

In [ ]:

    
import numpy as np
import matplotlib.pyplot as plt
% matplotlib inline
plt.rcParams["figure.dpi"] = 200
np.set_printoptions(precision=3)
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import scale, StandardScaler



In [ ]:

    
from sklearn.datasets import load_breast_cancer
cancer = load_breast_cancer()



In [ ]:

    
print(cancer.DESCR)



In [ ]:

    
X_train, X_test, y_train, y_test = train_test_split(
    cancer.data, cancer.target, stratify=cancer.target, random_state=0)

tree visualization



In [ ]:

    
from sklearn.tree import DecisionTreeClassifier, export_graphviz
tree = DecisionTreeClassifier(max_depth=2)
tree.fit(X_train, y_train)



In [ ]:

    
tree_dot = export_graphviz(tree, out_file=None, feature_names=cancer.feature_names, filled=True)



In [ ]:

    
print(tree_dot)



In [ ]:

    
import graphviz
graphviz.Source(tree_dot)

Parameter Tuning



In [ ]:

    
tree = DecisionTreeClassifier().fit(X_train, y_train)
tree_dot = export_graphviz(tree, out_file=None, feature_names=cancer.feature_names, filled=True)
graphviz.Source(tree_dot, format="png")



In [ ]:

    
tree = DecisionTreeClassifier(max_depth=1).fit(X_train, y_train)
tree_dot = export_graphviz(tree, out_file=None, feature_names=cancer.feature_names)
graphviz.Source(tree_dot, format="png")



In [ ]:

    
tree = DecisionTreeClassifier(max_leaf_nodes=8).fit(X_train, y_train)
tree_dot = export_graphviz(tree, out_file=None, feature_names=cancer.feature_names, filled=True)
graphviz.Source(tree_dot, format="png")



In [ ]:

    
tree = DecisionTreeClassifier(min_samples_split=50).fit(X_train, y_train)
tree_dot = export_graphviz(tree, out_file=None, feature_names=cancer.feature_names, filled=True)
graphviz.Source(tree_dot, format="png")



In [ ]:

    
from sklearn.model_selection import GridSearchCV
param_grid = {'max_depth':range(1, 7)}
grid = GridSearchCV(DecisionTreeClassifier(random_state=0), param_grid=param_grid, cv=10)
grid.fit(X_train, y_train)



In [ ]:

    
from sklearn.model_selection import GridSearchCV, StratifiedShuffleSplit
param_grid = {'max_depth':range(1, 7)}
grid = GridSearchCV(DecisionTreeClassifier(random_state=0), param_grid=param_grid,
                    cv=StratifiedShuffleSplit(100))
grid.fit(X_train, y_train)



In [ ]:

    
scores = pd.DataFrame(grid.cv_results_)
scores.plot(x='param_max_depth', y=['mean_train_score', 'mean_test_score'], ax=plt.gca())
plt.legend(loc=(1, 0))



In [ ]:

    
from sklearn.model_selection import GridSearchCV
param_grid = {'max_leaf_nodes':range(2, 20)}
grid = GridSearchCV(DecisionTreeClassifier(random_state=0), param_grid=param_grid, cv=StratifiedShuffleSplit(100, random_state=1))
grid.fit(X_train, y_train)

scores = pd.DataFrame(grid.cv_results_)
scores.plot(x='param_max_leaf_nodes', y=['mean_train_score', 'mean_test_score'], ax=plt.gca())
plt.legend(loc=(1, 0))



In [ ]:

    
scores = pd.DataFrame(grid.cv_results_)
scores.plot(x='param_max_leaf_nodes', y='mean_train_score', yerr='std_train_score', ax=plt.gca())
scores.plot(x='param_max_leaf_nodes', y='mean_test_score', yerr='std_test_score', ax=plt.gca())



In [ ]:

    
grid.best_params_



In [ ]:

    
tree_dot = export_graphviz(grid.best_estimator_, out_file=None, feature_names=cancer.feature_names, filled=True)
graph = graphviz.Source(tree_dot, format="png")
graph



In [ ]:

    
pd.Series(grid.best_estimator_.feature_importances_,
          index=cancer.feature_names).plot(kind="barh")



In [ ]:

    
# set PATH=PATH;<Anaconda>\Library\bin\graphviz

Exercise

Apply a decision tree to the "adult" dataset and visualize it.

Tune parameters with grid-search; use max_features, try at least max_leaf_nodes and max_depth, but separately.

Visualize the resulting tree and it's feature importances.



In [ ]: