def run(self, train_returns, train_sizes, bin_number):
cross_val = CrossValidation.CrossVal(train_sizes, bin_number)
bins = cross_val.get_bins()
scores = self.predict(train_returns, bins)
self.interpret_scores(scores)
print(scores) #decile scores
def run(self, train_corpus, freq_type, stopwords, train_returns,
bin_number, filename):
vectorizer = MatrixVectorizer.Vectorizer(train_corpus, freq_type,
stopwords)
train_count_matrix = vectorizer.get_count_matrix()
negative_word_list = self.create_negative_stuff(filename)
negative_word_matrix = vectorizer.transform_new_data(
negative_word_list)
document_scores = self.score_documents(negative_word_matrix,
train_count_matrix)
cross_val = CrossValidation.CrossVal(document_scores, bin_number)
bins = cross_val.get_bins()
scores = self.predict(train_returns, bins)
self.interpret_scores(scores)
print(scores)
def run(self, train_corpus, freq_type, stopwords, test_corpus, svals,
reduce_type, test_returns, bin_number, train_returns, method):
vectorizer = MatrixVectorizer.Vectorizer(train_corpus, freq_type,
stopwords)
train_count_matrix = vectorizer.get_count_matrix()
test_count_matrix = vectorizer.transform_new_data(test_corpus)
dim_reducer = DimensionReducer.Reducer(train_count_matrix)
reduced_train_count_matrix = dim_reducer.reduce_dimension(
svals, reduce_type)
reduced_test_count_matrix = dim_reducer.reduce_more_data(
test_count_matrix.todense())
cross_val = CrossValidation.CrossVal(test_returns, bin_number)
bins = cross_val.get_bins()
scores = self.fit_predict(reduced_train_count_matrix, train_returns,
reduced_test_count_matrix, bins, method)
self.interpret_scores(scores)
