I need to learn how to use Healpy and so I was trying to reproduce the results of the basic tutorial. I use Anaconda on Ubuntu 22.04 and I think I have all the pre-requisites (I have Python 3.9.13, Numpy, Matplotlib, Astropy, python3-dev and python-dev-is-python3 installed).
I have tried many variations of what is shown in the tutorial notebook, including a literal copy+paste of the code, I've tried to do this in Ipython on terminal, on a jupyter notebook, on Spyder, I've tried to include the %matplotlib inline (after importing matplotlib) in all of these options (I've tried not to include in all of them too), and in all situations I end up with the exact same error message (full error message in the end of the post):
ValueError: Passing a Normalize instance simultaneously with vmin/vmax
is not supported. Please pass vmin/vmax directly to the norm when
creating it.
Everything works except for the plot. I've tried setting min and max in the hp.mollview() command according to the documentation, but it didn't work too. It seems like a bug to me, so I thought about creating an issue ticket on github, but honestly the tutorial is very updated and I don't think this kind of bug would go unnoticed, so I'm thinking I missed some minor detail and I hope someone in here can help me identify what it is. In the meantime, I'll probably try to learn some other version of Healpix.
Here is the full error message when I run the code in a jupyter notebook (by the way, sorry if my question is not very well organized, this is my first post):
--------------------------------------------------------------------------- ValueError Traceback (most recent call
last) Cell In [5], line 2
1 m = np.arange(NPIX)
----> 2 hp.mollview(m, title="Mollview image RING")
3 hp.graticule()
File ~/anaconda3/lib/python3.9/site-packages/healpy/visufunc.py:250,
in mollview(map, fig, rot, coord, unit, xsize, title, nest, min, max,
flip, remove_dip, remove_mono, gal_cut, format, format2, cbar, cmap,
badcolor, bgcolor, notext, norm, hold, reuse_axes, margins, sub,
nlocs, return_projected_map)
246 elif remove_mono:
247 map = pixelfunc.remove_monopole(
248 map, gal_cut=gal_cut, nest=nest, copy=True, verbose=True
249 )
--> 250 img = ax.projmap(
251 map,
252 nest=nest,
253 xsize=xsize,
254 coord=coord,
255 vmin=min,
256 vmax=max,
257 cmap=cmap,
258 badcolor=badcolor,
259 bgcolor=bgcolor,
260 norm=norm,
261 )
262 if cbar:
263 im = ax.get_images()[0]
File ~/anaconda3/lib/python3.9/site-packages/healpy/projaxes.py:736,
in HpxMollweideAxes.projmap(self, map, nest, **kwds)
734 nside = pixelfunc.npix2nside(pixelfunc.get_map_size(map))
735 f = lambda x, y, z: pixelfunc.vec2pix(nside, x, y, z, nest=nest)
--> 736 return super(HpxMollweideAxes, self).projmap(map, f, **kwds)
File ~/anaconda3/lib/python3.9/site-packages/healpy/projaxes.py:726,
in MollweideAxes.projmap(self, map, vec2pix_func, xsize, **kwds)
724 def projmap(self, map, vec2pix_func, xsize=800, **kwds):
725 self.proj.set_proj_plane_info(xsize=xsize)
--> 726 img = super(MollweideAxes, self).projmap(map, vec2pix_func, **kwds)
727 self.set_xlim(-2.01, 2.01)
728 self.set_ylim(-1.01, 1.01)
File ~/anaconda3/lib/python3.9/site-packages/healpy/projaxes.py:202,
