I have two dataset in csv format:
df2
type prediction 100000 155000
0 0 2.60994 3.40305
1 1 10.82100 34.68900
0 0 4.29470 3.74023
0 0 7.81339 9.92839
0 0 28.37480 33.58000
df
TIMESTEP id type y z v_acc
100000 8054 1 -0.317192 -0.315662 15.54430
100000 669 0 0.352031 -0.008087 2.60994
100000 520 0 0.437786 0.000325 5.28670
100000 2303 1 0.263105 0.132615 7.81339
105000 8055 1 0.113863 0.036407 5.94311
I am trying to match value of df2[100000] to df1[v_acc]. If value matched, I am making scatter plot from df with columns y and z. After that I want to to annoted scatter point with matched value.
What I want is:
(I want all annotaions in a same plot).
I tried to code in python for such condition but I am not getting all annotation points in a single plot instead I am getting multi plots with a single annotation.
I am also getting this error:
TypeError Traceback (most recent call last)
File /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/IPython/core/formatters.py:339, in BaseFormatter.__call__(self, obj)
337 pass
338 else:
--> 339 return printer(obj)
340 # Finally look for special method names
341 method = get_real_method(obj, self.print_method)
File /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/IPython/core/pylabtools.py:151, in print_figure(fig, fmt, bbox_inches, base64, **kwargs)
148 from matplotlib.backend_bases import FigureCanvasBase
149 FigureCanvasBase(fig)
--> 151 fig.canvas.print_figure(bytes_io, **kw)
152 data = bytes_io.getvalue()
153 if fmt == 'svg':
File /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/matplotlib/backend_bases.py:2295, in FigureCanvasBase.print_figure(self, filename, dpi, facecolor, edgecolor, orientation, format, bbox_inches, pad_inches, bbox_extra_artists, backend, **kwargs)
2289 renderer = _get_renderer(
2290 self.figure,
2291 functools.partial(
2292 print_method, orientation=orientation)
2293 )
2294 with getattr(renderer, "_draw_disabled", nullcontext)():
-> 2295 self.figure.draw(renderer)
2297 if bbox_inches:
...
189 if len(self) == 1:
190 return converter(self.iloc[0])
--> 191 raise TypeError(f"cannot convert the series to {converter}")
TypeError: cannot convert the series to <class 'float'>
Can I get some help to make a plot as I want?
Thank you.
My code is here:
df2 = pd.read_csv('./result.csv')
print(df2.columns)
#print(df2.head(10))
df = pd.read_csv('./main.csv')
df = df[df['TIMESTEP'] == 100000]
for i in df['v_acc']:
for j in df2['100000']:
# sometimes numbers are long and different after decimals.So mathing 0.2f only
if "{0:0.2f}".format(i) == "{0:0.2f}".format(j):
plt.figure(figsize = (10,8))
sns.scatterplot(data = df, x = "y", y = "z", hue = "type", palette=['red','dodgerblue'], legend='full')
plt.annotate(i, (df['y'][df['v_acc'] == i], df['z'][df['v_acc'] == i]))
plt.grid(False)
plt.show()
break
the reason for the multiple plots is because are you using plt.figure() inside the loop. This will create a single figure for each loop. You need to create that outside and only the individual scatter and annotate within the loop. Here is the updated code that ran for the data you provided. Other than that, think your code is fine...
fig, ax=plt.subplots(figsize = (7,7)) ### Keep this before the loop and call it as subplot
for i in df['v_acc']:
for j in df2[100000]:
# sometimes numbers are long and different after decimals.So mathing 0.2f only
if "{0:0.2f}".format(i) == "{0:0.2f}".format(j):
#plt.figure(figsize = (10,8))
ax=sns.scatterplot(data = df, x = "y", y = "z", hue = "type", palette=['red','dodgerblue'], legend='full')
ax.annotate(i, (df['y'][df['v_acc'] == i], df['z'][df['v_acc'] == i]))
break
plt.grid(False) ### Keep these two after the loop, just one show for one plot
plt.show()
Output plot
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.
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.
x = (long list of data)
mymap = map(int, x.split())
box = []
mylist = list(mymap)
while len(mylist)>0:
box.append([str(mylist[1])]*mylist[0])
mylist = mylist[2:]
box.sort()
print(type(box))
type(box)
p=sns.displot(data = box)
p.set(xlabel = "Waiting time", ylabel = "Eruptions")
This is my code to create a histogram in sage from an extremely long list of data. The data is all like "3600 79 2800 58" etc with value and then frequency. Everything works well except the histogram generation itself. I've already tried outputting the list and it prints out perfectly fine.
