensures the output has the same columns, even if empty."""
-> 3684 df = func(*args, **kwargs)
3685 if isinstance(df, (pd.DataFrame, pd.Series, pd.Index)):
3686 if len(df) == 0:
<ipython-input-16-d5710cb00158> in <lambda>()
----> 1 data_out = data.map_partitions(lambda df: df.assign(geom= lambda k: Point(k.x_mp_100m,k.y_mp_100m)), meta=pd.DataFrame)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\frame.py in assign()
3549 if PY36:
3550 for k, v in kwargs.items():
-> 3551 data[k] = com.apply_if_callable(v, data)
3552 else:
3553 # <= 3.5: do all calculations first...
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\common.py in apply_if_callable()
327
328 if callable(maybe_callable):
--> 329 return maybe_callable(obj, **kwargs)
330
331 return maybe_callable
<ipython-input-16-d5710cb00158> in <lambda>()
----> 1 data_out = data.map_partitions(lambda df: df.assign(geom= lambda k: Point(k.x_mp_100m,k.y_mp_100m)), meta=pd.DataFrame)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\shapely\geometry\point.py in __init__()
47 BaseGeometry.__init__(self)
48 if len(args) > 0:
---> 49 self._set_coords(*args)
50
51 # Coordinate getters and setters
~\AppData\Local\Continuum\anaconda3\lib\site-packages\shapely\geometry\point.py in _set_coords()
130 self._geom, self._ndim = geos_point_from_py(args[0])
131 else:
--> 132 self._geom, self._ndim = geos_point_from_py(tuple(args))
133
134 coords = property(BaseGeometry._get_coords, _set_coords)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\shapely\geometry\point.py in geos_point_from_py()
207 coords = ob
208 n = len(coords)
--> 209 dx = c_double(coords[0])
210 dy = c_double(coords[1])
211 dz = None
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\series.py in wrapper()
91 return converter(self.iloc[0])
92 raise TypeError("cannot convert the series to "
---> 93 "{0}".format(str(converter)))
94
95 wrapper.__name__ = "__{name}__".format(name=converter.__name__)
TypeError: cannot convert the series to <class 'float'>
So I think, I am using pandas.assign() function in a wrong way, or there should be a better fitting function, I just cannot seem to wrap my head around it. Do you know a better way to handle this?
I also found this way:
data_out = data.map_partitions(lambda df: df.apply(lambda row: Point(row['x_mp_100m'],row['y_mp_100m']), axis=1))
But is that the most efficient way?
What you're doing seems fine. I would find a function that works well on a single row and then use the apply method or a function that works well on a single Pandas dataframe and then use the map_partitions method.
For the error that you're getting I would first verify that your function works on a pandas dataframe.
I have sequencing data of micro-RNAs (miR) under different conditions ('Comparisons'), and I want to create a point-plot which will show me on different graphs the fold-change for each miR. the data looks like this (and is a pandas data_frame)
mir_Names Comparison Fold_Change
9 9 mmu-miR-100-4373160\n15 m... YAD-YC 508539.390000
15 9 mmu-miR-100-4373160\n15 m... YAD-YC 26.816000
17 9 mmu-miR-100-4373160\n15 m... YAD-YC 728.608000
18 9 mmu-miR-100-4373160\n15 m... YAD-YC 11483029.706000
'upregulated' is a subset of the dataframe and i tried to visualize it using:
g = sns.FacetGrid(upregulated, col='Comparison', sharex=True, sharey=True, size=0.75, aspect=12./8, despine=True, margin_titles=True)
g.map(sns.pointplot, 'mir_Names', 'Fold_Change', data=upregulated)
**
but it gives me the error which I couldn't find any solution to it:
**
ValueError Traceback (most recent call last) <ipython-input-180-a1cf1b282869> in <module>()
1 g = sns.FacetGrid(upregulated, col='Comparison', sharex=True, sharey=True, size=0.75, aspect=12./8, despine=True, margin_titles=True)
----> 2 g.map(sns.pointplot, 'mir_Names', 'Fold_Change', data=upregulated) #maybe with .count
c:\pyzo2014a\lib\site-packages\seaborn\axisgrid.py in map(self, func,
*args, **kwargs)
446
447 # Finalize the annotations and layout
--> 448 self._finalize_grid(args[:2])
449
450 return self
c:\pyzo2014a\lib\site-packages\seaborn\axisgrid.py in
_finalize_grid(self, axlabels)
537 self.set_axis_labels(*axlabels)
538 self.set_titles()
--> 539 self.fig.tight_layout()
540
541 def facet_axis(self, row_i, col_j):
c:\pyzo2014a\lib\site-packages\matplotlib\figure.py in tight_layout(self, renderer, pad, h_pad, w_pad, rect) 1663 rect=rect) 1664
-> 1665 self.subplots_adjust(**kwargs) 1666 1667
c:\pyzo2014a\lib\site-packages\matplotlib\figure.py in subplots_adjust(self, *args, **kwargs) 1520 1521 """
-> 1522 self.subplotpars.update(*args, **kwargs) 1523 for ax in self.axes: 1524 if not isinstance(ax, SubplotBase):
c:\pyzo2014a\lib\site-packages\matplotlib\figure.py in update(self, left, bottom, right, top, wspace, hspace)
223 if self.bottom >= self.top:
224 reset()
--> 225 raise ValueError('bottom cannot be >= top')
226
227 def _update_this(self, s, val):
**ValueError: bottom cannot be >= top**
What causes this error?