in SphericalProjAxes.projmap(self, map, vec2pix_func, vmin, vmax,
badval, badcolor, bgcolor, cmap, norm, rot, coord, **kwds)
200 ext = self.proj.get_extent()
201 img = np.ma.masked_values(img, badval)
--> 202 aximg = self.imshow(
203 img,
204 extent=ext,
205 cmap=cm,
206 norm=nn,
207 interpolation="nearest",
208 origin="lower",
209 vmin=vmin,
210 vmax=vmax,
211 **kwds
212 )
213 xmin, xmax, ymin, ymax = self.proj.get_extent()
214 self.set_xlim(xmin, xmax)
File
~/anaconda3/lib/python3.9/site-packages/matplotlib/_api/deprecation.py:454,
in make_keyword_only..wrapper(*args, **kwargs)
448 if len(args) > name_idx:
449 warn_deprecated(
450 since, message="Passing the %(name)s %(obj_type)s "
451 "positionally is deprecated since Matplotlib %(since)s; the "
452 "parameter will become keyword-only %(removal)s.",
453 name=name, obj_type=f"parameter of {func.name}()")
--> 454 return func(*args, **kwargs)
File
~/anaconda3/lib/python3.9/site-packages/matplotlib/init.py:1423,
in _preprocess_data..inner(ax, data, *args, **kwargs) 1420
#functools.wraps(func) 1421 def inner(ax, *args, data=None,
**kwargs): 1422 if data is None:
-> 1423 return func(ax, *map(sanitize_sequence, args), **kwargs) 1425 bound = new_sig.bind(ax, *args, **kwargs) 1426 auto_label = (bound.arguments.get(label_namer) 1427
or bound.kwargs.get(label_namer))
File
~/anaconda3/lib/python3.9/site-packages/matplotlib/axes/_axes.py:5577,
in Axes.imshow(self, X, cmap, norm, aspect, interpolation, alpha,
vmin, vmax, origin, extent, interpolation_stage, filternorm,
filterrad, resample, url, **kwargs) 5574 if im.get_clip_path() is
None: 5575 # image does not already have clipping set, clip to
axes patch 5576 im.set_clip_path(self.patch)
-> 5577 im._scale_norm(norm, vmin, vmax) 5578 im.set_url(url) 5580 # update ax.dataLim, and, if autoscaling, set viewLim 5581 #
to tightly fit the image, regardless of dataLim.
File ~/anaconda3/lib/python3.9/site-packages/matplotlib/cm.py:405, in
ScalarMappable._scale_norm(self, norm, vmin, vmax)
403 self.set_clim(vmin, vmax)
404 if isinstance(norm, colors.Normalize):
--> 405 raise ValueError(
406 "Passing a Normalize instance simultaneously with "
407 "vmin/vmax is not supported. Please pass vmin/vmax "
408 "directly to the norm when creating it.")
410 # always resolve the autoscaling so we have concrete limits
411 # rather than deferring to draw time.
412 self.autoscale_None()
ValueError: Passing a Normalize instance simultaneously with vmin/vmax
is not supported. Please pass vmin/vmax directly to the norm when
creating it.
Related
I am attempting to generate a scatter plot to show data before and after the PCA transform, similar to this tutorial.
To do this, I am running the following code:
fig, axes = plt.subplots(1,2)
axes[0].scatter(X.iloc[:,0], X.iloc[:,1], c=y)
axes[0].set_xlabel('x1')
axes[0].set_ylabel('x2')
axes[0].set_title('Before PCA')
axes[1].scatter(X_new[:,0], X_new[:,1], c=y)
axes[1].set_xlabel('PC1')
axes[1].set_ylabel('PC2')
axes[1].set_title('After PCA')
plt.show()
Which is causing this error to appear:
ValueError: RGBA values should be within 0-1 range
X is the preprocessed matrix of features, which contains 196 samples and 59 features. Whereas y is the dependent variable and contains two classes [0, 1].
