This seems simple enough, but I can't find a solution online.
I am trying to create an sns.pairplot in Python. I have downloaded the wine dataset, kept the features that I need, and run the plot.
%matplotlib inline
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from sklearn.datasets import load_wine
# Load the wine dataset
wine = datasets.load_wine()
wine = list(zip(wine.data, wine.target))
wine = load_wine()
import numpy as np
import pandas as pd
from sklearn.datasets import load_iris
wine = load_wine
data = load_wine()
df = pd.DataFrame(data.data, columns=data.feature_names)
#This is the code that should run the plot
b=sns.pairplot(df, vars = df.columns[1 :], hue = "target", height = 2.5)
But I get this error:
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
~\anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2894 try:
-> 2895 return self._engine.get_loc(casted_key)
2896 except KeyError as err:
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()
pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()
KeyError: 'target'
The above exception was the direct cause of the following exception:
KeyError Traceback (most recent call last)
<ipython-input-108-1107acc27949> in <module>
----> 1 b=sns.pairplot(df, vars = df.columns[1 :], hue = "target", height = 2.5)
2
3 plt.show()
~\anaconda3\lib\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
~\anaconda3\lib\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)
1923 # Set up the PairGrid
1924 grid_kws.setdefault("diag_sharey", diag_kind == "hist")
-> 1925 grid = PairGrid(data, vars=vars, x_vars=x_vars, y_vars=y_vars, hue=hue,
1926 hue_order=hue_order, palette=palette, corner=corner,
1927 height=height, aspect=aspect, dropna=dropna, **grid_kws)
~\anaconda3\lib\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
~\anaconda3\lib\site-packages\seaborn\axisgrid.py in __init__(self, data, hue, hue_order, palette, hue_kws, vars, x_vars, y_vars, corner, diag_sharey, height, aspect, layout_pad, despine, dropna, size)
1212 index=data.index)
1213 else:
-> 1214 hue_names = categorical_order(data[hue], hue_order)
1215 if dropna:
1216 # Filter NA from the list of unique hue names
~\anaconda3\lib\site-packages\pandas\core\frame.py in __getitem__(self, key)
2900 if self.columns.nlevels > 1:
2901 return self._getitem_multilevel(key)
-> 2902 indexer = self.columns.get_loc(key)
2903 if is_integer(indexer):
2904 indexer = [indexer]
~\anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2895 return self._engine.get_loc(casted_key)
2896 except KeyError as err:
-> 2897 raise KeyError(key) from err
2898
2899 if tolerance is not None:
KeyError: 'target'
The solution linked to this question: How to convert a Scikit-learn dataset to a Pandas dataset unfortunately doesn't seem to work here.
I also tried 'class' instead of target. Could it be that the 'zip' function isn't working correctly above, so the program can't identify 'target'?
Thank you in advance!
