Add interactive 3D PCA views to dashboard Park Mind tab

Two spin/zoom Plotly scatter_3d sub-tabs in the PCA tab:
- Rides in PC1xPC2xPC3 (loadings), color by category / GPS
  k-means area / PC1 busyness. Adds GPS k-means areas to
  compute_pca(), auto-labeling the lowest-PC2 cluster Kiddieland.
- Moments in PC1xPC2xPC3 (per-snapshot scores), color by hour /
  day-of-week / weekend / month, sampled to 15k points if larger.

Pin numpy in requirements (now imported directly).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

app.py

@@ -1,6 +1,7 @@
 # Knoebels Queue Dashboard v1.1 - Scaled wait times fix
 import streamlit as st
 import pandas as pd
+import numpy as np
 import psycopg2
 from psycopg2.extras import RealDictCursor
 import plotly.express as px
@@ -113,6 +114,7 @@ def compute_pca():
     coordinates, so the same DataFrame drives the behavioral map."""
     from sklearn.preprocessing import StandardScaler
     from sklearn.decomposition import PCA
+    from sklearn.cluster import KMeans
 
     conn = get_db_connection()
     if not conn:
@@ -167,6 +169,20 @@ def compute_pca():
                             columns=["PC1", "PC2", "PC3"])
     loadings = loadings.join(meta)
 
+    # Spatial "areas" from GPS alone — k-means on standardized lat/lon, the same
+    # 5 clusters the write-up uses. Label the one whose rides lean most negative
+    # on PC2 as Kiddieland so the colors read in plain English.
+    located = loadings.dropna(subset=["lat", "lon"])
+    if len(located) >= 5:
+        km = KMeans(n_clusters=5, n_init=10, random_state=0).fit_predict(
+            StandardScaler().fit_transform(located[["lat", "lon"]]))
+        area = pd.Series(km, index=located.index)
+        kiddie = loadings.loc[area.index].assign(a=area).groupby("a")["PC2"].mean().idxmin()
+        names = {kiddie: "Kiddieland"}
+        loadings["area"] = area.map(lambda a: names.get(a, f"Area {a + 1}"))
+    else:
+        loadings["area"] = "Untagged"
+
     return {
         "loadings": loadings,
         "scores": scores,
@@ -415,6 +431,101 @@ with tab4:
 
         st.markdown("---")
 