I have created a package using the encoding utf-8.
When calling a function, it returns a DataFrame, with a column coded in utf-8.
When using IPython at the command line, I don't have any problems showing the content of this table. When using the Notebook, it crashes with the error 'utf8' codec can't decode byte 0xe7. I've attached a full traceback below.
What is the proper encoding to work with Notebook?
UnicodeDecodeError Traceback (most recent call last)
<ipython-input-13-92c0011919e7> in <module>()
3 ver = verif.VerificacaoNA()
4 comp, total = ver.executarCompRealFisica(DT_INI, DT_FIN)
----> 5 comp
c:\Python27-32\lib\site-packages\ipython-0.13.1-py2.7.egg\IPython\core\displayhook.pyc in __call__(self, result)
240 self.update_user_ns(result)
241 self.log_output(format_dict)
--> 242 self.finish_displayhook()
243
244 def flush(self):
c:\Python27-32\lib\site-packages\ipython-0.13.1-py2.7.egg\IPython\zmq\displayhook.pyc in finish_displayhook(self)
59 sys.stdout.flush()
60 sys.stderr.flush()
---> 61 self.session.send(self.pub_socket, self.msg, ident=self.topic)
62 self.msg = None
63
c:\Python27-32\lib\site-packages\ipython-0.13.1-py2.7.egg\IPython\zmq\session.pyc in send(self, stream, msg_or_type, content, parent, ident, buffers, subheader, track, header)
557
558 buffers = [] if buffers is None else buffers
--> 559 to_send = self.serialize(msg, ident)
560 flag = 0
561 if buffers:
c:\Python27-32\lib\site-packages\ipython-0.13.1-py2.7.egg\IPython\zmq\session.pyc in serialize(self, msg, ident)
461 content = self.none
462 elif isinstance(content, dict):
--> 463 content = self.pack(content)
464 elif isinstance(content, bytes):
465 # content is already packed, as in a relayed message
c:\Python27-32\lib\site-packages\ipython-0.13.1-py2.7.egg\IPython\zmq\session.pyc in <lambda>(obj)
76
77 # ISO8601-ify datetime objects
---> 78 json_packer = lambda obj: jsonapi.dumps(obj, default=date_default)
79 json_unpacker = lambda s: extract_dates(jsonapi.loads(s))
80
c:\Python27-32\lib\site-packages\pyzmq-13.0.0-py2.7-win32.egg\zmq\utils\jsonapi.pyc in dumps(o, **kwargs)
70 kwargs['separators'] = (',', ':')
71
---> 72 return _squash_unicode(jsonmod.dumps(o, **kwargs))
73
74 def loads(s, **kwargs):
c:\Python27-32\lib\json\__init__.pyc in dumps(obj, skipkeys, ensure_ascii, check_circular, allow_nan, cls, indent, separators, encoding, default, **kw)
236 check_circular=check_circular, allow_nan=allow_nan, indent=indent,
237 separators=separators, encoding=encoding, default=default,
--> 238 **kw).encode(obj)
239
240
c:\Python27-32\lib\json\encoder.pyc in encode(self, o)
199 # exceptions aren't as detailed. The list call should be roughly
200 # equivalent to the PySequence_Fast that ''.join() would do.
--> 201 chunks = self.iterencode(o, _one_shot=True)
202 if not isinstance(chunks, (list, tuple)):
203 chunks = list(chunks)
c:\Python27-32\lib\json\encoder.pyc in iterencode(self, o, _one_shot)
262 self.key_separator, self.item_separator, self.sort_keys,
263 self.skipkeys, _one_shot)
--> 264 return _iterencode(o, 0)
265
266 def _make_iterencode(markers, _default, _encoder, _indent, _floatstr,
UnicodeDecodeError: 'utf8' codec can't decode byte 0xe7 in position 199: invalid continuation byte
I had the same problem recently, and indeed setting the default encoding to UTF-8 did the trick:
import sys
reload(sys)
sys.setdefaultencoding("utf-8")
Running sys.getdefaultencoding() yielded 'ascii' on my environment (Python 2.7.3), so I guess that's the default.
Also see this related question and Ian Bicking's blog post on the subject.