app.py

import streamlit as st
import pandas as pd
import numpy as np
import openpyxl
from sklearn.preprocessing import MinMaxScaler
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.ensemble import RandomForestClassifier
import pickle

import warnings
warnings.filterwarnings('ignore')


st.set_page_config(page_title='Product Type Predictor')
st.title('Detect Product Type')
st.subheader('Upload your CSV file')
uploaded_file = st.file_uploader('Choose a CSV file', type='csv')
if uploaded_file is not None:
    st.markdown('---')
    # Loading the data
    @st.cache_data
    def load_excel(file1):
            df = pd.read_csv(file1)
            return df
        
    data = load_excel(uploaded_file)
    st.subheader('Data Preview')
    st.dataframe(data.head(20))
    # Feature selection
    features = ['a_ApplicableMarkets', 'Number of Unique Finished Packs in BOM',
       'Total Number of Finished Packs in BOM', 'GMN', 'Product_Description',
       'EA_GTIN', 'CV_GTIN', 'Product_Hierarchy_Code',
       'Product_Hierarchy_Units_Per_Pack_L8', 'myPSR_Pack_Variant',
       'Stibo_Pack_variant']
    df = data[features]
    df = df.replace(r'^\s*$', np.nan, regex=True)
    df[['EA_GTIN', 'CV_GTIN']] = df[['EA_GTIN', 'CV_GTIN']].apply(pd.to_numeric)
    df = df.replace(np.nan, 0, regex=True)
    text_cols = ['a_ApplicableMarkets', 'Product_Hierarchy_Units_Per_Pack_L8', 'myPSR_Pack_Variant', 'Stibo_Pack_variant']
    df = pd.get_dummies(data=df, columns=text_cols)
    v = CountVectorizer()
    text_vectors = v.fit_transform(df['Product_Description'])
    text_vectors_df = pd.DataFrame(text_vectors.toarray(), columns=v.get_feature_names_out())
    df_ext = pd.concat([df, text_vectors_df],axis=1)
    df = df_ext.drop("Product_Description",axis=1)
    scaler = MinMaxScaler()
    df[['GMN','EA_GTIN', 'CV_GTIN']] = scaler.fit_transform(df[['GMN','EA_GTIN', 'CV_GTIN']])
    loaded_model = pickle.load(open('rfc_model.pkl', 'rb'))
    result = loaded_model.predict(df)
    data['Product_Type']=result

    out=data.to_csv().encode('utf-8')
    st.download_button(label='DOWNLOAD RESULT',data=out, file_name='Product_Output.csv',mime='csv')