Restructured Files

app.py

@@ -8,16 +8,16 @@ import numpy as np
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import classification_report
-from tfidf import set_paths, read_data, preprocess, training_utils, tfidf
-from check import find_closest_match
-from check import is_str_in
+from src.tfidf import set_paths, read_data, preprocess, training_utils, tfidf
+from src.check import find_closest_match
+from src.check import is_str_in
 #tfidf = TfidfVectorizer(max_features=300, stop_words="english")
 import streamlit as st
 
 st.title("Expense Tagging")
 st.subheader("Upload a txt file with each line containing a brand, we'll tell you their categories")
 
-file_name = "brands.json"
+file_name = "src/brands.json"
 with open(file_name,'r') as f:
     data = json.load(f)
 brands = []
@@ -34,10 +34,10 @@ for k in data.keys():
 #if bo:
 #    print(categories[ind])
 #print(categories[b])
-filename = 'final_lr1.sav'
+filename = 'src/Models/final_lr1.sav'
 loaded_model = pickle.load(open(filename, 'rb'))
 
-with open('tfidf2.pickle','rb') as to_read:
+with open('src/Models/tfidf2.pickle','rb') as to_read:
    fitted_tfidf = pickle.load(to_read)
 
 map_dict = {0:"Food and Groceries", 1:"Medical and Healthcare",2:"Education",3:"Lifestyle and Entertainment",4:"Travel & Transportation",5:"Clothing"}

get_brands.py → src/get_brands.py

@@ -2,8 +2,8 @@
 # -*- coding: utf-8 -*-
 import json
 def get_brands_json():
-    brands_file = 'brands.txt'
-    categories_file = 'categories.txt'
+    brands_file = 'Misc/brands.txt'
+    categories_file = 'Misc/categories.txt'
 
     with open(brands_file) as f:
         brands = [line.rstrip() for line in f]