y = df['prognosis']
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.33,
random_state=42)
print("DecisionTree")
dt = DecisionTreeClassifier()
clf_dt = dt.fit(x_train, y_train)
print("Acurracy: ", clf_dt.score(x_test, y_test))
print("cross result========")
scores = cross_val_score(dt, x_test, y_test, cv=3)
print(scores)
print(scores.mean())
export_graphviz(dt, out_file='diseaseData/tree.dot', feature_names=cols)
dt.__getstate__()
importances = dt.feature_importances_
indices = np.argsort(importances)[::-1]
# Print the feature ranking
print("Feature ranking:")
features = cols
for f in range(5):
print(
"%d. feature %d - %s (%f)" %
(f + 1, indices[f], features[indices[f]], importances[indices[f]]))
export_graphviz(dt,
out_file='diseaseData/tree-top5.dot',
feature_names=cols,
max_depth=5)
Image(filename='tree-top5.png')
