Update app.py

app.py

@@ -1,9 +1,7 @@
 import streamlit as st
 import pandas as pd
 import numpy as np
-from sklearn.preprocessing import MinMaxScaler
 from sklearn.feature_extraction.text import CountVectorizer
-from sklearn.tree import DecisionTreeClassifier
 from sklearn.ensemble import RandomForestClassifier
 import pickle
 
@@ -27,27 +25,55 @@ if uploaded_file is not None:
     st.subheader('Data Preview')
     st.dataframe(data.head(20))
     # Feature selection
-    features = ['a_ApplicableMarkets', 'Number of Unique Finished Packs in BOM',
+    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 = df.replace(r'^\s*$', np.nan, regex=True)
-    df[['EA_GTIN', 'CV_GTIN']] = df[['EA_GTIN', 'CV_GTIN']].apply(pd.to_numeric)
+
+    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)
-    text_cols = ['a_ApplicableMarkets', 'Product_Hierarchy_Units_Per_Pack_L8', 'myPSR_Pack_Variant', 'Stibo_Pack_variant']
+    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("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'))
+    df = df_ext.drop(['GMN','Product_Description','EA_GTIN','CV_GTIN'],axis=1)
+
+    loaded_model = pickle.load(open('rfc_model_grid.pkl', 'rb'))
     result = loaded_model.predict(df)
-    data['Product_Type']=result
+    data['Product_Type_Predicted']=result
 
     out=data.to_csv().encode('utf-8')
-    st.download_button(label='DOWNLOAD RESULT',data=out, file_name='Product_Output.csv',mime='csv')
+    st.download_button(label='DOWNLOAD RESULT',data=out, file_name='Product_Type_Output.csv',mime='csv')