contestant.eviction_risk && ( <div className="mt-3 p-2 rounded bg-gray-800"> <span className="text-sm">⚠️ Eviction risk: </span> <span style=color: riskColor>(contestant.eviction_risk * 100).toFixed(0)%</span> </div> ) </div> );
@app.get("/bbms6/winner-picks") def winner_picks(): return analyzer.get_winner_recommendation() // ContestantCard.jsx import React from 'react'; export default function ContestantCard( contestant ) const riskColor = contestant.eviction_risk > 0.7 ? 'red' : contestant.eviction_risk > 0.4 ? 'orange' : 'green'; bigg boss season 6 contestants malayalam
def get_winner_recommendation(self): active = [c for c in self.contestants if c['status'] == 'Active'] scored = [] for c in active: gameplay_score = (c['tasksWonAsCaptain'] * 2) - (c['taskFailures'] * 1.5) audience_score = c['fanPollRank'] # lower rank = better controversy_penalty = 2 if 'Aggressive' in c['personalityTraits'] else 0 total = gameplay_score - controversy_penalty - audience_score scored.append((c['name'], total)) scored.sort(key=lambda x: x[1], reverse=True) return scored[:3] from fastapi import FastAPI app = FastAPI() @app.get("/bbms6/contestants") def get_all_contestants(): return contestants_list contestant
return ( <div className="bg-gray-900 rounded-xl p-4 shadow-lg border-l-8 border-yellow-500"> <h2 className="text-2xl font-bold text-white">contestant.name</h2> <p className="text-gray-400">contestant.occupation • contestant.age</p> contestant.eviction_risk && ( <
<div className="mt-4 grid grid-cols-2 gap-2 text-sm"> <div>📋 Nominations: contestant.nominationsCount</div> <div>👑 Captain wins: contestant.tasksWonAsCaptain</div> <div>📈 IG growth: +contestant.instagramGrowthPercent%</div> <div>⭐ Fan rank: #contestant.fanPollRank</div> </div>
@app.get("/bbms6/compare/id1/id2") def compare(id1: str, id2: str): return analyzer.compare_contestants(id1, id2)
def predict_eviction_risk(self, week_number): # Simplified logistic regression mock nominated = [c for c in self.contestants if week_number in c['nominationWeeks']] for c in nominated: risk = ( 0.3 * c['nominationsCount'] + 0.4 * (1 - c['fanPollRank'] / len(self.contestants)) + 0.3 * (c['taskFailures'] / max(1, c['tasksWonAsCaptain'] + c['taskFailures'])) ) c['eviction_risk'] = min(0.99, risk) return sorted(nominated, key=lambda x: x['eviction_risk'], reverse=True)