23 lines
636 B
Python
23 lines
636 B
Python
|
import os
|
||
|
import pandas as pd
|
||
|
from NaturalLanguageAnalyzer import NaturalLanguageAnalyzer
|
||
|
|
||
|
data_directory = 'data'
|
||
|
|
||
|
file_list = os.listdir(data_directory)
|
||
|
dfs = []
|
||
|
for file_name in file_list:
|
||
|
file_path = os.path.join(data_directory, file_name)
|
||
|
df = pd.read_csv(file_path, sep='\t', encoding='utf-8')
|
||
|
df_user = df[df['role'] == 'user'].drop('role', axis=1)
|
||
|
dfs.append(df_user)
|
||
|
|
||
|
combined_df = pd.concat(dfs, ignore_index=True)
|
||
|
|
||
|
for text, act in zip(combined_df["value"].values, combined_df["act"].values):
|
||
|
nla = NaturalLanguageAnalyzer()
|
||
|
user_act = nla.process(text)
|
||
|
print(user_act)
|
||
|
print(act)
|
||
|
print()
|