def read_texts(self):
for file in os.listdir("."):
stuff = read_files(file)
if not stuff:
continue
text = stuff[1].split()
for word in text:
self.word_counts[word] +=1
self.all_texts.append(text)
def build_data_frame(file, classification):
rows = []
index = []
file_name, text = read_files(file)
rows.append({'text': text, 'class': classification})
index.append(file_name)
data_frame = DataFrame(rows, index=index)
return data_frame