app.py

from sklearn.model_selection import train_test_split

import streamlit as st
import pandas as pd
import pickle
import requests
import base64

@st.cache_data(ttl=3600)
def read_model(url):
    response = requests.get(url)
    open("temp.pkl", "wb").write(response.content)
    with open("temp.pkl", "rb") as f:
        svm_classifier = pickle.load(f)
    return svm_classifier


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("https://github.com/manika-lamba/ml/raw/main/model2.pkl")
preprocessing = read_tf("https://github.com/manika-lamba/ml/raw/main/preprocessing.pkl")



# Create sidebar

# Create tab for choosing CSV file
st.sidebar.header("Choose CSV File with 'Abstract' field")
uploaded_file = st.sidebar.file_uploader("", type=["csv"])

st.sidebar.header("Download Results")
st.sidebar.text("Download the tagged results as a CSV file.")



st.title("About")
st.subheader("You can tag your input CSV file of theses and dissertations with Library Science, Archival Studies, and Information Science categories. The screen will show the output.")

tab1, tab2, tab3 = st.tabs(["📈 Load Data", "📃 Tagged ETDs", "📓 Download Data"])

with tab1:
#===load data===

    if uploaded_file is not None:
    df = pd.read_csv(uploaded_file, encoding='latin-1')
    st.dataframe(df)
    
with tab2:
#===tagged ETDs===
# Tag the "Abstract" column with the corresponding categories

    if uploaded_file is not None:
    df = pd.read_csv(uploaded_file, encoding='latin-1')
    st.dataframe(df)
    df['category'] = df['Abstract'].apply(predict_category)
    st.dataframe(df)
    
# 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

with tab3:
#===download result===
# Create a download button

    if st.sidebar.button("Download"):
    csv = df.to_csv(index=False)
    b64 = base64.b64encode(csv.encode()).decode()
    href = f'<a href="data:file/csv;base64,{b64}" download="results.csv">Download csv file</a>'
    st.markdown(href, unsafe_allow_html=True)