Upload 3 files

.streamlit/config.toml

@@ -0,0 +1,2 @@
+[theme]
+base="light"

Home.py

@@ -0,0 +1,54 @@
+#import module
+import streamlit as st
+from PIL import Image
+
+#===config===
+st.set_page_config(
+     page_title="ETDs Tagging",
+     page_icon="",
+     layout="wide"
+)
+st.title('ETDs Tagging Tool')
+st.sidebar.success('Select page above')
+
+#===page===
+mt1, mt2, mt3 = st.tabs(["About", "How to", "Behind this app"])
+
+with mt1:
+   st.header("🌌 Hello ")
+   st.write('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.')
+   st.text('')
+   st.text('')
+   st.text('')
+   st.text('')
+   st.divider()
+   st.error("This app works on CSV file having 'Abstract' field", icon="🚨")
+
+with mt2:
+   st.header("Before you start")
+   option = st.selectbox(
+    'Please choose....',
+    ('Tagging Categories', 'Tagging Sub-Categories'))
+
+   if option == 'Tagging Categories':
+        tab1 = st.tabs(["Prologue"])
+        with tab1:
+            st.text("""
+            +----------------+------------------------+---------------------------------+
+            |     S.No.    |      Category name                        |
+            +----------------+------------------------+---------------------------------+
+            |     1     | Library Science               |
+            +----------------+------------------------+---------------------------------+
+            | 2 |   Information Science             |
+            +----------------+------------------------+---------------------------------+
+            |   3      | Archival Studies               ' |
+            +----------------+------------------------+---------------------------------+
+            """)
+
+with mt3:
+   st.header('Behind this app')
+   st.subheader('Dr. Manika Lamba')
+   st.text('Elected Standing Committee Member & Chair of Professional Development Sub-Committee at IFLA STL Section | Editor-in-Chief for IJLIS (IGI Global).')
+   st.text('')
+   st.text('')
+   st.divider()

pages/ml.py

@@ -0,0 +1,92 @@
+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
+
+
+
+@st.cache
+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")
+
+# 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'], on_change=reset_all)
+
+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)
+    st.dataframe(df)
+
+st.sidebar.header("Download Results")
+st.sidebar.text("Download the tagged results as a CSV file.")
+
+# 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)