Spaces:
Runtime error
Runtime error
Restructured Files
Browse files- app.py +6 -6
- {Data β src/Data}/Consolidated Expense Tagging.xlsx +0 -0
- brands.txt β src/Misc/brands.txt +0 -0
- categories.txt β src/Misc/categories.txt +0 -0
- hyperparams.txt β src/Misc/hyperparams.txt +0 -0
- final_lr.sav β src/Models/final_lr.sav +0 -0
- final_lr1.sav β src/Models/final_lr1.sav +0 -0
- finalized_model.sav β src/Models/finalized_model.sav +0 -0
- finalized_model1.sav β src/Models/finalized_model1.sav +0 -0
- tfidf.pickle β src/Models/tfidf.pickle +0 -0
- tfidf2.pickle β src/Models/tfidf2.pickle +0 -0
- src/__pycache__/check.cpython-310.pyc +0 -0
- src/__pycache__/tfidf.cpython-310.pyc +0 -0
- brands.json β src/brands.json +0 -0
- check.py β src/check.py +0 -0
- get_brands.py β src/get_brands.py +2 -2
- tfidf.py β src/tfidf.py +0 -0
app.py
CHANGED
@@ -8,16 +8,16 @@ import numpy as np
|
|
8 |
from sklearn.feature_extraction.text import TfidfVectorizer
|
9 |
from sklearn.model_selection import train_test_split
|
10 |
from sklearn.metrics import classification_report
|
11 |
-
from tfidf import set_paths, read_data, preprocess, training_utils, tfidf
|
12 |
-
from check import find_closest_match
|
13 |
-
from check import is_str_in
|
14 |
#tfidf = TfidfVectorizer(max_features=300, stop_words="english")
|
15 |
import streamlit as st
|
16 |
|
17 |
st.title("Expense Tagging")
|
18 |
st.subheader("Upload a txt file with each line containing a brand, we'll tell you their categories")
|
19 |
|
20 |
-
file_name = "brands.json"
|
21 |
with open(file_name,'r') as f:
|
22 |
data = json.load(f)
|
23 |
brands = []
|
@@ -34,10 +34,10 @@ for k in data.keys():
|
|
34 |
#if bo:
|
35 |
# print(categories[ind])
|
36 |
#print(categories[b])
|
37 |
-
filename = 'final_lr1.sav'
|
38 |
loaded_model = pickle.load(open(filename, 'rb'))
|
39 |
|
40 |
-
with open('tfidf2.pickle','rb') as to_read:
|
41 |
fitted_tfidf = pickle.load(to_read)
|
42 |
|
43 |
map_dict = {0:"Food and Groceries", 1:"Medical and Healthcare",2:"Education",3:"Lifestyle and Entertainment",4:"Travel & Transportation",5:"Clothing"}
|
|
|
8 |
from sklearn.feature_extraction.text import TfidfVectorizer
|
9 |
from sklearn.model_selection import train_test_split
|
10 |
from sklearn.metrics import classification_report
|
11 |
+
from src.tfidf import set_paths, read_data, preprocess, training_utils, tfidf
|
12 |
+
from src.check import find_closest_match
|
13 |
+
from src.check import is_str_in
|
14 |
#tfidf = TfidfVectorizer(max_features=300, stop_words="english")
|
15 |
import streamlit as st
|
16 |
|
17 |
st.title("Expense Tagging")
|
18 |
st.subheader("Upload a txt file with each line containing a brand, we'll tell you their categories")
|
19 |
|
20 |
+
file_name = "src/brands.json"
|
21 |
with open(file_name,'r') as f:
|
22 |
data = json.load(f)
|
23 |
brands = []
|
|
|
34 |
#if bo:
|
35 |
# print(categories[ind])
|
36 |
#print(categories[b])
|
37 |
+
filename = 'src/Models/final_lr1.sav'
|
38 |
loaded_model = pickle.load(open(filename, 'rb'))
|
39 |
|
40 |
+
with open('src/Models/tfidf2.pickle','rb') as to_read:
|
41 |
fitted_tfidf = pickle.load(to_read)
|
42 |
|
43 |
map_dict = {0:"Food and Groceries", 1:"Medical and Healthcare",2:"Education",3:"Lifestyle and Entertainment",4:"Travel & Transportation",5:"Clothing"}
|
{Data β src/Data}/Consolidated Expense Tagging.xlsx
RENAMED
File without changes
|
brands.txt β src/Misc/brands.txt
RENAMED
File without changes
|
categories.txt β src/Misc/categories.txt
RENAMED
File without changes
|
hyperparams.txt β src/Misc/hyperparams.txt
RENAMED
File without changes
|
final_lr.sav β src/Models/final_lr.sav
RENAMED
File without changes
|
final_lr1.sav β src/Models/final_lr1.sav
RENAMED
File without changes
|
finalized_model.sav β src/Models/finalized_model.sav
RENAMED
File without changes
|
finalized_model1.sav β src/Models/finalized_model1.sav
RENAMED
File without changes
|
tfidf.pickle β src/Models/tfidf.pickle
RENAMED
File without changes
|
tfidf2.pickle β src/Models/tfidf2.pickle
RENAMED
File without changes
|
src/__pycache__/check.cpython-310.pyc
ADDED
Binary file (897 Bytes). View file
|
|
src/__pycache__/tfidf.cpython-310.pyc
ADDED
Binary file (4.73 kB). View file
|
|
brands.json β src/brands.json
RENAMED
File without changes
|
check.py β src/check.py
RENAMED
File without changes
|
get_brands.py β src/get_brands.py
RENAMED
@@ -2,8 +2,8 @@
|
|
2 |
# -*- coding: utf-8 -*-
|
3 |
import json
|
4 |
def get_brands_json():
|
5 |
-
brands_file = 'brands.txt'
|
6 |
-
categories_file = 'categories.txt'
|
7 |
|
8 |
with open(brands_file) as f:
|
9 |
brands = [line.rstrip() for line in f]
|
|
|
2 |
# -*- coding: utf-8 -*-
|
3 |
import json
|
4 |
def get_brands_json():
|
5 |
+
brands_file = 'Misc/brands.txt'
|
6 |
+
categories_file = 'Misc/categories.txt'
|
7 |
|
8 |
with open(brands_file) as f:
|
9 |
brands = [line.rstrip() for line in f]
|
tfidf.py β src/tfidf.py
RENAMED
File without changes
|