Update app.py

app.py

@@ -12,17 +12,47 @@ from bs4 import BeautifulSoup
 from joblib import Parallel, delayed
 import gradio as gr
 from io import StringIO
+from nltk import ngrams
 
-default_csv = "addresses 100 generated.csv"
 
+def normalize_string(string):
+    normalized_string = string.lower()
+    normalized_string = re.sub(r'[^\w\s]', '', normalized_string)
+    
+    return normalized_string
+
+
+def jaccard_similarity(string1, string2,n = 2, normalize=True):
+    try:
+        if normalize:
+           string1,string2= normalize_string(string1),normalize_string(string2)
+           
+        grams1 = set(ngrams(string1, n))
+        grams2 = set(ngrams(string2, n))
+        similarity = len(grams1.intersection(grams2)) / len(grams1.union(grams2))
+    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]
     
     search_query = quote(address)
     url=f'https://www.google.com/search?q={search_query}'
@@ -35,7 +65,6 @@ 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=[]
@@ -51,13 +80,16 @@ def google_address(address):
     
     df=pd.DataFrame(texts_links_des,columns=['Title','Link','Description'])
     df['Description']=df['Description'].bfill()
-    df['Address']=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")
     
     
@@ -66,18 +98,21 @@ def google_address(address):
     
     df['Year Built']=df['Description'].str.extract(r"built in (\d{4})")
     
-    df_final=df[df['Address'].notnull()]
-    df_final=df_final[(df_final['Address'].str.contains(str(address_number))) & (df_final['Address'].str.contains(str(address_zip)))]
+    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()]
+    # df_final=df_final[(df_final['Address Output'].str.contains(str(address_number))) & (df_final['Address Output'].str.contains(str(address_zip)))]
 
-    df_final.insert(0,'Address Input',address)
-    return df_final
+    df.insert(0,'Address Input',address)
+    return df
 
 
 def process_csv_text(temp_file):
     if isinstance(temp_file, str):
-      df = pd.read_csv(StringIO(temp_file))
+        df = pd.read_csv(StringIO(temp_file))
     else:
-      df = pd.read_csv(temp_file.name)
+        df = pd.read_csv(temp_file.name)
       
     address_cols=list(df.columns[:4])
     df[address_cols[-1]]=df[address_cols[-1]].astype(str).str[:5].astype(int).astype(str)
@@ -86,11 +121,11 @@ def process_csv_text(temp_file):
     df['Address All']=df[address_cols[0]]+', '+df[address_cols[1]]+', '+df[address_cols[2]]+' '+df[address_cols[3]]
     return df
 
-def catch_errors(addresses):
+def catch_errors(address):
     try: 
-        return google_address(addresses)
+        return google_address(address)
     except:
-        return pd.DataFrame({'Address Input':[addresses]})
+        return pd.DataFrame({'Address Input':[address]})
 
 def process_multiple_address(addresses):
     results=Parallel(n_jobs=32, prefer="threads")(delayed(catch_errors)(i) for i in addresses)