Spaces:
Sleeping
Sleeping
File size: 2,416 Bytes
46af628 14ff9c4 b62e42f 6169f27 02d9582 e2393a1 776f615 2fc2e11 02d9582 e2393a1 d70c8d8 e2393a1 44e0cdf e8ad8b1 44e0cdf 4728363 e8ad8b1 44e0cdf e8ad8b1 da7e215 44e0cdf e2393a1 fc93e08 e8ad8b1 da7e215 fc93e08 776f615 839c140 cd42a41 776f615 cd42a41 776f615 cd42a41 776f615 9031d57 075f350 da7e215 e2393a1 e8ad8b1 c475583 da7e215 44e0cdf da7e215 b3d7164 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 |
import streamlit as st
import pandas as pd
from huggingface_hub import Repository
import os
from pathlib import Path
import json
import numpy as np
# Declaring the variables for later use to talk to dataset
# the token is saved as secret key-value pair in the environment which can be access as shown below
auth_token = os.environ.get("space_to_dataset") or True
DATASET_REPO_URL = 'ppsingh/annotation_data' # path to dataset repo
DATA_FILENAME = "paralist.json"
DATA_FILE = os.path.join("data", DATA_FILENAME)
# cloning the dataset repo
repo = Repository( local_dir="data", clone_from=DATASET_REPO_URL, repo_type="dataset", use_auth_token= auth_token)
# Data file name
file_name = 'paralist.json'
# reading the json
with open('data/{}'.format(file_name), 'r', encoding="utf8") as json_file:
paraList = json.load(json_file)
# getting outer level keys in json
keys = paraList.keys()
#data = pd.read_csv("test.csv")
# sidebar with info and drop down to select from the keys
st.sidebar.markdown(
"""
# Data Annotation Demo
This app is demo how to use the space to provide user interface for the data annotation/tagging. The data resides in repo_type 'dataset'.
"""
)
topic = None
if keys is not None:
topic = st.sidebar.selectbox(
label="Choose dataset topic to load", options=keys )
# st.write(line)
if topic is not None:
c1, c2, c3 = st.columns([3, 1, 1])
if np.random.randint(0,1) == 0:
choice = 'Gender'
else:
choice = 'Women Empowernment'
with c1:
st.header('Text')
st.text(paraList[label][choice][0]
with c2:
st.header('Tag')
st.text(choice)
with c3:
st.header('Feedback')
st.selectbox('0 If Tag is not a good keyword for text, 5 for prefect match',(0,1,2,3,4,5))
title = st.text_input('Movie title', 'Life of Brian')
if st.button('Submit'):
new_row = title
# data = data.append(new_row, ignore_index=True)
# st.write(data)
# st.write(os.getcwd())
# data.to_csv('test.csv', index= False)
#st.write(df)
# st.write('data/test.csv')
# iterate over files in
# that directory
#directory = os.getcwd()
#files = Path(directory).glob('*')
#for file in files:
# st.write(file)
#with open(DATA_FILE, "a") as csvfile:
# writer = csv.DictWriter(csvfile, fieldnames=["Sentences"])
# writer.writerow({'Sentences': new_row})
# repo.push_to_hub('adding new line')
# st.write('Succcess')
|