From c082a9882b2e02fee19df70dd85996ca09831c5d Mon Sep 17 00:00:00 2001 From: Dani Date: Wed, 30 Apr 2025 22:32:18 -0400 Subject: [PATCH] Updated the brainmap --- context/context.py | 16 +++--- dashboard/dashboard.py | 5 +- dashboard/templates/brainmap.html | 86 ++++++++++++++++++++++++------- model/brainmap.py | 52 ++++++++++++++++--- model/cleanup.py | 8 +-- 5 files changed, 128 insertions(+), 39 deletions(-) diff --git a/context/context.py b/context/context.py index 6506866..3ec9697 100644 --- a/context/context.py +++ b/context/context.py @@ -3,19 +3,23 @@ import os import time from typing import List -CONTEXT_FILE = "data/memory/context.json" +CONTEXT_PATH = "data/memory/context.json" MAX_MEMORY = 100 -def load_context() -> List[dict]: - if os.path.exists(CONTEXT_FILE): - with open(CONTEXT_FILE, "r", encoding="utf-8") as f: +def load_context(): + if not os.path.exists(CONTEXT_PATH): + return [] + try: + with open(CONTEXT_PATH, "r", encoding="utf-8") as f: return json.load(f) - return [] + except json.JSONDecodeError: + print("[Context] Corrupted context.json. Returning empty list.") + return [] def save_context(mem: List[dict]): - with open(CONTEXT_FILE, "w", encoding="utf-8") as f: + with open(CONTEXT_PATH, "w", encoding="utf-8") as f: json.dump(mem[-MAX_MEMORY:], f, indent=2) diff --git a/dashboard/dashboard.py b/dashboard/dashboard.py index 2aa367a..640e5ed 100644 --- a/dashboard/dashboard.py +++ b/dashboard/dashboard.py @@ -9,13 +9,12 @@ from model.journal import read_journal_entries from model.dreams import load_dreams from model.tokenizer import Tokenizer from model.abstraction import cluster_vocab -from model.dreams import load_dreams from model.scheduler import get_time_until_next_action, get_next_action_label from context.context import load_context from reader.reader import get_books, load_progress -app = Flask(__name__) +app = Flask(__name__, static_folder="static") tokenizer = Tokenizer() next_cycle_time = time.time() + 900 # Example: 15 minutes from now @@ -128,7 +127,7 @@ def brainmap(): print(f"[Dashboard] Failed to load brainmap cache: {e}") nodes, links = [], [] - return render_template("brainmap.html", nodes=json.dumps(nodes), links=json.dumps(links)) + return render_template("brainmap.html", nodes=nodes, links=links) @app.route("/journal") diff --git a/dashboard/templates/brainmap.html b/dashboard/templates/brainmap.html index 1dd457b..afe6266 100644 --- a/dashboard/templates/brainmap.html +++ b/dashboard/templates/brainmap.html @@ -2,16 +2,14 @@ - Ruby's Brain Map
- 🏠 Home + 📊 Dashboard 📓 Journal 🧠 Concepts 🕸️ Brain Map @@ -44,21 +58,55 @@ ❤️ Health
+ +
diff --git a/model/brainmap.py b/model/brainmap.py index 8179ccb..c83a7c8 100644 --- a/model/brainmap.py +++ b/model/brainmap.py @@ -1,6 +1,9 @@ import re import json import os +import shutil +from sklearn.cluster import KMeans +import numpy as np from utils.unicleaner import clean_unicode BRAINMAP_PATH = "data/memory/brainmap.json" # actual connection data @@ -99,7 +102,12 @@ def get_brainmap(): return brainmap -def refresh_brainmap_cache(min_weight=5, max_nodes=300): +def refresh_brainmap_cache(min_weight=2, max_nodes=300): + """ + Generates a clustered brainmap view and writes to: + - data/memory/brainmap_cache.json (master copy) + - static/brainmap.json (served to frontend) + """ map_data = get_brainmap() links = [] seen_words = set() @@ -108,7 +116,6 @@ def refresh_brainmap_cache(min_weight=5, max_nodes=300): if not isinstance(connections, dict): print(f"[Brainmap] Skipping corrupted entry: {word} => {type(connections)}") continue - for linked_word, weight in connections.items(): if weight >= min_weight: links.append({ @@ -119,13 +126,44 @@ def refresh_brainmap_cache(min_weight=5, max_nodes=300): seen_words.add(word) seen_words.add(linked_word) - nodes = [{"id": word} for word in seen_words] - + node_set = {link["source"] for link in links} | {link["target"] for link in links} + nodes = sorted(node_set) if len(nodes) > max_nodes: nodes = nodes[:max_nodes] - node_set = {n["id"] for n in nodes} + node_set = set(nodes) links = [l for l in links if l["source"] in node_set and l["target"] in node_set] + index_lookup = {word: i for i, word in enumerate(nodes)} + word_vectors = [] + for word in nodes: + vec = np.zeros(len(nodes), dtype=np.float32) + connections = map_data.get(word, {}) + for other, strength in connections.items(): + if other in index_lookup: + vec[index_lookup[other]] = strength + word_vectors.append(vec) + + if len(word_vectors) < 2: + print("[Brainmap] Not enough nodes to cluster.") + return + + kmeans = KMeans(n_clusters=min(8, len(nodes)), n_init="auto") + labels = kmeans.fit_predict(word_vectors) + clustered_nodes = [{"id": word, "group": int(label)} for word, label in zip(nodes, labels)] + + output = { + "nodes": clustered_nodes, + "links": links + } + os.makedirs("data/memory", exist_ok=True) - with open(BRAINMAP_CACHE_PATH, "w", encoding="utf-8") as f: - json.dump({"nodes": nodes, "links": links}, f, indent=2) + os.makedirs("static", exist_ok=True) + + cache_path = "data/memory/brainmap_cache.json" + static_path = "static/brainmap.json" + + with open(cache_path, "w", encoding="utf-8") as f: + json.dump(output, f, indent=2) + + shutil.copyfile(cache_path, static_path) + # print(f"[Brainmap] Cache written to {cache_path} and copied to {static_path}") diff --git a/model/cleanup.py b/model/cleanup.py index 3384570..167f6b6 100644 --- a/model/cleanup.py +++ b/model/cleanup.py @@ -4,7 +4,7 @@ import os import time from model.tokenizer import VOCAB_PATH from model.dreams import DREAM_LOG_PATH -from context.context import CONTEXT_FILE +from context.context import CONTEXT_PATH from model.brainmap import load_brainmap, save_brainmap CLEANUP_LOG = "data/logs/cleanup.log" @@ -59,15 +59,15 @@ def cleanup_dreams(): def cleanup_context(): - if not os.path.exists(CONTEXT_FILE): + if not os.path.exists(CONTEXT_PATH): return - with open(CONTEXT_FILE, "r", encoding="utf-8") as f: + with open(CONTEXT_PATH, "r", encoding="utf-8") as f: context = json.load(f) filtered = context[-100:] - with open(CONTEXT_FILE, "w", encoding="utf-8") as f: + with open(CONTEXT_PATH, "w", encoding="utf-8") as f: json.dump(filtered, f, indent=2) if len(filtered) < len(context):