+        # --- the same idea in 3D: add PC1 as a third axis -------------------
+        st.markdown("#### The full 3-D picture")
+        st.markdown(
+            "The map above flattens out **PC1** (overall busyness) to fit on a "
+            "page. Here are both clouds in their native 3-D — click-drag to spin, "
+            "scroll to zoom. Two different things get plotted:"
+        )
+
+        rides_tab, moments_tab = st.tabs(
+            ["🎢 Rides in PC-space", "⏱️ Moments in PC-space"])
+
+        # ---- A) each RIDE as a point (the loadings) ----
+        with rides_tab:
+            st.caption(
+                "Every **ride** placed by how its queue behaves. Notice the cloud "
+                "is nearly flat along **PC1** — almost every ride loads the same "
+                "way on overall-busyness, so it barely separates them. All the "
+                "real structure lives in the PC2/PC3 plane you saw above.")
+            ride_color = st.selectbox(
+                "Color the rides by",
+                ["Park category tag", "Spatial area (GPS k-means)",
+                 "Overall busyness (PC1 loading)"],
+                key="ride_color3d")
+            rdf = loadings.reset_index().copy()
+            rdf["category"] = rdf["category"].fillna("Untagged")
+            common = dict(x="PC1", y="PC2", z="PC3", hover_name="ride_name", height=640)
+            if ride_color == "Park category tag":
+                fig3d_r = px.scatter_3d(rdf, color="category",
+                    color_discrete_map={**CATEGORY_COLORS, "Untagged": "#888"}, **common)
+            elif ride_color == "Spatial area (GPS k-means)":
+                fig3d_r = px.scatter_3d(rdf, color="area", **common)
+            else:
+                fig3d_r = px.scatter_3d(rdf, color="PC1",
+                    color_continuous_scale="Viridis", **common)
+            fig3d_r.update_traces(marker=dict(size=5, line=dict(width=0.5, color="#1A1C18")))
+            fig3d_r.update_layout(
+                margin=dict(l=0, r=0, t=0, b=0),
+                scene=dict(xaxis_title="PC1 · busyness",
+                           yaxis_title="PC2 · Kiddieland↔midway",
+                           zaxis_title="PC3 · evening↔daytime"))
+            st.plotly_chart(fig3d_r, use_container_width=True)
+
+        # ---- B) each MOMENT as a point (the scores) ----
+        with moments_tab:
+            st.caption(
+                "Every **5-minute snapshot** of the park as one point — this is the "
+                "direct analog of an embedding cloud, but each dot is a *moment*, "
+                "not a note. Unlike the rides, the moments spread on all three "
+                "axes: a packed evening sits far out on PC1, a kiddie-heavy morning "
+                "pulls toward the PC2/PC3 corners.")
+            mom_color = st.selectbox(
+                "Color the moments by",
+                ["Hour of day", "Day of week", "Weekend vs. weekday", "Month"],
+                key="mom_color3d")
+            sdf = scores.copy()
+            idx = pd.DatetimeIndex(sdf.index)
+            sdf["Hour of day"] = idx.hour
+            sdf["Day of week"] = idx.day_name()
+            sdf["Weekend vs. weekday"] = np.where(idx.weekday >= 5, "Weekend", "Weekday")
+            sdf["Month"] = idx.month_name()
+            # keep it responsive — sample if the history is large
+            cap = 15000
+            note = ""
+            if len(sdf) > cap:
+                sdf = sdf.sample(cap, random_state=0)
+                note = f"  *(showing a random {cap:,} of {len(scores):,} snapshots)*"
+            common_m = dict(x="PC1", y="PC2", z="PC3", height=640, opacity=0.55)
+            if mom_color == "Hour of day":
+                fig3d_m = px.scatter_3d(sdf, color="Hour of day",
+                    color_continuous_scale="Turbo", **common_m)
+            elif mom_color == "Month":
+                order = [pd.Timestamp(2020, m, 1).month_name() for m in range(1, 13)]
+                fig3d_m = px.scatter_3d(sdf, color="Month",
+                    category_orders={"Month": order}, **common_m)
+            elif mom_color == "Day of week":
+                order = ["Monday", "Tuesday", "Wednesday", "Thursday",
+                         "Friday", "Saturday", "Sunday"]
+                fig3d_m = px.scatter_3d(sdf, color="Day of week",
+                    category_orders={"Day of week": order}, **common_m)
+            else:
+                fig3d_m = px.scatter_3d(sdf, color="Weekend vs. weekday",
+                    color_discrete_map={"Weekday": "#4C9BE8", "Weekend": "#E0524E"},
+                    **common_m)
+            fig3d_m.update_traces(marker=dict(size=2.5))
+            fig3d_m.update_layout(
+                margin=dict(l=0, r=0, t=0, b=0),
+                scene=dict(xaxis_title="PC1 · busyness",
+                           yaxis_title="PC2 · Kiddieland↔midway",
+                           zaxis_title="PC3 · evening↔daytime"))
+            st.plotly_chart(fig3d_m, use_container_width=True)
+            if note:
+                st.caption(note.strip(" *"))
+
+        st.markdown("---")
+
         # --- loadings explorer: which rides drive a chosen component ---
         lcol, rcol = st.columns([1, 2])
         with lcol:

requirements.txt

@@ -2,6 +2,7 @@ requests
 psycopg2-binary
 streamlit
 pandas
+numpy
 plotly
 python-dotenv
 scikit-learn