refactor

apps/cluster_map/config.py

@@ -0,0 +1,73 @@
+"""
+Configuration settings and constants for the Discord Chat Embeddings Visualizer.
+"""
+
+# Application settings
+APP_TITLE = "Discord Chat Embeddings Visualizer"
+APP_ICON = "🗨️"
+APP_LAYOUT = "wide"
+
+# File paths
+CHAT_LOGS_PATH = "../../discord_chat_logs"
+
+# Algorithm parameters
+DEFAULT_RANDOM_STATE = 42
+DEFAULT_N_COMPONENTS = 2
+DEFAULT_N_CLUSTERS = 5
+
+# Visualization settings
+DEFAULT_POINT_SIZE = 8
+DEFAULT_POINT_OPACITY = 0.7
+MAX_DISPLAYED_AUTHORS = 10
+MESSAGE_CONTENT_PREVIEW_LENGTH = 200
+MESSAGE_CONTENT_DISPLAY_LENGTH = 100
+
+# Performance thresholds
+LARGE_DATASET_WARNING_THRESHOLD = 1000
+
+# Color palettes
+PRIMARY_COLORS = ["#1f77b4", "#ff7f0e", "#2ca02c", "#d62728", "#9467bd", 
+                  "#8c564b", "#e377c2", "#7f7f7f", "#bcbd22", "#17becf"]
+
+# Clustering method categories
+CLUSTERING_METHODS_REQUIRING_N_CLUSTERS = [
+    "Spectral Clustering", 
+    "Gaussian Mixture", 
+    "Agglomerative (Ward)", 
+    "Agglomerative (Complete)"
+]
+
+COMPUTATIONALLY_INTENSIVE_METHODS = {
+    "dimension_reduction": ["t-SNE", "Spectral Embedding"],
+    "clustering": ["Spectral Clustering", "OPTICS"]
+}
+
+# Method explanations
+METHOD_EXPLANATIONS = {
+    "dimension_reduction": {
+        "PCA": "Linear, fast, preserves global variance",
+        "t-SNE": "Non-linear, good for local structure, slower",
+        "UMAP": "Balanced speed/quality, preserves local & global structure",
+        "Spectral Embedding": "Uses graph theory, good for non-convex clusters",
+        "Force-Directed": "Physics-based layout, creates natural spacing"
+    },
+    "clustering": {
+        "HDBSCAN": "Density-based, finds variable density clusters, handles noise",
+        "Spectral Clustering": "Uses eigenvalues, good for non-convex shapes",
+        "Gaussian Mixture": "Probabilistic, assumes gaussian distributions",
+        "Agglomerative (Ward)": "Hierarchical, minimizes within-cluster variance",
+        "Agglomerative (Complete)": "Hierarchical, minimizes maximum distance",
+        "OPTICS": "Density-based, finds clusters of varying densities"
+    },
+    "separation": {
+        "Spread Factor": "Applies repulsive forces between nearby points",
+        "Smart Jittering": "Adds intelligent noise to separate overlapping points",
+        "Density-Based Jittering": "Stronger separation in crowded areas",
+        "Perplexity Factor": "Controls t-SNE's focus on local vs global structure",
+        "Min Distance Factor": "Controls UMAP's point packing tightness"
+    },
+    "metrics": {
+        "Silhouette Score": "Higher is better (range: -1 to 1)",
+        "Calinski-Harabasz": "Higher is better, measures cluster separation"
+    }
+}