This is the output when I run it:
<class 'list'>
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-26-87f016146a7f> in <module>
9 print(type(box))
10 type(box)
---> 11 p=sns.displot(data = box)
12 p.set(xlabel = "Waiting time", ylabel = "Eruptions")
/usr/local/lib/python3.8/dist-packages/seaborn/distributions.py in displot(data, x, y, hue, row, col, weights, kind, rug, rug_kws, log_scale, legend, palette, hue_order, hue_norm, color, col_wrap, row_order, col_order, height, aspect, facet_kws, **kwargs)
2225
2226 _assign_default_kwargs(hist_kws, p.plot_univariate_histogram, histplot)
-> 2227 p.plot_univariate_histogram(**hist_kws)
2228
2229 else:
/usr/local/lib/python3.8/dist-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)
422
423 # First pass through the data to compute the histograms
--> 424 for sub_vars, sub_data in self.iter_data("hue", from_comp_data=True):
425
426 # Prepare the relevant data
/usr/local/lib/python3.8/dist-packages/seaborn/_core.py in iter_data(self, grouping_vars, reverse, from_comp_data)
994 grouping_keys.append(self.var_levels.get(var, []))
995
--> 996 iter_keys = itertools.product(*grouping_keys)
997 if reverse:
998 iter_keys = reversed(list(iter_keys))
TypeError: 'NoneType' object is not iterable
Clearly box is a list since type(box) returns list, so what am I missing here? What is making its type become none?
insted of using while use for, something like this
x = (long list of data)
mymap = map(int, x.split())
box = []
mylist = list(mymap)
for i in range (len(mylist)):
box.insert(i, str(mylist[1] *mylist[0]) # or append
mylist = mylist[2:]
box.sort()
print(type(box))
type(box)
p=sns.displot(data = box)
p.set(xlabel = "Waiting time", ylabel = "Eruptions")
I am trying to draw some basic plots using the seaborn's jointplot() method.
My pandas data frame looks like this:
Out[250]:
YEAR Yields avgSumPcpn avgMaxSumTemp avgMinSumTemp
1970 5000 133.924981 30.437124 19.026974
1971 5560 107.691316 31.161974 19.278186
1972 5196 116.830066 31.454192 19.443712
1973 4233 181.550733 30.373581 19.097679
1975 5093 112.137538 30.428966 18.863224
I am trying to draw 'Yields' against 'YEAR' (So a plot to see how 'Yields' is varying over time). A simple plot.
But when I do this:
sns.jointplot(x='YEAR',y='Yeilds', data = summer_pcpn_temp_yeild, kind = 'reg', size = 10)
I am getting the following error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-251-587582a746b8> in <module>()
3 #ax = plt.axes()
4 #sns_sum_reg_min_temp_pcpn = sns.regplot(x='avgSumPcpn',y='avgMaxSumTemp', data = df_sum_temp_pcpn)
----> 5 sns.jointplot(x='Yeilds',y='YEAR', data = summer_pcpn_temp_yeild, kind = 'reg', size = 10)
6 plt.title('Avg Summer Precipitation vs Yields of Wharton TX', fontsize = 10)
7
//anaconda/lib/python2.7/site-packages/seaborn/distributions.pyc in jointplot(x, y, data, kind, stat_func, color, size, ratio, space, dropna, xlim, ylim, joint_kws, marginal_kws, annot_kws, **kwargs)
793 grid = JointGrid(x, y, data, dropna=dropna,
794 size=size, ratio=ratio, space=space,
--> 795 xlim=xlim, ylim=ylim)
796
797 # Plot the data using the grid
//anaconda/lib/python2.7/site-packages/seaborn/axisgrid.pyc in __init__(self, x, y, data, size, ratio, space, dropna, xlim, ylim)
1637 if dropna:
1638 not_na = pd.notnull(x) & pd.notnull(y)
-> 1639 x = x[not_na]
1640 y = y[not_na]
1641
TypeError: string indices must be integers, not Series
So I printed out the types of each column. Here is how:
for i in summer_pcpn_temp_yeild.columns.values.tolist():
print type(summer_pcpn_temp_yeild[[i]])
print type(summer_pcpn_temp_yeild.index.values)
which gives me:
<class 'pandas.core.frame.DataFrame'>
<class 'pandas.core.frame.DataFrame'>
<class 'pandas.core.frame.DataFrame'>
<class 'pandas.core.frame.DataFrame'>
<class 'pandas.core.frame.DataFrame'>
<type 'numpy.ndarray'>
SO, I am not being able to understand how to fix it.
Any help would be greatly appreciated.
