# In[8]: #calling gridsearchcv grid = utils.grid_search_cv(X_train, y_train, scoring_method="accuracy") """ print(grid.cv_results_) print("============================") print(grid.best_estimator_) print("============================") print(grid.best_score_) print("============================") print(grid.best_params_) print("============================") """ # Prediction using gini y_pred_gini = utils.prediction(X_test, grid.best_estimator_) print("Results for gini algo") utils.cal_accuracy(y_test, y_pred_gini) output_filename = "%s/ML/DT/python/best_fit_graphviz_b_cancer_accuracy.txt" % q_src_dir export_graphviz(grid.best_estimator_, out_file=output_filename, filled=True, rounded=True, special_characters=True, feature_names=X_train.columns) # Train using gini clf_gini = utils.train_using_gini(X_train, y_train) #pickle_path = "dt_gini.pkl" #utils.save(clf_gini, pickle_path)
# In[10]: # Train using gini clf_gini = utils.train_using_gini(X_train, y_train) # print(X_train[1]) export_graphviz(clf_gini, out_file=graphviz_gini, filled=True, rounded=True, special_characters=True, feature_names=X_train.columns) # In[11]: # Prediction using test data and gini y_pred_gini = utils.prediction(X_test, clf_gini) print("Results for gini algo") utils.cal_accuracy(y_test, y_pred_gini) # In[12]: # Train using entropy clf_entropy = utils.tarin_using_entropy(X_train, y_train) # print(clf_entropy) utils.export_graphviz(clf_entropy, out_file=graphviz_entropy) # In[13]: # Prediction using entropy y_pred_entropy = utils.prediction(X_test, clf_entropy) print("Results for entropy algo")