File size: 3,248 Bytes
ed9dc6d fadb089 ed9dc6d fadb089 ed9dc6d 47660b1 1536a4a bcdcc8b bf85a00 1536a4a ed9dc6d bf85a00 ed9dc6d bf85a00 ed9dc6d bf85a00 1536a4a bf85a00 1536a4a bf85a00 1536a4a bf85a00 |
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 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 |
import streamlit as st
import pandas as pd
import pickle
import requests
import base64
#===config===
st.set_page_config(
page_title="ETDs Tagging",
page_icon="",
layout="wide"
)
st.header("Tagging Categories")
st.subheader('Put your file here...')
#========unique id========
@st.cache_resource(ttl=3600)
def create_list():
l = [1, 2, 3]
return l
l = create_list()
first_list_value = l[0]
l[0] = first_list_value + 1
uID = str(l[0])
@st.cache_data(ttl=3600)
def get_ext(uploaded_file):
extype = uID+uploaded_file.name
return extype
def read_tf(url):
response = requests.get(url)
open("temp.pkl", "wb").write(response.content)
with open("temp.pkl", "rb") as f:
preprocessing = pickle.load(f)
return preprocessing
svm_classifier = read_model("model2.pkl")
preprocessing = read_tf("preprocessing.pkl")
# Function to predict the category for a given abstract
def predict_category(abstract):
# Preprocess the abstract
abstract_preprocessed = preprocessing.transform([abstract])
# Make prediction
prediction = svm_classifier.predict(abstract_preprocessed)
return prediction
# Create sidebar
#===upload file===
@st.cache_data(ttl=3600)
def upload(file):
papers = pd.read_csv(uploaded_file)
return papers
@st.cache_data(ttl=3600)
def conv_txt(extype):
papers = pd.read_csv(uploaded_file, sep='\t', lineterminator='\r')
papers.rename(columns=col_dict, inplace=True)
return papers
#===Read data===
# uploaded_file = st.file_uploader("Choose a file", type=['csv'])
# df = None # Initialize df as None outside the if block
# if uploaded_file is not None:
# df = pd.read_csv(uploaded_file, encoding='latin-1')
# st.dataframe(df)
# # Tag the "Abstract" column with the corresponding categories
# df['category'] = df['Abstract'].apply(predict_category)
# # df['category'] = df['category'].str[2:-2]
# st.dataframe(df)
# st.sidebar.header("Download Results")
# st.sidebar.text("Download the tagged results as a CSV file.")
# if df is not None:
# csv = df.to_csv(index=False)
# b64 = base64.b64encode(csv.encode()).decode()
# st.sidebar.download_button(
# label="Download",
# data=b64,
# file_name="results.csv",
# mime="text/csv"
# )
# else:
# st.sidebar.text("Please upload a file first to enable the download button.")
uploaded_file = st.file_uploader("Choose a file", type=['csv'])
st.sidebar.header("Download Results")
st.sidebar.text("Download the tagged results as a CSV file.")
if uploaded_file is not None:
df = pd.read_csv(uploaded_file, encoding='latin-1')
st.dataframe(df)
# Tag the "Abstract" column with the corresponding categories
df['category'] = df['Abstract'].apply(lambda x: predict_category(x)[0])
st.dataframe(df)
# Convert DataFrame to CSV and encode it properly
csv = df.to_csv(index=False).encode('utf-8')
b64 = base64.b64encode(csv).decode() # Decode the Base64 encoded bytes
st.sidebar.download_button(
label="Download CSV",
data=base64.b64decode(b64), # Decode Base64 to bytes
file_name="results.csv",
mime="text/csv",
key='download-csv'
) |