Here is the full error message:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-109-2c4f74ddce3f> in <module>
1 fig, axes = plt.subplots(1,2)
----> 2 axes[0].scatter(X.iloc[:,0], X.iloc[:,1], c=y)
3 axes[0].set_xlabel('x1')
4 axes[0].set_ylabel('x2')
5 axes[0].set_title('Before PCA')
~/anaconda3/lib/python3.7/site-packages/matplotlib/__init__.py in inner(ax, data, *args, **kwargs)
1597 def inner(ax, *args, data=None, **kwargs):
1598 if data is None:
-> 1599 return func(ax, *map(sanitize_sequence, args), **kwargs)
1600
1601 bound = new_sig.bind(ax, *args, **kwargs)
~/anaconda3/lib/python3.7/site-packages/matplotlib/axes/_axes.py in scatter(self, x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, verts, edgecolors, plotnonfinite, **kwargs)
4495 offsets=offsets,
4496 transOffset=kwargs.pop('transform', self.transData),
-> 4497 alpha=alpha
4498 )
4499 collection.set_transform(mtransforms.IdentityTransform())
~/anaconda3/lib/python3.7/site-packages/matplotlib/collections.py in __init__(self, paths, sizes, **kwargs)
881 """
882
--> 883 Collection.__init__(self, **kwargs)
884 self.set_paths(paths)
885 self.set_sizes(sizes)
~/anaconda3/lib/python3.7/site-packages/matplotlib/collections.py in __init__(self, edgecolors, facecolors, linewidths, linestyles, capstyle, joinstyle, antialiaseds, offsets, transOffset, norm, cmap, pickradius, hatch, urls, offset_position, zorder, **kwargs)
125
126 self._hatch_color = mcolors.to_rgba(mpl.rcParams['hatch.color'])
--> 127 self.set_facecolor(facecolors)
128 self.set_edgecolor(edgecolors)
129 self.set_linewidth(linewidths)
~/anaconda3/lib/python3.7/site-packages/matplotlib/collections.py in set_facecolor(self, c)
676 """
677 self._original_facecolor = c
--> 678 self._set_facecolor(c)
679
680 def get_facecolor(self):
~/anaconda3/lib/python3.7/site-packages/matplotlib/collections.py in _set_facecolor(self, c)
659 except AttributeError:
660 pass
--> 661 self._facecolors = mcolors.to_rgba_array(c, self._alpha)
662 self.stale = True
663
~/anaconda3/lib/python3.7/site-packages/matplotlib/colors.py in to_rgba_array(c, alpha)
277 result[mask] = 0
278 if np.any((result < 0) | (result > 1)):
--> 279 raise ValueError("RGBA values should be within 0-1 range")
280 return result
281 # Handle single values.
ValueError: RGBA values should be within 0-1 range
I am unsure what is causing this error and would appreciate help in figuring this out. Thanks!
The c= parameter of ax.scatter can be given in several ways:
A scalar or sequence of n numbers to be mapped to colors using cmap and norm. So a single number, or a list-like 1D sequence of numbers.
A 2D array in which the rows are RGB or RGBA. E.g. something like [[1,0,0], [0,0,1]]. All these values need to be between 0 and 1. Moreover, there should be either 3 (for RGB) or 4 (for RGBA) values per entry.
A sequence of colors of length n. E.g. ["red", "#B789C0", "turquoise"]
A single color format string. E.g. "cornflowerblue".
Now, when an array of numbers is given, to be able to distinguish between the first and the second case, matplotlib just looks at the array dimension. If it is 1D, matplotlib assumes the first case. For 2D, it assumes the second case. Note that also an Nx1 or an 1xN array is considered 2D. You can use np.squeeze() to "squeeze out" the dummy second dimension.
