Upload 4 files

app.py

@@ -0,0 +1,109 @@
+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_resource(ttl=3600)
+# def read_model(local_path):
+#     with open(local_path, "rb") as f:
+#         svm_classifier = pickle.load(f)
+#     return svm_classifier
+
+
+# def read_tf(local_path):
+#     with open(local_path, "rb") as f:
+#         preprocessing = pickle.load(f)
+#     return preprocessing
+
+
+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/category/model2.pkl")
+preprocessing = read_tf("https://github.com/manika-lamba/ml/raw/main/category/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'])
+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'
+    )

model-topics.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23020e255ce442b0a6e52932278b23cec8e798834aa3241fd2d376e20d743cf
+size 1518

requirements.txt

@@ -0,0 +1,28 @@
+pip
+streamlit==1.10.0
+scikit-learn
+gensim
+matplotlib
+nltk
+numpy
+pandas
+pickleshare
+plotly-express
+plotly
+pyldavis
+regex
+seaborn
+setuptools
+streamlit
+streamlit-agraph
+umap-learn
+wordcloud
+mlxtend
+bertopic
+ipywidgets==7.6.6
+bitermplus
+tmplot
+tomotopy
+pipeline
+spacy==3.5.0
+https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.5.0/en_core_web_sm-3.5.0-py3-none-any.whl

tfidf-topics.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeacc5c20b8f1ff2451d7395598645fc81dc1585ea5e7d3aa5251ec0620656c0
+size 553208