Duplicate from amoldwalunj/matches_using_lavenstein_and_embeddings

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+cleaned.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Matches Using Lavenstein And Embeddings
+emoji: 🦀
+colorFrom: green
+colorTo: blue
+sdk: streamlit
+sdk_version: 1.17.0
+app_file: app.py
+pinned: false
+duplicated_from: amoldwalunj/matches_using_lavenstein_and_embeddings
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,115 @@
+import streamlit as st
+import pandas as pd
+import json
+import numpy as np
+from fuzzywuzzy import fuzz
+
+import pinecone
+from sentence_transformers import SentenceTransformer
+
+pinecone.init(api_key='5c5b5687-b73d-47e9-9cc8-e184ff72cc45', environment='us-central1-gcp')
+
+model = SentenceTransformer('all-mpnet-base-v2',device='cpu')
+
+def process_string(s):
+    return s.lower().replace('&', 'and')
+
+def levenshtein_distance(s1, s2):
+    return fuzz.ratio(s1, s2)
+
+def compare_string_all(string, df):
+    string = string.lower().replace('&', 'and')
+
+    df['distance'] = df['cleaned_text'].apply(lambda x: levenshtein_distance(string, x.lower()))
+
+    top_5_df = df.sort_values('distance', ascending=False).head(5)
+
+    top_5_df = top_5_df[['label','Ingredients', 'distance']]
+
+    return top_5_df
+
+def compare_string_label(string, df):
+    string = string.lower().replace('&', 'and')
+
+    df['distance'] = df['cleaned_label'].apply(lambda x: levenshtein_distance(string, x.lower()))
+
+    top_5_df = df.sort_values('distance', ascending=False).head(5)
+
+    top_5_df = top_5_df[['label','Ingredients', 'distance']]
+
+    return top_5_df
+
+df= pd.read_json('cleaned.json')
+
+df['label+ingradient'] = df['label'] + ' : ' + df['Ingredients']
+
+df['cleaned_text']= df['label+ingradient'].apply(process_string)
+
+df['cleaned_label'] = df['label'].apply(process_string)
+
+index = pinecone.Index('menuingradientsearch')
+
+
+# Create a Streamlit app
+def main():
+    st.set_page_config(page_title="String Matching App", page_icon=":smiley:", layout="wide")
+    st.title("String Matching App :smiley:")
+
+    # Define pages
+    pages = ["Fuzzy match", "Semantic search"]
+
+    # Add radio buttons to toggle between pages
+    page = st.sidebar.radio("Select a page", pages)
+
+    if page == pages[0]:
+        st.header("Matches using levenshtein_distance")
+        st.write("Enter a menu along with its ingredients:")
+        st.write("e.g. Pita & HUMMUS Garlic Hummus, crispy seasoned pita")
+        input_string = st.text_input("")
+
+        input_string= process_string(input_string)
+
+        if input_string:
+            st.write("Top 5 matches:")
+
+            if len(input_string.split())>4: 
+                top_matches = compare_string_all(input_string, df)
+            else:
+                top_matches= compare_string_label(input_string, df)
+
+            st.dataframe(top_matches)
+
+    elif page == pages[1]:
+        st.header("Matches using embeddings (semantic search)")
+        st.write("Enter a menu along with its ingredients:")
+        st.write("e.g. Pita & HUMMUS Garlic Hummus, crispy seasoned pita")
+        input_string = st.text_input("")
+
+        input_string = process_string(input_string)
+
+        if input_string:
+            st.write("Top 10 matches using semantic search:")
+
+            # if len(input_string.split()) > 4:
+            #     top_matches = compare_string_all(input_string, df)
+            # else:
+            #     top_matches = compare_string_label(input_string, df)
+
+            xq = model.encode([input_string]).tolist()
+            result = index.query(xq, top_k=10, includeMetadata=True)
+
+            labels=[]
+            ingradients=[]
+            score=[]
+            for matches in result['matches']:
+                labels.append(matches['metadata']['label'])
+                ingradients.append(matches['metadata']['Ingredients'])
+                score.append(matches['score'])
+
+            final_result= pd.DataFrame(list(zip(labels, ingradients, score)),
+               columns =['labels', 'ingradients','score' ])
+
+            st.dataframe(final_result)
+
+if __name__ == "__main__":
+    main()

cleaned.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd04e95a5a8e294fbdd489e20c2c0a13daa6befae0cad18252936b95167149b
+size 11689865

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+pandas
+numpy
+fuzzywuzzy
+sentence-transformers
+pinecone-client