From Dataset Australia Rainfall, I'm trying to predict RainTomorrow. Here is my code given below :
Downloading dataset directly from Kaggle using opendatasets library
import opendatasets as od
dataset_url = 'https://www.kaggle.com/jsphyg/weather-dataset-rattle-package'
od.download(dataset_url)
Importing necessary libraries
import os
import pandas as pd
import numpy as np
import plotly.express as px
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
sns.set_style('darkgrid')
matplotlib.rcParams['font.size'] = 14
matplotlib.rcParams['figure.figsize'] = (10,6)
matplotlib.rcParams['figure.facecolor'] = '#00000000'
Loading Dataset
data_dir = './weather-dataset-rattle-package'
os.listdir(data_dir)
train_csv = data_dir + '/weatherAUS.csv'
raw_df = pd.read_csv(train_csv)
Explore WindGustDir variable
print('WindGustDir contains', len(raw_df['WindGustDir'].unique()), 'labels')
raw_df['WindGustDir'].unique()
raw_df.WindGustDir.value_counts()
pd.get_dummies(raw_df.WindGustDir, drop_first=True, dummy_na=True).head()
pd.get_dummies(raw_df.WindGustDir, drop_first=True, dummy_na=True).sum(axis=0)
Plotting Windrose
from windrose import WindroseAxes
ax = WindroseAxes.from_ax()
ax.bar(raw_df.WindGustDir, raw_df.Rainfall, normed=True, opening=0.8,
edgecolor='white')
ax.set_legend()
I am unable to figure out which columns should use with WindGustDir or if their is any other option of compare RainTomorrow and WindGustDir .
Error Message
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
e:\Anaconda3\lib\site-packages\numpy\core\fromnumeric.py in _wrapfunc(obj, method, *args, **kwds)
57 try:
---> 58 return bound(*args, **kwds)
59 except TypeError:
TypeError: '<' not supported between instances of 'float' and 'str'
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-253-1a1f0fa6bf7a> in <module>
1 ax = WindroseAxes.from_ax()
----> 2 ax.bar(direction=df.WindGustDir, var=df.Rainfall, normed=True, opening=0.8, edgecolor='white')
3 ax.set_legend()
e:\Anaconda3\lib\site-packages\windrose\windrose.py in bar(self, direction, var, **kwargs)
547 """
548
--> 549 bins, nbins, nsector, colors, angles, kwargs = self._init_plot(
550 direction, var, **kwargs
551 )
e:\Anaconda3\lib\site-packages\windrose\windrose.py in _init_plot(self, direction, var, **kwargs)
359
360 # Set the global information dictionnary
--> 361 self._info["dir"], self._info["bins"], self._info["table"] = histogram(
362 direction, var, bins, nsector, normed, blowto
363 )
e:\Anaconda3\lib\site-packages\windrose\windrose.py in histogram(direction, var, bins, nsector, normed, blowto)
746 direction[direction >= 360.] = direction[direction >= 360.] - 360
747
--> 748 table = histogram2d(x=var, y=direction, bins=[var_bins, dir_bins], normed=False)[0]
749 # add the last value to the first to have the table of North winds
750 table[:, 0] = table[:, 0] + table[:, -1]
<__array_function__ internals> in histogram2d(*args, **kwargs)
e:\Anaconda3\lib\site-packages\numpy\lib\twodim_base.py in histogram2d(x, y, bins, range, normed, weights, density)
742 xedges = yedges = asarray(bins)
743 bins = [xedges, yedges]
--> 744 hist, edges = histogramdd([x, y], bins, range, normed, weights, density)
745 return hist, edges[0], edges[1]
746
<__array_function__ internals> in histogramdd(*args, **kwargs)
e:\Anaconda3\lib\site-packages\numpy\lib\histograms.py in histogramdd(sample, bins, range, normed, weights, density)
1071
1072 # Compute the bin number each sample falls into.
-> 1073 Ncount = tuple(
1074 # avoid np.digitize to work around gh-11022
1075 np.searchsorted(edges[i], sample[:, i], side='right')
e:\Anaconda3\lib\site-packages\numpy\lib\histograms.py in <genexpr>(.0)
1073 Ncount = tuple(
1074 # avoid np.digitize to work around gh-11022
-> 1075 np.searchsorted(edges[i], sample[:, i], side='right')
1076 for i in _range(D)
1077 )
<__array_function__ internals> in searchsorted(*args, **kwargs)
e:\Anaconda3\lib\site-packages\numpy\core\fromnumeric.py in searchsorted(a, v, side, sorter)
1346
1347 """
-> 1348 return _wrapfunc(a, 'searchsorted', v, side=side, sorter=sorter)
1349
1350
e:\Anaconda3\lib\site-packages\numpy\core\fromnumeric.py in _wrapfunc(obj, method, *args, **kwds)
65 # Call _wrapit from within the except clause to ensure a potential
66 # exception has a traceback chain.
