Spaces:
Runtime error
Runtime error
File size: 2,771 Bytes
f51e197 c90e96d 4132514 f51e197 4132514 f51e197 b1a0d5b f51e197 b1a0d5b d38ab04 4132514 c90e96d d38ab04 4132514 c90e96d d38ab04 c90e96d 4132514 c90e96d 4132514 c90e96d d38ab04 4132514 b1a0d5b 4132514 |
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 80 |
import streamlit as st
import pandas as pd
import numpy as np
import torch
#from transformers import AlbertTokenizer, AlbertModel
#from sklearn.metrics.pairwise import cosine_similarity
#tokenizer = AlbertTokenizer.from_pretrained('albert-base-v2')
#model = AlbertModel.from_pretrained("albert-base-v2")
#def get_embedding(input_text):
# encoded_input = tokenizer(input_text, return_tensors='pt')
# input_ids = encoded_input.input_ids
# input_num_tokens = input_ids.shape[1]
#
# #print( "Number of input tokens: " + str(input_num_tokens))
# #print("Length of input: " + str(len(input_text)))
#
# list_of_tokens = tokenizer.convert_ids_to_tokens(input_ids.view(-1).tolist())
#
# #print( "Tokens : " + ' '.join(list_of_tokens))
# with torch.no_grad():
# output = model(**encoded_input)
#
# embedding = output.last_hidden_state[0][0]
# return embedding.tolist()
st.title('Upload the Address Dataset')
st.markdown('Upload an Excel file to view the data in a table.')
uploaded_file = st.file_uploader('Choose a file', type='xlsx')
if uploaded_file is not None:
data_caqh = pd.read_excel(uploaded_file, sheet_name='CAQH')
data_ndb = pd.read_excel(uploaded_file, sheet_name='NDB')
# Data cleaning CAQH
data_caqh['postalcode'] = data_caqh['postalcode'].astype(str).apply(lambda x: x[:5] + '-' + x[5:] if len(x) > 5 and not '-' in x else x)
data_caqh['full-addr'] = data_caqh['address1'].astype(str) + ', ' \
+ np.where(data_caqh['address2'].isnull(), '' , data_caqh['address2'].astype(str)) \
+ data_caqh['city'].astype(str) + ', '\
+ data_caqh['state'].astype(str) + ', ' \
+ data_caqh['postalcode'].astype(str)
# Data cleaning NDB
data_ndb['zip_pls_4_cd'] = data_ndb['zip_pls_4_cd'].astype(str).apply(lambda x: x if (x[-1] != '0' and x[-1] != '1') else '')
data_ndb['zip_cd_zip_pls_4_cd'] = data_ndb['zip_cd'].astype(str) +\
np.where( data_ndb['zip_pls_4_cd'] == '', '', '-' \
+ data_ndb['zip_pls_4_cd'].astype(str))
data_ndb['full-addr'] = data_ndb['adr_ln_1_txt'].astype(str).str.strip() + ', ' \
+ data_ndb['st_cd'].astype(str) + ', ' + data_ndb['zip_cd_zip_pls_4_cd']
# Add a matched column
data_caqh['matched-addr'] = ''
# App
#data_caqh['embed'] = data_caqh['full-addr'].apply(get_embedding)
st.dataframe(data_caqh)
st.dataframe(data_ndb)
# Do some matching
#data_caqh.loc[data_caqh['full-addr'] == '1000 Vale Terrace, Vista, CA, 92084', 'matched-addr'] = '456 Main St'
#time.sleep(10)
#st.dataframe(data_caqh)
|