File size: 3,333 Bytes
3c24daa | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | import streamlit as st
import pandas as pd
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity
from sklearn.feature_extraction.text import CountVectorizer
# Dummy data for agents
agents = pd.DataFrame({
'agent_id': range(1, 21),
'location_expertise': ['Toronto', 'Vancouver', 'Montreal'] * 6 + ['Toronto', 'Vancouver'],
'property_type_expertise': ['Condo', 'House', 'Apartment'] * 6 + ['Condo', 'House'],
'average_deal_completion_rate': np.random.random(20),
'language': ['English', 'French', 'Hindi', 'English', 'French', 'English', 'Hindi', 'French', 'English', 'Hindi'] * 2,
'amenities': ['Pool,Gym', 'Gym,Parking', 'Pool,Parking,Gym', 'Parking', 'Pool,Gym', 'Gym,Parking', 'Pool', 'Gym', 'Parking,Pool', 'Pool'] * 2
})
# Function to calculate cosine similarity
def calculate_similarity(client_features, agents):
# Combining client features
client_combined_features = [client_features['preferred_location'] + " " + client_features['preferred_property_type'] + " " + client_features['language'] + " " + client_features['amenities']]
agents['combined_features'] = agents['location_expertise'] + " " + agents['property_type_expertise'] + " " + agents['language'] + " " + agents['amenities']
# Count Vectorizer for combined features
vectorizer = CountVectorizer()
count_matrix = vectorizer.fit_transform(pd.concat([pd.Series(client_combined_features), agents['combined_features']]))
# Calculate cosine similarity
similarity = cosine_similarity(count_matrix[0:1], count_matrix[1:])
# Get top 3 agents
top_agents_indices = np.argsort(similarity[0])[-3:][::-1]
top_agents_scores = [similarity[0][i] for i in top_agents_indices]
top_agents = [agents.iloc[i] for i in top_agents_indices]
return zip(top_agents_scores, top_agents)
# Streamlit app
st.title("Real Estate Agent Recommender")
# Input fields
preferred_location = st.selectbox("Preferred Location", ['Toronto', 'Vancouver', 'Montreal'])
preferred_property_type = st.selectbox("Preferred Property Type", ['Condo', 'House', 'Apartment'])
max_budget = st.slider("Maximum Budget", 100000, 1000000, 300000, 10000)
language = st.selectbox("Preferred Agent Language", ['English', 'French', 'Hindi'])
amenities = st.multiselect("Preferred Amenities", ['Pool', 'Gym', 'Parking'])
# Button to get recommendations
if st.button("Get Recommendations"):
client_features = {
'preferred_location': preferred_location,
'preferred_property_type': preferred_property_type,
'max_budget': max_budget,
'language': language,
'amenities': ",".join(amenities)
}
recommendations = calculate_similarity(client_features, agents)
# Create DataFrame for displaying the results in a table
recommendation_data = []
rank = 1
for score, agent in recommendations:
recommendation_data.append([rank, score, agent['agent_id'], agent['location_expertise'], agent['property_type_expertise'], agent['average_deal_completion_rate'], agent['language'], agent['amenities']])
rank += 1
recommendation_df = pd.DataFrame(recommendation_data, columns=['Rank', 'Score', 'Agent ID', 'Location Expertise', 'Property Type Expertise', 'Average Deal Completion Rate', 'Language', 'Amenities'])
st.table(recommendation_df) |