---> 67 return _wrapit(obj, method, *args, **kwds)
68
69
e:\Anaconda3\lib\site-packages\numpy\core\fromnumeric.py in _wrapit(obj, method, *args, **kwds)
42 except AttributeError:
43 wrap = None
---> 44 result = getattr(asarray(obj), method)(*args, **kwds)
45 if wrap:
46 if not isinstance(result, mu.ndarray):
TypeError: '<' not supported between instances of 'float' and 'str'
It seems that the direction parameter must be numeric.
Create a dict where each key is a each direction in 'WindGustDir' and the corresponding value is a float in degrees.
.map the dict to df.WindGustDir and plot
Alternatively, create and plot a new column
df.insert(loc=8, column='WindGustDirDeg', value=df.WindGustDir.map(wind_dir_deg))
import pandas as pd
from windrose import WindroseAxes
import numpy as np
# load the downloaded data and dropna
df = pd.read_csv('weatherAUS/weatherAUS.csv').dropna(subset=['WindGustDir'])
# create a dict for WindGustDir to numeric values
wind_dir = ['E', 'ENE', 'NE', 'NNE', 'N', 'NNE', 'NW', 'WNW', 'W', 'WSW', 'SW', 'SSW', 'S', 'SSE', 'SE', 'ESE']
degrees = np.arange(0, 360, 22.5)
wind_dir_deg = dict((zip(wind_dir, degrees)))
# plot and map WindGustDir to the dict
ax = WindroseAxes.from_ax()
ax.bar(direction=df.WindGustDir.map(wind_dir_deg), var=df.Rainfall, normed=True, opening=0.8, edgecolor='white')
ax.set_legend()
I am reading a geojson data from here into a GeoDataFrame named gdf.
I have also calculated the centroids of each polygon using gdf['centroid'] = gdf.centroid.
I can individually plot either the centroids or the polygons by setting the column as the geometry column using gdf.set_geometry("<centroid | geometry>"). So, the following code works:
gdf.plot() #By default the geometry column is the column to plot
gdf = gdf.set_geometry("centroid")
gdf.plot()
However, when I try to run the following code:
gdf['geometry'].plot() #Geometry column has been set as centroid before
Or,
gdf = gdf.set_geometry("geometry")
gdf["centroid"].plot()
I get the following error:
TypeError Traceback (most recent call last)
<ipython-input-22-0330c435e2c9> in <module>
1 gdf = gdf.set_geometry("centroid")
----> 2 ax = gdf['geometry'].plot()
3 #gdf["centroid"].plot(ax=ax, color="black")
C:\Program Files\ArcGIS\Pro\bin\Python\envs\arcgispro-py3\lib\site-packages\pandas\plotting\_core.py in __call__(self, *args, **kwargs)
953 data.columns = label_name
954
--> 955 return plot_backend.plot(data, kind=kind, **kwargs)
956
957 __call__.__doc__ = __doc__
C:\Program Files\ArcGIS\Pro\bin\Python\envs\arcgispro-py3\lib\site-packages\pandas\plotting\_matplotlib\__init__.py in plot(data, kind, **kwargs)
59 kwargs["ax"] = getattr(ax, "left_ax", ax)
60 plot_obj = PLOT_CLASSES[kind](data, **kwargs)
---> 61 plot_obj.generate()
62 plot_obj.draw()
63 return plot_obj.result
C:\Program Files\ArcGIS\Pro\bin\Python\envs\arcgispro-py3\lib\site-packages\pandas\plotting\_matplotlib\core.py in generate(self)
276 def generate(self):
277 self._args_adjust()
--> 278 self._compute_plot_data()
279 self._setup_subplots()
280 self._make_plot()
C:\Program Files\ArcGIS\Pro\bin\Python\envs\arcgispro-py3\lib\site-packages\pandas\plotting\_matplotlib\core.py in _compute_plot_data(self)
439 # no non-numeric frames or series allowed
440 if is_empty:
--> 441 raise TypeError("no numeric data to plot")
442
443 self.data = numeric_data.apply(self._convert_to_ndarray)
TypeError: no numeric data to plot
Even though I can set the column as the geometry and then do the plotting, plotting by specifying the particular column at plot time is needed to overlay multiple geometries.
