Is there a better way to read in
- the name of a textfile and
- the content of a text file into a dataframe?
(Or is my implementation even okay?) Can I avoid storing the data in lists?
path =r'.../test_age7'
allFiles = glob.glob(path + "/*.txt")
df_7 = pd.DataFrame() # create empty DF
stories = []
filenames = []
for file_ in allFiles:
with open(file_) as f:
textf = " ".join(line.strip() for line in f)
stories.append(textf)
filenames.append(os.path.basename(file_[0:-4])) # extract filename without .txt
df_7["filename"] = filenames
df_7["stories"] = stories
df_7["age"] = path[-1]