Fix/dashboard setup by sxhaakee · Pull Request #31 · hacktofuture-sjec/hacktofuture4

sxhaakee · 2026-04-16T04:51:38Z

created a dashboard for the ml model

Updated project title and description in README.

Copilot

Pull request overview

This PR adds an end-to-end “NeuroMesh” demo: training scripts and prediction modules for multiple sensor models, an orchestration pipeline that generates an LLM SITREP, and a Next.js dashboard to simulate scenarios and visualize the pipeline.

Changes:

Added training scripts + synthetic data generators for seismic/gas/survivor/validator models, plus saved model artifacts.
Added prediction modules and a Python pipeline that runs all models and generates a SITREP via Mistral.
Added a Next.js “SimulationDashboard” UI to run predefined scenarios and display outputs.

Reviewed changes

Copilot reviewed 27 out of 45 changed files in this pull request and generated 17 comments.

Show a summary per file

File	Description
train/train_validator.py	Trains an IsolationForest “validator” model and saves it.
train/train_survivor.py	Trains a logistic regression survivor model + scaler and saves them.
train/train_seismic.py	Trains a small 1D CNN seismic classifier and saves it.
train/train_gas.py	Trains a RandomForest gas classifier and saves it.
predict/predict_validator.py	Loads validator model and predicts authenticity/anomaly info.
predict/predict_survivor.py	Loads survivor model+scaler and predicts survivor probability/urgency.
predict/predict_seismic.py	Loads seismic Keras model and predicts class/magnitude/is_crisis.
predict/predict_gas.py	Loads gas model and predicts hazard type/severity/entry safety.
predict/pycache/predict_validator.cpython-313.pyc	Committed compiled Python artifact.
predict/pycache/predict_survivor.cpython-313.pyc	Committed compiled Python artifact.
predict/pycache/predict_seismic.cpython-313.pyc	Committed compiled Python artifact.
predict/pycache/predict_gas.cpython-313.pyc	Committed compiled Python artifact.
pipeline/langgraph_pipeline.py	Orchestrates model inference and calls Mistral to generate SITREP.
models/survivor_scaler.pkl	Committed trained scaler artifact.
models/survivor_model.pkl	Committed trained model artifact.
data/survivor_data.csv	Committed generated training dataset.
data/generate_survivor_data.py	Generates survivor training dataset.
data/generate_seismic_data.py	Generates seismic training dataset.
data/generate_gas_data.py	Generates gas training dataset.
dashboard/tsconfig.json	Adds TS config for the dashboard app.
dashboard/src/components/SimulationDashboard.tsx	Main dashboard UI + scenario simulation/pipeline visualization.
dashboard/src/app/page.tsx	Renders the dashboard component.
dashboard/src/app/layout.tsx	Next.js layout wrapper + font setup.
dashboard/src/app/globals.css	Global styles / Tailwind setup.
dashboard/src/app/favicon.ico	Dashboard favicon asset.
dashboard/public/window.svg	Next.js template public asset.
dashboard/public/vercel.svg	Next.js template public asset.
dashboard/public/next.svg	Next.js template public asset.
dashboard/public/globe.svg	Next.js template public asset.
dashboard/public/file.svg	Next.js template public asset.
dashboard/postcss.config.mjs	PostCSS config for Tailwind.
dashboard/package.json	Dashboard dependencies/scripts.
dashboard/next.config.ts	Next.js config (turbopack root).
dashboard/eslint.config.mjs	ESLint config for the dashboard.
dashboard/README.md	Next.js template README for the dashboard.
dashboard/CLAUDE.md	Links to agent rules doc.
dashboard/AGENTS.md	Agent rules / warning doc.
dashboard/.gitignore	Dashboard-specific gitignore.
README.md	Removes the repo’s root README template content.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-04-16T04:56:03Z

+import { useState, useEffect } from 'react';
+import { motion, AnimatePresence } from 'framer-motion';
+import { Radio, AlertTriangle, ShieldCheck, Flame, Users, CheckCircle2, Activity, MapPin, Orbit, Zap, Wind, Database } from 'lucide-react';


useEffect and Wind are imported but never used. Remove unused imports to keep the module clean and avoid lint failures.

Suggested change

import { useState, useEffect } from 'react';

import { motion, AnimatePresence } from 'framer-motion';

import { Radio, AlertTriangle, ShieldCheck, Flame, Users, CheckCircle2, Activity, MapPin, Orbit, Zap, Wind, Database } from 'lucide-react';

import { useState } from 'react';

import { motion, AnimatePresence } from 'framer-motion';

import { Radio, AlertTriangle, ShieldCheck, Flame, Users, CheckCircle2, Activity, MapPin, Orbit, Zap, Database } from 'lucide-react';

Copilot · 2026-04-16T04:56:03Z

+
+                 <PipelineStage 
+                   label="Sensor Ingestion" icon={<Activity />} 
+                   state={pipelineState === 'transmitting' ? 'active' : 'done'} 


When pipelineState is 'idle', this stage is rendered as 'done', so the UI shows “Sensor Ingestion” completed even before a scenario runs. Consider mapping 'idle' to 'idle' here and only showing 'done' after the pipeline has progressed past this step.