--FULL CODE--
import geopandas
import geoplot
gdf = geopandas.read_file("<path to file>.geojson")
print(gdf.head())
print(gdf.crs)
gdf.plot(legend=True)
gdf['centroid'] = gdf.centroid
gdf = gdf.set_geometry("centroid")
gdf.plot() #Works
gdf['centroid'].plot() #Works
gdf['geometry'].plot() #Error is thrown here
type(gdf)
Can you try it without the line import geoplot? It seems to be working fine for me.
I have a large dataset [time,lat,lon]. I want to regress a variable against time for each point in the grid, but using a for loop takes forever. I found that grouping the dataarray by lat/lon and applying a function reduces the computation time by a lot. I'm applying a function to a dataarray [time,lat,lon] that has been grouped by lat/lon. My end result would be [lat,lon]. Some grid points don't have any data all (np.nan). I want the function to return np.nan for such grid point, but I'm getting the following error:
SVD did not converge in Linear Least Squares
Here's the code:
hus = ifile.hus
#stack lat and lon into a single dimension called allpoints
stacked = hus.stack(allpoints=['lat','lon'])
# define a function to compute a linear trend of a timeseries
def linear_trend(x):
x = x.dropna(dim='time')
if len(x)==0:
return xr.DataArray(np.nan)
else:
time = np.arange(len(x))
pf = np.polyfit(time, x, 1)
return xr.DataArray(pf[0])
trend = stacked.groupby('allpoints').apply(linear_trend)
trend_unstacked = trend.unstack('allpoints')
trend_unstacked
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-9-4e885325e9c4> in <module>
13
14 # apply the function over allpoints to calculate the trend at each point
---> 15 trend = t.groupby('allpoints').apply(linear_trend)
16 trend_unstacked = trend.unstack('allpoints')
17
~/anaconda3/lib/python3.7/site-packages/xarray/core/groupby.py in apply(self, func, shortcut, args, **kwargs)
824 stacklevel=2,
825 )
--> 826 return self.map(func, shortcut=shortcut, args=args, **kwargs)
827
828 def _combine(self, applied, restore_coord_dims=False, shortcut=False):
~/anaconda3/lib/python3.7/site-packages/xarray/core/groupby.py in map(self, func, shortcut, args, **kwargs)
809 grouped = self._iter_grouped()
810 applied = (maybe_wrap_array(arr, func(arr, *args, **kwargs)) for arr in grouped)
--> 811 return self._combine(applied, shortcut=shortcut)
812
813 def apply(self, func, shortcut=False, args=(), **kwargs):
~/anaconda3/lib/python3.7/site-packages/xarray/core/groupby.py in _combine(self, applied, restore_coord_dims, shortcut)
833 combined = self._concat_shortcut(applied, dim, positions)
834 else:
--> 835 combined = concat(applied, dim)
836 combined = _maybe_reorder(combined, dim, positions)
837
~/anaconda3/lib/python3.7/site-packages/xarray/core/concat.py in concat(objs, dim, data_vars, coords, compat, positions, fill_value, join)
133 "objects, got %s" % type(first_obj)
134 )
--> 135 return f(objs, dim, data_vars, coords, compat, positions, fill_value, join)
136
137
~/anaconda3/lib/python3.7/site-packages/xarray/core/concat.py in _dataarray_concat(arrays, dim, data_vars, coords, compat, positions, fill_value, join)
427 join="outer",
428 ):
--> 429 arrays = list(arrays)
430
431 if data_vars != "all":
