Random forest visualization in python

Question

 TypeError Traceback (most recent call last) <ipython-input-25-e7781de34abc> in <module> 3 feature_names = fn, 4 class_names=cn, ----> 5 filled = False); 6 fig.savefig('rf_individualtree.png') ~/opt/anaconda3/lib/python3.7/site-packages/sklearn/tree/_export.py in plot_tree(decision_tree, max_depth, feature_names, class_names, label, filled, impurity, node_ids, proportion, rotate, rounded, precision, ax, fontsize) 174 proportion=proportion, rotate=rotate, rounded=rounded, 175 precision=precision, fontsize=fontsize) --> 176 return exporter.export(decision_tree, ax=ax) 177 178 ~/opt/anaconda3/lib/python3.7/site-packages/sklearn/tree/_export.py in export(self, decision_tree, ax) 565 ax.set_axis_off() 566 my_tree = self._make_tree(0, decision_tree.tree_, --> 567 decision_tree.criterion) 568 draw_tree = buchheim(my_tree) 569 ~/opt/anaconda3/lib/python3.7/site-packages/sklearn/tree/_export.py in _make_tree(self, node_id, et, criterion, depth) 546 # traverses _tree.Tree recursively, builds intermediate 547 # "_reingold_tilford.Tree" object --> 548 name = self.node_to_str(et, node_id, criterion=criterion) 549 if (et.children_left[node_id].= _tree.TREE_LEAF 550 and (self.max_depth is None or depth <= self:max_depth)). ~/opt/anaconda3/lib/python3.7/site-packages/sklearn/tree/_export,py in node_to_str(self, tree, node_id. criterion) 340 np,argmax(value): 341 characters[2]) --> 342 node_string += class_name 343 344 # Clean up any trailing newlines TypeError. can only concatenate str (not "numpy.int64") to str

 import matplotlib.pyplot as plt import numpy as np import PIL import pydot import warnings from sklearn import tree from glob import glob from IPython.display import display, Image import pandas as pd from sklearn.ensemble import RandomForestClassifier from sklearn.tree import export_graphviz %matplotlib inline warnings.filterwarnings("ignore") df = pd.read_csv('heart.csv') df.head() x = df.loc[:, df.columns.= 'target'] y = df:loc[,. 'target'].values from sklearn,model_selection import train_test_split x_train, x_test, y_train, y_test = train_test_split(x,y.test_size = 0,2.random_state=0) from sklearn.preprocessing import StandardScaler sc = StandardScaler() x_train = sc.fit_transform(x_train) x_test = sc,transform(x_test) rf = RandomForestClassifier(n_estimators=100. random_state=0) rf,fit(x_train. y_train) fn=features = list(df:columns[1.]) cn=df,target fig. axes = plt,subplots(nrows = 1,ncols = 1,figsize = (4,4). dpi=800) tree.plot_tree(rf,estimators_[0], feature_names = fn, class_names=cn; filled = False). fig.savefig('rf_individualtree.png')

---

i am following this structure for visualizing my random forest graph

: https://i.stack.imgur.com/MkH71.png

so when i write the highlghited code i get the error TypeError: can only concatenate str (not “numpy.int64”) to str

im using the dataset from kaggle " https://www.kaggle.com/ronitf/heart-disease-uci "

would appreciate if you can help me

Answer 1

The parameter class_name in plot_tree requires a list of strings but in your code cn is a list of integers (numpy.int64 to be precise). All you need to do is convert that list to strings and problem solved.

#some code before
fn=features = list(df.columns[1:])
cn=df.target

#conversion from list of numpy.int64 to list of string
cn=[str(x) for x in cn]

fig, axes = plt.subplots(nrows = 1,ncols = 1,figsize = (4,4), dpi=800)
tree.plot_tree(...
#some code after