def train_models(dataset, models):
""" Train the models for the dataset """
output_dir = OUTPUT_DATA_DIR + dataset.get_name() + "/"
result = {}
if "rf" in models:
rf = classifierwrapper.SklearnClassifier(dataset)
rf.set_properties("sklearn", "rf", output_dir)
rf.fit_model()
print(dir(rf))
rf.save_model()
result["rf"] = rf
if "lr" in models:
lr = classifierwrapper.SklearnClassifier(dataset)
lr.set_properties("sklearn", "lr", output_dir)
lr.fit_model()
lr.save_model()
lr.evaluate_model()
result["lr"] = lr
if "MLP" in models:
# Train models
MLP = keras_networks.MLPSimple2(dataset)
MLP.set_properties("keras", "mlp", output_dir)
MLP.fit_model()
MLP.save_model()
MLP.evaluate_model()
result["MLP"] = MLP
return result
def get_news_data_and_models():
""" Read in the data and saved models for the movie dataset"""
news_data = twentynewsgroups_dataset.TwentyNewssGroupsData()
news_data.load_dataset(OUTPUT_DATA_DIR + NEWS_DATA_DIR)
MLP_news = keras_networks.MLPSimple2(news_data)
MLP_news.load_model(OUTPUT_DATA_DIR + NEWS_DATA_DIR + NEWS_MLP)
lr_news = classifierwrapper.SklearnClassifier(news_data)
lr_news.load_model(OUTPUT_DATA_DIR + NEWS_DATA_DIR + NEWS_LR)
return news_data, MLP_news, lr_news
def get_rationales_data_and_models():
""" Read in the data and saved models for the rationales dataset """
rationales_data = rationales_dataset.RationalesData()
rationales_data.load_dataset(OUTPUT_DATA_DIR + RATIONALES_DATA_DIR)
MLP_rationales = keras_networks.MLPSimple2(rationales_data)
MLP_rationales.load_model(OUTPUT_DATA_DIR + RATIONALES_DATA_DIR +
RATIONALES_MLP)
lr_rationales = classifierwrapper.SklearnClassifier(rationales_data)
lr_rationales.load_model(OUTPUT_DATA_DIR + RATIONALES_DATA_DIR +
RATIONALES_LR)
return rationales_data, MLP_rationales, lr_rationales
def print_stats_and_evaluate_models_news():
"""Load the 20news dataset, print stats and evaluate the models """
news_data = twentynewsgroups_dataset.TwentyNewssGroupsData()
news_data.load_dataset(OUTPUT_DATA_DIR + NEWS_DATA_DIR)
news_data.print_stats()
print("Evaluate models")
lr_news = classifierwrapper.SklearnClassifier(news_data)
lr_news.load_model(OUTPUT_DATA_DIR + NEWS_DATA_DIR + NEWS_LR)
lr_news.evaluate_model()
MLP_news = keras_networks.MLPSimple2(news_data)
MLP_news.load_model(OUTPUT_DATA_DIR + NEWS_DATA_DIR + NEWS_MLP)
MLP_news.evaluate_model()
def print_stats_and_evaluate_models_rationales():
"""Load the movie (rationales) dataset, print stats and evaluate the models """
print("Load rationales")
rationales_data = rationales_dataset.RationalesData()
rationales_data.load_dataset(OUTPUT_DATA_DIR + RATIONALES_DATA_DIR)
rationales_data.print_stats()
print("Evaluate models")
lr_rationales = classifierwrapper.SklearnClassifier(rationales_data)
lr_rationales.load_model(OUTPUT_DATA_DIR + RATIONALES_DATA_DIR +
RATIONALES_LR)
lr_rationales.evaluate_model()
MLP_rationales = keras_networks.MLPSimple2(rationales_data)
MLP_rationales.load_model(OUTPUT_DATA_DIR + RATIONALES_DATA_DIR +
RATIONALES_MLP)
MLP_rationales.evaluate_model()
def test_omission(self):
rationales_data = rationales_dataset.RationalesData()
rationales_data.load_dataset(experiments.OUTPUT_DATA_DIR + experiments.RATIONALES_DATA_DIR)
MLP_rationales = keras_networks.MLPSimple2(rationales_data)
MLP_rationales.load_model(experiments.OUTPUT_DATA_DIR + experiments.RATIONALES_DATA_DIR + experiments.RATIONALES_MLP)
MLP_rationales.evaluate_model()
doc_id = 0
base_pred = MLP_rationales.model.predict_proba(np.array([rationales_data.x_test_trans_bin[doc_id]]), verbose=0)[0]
max_index = np.argmax(base_pred)
omission_summary = keras_networks.omission_summary_binary(rationales_data.x_test_trans_bin[doc_id], MLP_rationales.model, rationales_data.inv_vocab)
for word, score in omission_summary.items():
s = score[1]
modified_text = list(rationales_data.x_test_trans_bin[doc_id]) #copy
modified_text[rationales_data.vocab[word]] = 0
new_pred = MLP_rationales.model.predict_proba(np.array([modified_text]), verbose=0)[0]
npt.assert_almost_equal(base_pred[max_index] - new_pred[max_index], s, decimal=7)