Thanks
Check that the YEAR and Yields have integer ( not string) types of values.
Try changing x='Yeilds' to x='Yields' in your call to jointplot:
sns.jointplot(x='YEAR',y='Yeilds', data = summer_pcpn_temp_yeild, kind = 'reg', size = 10)
The error message is misleading. Seaborn can't find the column named "Yeilds" in your summer_pcpn_temp_yeild dataframe, because the dataframe column is spelled "Yields".
I had the same problem, and fixed it by correcting the x= argument to sns.jointplot()
The goal of my code is to sort through the data and select only the Visual band or "Vis." band data. From that I eliminated all values that were upper and lower limits to clean up the graph. Finally I wanted to remove all the data that was not a part of the outbursts or decays. My filtering of Vis. band and the upper/lower limit data seems to work fine, but when I try to remove data that had a small slope it shows key error:1, I don't have enough reputation to post an image so I included a link to the plot. The plot shows data after filtering the vis band and upper/lower limits.
def timeplot():
import pandas as pd
import matplotlib.pyplot as plt
import jdcal as jd
import math
#Getting input from user as to start and end dates for the data
(miny,minm,mind) = input("Enter the start date for data in the format (yyyy,mm,dd) ex. (2000,01,01):")
(maxy,maxm,maxd) = input("Enter the end date for data in the format (yyyy,mm,dd) ex. (2000,01,01):")
#Calculating modified julian dates from the gregorian date input
(x,Amin)=jd.gcal2jd(miny,minm,mind)
(y,Amax)=jd.gcal2jd(maxy,maxm,maxd)
#Creating a table with the numbers corresponding to their month
Month = {1:'Jan', 2:'Feb', 3:'Mar', 4:'Apr', 5:'May', 6:'Jun', 7:'Jul', 8:'Aug', 9:'Sep', 10:'Oct', 11:'Nov', 12:'Dec'}
#Read in data file
pd.set_option('html', False)
pd.set_option('max_columns', 30)
pd.set_option('max_rows', 2000)
data1 = pd.read_csv("50yrdata.csv")
data1['ulflag']=1
#Deal with any bad columns
data1_limit = data1.JD * 0
ii=0
for mag in data1.Magnitude:
if mag[0] == '<':
data1.ulflag[ii]=0
data1.Magnitude[ii] = mag[1:]
data1_limit[ii] = 1
if mag[0] == '>':
data1.ulflag[ii]=0
data1.Magnitude[ii] = mag[1:]
data1_limit[ii] = -1
ii +=1
#The data set has Vis, V, I, R, B, TG, TB, TR, CV bands
#Selecting data only in the visual band with no upper or lower limits in
#magnitude
#Converting Julian Date to Modified Julian Date
data1.JD=data1.JD-2400000.5
data1.index=data1.ulflag
data1=data1.ix[1,['JD','Magnitude','Band']]
data1.index=data1.Band
tdata=data1.ix['Vis.',['JD','Magnitude']]
#Changing all of the values from Magnitude from string to float
tdata=tdata.astype(float)
#Adding on columns to make computations easier
tdata['sflag']=0
tdata['slope']=0.000
tdata['aslope']=0.000
tdata['A']=0.000
tdata['B']=0.000
#Finding max and min values of our MJD,
Max=Amax
Min=Amin
#We split the data into N graphs where N is the number of years the data spans
N=(int((Max-Min)/365))
#Finding slope of the curve
#Attempt to filter the data using
#1. A positive slope greater than a certain threshold = outburst
#2. A negtaive slope smaller than a certain threshold = decay
#3. The absolute value of the slope is smaller than a certain threshold = quiescence
length=len(tdata.JD)-1
tdata.A[length]=0
tdata.B[length]=1
for i in range(length):
tdata.A[i] = tdata.Magnitude[i+1]-tdata.Magnitude[i]
for i in range(length):
tdata.B[i] = tdata.JD[i+1]-tdata.JD[i]
for i in range(length+1):
tdata.slope[i] = tdata.A[i]/tdata.B[i]
tdata.aslope=abs(tdata.slope)
for i in range(length):
if tdata.aslope[i] > 1:
tdata.sflag = 1
if tdata.aslope[i] < 1:
tdata.sflag = 0
i += 1
#filtering out all the data that has a slope less than a certain threshold
tdata.index = tdata.sflag
tdata=tdata.astype(float)
tdata=tdata.ix[1,['JD','Magnitude']]
#Plot selected data
fig ,axs = plt.subplots(N,1)
fig.subplots_adjust(hspace = .5)
#Due to data set being so large, make multiple sub plots instead of one large plot
#Magnitude axis needs to be flipped to see when the star has outbursts
#When setting the limits of our subplots, we extend them by a small value in
#order to make the data easier to read. The large value being added and subtracted
#of 365 causes the graph to cover approximately one year in data.