~/anaconda3/lib/python3.7/site-packages/xarray/core/groupby.py in <genexpr>(.0)
808 else:
809 grouped = self._iter_grouped()
--> 810 applied = (maybe_wrap_array(arr, func(arr, *args, **kwargs)) for arr in grouped)
811 return self._combine(applied, shortcut=shortcut)
812
<ipython-input-9-4e885325e9c4> in linear_trend(x)
8 else:
9 time = np.arange(len(y))
---> 10 pf = np.polyfit(time, x, 1)
11 # we need to return a dataarray or else xarray's groupby won't be happy
12 return xr.DataArray(pf[0])
<__array_function__ internals> in polyfit(*args, **kwargs)
~/anaconda3/lib/python3.7/site-packages/numpy/lib/polynomial.py in polyfit(x, y, deg, rcond, full, w, cov)
603 raise TypeError("expected 1D or 2D array for y")
604 if x.shape[0] != y.shape[0]:
--> 605 raise TypeError("expected x and y to have same length")
606
607 # set rcond
TypeError: expected x and y to have same length
producing a series calculation of a dataframe to provide a percentage of NaN's to the total amount of rows as shown:
data = df.isnull().sum()/len(df)*100
RecordID 0.000000
ContactID 0.000000
EmailAddress 0.000000
ExternalID 100.000000
Date 0.000000
Name 0.000000
Owner 67.471362
Priority 0.000000
Status 0.000000
Subject 0.000000
Description 0.000000
Type 0.000000
dtype: float64
What I'm keen to do is represent this as a heatmap in seaborn sns.heatmap(data), drawing the readers attention those with 100 and 67%, unfortunately I'm getting this error
IndexError: Inconsistent shape between the condition and the input
(got (12, 1) and (12,))
Full traceback:
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-17-05db696a3a9b> in <module>()
----> 1 sns.heatmap(data)
~\AppData\Local\Programs\Python\Python36-32\lib\site-packages\seaborn\matrix.py in heatmap(data, vmin, vmax, cmap, center, robust, annot, fmt, annot_kws, linewidths, linecolor, cbar, cbar_kws, cbar_ax, square, xticklabels, yticklabels, mask, ax, **kwargs)
515 plotter = _HeatMapper(data, vmin, vmax, cmap, center, robust, annot, fmt,
516 annot_kws, cbar, cbar_kws, xticklabels,
--> 517 yticklabels, mask)
518
519 # Add the pcolormesh kwargs here
~\AppData\Local\Programs\Python\Python36-32\lib\site-packages\seaborn\matrix.py in __init__(self, data, vmin, vmax, cmap, center, robust, annot, fmt, annot_kws, cbar, cbar_kws, xticklabels, yticklabels, mask)
114 mask = _matrix_mask(data, mask)
115
--> 116 plot_data = np.ma.masked_where(np.asarray(mask), plot_data)
117
118 # Get good names for the rows and columns
~\AppData\Local\Programs\Python\Python36-32\lib\site-packages\numpy\ma\core.py in masked_where(condition, a, copy)
1934 if cshape and cshape != ashape:
1935 raise IndexError("Inconsistent shape between the condition and the input"
-> 1936 " (got %s and %s)" % (cshape, ashape))
1937 if hasattr(a, '_mask'):
1938 cond = mask_or(cond, a._mask)
IndexError: Inconsistent shape between the condition and the input (got (12, 1) and (12,))
My research if hitting a lot of walls around numpy broadcasting rules, or a bug from 3 years ago - none of which are super helpful.
Thanks as always.
Your data variable is an instance of pd.Series which is inherently 1D. However,
sns.heatmap expects a 2D input. A quick fix is for example the following:
sns.heatmap(data.to_frame())