Update app.py

app.py

@@ -9,6 +9,7 @@ import time
 from joblib import Parallel, delayed
 from nltk import ngrams
 
+
 @st.cache_data
 def convert_df(df):
     return df.to_csv()
@@ -19,6 +20,7 @@ def normalize_string(string):
     
     return normalized_string
 
+
 def jaccard_similarity(string1, string2,n = 2, normalize=True):
     try:
         if normalize:
@@ -30,18 +32,30 @@ def jaccard_similarity(string1, string2,n = 2, normalize=True):
     except:
         similarity=0
         
+    if string2=='did not extract address':
+        similarity=0
+        
     return similarity
 
+def jaccard_sim_split_word_number(string1,string2):
+    numbers1 = ' '.join(re.findall(r'\d+', string1))
+    words1 = ' '.join(re.findall(r'\b[A-Za-z]+\b', string1))
+    
+    numbers2 = ' '.join(re.findall(r'\d+', string2))
+    words2 = ' '.join(re.findall(r'\b[A-Za-z]+\b', string2))   
+    
+    number_similarity=jaccard_similarity(numbers1,numbers2)
+    words_similarity=jaccard_similarity(words1,words2)
+    return (number_similarity+words_similarity)/2
 
 def extract_website_domain(url):
     parsed_url = urlparse(url)
     return parsed_url.netloc
 
 
-def google_address(address):
-        
-    address_number = re.findall(r'\b\d+\b', address)[0]
-    address_zip =re.search(r'(\d{5})$', address).group()[:2]
+def google_address(address):     
+    # address_number = re.findall(r'\b\d+\b', address)[0]
+    # address_zip =re.search(r'(\d{5})$', address).group()[:2]
     
     search_query = quote(address)
     url=f'https://www.google.com/search?q={search_query}'
@@ -54,7 +68,6 @@ def google_address(address):
         if (l[:11]=='/url?q=http') and (len(t)>20 ):
             texts_links.append((t,l))
     
-    
     text = soup.get_text()
     
     texts_links_des=[]
@@ -70,13 +83,16 @@ def google_address(address):
     
     df=pd.DataFrame(texts_links_des,columns=['Title','Link','Description'])
     df['Description']=df['Description'].bfill()
-    df['Address Output']=df['Title'].str.extract(r'(.+? \d{5})')
+    df['Address Output']=df['Title'].str.extract(r'(.+? \d{5})').fillna("**DID NOT EXTRACT ADDRESS**")
+    
     df['Link']=[i[7:i.find('&sa=')] for i in df['Link']]
     df['Website'] = df['Link'].apply(extract_website_domain)
     
     df['Square Footage']=df['Description'].str.extract(r"((\d+) Square Feet|(\d+) sq. ft.|(\d+) sqft|(\d+) Sq. Ft.|(\d+) sq|(\d+(?:,\d+)?) Sq\. Ft\.|(\d+(?:,\d+)?) sq)")[0]
-    df['Square Footage']=df['Square Footage'].replace({',':''},regex=True).str.replace(r'\D', '')
-    
+    try:
+        df['Square Footage']=df['Square Footage'].replace({',':''},regex=True).str.replace(r'\D', '')
+    except:
+        pass
     df['Beds']=df['Description'].replace({'-':' ','total':''},regex=True).str.extract(r"(\d+) bed")
     
     
@@ -84,7 +100,8 @@ def google_address(address):
     df['Baths']=df['Baths'].str.extract(r'([\d.]+)').astype(float)
     
     df['Year Built']=df['Description'].str.extract(r"built in (\d{4})")
-    df['Match Percent']=[jaccard_similarity(address,i)*100 for i in df['Address Output']]
+    
+    df['Match Percent']=[jaccard_sim_split_word_number(address,i)*100 for i in df['Address Output']]
     df['Google Search Result']=[*range(1,df.shape[0]+1)]
    
     # df_final=df[df['Address Output'].notnull()]
@@ -93,7 +110,8 @@ def google_address(address):
     df.insert(0,'Address Input',address)
     
     return df
- 
+
+    
 def catch_errors(addresses):
     try: 
         return google_address(addresses)
@@ -106,12 +124,10 @@ def process_multiple_address(addresses):
     return results
     
   
-
 st.set_page_config(layout="wide")
 
 address = st.sidebar.text_input("Single Address:", "190 Pebble Creek Dr Etna, OH 43062")
 uploaded_file = st.sidebar.file_uploader("Upload Multiple Addresses:")
-# address_file = st.sidebar.radio('Choose',('Single Address', 'File'))
 match_percent = st.sidebar.selectbox('Address Match Percentage At Least:',(70, 80, 90, 100, 0))
 return_sq = st.sidebar.radio('Return Only Results with Square Footage',('No', 'Yes'))
 
@@ -136,7 +152,7 @@ else:
     # results.index=results.index+1
 
     
-results=results[['Address Input', 'Address Output','Match Percent', 'Website','Square Footage', 'Beds', 'Baths', 'Year Built',
+results=results[['Address Input', 'Address Output','Match Percent','Website','Square Footage', 'Beds', 'Baths', 'Year Built',
  'Link','Google Search Result', 'Description' ]]
 results=results.query(f"`Match Percent`>={match_percent}")