def infer_file_callback(attr, old, new):
# run inference on input data and current aspect/opinion lexicons in view
global infer_data, stats, aspects
SENTIMENT_OUT.mkdir(parents=True, exist_ok=True)
df_aspect = pd.DataFrame.from_dict(asp_filter_src.data)
aspect_col_list = ["Term", "Alias1", "Alias2", "Alias3"]
df_aspect = df_aspect[aspect_col_list]
df_aspect.to_csv(SENTIMENT_OUT / "aspects.csv",
index=False,
na_rep="NaN")
df_opinion = pd.DataFrame.from_dict(op_filter_src.data)
opinion_col_list = ["Term", "Score", "Polarity", "isAcquired"]
df_opinion = df_opinion[opinion_col_list]
df_opinion.to_csv(SENTIMENT_OUT / "opinions.csv",
index=False,
na_rep="NaN")
solution = SentimentSolution()
if len(infer_src.data["file_contents"]) == 1:
infer_data = read_csv(infer_src, index_cols=0)
file_name = infer_src.data["file_name"][0]
raw_data_path = SENTIMENT_OUT / file_name
infer_data.to_csv(raw_data_path, header=False)
print(f"Running_SentimentInference on data...")
text_status.value = "Running classification on data..."
stats = solution.run(
data=raw_data_path,
aspect_lex=SENTIMENT_OUT / "aspects.csv",
opinion_lex=SENTIMENT_OUT / "opinions.csv",
)
else:
f_contents = infer_src.data["file_contents"]
f_names = infer_src.data["file_name"]
raw_data_path = SENTIMENT_OUT / infer_src.data["file_name"][
0].split("/")[0]
if not os.path.exists(raw_data_path):
os.makedirs(raw_data_path)
for f_content, f_name in zip(f_contents, f_names):
read_parsed_files(f_content, f_name)
print(f"Running_SentimentInference on data...")
text_status.value = "Running classification on data..."
stats = solution.run(
parsed_data=raw_data_path,
aspect_lex=SENTIMENT_OUT / "aspects.csv",
opinion_lex=SENTIMENT_OUT / "opinions.csv",
)
aspects = pd.read_csv(SENTIMENT_OUT / "aspects.csv",
encoding="utf-8")["Term"]
text_status.value = "Classification completed"
show_analysis()
def train_file_callback(attr, old, new):
global train_data
SENTIMENT_OUT.mkdir(parents=True, exist_ok=True)
train = TrainSentiment(parse=True, rerank_model=None)
if len(train_src.data["file_contents"]) == 1:
train_data = read_csv(train_src, index_cols=0)
file_name = train_src.data["file_name"][0]
raw_data_path = SENTIMENT_OUT / file_name
train_data.to_csv(raw_data_path, header=False)
print(f"Running_SentimentTraining on data...")
train.run(data=raw_data_path)
else:
f_contents = train_src.data["file_contents"]
f_names = train_src.data["file_name"]
raw_data_path = SENTIMENT_OUT / train_src.data["file_name"][
0].split("/")[0]
if not os.path.exists(raw_data_path):
os.makedirs(raw_data_path)
for f_content, f_name in zip(f_contents, f_names):
read_parsed_files(f_content, f_name)
print(f"Running_SentimentTraining on data...")
train.run(parsed_data=raw_data_path)
text_status.value = "Lexicon extraction completed"
with io.open(AcquireTerms.acquired_aspect_terms_path, "r") as fp:
aspect_data_csv = fp.read()
file_data = base64.b64encode(str.encode(aspect_data_csv))
file_data = file_data.decode("utf-8")
asp_src.data = {
"file_contents": [file_data],
"file_name": ["nameFile.csv"]
}
out_path = LEXICONS_OUT / "generated_opinion_lex_reranked.csv"
with io.open(out_path, "r") as fp:
opinion_data_csv = fp.read()
file_data = base64.b64encode(str.encode(opinion_data_csv))
file_data = file_data.decode("utf-8")
op_src.data = {
"file_contents": [file_data],
"file_name": ["nameFile.csv"]
}