else:
raise ValueError("Unknown tag: " + test_type)
data = data_utils.read_from_csv(data_file)
filtered_data = [x for x in data if getattr(x, tag_attr) != "" and getattr(x, tag_attr) != "u"]
filtered_data = filtered_data[:2500] # put a limit on the size for performance
labels = [np.float32(getattr(x, tag_attr) == TARGET_POSITIVE) for x in filtered_data]
report_ids = [x.report_id for x in filtered_data]
sentences = [x.processed_sentence for x in filtered_data]
train_data, train_labels, test_data, test_labels = data_utils.split_data(sentences, labels, report_ids, split_value)
# Create transformation pipeline
if USE_RF:
pipe = pipelines.get_count_lsi_randomforest()
else:
pipe = pipelines.get_count_lsi_SVM()
# set pipe parameters and train model
pipe.set_params(**model_params)
pipe.fit(train_data, train_labels)
print "Total = " + str(len(filtered_data)) + " [" + str(labels.count(0)) + ", " + str(labels.count(1)) + "]"
print "Train = " + str(len(train_data)) + " [" + str(train_labels.count(0)) + ", " + str(
train_labels.count(1)
) + "]"
print "Test = " + str(len(test_data)) + " [" + str(test_labels.count(0)) + ", " + str(test_labels.count(1)) + "]"
# Training performance data
y_true_train = train_labels
# change these parameters for the grid search
# parameters = {'lsi__n_components': [100],
# 'classifier__C': [3, 4, 5, 6, 7, 8, 9, 10],
# 'classifier__kernel': ["rbf"]
# }
parameters = {'lsi__n_components': [100],
'classifier__n_estimators': [1000],
'classifier__max_depth': [5, 10],
'classifier__min_samples_split': [5, 10],
'classifier__min_samples_leaf': [5, 10],
}
# clf = GridSearchCV(pipelines.get_count_lsi_SVM(), parameters)
clf = GridSearchCV(pipelines.get_count_lsi_randomforest(), parameters)
clf.fit(train_data, train_labels)
print "Best parameters set found o n development set:"
print ""
print clf.best_params_
print ""
print "Grid scores on development set:"
print ""
for params, mean_score, scores in clf.grid_scores_:
print "%0.3f (+/-%0.03f) for %r" % (mean_score, scores.std() * 2, params)
print ""
print "Detailed classification report:"
print ""
print "The model is trained on the full development set."
print "The scores are computed on the full evaluation set."