Suggested change

state={pipelineState === 'transmitting' ? 'active' : 'done'}

state={pipelineState === 'transmitting' ? 'active' : (['models', 'validating', 'llm', 'complete'].includes(pipelineState) ? 'done' : 'idle')}

Copilot · 2026-04-16T04:56:04Z

+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
+import tensorflow as tf


LabelEncoder is imported but never used. Remove it (or actually encode labels if needed) to keep dependencies minimal.

Copilot · 2026-04-16T04:56:04Z

+import tensorflow as tf
+from tensorflow import keras


tensorflow as tf is imported but never used (you only use keras from tensorflow). Remove the unused import to avoid lint noise and clarify dependencies.

Copilot · 2026-04-16T04:56:04Z

+model = joblib.load('models/validator_model.pkl')
+


Models are loaded at module import time. This makes importing the module fail if the model file isn't present and increases cold-start latency. Prefer lazy-loading inside the function (optionally with a cached singleton) and provide a clear error if the model file is missing.

Copilot · 2026-04-16T04:56:06Z

+import numpy as np
+import pandas as pd
+from sklearn.ensemble import IsolationForest


pandas is imported but never used. Remove the unused import to avoid unnecessary dependency/overhead and lint noise.

Copilot · 2026-04-16T04:56:06Z

+pir_count,time_since_event_mins,magnitude,survivor_present
+15,0.6556794712879388,3.2188075050696052,1
+14,3.5655650546979523,4.903594689121354,1


This large generated dataset is committed directly to the repo. If it’s reproducible via data/generate_survivor_data.py, consider not committing the CSV (or store it via Git LFS) to keep the repository size and diff noise manageable.

Copilot · 2026-04-16T04:56:07Z

+# Import all prediction functions
+import sys
+sys.path.append('.')
+from predict.predict_seismic import predict_seismic
+from predict.predict_gas import predict_gas
+from predict.predict_survivor import predict_survivor
+from predict.predict_validator import predict_validator


sys.path.append('.') is a brittle import workaround that can break when the working directory changes and can also cause module shadowing. Prefer proper packaging (e.g., make the repo a package / use relative imports) or invoke via python -m ... so imports resolve without mutating sys.path.

Copilot · 2026-04-16T04:56:07Z

+model = joblib.load('models/gas_model.pkl')
+LABELS = ['safe', 'LPG_leak', 'smoke_fire']


Models are loaded at module import time. This makes importing the module fail if the model file isn't present and increases cold-start latency. Prefer lazy-loading inside the function (optionally with a cached singleton) and provide a clear error if the model file is missing.

Copilot · 2026-04-16T04:56:07Z

+model = joblib.load('models/survivor_model.pkl')
+scaler = joblib.load('models/survivor_scaler.pkl')
+


Models are loaded at module import time. This makes importing the module fail if the model file isn't present and increases cold-start latency. Prefer lazy-loading inside the function (optionally with a cached singleton) and provide a clear error if the model file is missing.

haashid and others added 2 commits April 15, 2026 19:32

Change project title to 'ABRA CODE ABRA'

8ad0ffc

Updated project title and description in README.

Initialize project and fix Next.js dashboard

2ed7795

Copilot AI review requested due to automatic review settings April 16, 2026 04:51

Copilot started reviewing on behalf of sxhaakee April 16, 2026 04:52 View session

Copilot AI reviewed Apr 16, 2026

View reviewed changes

docs: Beautify README following HackToFuture template

6f3d762

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Fix/dashboard setup#31

Fix/dashboard setup#31
sxhaakee wants to merge 3 commits intohacktofuture-sjec:mainfrom
haashid:fix/dashboard-setup

sxhaakee commented Apr 16, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Apr 16, 2026

Uh oh!

Copilot AI Apr 16, 2026

Uh oh!

Copilot AI Apr 16, 2026

Uh oh!

Copilot AI Apr 16, 2026

Uh oh!

Copilot AI Apr 16, 2026

Uh oh!

Copilot AI Apr 16, 2026

Uh oh!

Copilot AI Apr 16, 2026

Uh oh!

Copilot AI Apr 16, 2026

Uh oh!

Copilot AI Apr 16, 2026

Uh oh!

Copilot AI Apr 16, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

	state={pipelineState === 'transmitting' ? 'active' : 'done'}
	state={pipelineState === 'transmitting' ? 'active' : (['models', 'validating', 'llm', 'complete'].includes(pipelineState) ? 'done' : 'idle')}

		model = joblib.load('models/gas_model.pkl')
		LABELS = ['safe', 'LPG_leak', 'smoke_fire']

		model = joblib.load('models/survivor_model.pkl')
		scaler = joblib.load('models/survivor_scaler.pkl')

Conversation

sxhaakee commented Apr 16, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Apr 16, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 16, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 16, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 16, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 16, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 16, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 16, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 16, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 16, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 16, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants