I am trying to use plotnine to build graphs and I keep coming across the same KeyError problem when I want to plot just the x-axis. See the traceback error below.
A sample of my data is:
WORD TAG TOPIC Value
0 hey aa 1 234
1 working bb 1 123
2 lullaby cc 2 32
3 Doggy cc 2 63
4 document aa 3 84
sample of my code:
from plotnine import *
import pandas as pd
inFile = 'infile.csv'
df = pd.read_csv(inFile, names = ['WORD', 'TAG','TOPIC','VALUE'], header=0,sep='\t')
df.sort_values('value',ascending=False)
sortedDf = df[:5]
plot1 = ggplot(sortedDf) + aes(x='TOPIC') + geom_histogram(binwidth=3)
where the final goal is to plot the count of each topic in a histogram.
I am not sure what data is missing that is raising the following key error, as there is no need for a weight as I am only interested in plotting the count of that one particular variable, ie. topic 1 = 2, topic 2= 2, topic 3 = 1.
Does anyone have any link to more detailled documentation of plotline or any experience with the library to help me understand more in detail what I am missing.
Traceback Error:
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-112-71707b4cf21a> in <module>()
1 plot2 = ggplot(sortedDf) + aes(x='TOPIC') + geom_histogram(binwidth=3)
----> 2 print plot2
/Users/anaconda/lib/python2.7/site-packages/plotnine/ggplot.pyc in __repr__(self)
82 Print/show the plot
83 """
---> 84 self.draw()
85 plt.show()
86 return '<ggplot: (%d)>' % self.__hash__()
/Users/anaconda/lib/python2.7/site-packages/plotnine/ggplot.pyc in draw(self)
139 # assign a default theme
140 self = deepcopy(self)
--> 141 self._build()
142
143 # If no theme we use the default
/Users/anaconda/lib/python2.7/site-packages/plotnine/ggplot.pyc in _build(self)
235
236 # Apply and map statistics
--> 237 layers.compute_statistic(layout)
238 layers.map_statistic(self)
239
/Users/anaconda/lib/python2.7/site-packages/plotnine/layer.pyc in compute_statistic(self, layout)
92 def compute_statistic(self, layout):
93 for l in self:
---> 94 l.compute_statistic(layout)
95
96 def map_statistic(self, plot):
/Users/anaconda/lib/python2.7/site-packages/plotnine/layer.pyc in compute_statistic(self, layout)
369 data = self.stat.use_defaults(data)
370 data = self.stat.setup_data(data)
--> 371 data = self.stat.compute_layer(data, params, layout)
372 self.data = data
373
/Users/anaconda/lib/python2.7/site-packages/plotnine/stats/stat.pyc in compute_layer(cls, data, params, layout)
194 return cls.compute_panel(pdata, pscales, **params)
195
--> 196 return groupby_apply(data, 'PANEL', fn)
197
198 @classmethod
/Users/anaconda/lib/python2.7/site-packages/plotnine/utils.pyc in groupby_apply(df, cols, func, *args, **kwargs)
615 # do not mark d as a slice of df i.e no SettingWithCopyWarning
616 d.is_copy = None
--> 617 lst.append(func(d, *args, **kwargs))
618 return pd.concat(lst, axis=axis, ignore_index=True)
619
/Users/anaconda/lib/python2.7/site-packages/plotnine/stats/stat.pyc in fn(pdata)
192 return pdata
193 pscales = layout.get_scales(pdata['PANEL'].iat[0])
--> 194 return cls.compute_panel(pdata, pscales, **params)
195
196 return groupby_apply(data, 'PANEL', fn)
/Users/anaconda/lib/python2.7/site-packages/plotnine/stats/stat.pyc in compute_panel(cls, data, scales, **params)
221 for _, old in data.groupby('group'):
222 old.is_copy = None
--> 223 new = cls.compute_group(old, scales, **params)
224 unique = uniquecols(old)
225 missing = unique.columns.difference(new.columns)
/Users/anaconda/lib/python2.7/site-packages/plotnine/stats/stat_bin.pyc in compute_group(cls, data, scales, **params)
107 new_data = assign_bins(
108 data['x'], breaks, data.get('weight'),
--> 109 params['pad'], params['closed'])
110 return new_data
/Users/anaconda/lib/python2.7/site-packages/plotnine/stats/binning.pyc in assign_bins(x, breaks, weight, pad, closed)
163 df = pd.DataFrame({'bin_idx': bin_idx, 'weight': weight})
164 wftable = df.pivot_table(
--> 165 'weight', index=['bin_idx'], aggfunc=np.sum)['weight']
166
167 # Empty bins get no value in the computed frequency table.
/Users/anaconda/lib/python2.7/site-packages/pandas/core/series.pyc in __getitem__(self, key)
601 result = self.index.get_value(self, key)
602
--> 603 if not is_scalar(result):
604 if is_list_like(result) and not isinstance(result, Series):
605
/Users/anaconda/lib/python2.7/site-packages/pandas/indexes/base.pyc in get_value(self, series, key)
pandas/index.pyx in pandas.index.IndexEngine.get_value (pandas/index.c:3557)()
pandas/index.pyx in pandas.index.IndexEngine.get_value (pandas/index.c:3240)()
pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4363)()
KeyError: 'weight'
