Spaces:
Runtime error
Runtime error
File size: 3,230 Bytes
5689533 3254423 5689533 ad20e1a 5689533 ad20e1a 5689533 ad20e1a 5689533 ad20e1a 5689533 ad20e1a 3254423 5689533 ad20e1a 5689533 ad20e1a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 |
import streamlit as st
import pandas as pd
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.ensemble import RandomForestClassifier
import joblib
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', 'Manufacturing Plant','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['Manufacturing Plant'] = df['Manufacturing Plant'].replace({'Commerical Plant':'Commercial Plant'})
df['Stibo_Pack_variant'] = df['Stibo_Pack_variant'].replace({'Migration Open Stock':'Migration OpenStock'})
df = df.replace(np.nan, 0, regex=True)
df['EA_GTIN'] = df['EA_GTIN'].astype(str)
df['CV_GTIN'] = df['CV_GTIN'].astype(str)
def GTIN_validity(x):
gtin=str(x)
if x=="0.0":
return False
if x:
gtin=gtin[:-2]
original_digits = [int(x) for x in gtin]
digits_without_check_digit = original_digits[:-1]
digits_without_check_digit.reverse()
multiplied_digits = [x*3 if not i%2 else x
for i,x
in enumerate(digits_without_check_digit)]
digits_sum = sum(multiplied_digits)
if (digits_sum % 10):
uprounded_sum = digits_sum + (10 - digits_sum % 10)
else:
uprounded_sum = digits_sum
expected_check_digit = uprounded_sum - digits_sum
return (original_digits[-1] == expected_check_digit)
df['EA_GTIN_valid']=df.apply(lambda x: GTIN_validity(x['EA_GTIN']),axis=1)
df['CV_GTIN_valid']=df.apply(lambda x: GTIN_validity(x['CV_GTIN']),axis=1)
text_cols = ['a_ApplicableMarkets', 'Manufacturing Plant', '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(['GMN','Product_Description','EA_GTIN','CV_GTIN'],axis=1)
loaded_model = joblib.load(open('rfc_model_grid.sav', 'rb'))
result = loaded_model.predict(df)
data['Product_Type_Predicted']=result
out=data.to_csv().encode('utf-8')
st.download_button(label='DOWNLOAD RESULT',data=out, file_name='Product_Type_Output.csv',mime='csv') |