list index out of range for regressor with y in {0,1}

[georgesteve]

Hi, thank you for your library, I think it's very useful to show the results, specially I like treeviz_bivar_3D , I was trying to compile a code with 2 variables and 1 binary output, but I obtain this error, I'm not sure if it was because the data type:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-217-d956e21d7290> in <module>
     47                       dist=12,
     48 
---> 49                       show={'splits','title'})
     50 
     51 

~/anaconda3/lib/python3.7/site-packages/dtreeviz/trees.py in rtreeviz_bivar_3D(ax, X_train, y_train, max_depth, feature_names, target_name, fontsize, ticks_fontsize, fontname, azim, elev, dist, show, colors, n_colors_in_map)
    234 
    235     rt = tree.DecisionTreeRegressor(max_depth=max_depth)
--> 236     rt.fit(X_train, y_train)
    237 
    238     y_lim = np.min(y_train), np.max(y_train)

~/anaconda3/lib/python3.7/site-packages/sklearn/tree/tree.py in fit(self, X, y, sample_weight, check_input, X_idx_sorted)
   1155             sample_weight=sample_weight,
   1156             check_input=check_input,
-> 1157             X_idx_sorted=X_idx_sorted)
   1158         return self
   1159 

~/anaconda3/lib/python3.7/site-packages/sklearn/tree/tree.py in fit(self, X, y, sample_weight, check_input, X_idx_sorted)
    248         if len(y) != n_samples:
    249             raise ValueError("Number of labels=%d does not match "
--> 250                              "number of samples=%d" % (len(y), n_samples))
    251         if not 0 <= self.min_weight_fraction_leaf <= 0.5:
    252             raise ValueError("min_weight_fraction_leaf must in [0, 0.5]")

ValueError: Number of labels=1 does not match number of samples=21

[parrt]

hi. Seems like X_train, y_train are a bit out of sync sizewise based upon that error msg.

[georgesteve]

Thank you for the answer!
You are right, I'm really sorry, I uploaded that error by mistake, I actually wanted to upload this one:

--------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
<ipython-input-40-4568def0d1f4> in <module>
     76                       azim=35,
     77                       dist=12,
---> 78                       show={'splits','title'})
     79 
     80 

~/anaconda3/lib/python3.7/site-packages/dtreeviz/trees.py in rtreeviz_bivar_3D(ax, X_train, y_train, max_depth, feature_names, target_name, fontsize, ticks_fontsize, fontname, azim, elev, dist, show, colors, n_colors_in_map)
    246 
    247     for node, bbox in tesselation:
--> 248         plane(node, bbox)
    249 
    250     x, y, z = X_train[:, 0], X_train[:, 1], y_train

~/anaconda3/lib/python3.7/site-packages/dtreeviz/trees.py in plane(node, bbox)
    230         # print(f"{color_map[int(((node.prediction()-y_lim[0])/y_range)*(n_colors_in_map-1))]}")
    231         ax.plot_surface(xx, yy, z, alpha=.85, shade=False,
--> 232                         color=color_map[int(((node.prediction()-y_lim[0])/y_range)*(n_colors_in_map-1))],
    233                         edgecolor=colors['edge'], lw=.3)
    234 

IndexError: list index out of range

[parrt]

ah. are there more than 10 classes? Can't do more than that.

[georgesteve]

No, that's the fact, first I though the error was because I was using many classes, but actually in this case there are only two classes.

[parrt]

Weird. Any chance you could send me a small data set that reproduces this?

[georgesteve]

This is my code, I only was trainning:

from sklearn.datasets import *
from sklearn import tree
from dtreeviz.trees import *

from mpl_toolkits.mplot3d import Axes3D




data = pd.DataFrame({'Edad': [ 17, 64, 18, 20, 38, 49, 55, 25, 29,  31, 33, 52, 65, 27, 39,  54, 30, 28, 27, 18, 47],
                     'Sexo': ['H', 'M', 'M', 'M', 'M', 'H', 'H', 'M', 'H', 'H', 'H', 'M', 'M', 'M', 'M',  'H', 'H', 'H', 'M', 'H', 'M'],
                      'Salario': [25, 80, 22, 36, 37, 59, 74, 70, 33, 102, 88, 35, 70, 51, 38,  94, 50, 35, 74, 32, 45], 
                      'Pagador': [1,   0,  1,  0,  1,  0,  0,  1,  1,   0,  1,  0,  0,  1,  1,   0,  1,  0,  0,  1,  0]})


from sklearn import preprocessing
code = preprocessing.LabelEncoder()
code.fit(["H", "M"])
data['Sexo']= code.transform(data['Sexo'])
data = data.sort_values('Edad')


features = [2,0]
X = data.values[:,features]
print(X)


y = data['Pagador'].values
print(y)

figsize = (42,16)
fig = plt.figure(figsize=figsize)
ax = fig.add_subplot(111, projection='3d')
t = rtreeviz_bivar_3D(ax,
                      X,y,
                      max_depth=None,
                      feature_names=['Edad','Sexo'],
                      target_name='Pagador',
                      fontsize=11,
                      elev=30,
                      azim=35,
                      dist=12,
                      show={'splits','title'})



plt.show()

Actually I tried with other internet data sets and every work fine, for example in the image. I am a little confused.

Thank you for your support.

[parrt]

Heh, don't you want a classifier here not a regressor? Pagador looks boolean

[parrt]

I think you want:

ctreeviz_bivar(ax, X, y, max_depth=5,
               feature_names=['Edad', 'Sexo'],
               class_names=['yes', 'no'],
               target_name='Pagador',
               show={'splits', 'title'},
               colors={'scatter_edge': 'black'}
               )

Regardless, I fixed so {0,1} doesn't cause crash for regression partitioning :)