Upload app.py

app.py

@@ -1,64 +1,19 @@
-import gradio as gr
-import numpy as np
-import pandas as pd
-from nltk.corpus import stopwords 
+_A='countries'
+import gradio as gr,numpy as np,pandas as pd
+from nltk.corpus import stopwords
 from nltk.tokenize import word_tokenize
 from nltk.stem.wordnet import WordNetLemmatizer
-import nltk
-
-nltk.download('punkt')
-nltk.download('wordnet')
-nltk.download('stopwords')
-
-# Import the dataset
-df = pd.read_csv('Hotel_Reviews.csv')
-df['countries'] = df.Hotel_Address.apply(lambda x: x.split(' ')[-1])
-
-# Define the function to recommend hotels
+df=pd.read_csv('Hotel_Reviews.csv')
+df[_A]=df.Hotel_Address.apply(lambda x:x.split(' ')[-1])
 def Input_your_destination_and_description(location,description):
-    # Making these columns lowercase
-    df['countries']=df['countries'].str.lower()
-    df['Tags']=df['Tags'].str.lower()
-    
-    # Dividing the texts into small tokens (sentences into words)
-    description = description.lower()
-    description_tokens=word_tokenize(description)  
-    
-    sw = stopwords.words('english') # List of predefined english  stopwords to be used for computing
-    lemm = WordNetLemmatizer() # We now define the functions below connecting these imported packages
-    filtered_sen = {w for w in description_tokens if not w in sw}
-    f_set=set()
-    for fs in filtered_sen:
-        f_set.add(lemm.lemmatize(fs))
-    
-    # Defining a new variable that takes in the location inputted and bring out the features defined below
-    country_feat = df[df['countries']==location.lower()]
-    country_feat = country_feat.set_index(np.arange(country_feat.shape[0]))
-    cos=[];
-    for i in range(country_feat.shape[0]):
-        temp_tokens=word_tokenize(country_feat['Tags'][i])
-        temp1_set={w for w in temp_tokens if not w in sw}
-        temp_set=set()
-        for se in temp1_set:
-            temp_set.add(lemm.lemmatize(se))
-        rvector = temp_set.intersection(f_set)
-        cos.append(len(rvector))
-    country_feat['similarity']=cos
-    country_feat=country_feat.sort_values(by='similarity',ascending=False)
-    country_feat.drop_duplicates(subset='Hotel_Name',keep='first',inplace=True)
-    country_feat.sort_values('Average_Score',ascending=False,inplace=True)
-    country_feat.reset_index(inplace=True)
-    return country_feat[['Hotel_Name','Average_Score','Hotel_Address']].head(10)
-
-# Create the input interface
-inputs = [gr.inputs.Textbox(label="Location"), 
-          gr.inputs.Textbox(label="Purpose of Travel")]
-
-# Create the output interface
-outputs=gr.outputs.Dataframe(label="Hotel Recommendations",type="pandas")
-
-# Create the interface
-gr.Interface(fn=Input_your_destination_and_description, 
-             inputs=inputs, 
-             outputs=outputs,theme=gr.themes.Default(primary_hue="slate")).launch()
-
+        M='Average_Score';L='Hotel_Name';K=False;J='similarity';D=True;C='Tags';B=description;df[_A]=df[_A].str.lower();df[C]=df[C].str.lower();B=B.lower();N=word_tokenize(B);E=stopwords.words('english');F=WordNetLemmatizer();O={A for A in N if not A in E};G=set()
+        for P in O:G.add(F.lemmatize(P))
+        A=df[df[_A]==location.lower()];A=A.set_index(np.arange(A.shape[0]));H=[]
+        for Q in range(A.shape[0]):
+                R=word_tokenize(A[C][Q]);S={A for A in R if not A in E};I=set()
+                for T in S:I.add(F.lemmatize(T))
+                U=I.intersection(G);H.append(len(U))
+        A[J]=H;A=A.sort_values(by=J,ascending=K);A.drop_duplicates(subset=L,keep='first',inplace=D);A.sort_values(M,ascending=K,inplace=D);A.reset_index(inplace=D);return A[[L,M,'Hotel_Address']].head(10)
+inputs=[gr.inputs.Textbox(label='Location'),gr.inputs.Textbox(label='Purpose of Travel')]
+outputs=gr.outputs.Dataframe(label='Hotel Recommendations',type='pandas')
+gr.Interface(fn=Input_your_destination_and_description,inputs=inputs,outputs=outputs,theme=gr.themes.Default(primary_hue='slate')).launch()