Create app.py

app.py

@@ -0,0 +1,149 @@
+import streamlit as st
+import pandas as pd
+from eventbrite_scrapper import Eventbrite
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+from datetime import datetime
+from dataclasses import dataclass, field, replace
+from typing import List, Any
+
+# Dataclasses for event structure
+@dataclass(frozen=True)
+class EventAddress:
+    latitude: float = None
+    longitude: float = None
+    region: str = None
+    postal_code: str = None
+    address_1: str = None
+
+@dataclass(frozen=True)
+class EventVenue:
+    id: str = None
+    name: str = None
+    url: str = None
+    address: EventAddress = field(default_factory=lambda: EventAddress())
+
+@dataclass(frozen=True)
+class EventImage:
+    url: str = None
+
+@dataclass(frozen=True)
+class EventTag:
+    text: str = None
+
+@dataclass(frozen=True)
+class Event:
+    id: str = None
+    name: str = None
+    url: str = None
+    is_online_event: bool = False
+    short_description: str = None
+    published_datetime: datetime = None
+    start_datetime: datetime = None
+    end_datetime: datetime = None
+    timezone: str = None
+    hide_start_date: bool = False
+    hide_end_date: bool = False
+    parent_event_url: str = None
+    series_id: str = None
+    primary_venue: EventVenue = field(default_factory=lambda: EventVenue())
+    tickets_url: str = None
+    checkout_flow: str = None
+    language: str = None
+    image: EventImage = field(default_factory=lambda: EventImage())
+    tags_categories: tuple = field(default_factory=tuple)
+    tags_formats: tuple = field(default_factory=tuple)
+    tags_by_organizer: tuple = field(default_factory=tuple)
+
+    def __hash__(self):
+        return hash(self.id) if self.id else hash((self.name, self.is_online_event, self.start_datetime, self.primary_venue.name))
+
+# Event Retrieval Pipeline
+class EventbriteRAGPipeline:
+    def __init__(self, events: List[Event], embedding_model: str = 'all-MiniLM-L6-v2'):
+        self.events = [
+            replace(
+                event,
+                tags_categories=tuple(event.tags_categories),
+                tags_formats=tuple(event.tags_formats),
+                tags_by_organizer=tuple(event.tags_by_organizer),
+            )
+            for event in events
+        ]
+        self.model = SentenceTransformer(embedding_model)
+        self.event_embeddings = self._compute_embeddings()
+
+    def _compute_embeddings(self) -> List[np.ndarray]:
+        def event_to_text(event: Event) -> str:
+            text_parts = [
+                event.name or '',
+                event.short_description or '',
+                ' '.join(tag.text for tag in event.tags_categories),
+                ' '.join(tag.text for tag in event.tags_formats),
+                ' '.join(tag.text for tag in event.tags_by_organizer),
+                event.primary_venue.name or '',
+                event.primary_venue.address.region or '',
+                event.language or ''
+            ]
+            return ' '.join(filter(bool, text_parts))
+
+        return self.model.encode([event_to_text(event) for event in self.events])
+
+    def query_events(self, query: str, top_k: int = 5) -> List[Event]:
+        query_embedding = self.model.encode(query).reshape(1, -1)
+        similarities = cosine_similarity(query_embedding, self.event_embeddings)[0]
+        top_indices = similarities.argsort()[-top_k:][::-1]
+        return [self.events[idx] for idx in top_indices]
+
+# Event Evaluator
+class EventEvaluator:
+    def __init__(self, pipeline):
+        self.pipeline = pipeline
+
+    def evaluate_query(self, query):
+        """Evaluate a single query and return results."""
+        top_events = self.pipeline.query_events(query)
+        results = []
+        for event in top_events:
+            result = {
+                "Event Name": event.name,
+                "Online Event": event.is_online_event,
+                "Start Time": event.start_datetime,
+                "Venue Address": event.primary_venue.address.address_1,
+                "Venue Name": event.primary_venue.name,
+                "Description": event.short_description,
+                "Tickets URL": event.tickets_url,
+                "Language": event.language,
+                "Categories": [tag.text for tag in event.tags_categories],
+            }
+            results.append(result)
+        return results
+
+# Fetch events from Eventbrite API
+client = Eventbrite()
+events = client.search_events.get_results(
+    region="ca--los-angeles",
+    dt_start="2024-11-28",
+    dt_end="2024-12-25",
+    max_pages=4,
+)
+
+# Initialize pipeline and evaluator
+rag_pipeline = EventbriteRAGPipeline(events)
+evaluator = EventEvaluator(rag_pipeline)
+
+# Streamlit UI
+st.title("🎟️ Event Search App")
+
+st.write("Find events based on your interests!")
+
+query = st.text_input("🔎 Enter your search query:")
+if query:
+    results = evaluator.evaluate_query(query)
+
+    if results:
+        df = pd.DataFrame(results)
+        st.dataframe(df)  # Display results as a formatted table
+    else:
+        st.warning("No results found.")