def classify_category(self, category_path, model_func):
confusion_row = {}
for article in os.listdir(category_path):
article_words = {}
parse_article(category_path, article, article_words, self.stop_list)
best_probability = -sys.maxint - 1
best_category = None
for category_name in self.categories:
probability = model_func(self.categories[category_name], article_words)
if probability > best_probability:
best_probability = probability
best_category = category_name
confusion_row[best_category] = confusion_row.setdefault(best_category, 0) + 1
self.confusion_matrix[os.path.basename(category_path)] = confusion_row
def classify_category(self, category_path, model_func):
confusion_row = {}
for article in os.listdir(category_path):
article_words = {}
parse_article(category_path, article, article_words,
self.stop_list)
best_probability = -sys.maxint - 1
best_category = None
for category_name in self.categories:
probability = model_func(self.categories[category_name],
article_words)
if probability > best_probability:
best_probability = probability
best_category = category_name
confusion_row[best_category] = confusion_row.setdefault(
best_category, 0) + 1
self.confusion_matrix[os.path.basename(category_path)] = confusion_row
def categorize(self, path):
for article in os.listdir(path):
self.article_count += 1
# TODO add exception handling
parse_article(path, article, self.word_counts, self.stop_words)
def categorize(self, path):
for article in os.listdir(path):
self.article_count += 1
# TODO add exception handling
parse_article(path, article, self.word_counts, self.stop_words)
