vmalapaka's picture
Update pages/Classification.py
670f6d3 verified
Raw History Blame Contribute Delete
2.65 kB
import streamlit as st
from pages.utils import *
from sklearn.svm import SVC
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
import joblib
from utils import *
if 'cleaned_data' not in st.session_state:
st.session_state['cleaned_data'] =''
if 'sentences_train' not in st.session_state:
st.session_state['sentences_train'] =''
if 'sentences_test' not in st.session_state:
st.session_state['sentences_test'] =''
if 'labels_train' not in st.session_state:
st.session_state['labels_train'] =''
if 'labels_test' not in st.session_state:
st.session_state['labels_test'] =''
if 'svm_classifier' not in st.session_state:
st.session_state['svm_classifier'] =''
tab_titles = ['Data Preprocessing', 'Model Training', 'Model Evaluation',"Save Model"]
tabs = st.tabs(tab_titles)
with tabs[0]:
st.header('Data Preprocessing')
# Upload the CSV file
data = st.file_uploader("Upload CSV file",type="csv")
button = st.button("Load data",key="data")
if button:
with st.spinner('Loading...'):
our_data=read_data(data)
embeddings=get_embeddings()
st.session_state['cleaned_data'] = create_embeddings(our_data,embeddings)
st.success('Data Preprocessed')
with tabs[1]:
st.header('Model Training')
button = st.button("Train model",key="model")
if button:
with st.spinner('Loading...'):
st.session_state['sentences_train'], st.session_state['sentences_test'], st.session_state['labels_train'], st.session_state['labels_test']=split_train_test__data(st.session_state['cleaned_data'])
st.session_state['svm_classifier'] = make_pipeline(StandardScaler(), SVC(class_weight='balanced'))
# fit the support vector machine
st.session_state['svm_classifier'].fit(st.session_state['sentences_train'], st.session_state['labels_train'])
st.success('Model Trained')
with tabs[2]:
st.header('Model Evaluation')
button = st.button("Evaluate model",key="Evaluation")
if button:
with st.spinner('Loading...'):
accuracy_score=get_score(st.session_state['svm_classifier'],st.session_state['sentences_test'],st.session_state['labels_test'])
st.success(f"Validation accuracy is {100*accuracy_score}%!")
with tabs[3]:
st.header('Save classified model')
button = st.button("Save model",key="save")
if button:
with st.spinner('Loading...'):
joblib.dump(st.session_state['svm_classifier'], 'modelsvm.pk1')
st.success('Done!')