axs = axs.ravel()
for i in range(N):
axs[i].scatter(tdata.JD, tdata.Magnitude)
axs[i].invert_yaxis()
axs[i].set_xlim([Min+(365*(i-1))-5, Max+5-(365*(N-i))])
A=str(miny+i)
B=Month[minm]
C=str(mind)
axs[i].set_title('A Year of data starting from ' + A + ',' + B + ',' +C)
#Setting title and axis, I was unable to set a shared x and y axis title
#between the subplots, when I attempted to do this it would create another
#plot overlapping the 4 subplots making it difficult to see the values
fig.suptitle('SS Cyg Data', fontsize = 20)
fig.text(0.5, 0.04, 'Modified Julian Date', ha='center', va='center')
fig.text(0.04, 0.5, 'Magnitude', ha='center', va='center', rotation='vertical')
plt.show()
timeplot()
The full Traceback to the error is
KeyError Traceback (most recent call last)
C:\Users\Kenny\AppData\Local\Enthought\Canopy\App\appdata\canopy-1.2.0.1610.win-x86_64\lib\site-packages\IPython\utils\py3compat.pyc in execfile(fname, glob, loc)
195 else:
196 filename = fname
--> 197 exec compile(scripttext, filename, 'exec') in glob, loc
198 else:
199 def execfile(fname, *where):
C:\Users\Kenny\Dropbox\499\timeplot.py in <module>()
136 plt.show()
137
--> 138 timeplot()
C:\Users\Kenny\Dropbox\499\timeplot.py in timeplot()
102 tdata.index = tdata.sflag
103 tdata=tdata.astype(float)
--> 104 tdata=tdata.ix[1,['JD','Magnitude']]
105
106 #Plot selected data
E:\Enthought\Canopy\User\lib\site-packages\pandas\core\indexing.pyc in __getitem__(self, key)
45 pass
46
---> 47 return self._getitem_tuple(key)
48 else:
49 return self._getitem_axis(key, axis=0)
E:\Enthought\Canopy\User\lib\site-packages\pandas\core\indexing.pyc in _getitem_tuple(self, tup)
251 def _getitem_tuple(self, tup):
252 try:
--> 253 return self._getitem_lowerdim(tup)
254 except IndexingError:
255 pass
E:\Enthought\Canopy\User\lib\site-packages\pandas\core\indexing.pyc in _getitem_lowerdim(self, tup)
361 for i, key in enumerate(tup):
362 if _is_label_like(key) or isinstance(key, tuple):
--> 363 section = self._getitem_axis(key, axis=i)
364
365 # we have yielded a scalar ?
E:\Enthought\Canopy\User\lib\site-packages\pandas\core\indexing.pyc in _getitem_axis(self, key, axis)
411 return self._get_loc(key, axis=axis)
412
--> 413 return self._get_label(key, axis=axis)
414
415 def _getitem_iterable(self, key, axis=0):
E:\Enthought\Canopy\User\lib\site-packages\pandas\core\indexing.pyc in _get_label(self, label, axis)
59 return self.obj._xs(label, axis=axis, copy=False)
60 except Exception:
---> 61 return self.obj._xs(label, axis=axis, copy=True)
62
63 def _get_loc(self, key, axis=0):
E:\Enthought\Canopy\User\lib\site-packages\pandas\core\frame.pyc in xs(self, key, axis, level, copy)
2369 loc, new_index = self.index.get_loc_level(key)
2370 else:
-> 2371 loc = self.index.get_loc(key)
2372
2373 if isinstance(loc, np.ndarray):
E:\Enthought\Canopy\User\lib\site-packages\pandas\core\index.pyc in get_loc(self, key)
714 loc : int if unique index, possibly slice or mask if not
715 """
--> 716 return self._engine.get_loc(key)
717
718 def get_value(self, series, key):
E:\Enthought\Canopy\User\lib\site-packages\pandas\index.pyd in pandas.index.IndexEngine.get_loc (pandas\index.c:3542)()
E:\Enthought\Canopy\User\lib\site-packages\pandas\index.pyd in pandas.index.IndexEngine.get_loc (pandas\index.c:3373)()
E:\Enthought\Canopy\User\lib\site-packages\pandas\index.pyd in pandas.index.IndexEngine._get_loc_duplicates (pandas\index.c:3709)()
KeyError: 1