Create app.py

app.py

@@ -0,0 +1,75 @@
+import gradio as gr
+import spacy
+import pandas as pd
+import numpy as np
+from sentence_transformers import SentenceTransformer
+import spacy
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+import pandas as pd
+from transformers import pipeline
+
+
+df = pd.read_csv("df_end.csv")
+model = SentenceTransformer('all-MiniLM-L6-v2').to('cuda')
+nlp = spacy.load("en_core_web_sm")
+cities = df['locality'].unique()
+
+
+def extract_city(query,cities):
+    city = None
+    doc = nlp(query)
+    for ent in doc.ents:
+        if ent.label_ == "GPE":  # Geo-Political Entity
+            # Assuming the entity is a city
+            return ent.text
+    print(cities)
+    if city in cities :
+        df_to_test = df_to_test.loc[df_to_test['locality'] == city]
+        print(f"City found: {city}")
+    else:
+        print("No city found.")
+    return city
+
+def filter_and_rank_by_similarity_sentiment_ranking(query, df, model,cities, k):
+    city = extract_city(query, cities)
+    cities = df['locality'].unique()
+    if city in cities:
+        df = df.loc[df['locality'] == city]
+        print(f"City: {city}")
+    else:
+        print("No city found.")
+
+
+    query_embedding = model.encode(query)
+    embeddings_matrix = np.stack(df['embedding'].values)
+    similarities = cosine_similarity([query_embedding], embeddings_matrix).flatten()
+    df['similarity'] = similarities
+    df = df.loc[df.groupby('hotel_name')['similarity'].idxmax()]
+
+    top_5_similar = df.nlargest(k, 'similarity').sort_values(by=['result'], ascending=False)
+    return top_5_similar
+
+
+
+
+
+
+
+def gr_request(query):
+    result = filter_and_rank_by_similarity_sentiment_ranking(query ,df, model, cities, 3)
+    #print(result.head(5))
+    result = result[['hotel_name','locality','similarity','result','rate','review_text',"hotel_image"]].values
+    result_images = [res[6] for res in result]
+    result_texts = [f"Hotel name: {hotel[0]} \nCity: {hotel[1]}\nSimilarity score: {round(hotel[2],2)} \nSentiment score: {round(hotel[3],2)} \nRate: {hotel[4]}/5.0 \n\n\nBest Match Review:\n{hotel[5]}" for hotel in result]
+
+    output_list = list()
+    for i in range(len(result_images)):
+        output_list.append(result_images[i])
+        output_list.append(result_texts[i])
+    return output_list
+
+
+demo = gr.Interface(fn=gr_request,inputs = ["text"], outputs=['image',"text",'image', "text",'image', "text"])
+demo.launch()