UI adjustments..

src/phyphox_app_block.py

@@ -1,4 +1,4 @@
-"""Streamlit UI block for Tab 2 — Phyphox live sensor upload.
+"""Streamlit UI block for Tab 2: Phyphox live sensor upload.
 
 Call from streamlit_app.py:
 
@@ -28,12 +28,12 @@ LABEL_MAP = {
 }
 
 EXPLANATIONS = {
-    "LAYING": "Minimal movement detected across all axes — consistent with a stationary horizontal posture.",
-    "SITTING": "Low dynamic acceleration with stable gravity — stationary upright posture.",
+    "LAYING": "Minimal movement detected across all axes: consistent with a stationary horizontal posture.",
+    "SITTING": "Low dynamic acceleration with stable gravity: stationary upright posture.",
     "STANDING": "Similar to sitting with slight postural micro-movements.",
-    "WALKING": "Rhythmic periodic acceleration on the vertical axis — level walking at normal cadence.",
-    "WALKING_DOWNSTAIRS": "Downward gravitational shift with higher impact peaks — descending stairs.",
-    "WALKING_UPSTAIRS": "Elevated vertical acceleration effort — climbing stairs.",
+    "WALKING": "Rhythmic periodic acceleration on the vertical axis: level walking at normal cadence.",
+    "WALKING_DOWNSTAIRS": "Downward gravitational shift with higher impact peaks: descending stairs.",
+    "WALKING_UPSTAIRS": "Elevated vertical acceleration effort: climbing stairs.",
 }
 
 # ── Normalisation ─────────────────────────────────────────────────────────────
@@ -52,7 +52,7 @@ def _normalize(features: np.ndarray, min_vals: np.ndarray, max_vals: np.ndarray)
     """Best-effort feature-level min-max scaling to [-1, 1].
 
     Uses per-feature min/max observed in the UCI HAR training set. This is
-    an approximation — the UCI pipeline normalises raw signals before feature
+    an approximation: the UCI pipeline normalises raw signals before feature
     extraction, so physical-unit features may fall outside the training range.
     Values are clipped before scaling to keep outputs bounded.
     """
@@ -73,7 +73,7 @@ def render_phyphox_tab(
     st.markdown("""
 **How to record your own data:**
 1. Install [Phyphox](https://phyphox.org/) on your phone
-2. Open **Acceleration (without g)** and **Gyroscope** — record simultaneously
+2. Open **Acceleration (without g)** and **Gyroscope**: record simultaneously
 3. Hold the phone at your waist (same position as the UCI dataset)
 4. Record at least 3 seconds of a single activity
 5. Export both experiments as CSV and upload below
@@ -135,13 +135,13 @@ def render_phyphox_tab(
         )
     else:
         st.warning(
-            "norm_params.json not found — features are in physical units. "
+            "norm_params.json not found: features are in physical units. "
             "Predictions will be unreliable until normalisation is applied."
         )
 
     # ── Predictions ───────────────────────────────────────────────────────────
     if ffn_status != "ready" and cnn_status != "ready":
-        st.warning("Models not loaded — cannot predict yet.")
+        st.warning("Models not loaded: cannot predict yet.")
         return
 
     st.markdown("---")
@@ -153,7 +153,7 @@ def render_phyphox_tab(
         with col:
             st.markdown(f"#### {name}")
             if status != "ready":
-                st.error(f"Model not loaded — {status}")
+                st.error(f"Model not loaded: {status}")
                 return
 
             probs_all = model.predict(features, verbose=0)       # (n_windows, 6)

src/streamlit_app.py

@@ -21,12 +21,12 @@ LABEL_MAP = {
 }
 
 EXPLANATIONS = {
-    "LAYING": "Minimal movement detected across all axes with low acceleration magnitude — consistent with a stationary horizontal posture.",
+    "LAYING": "Minimal movement detected across all axes with low acceleration magnitude: consistent with a stationary horizontal posture.",
     "SITTING": "Low dynamic acceleration with a stable gravity component suggests a stationary upright posture with little body movement.",
     "STANDING": "Similar to sitting but with slight postural micro-movements. This class is often the hardest to distinguish from sitting.",
-    "WALKING": "Rhythmic periodic acceleration with peaks on the vertical axis — consistent with level walking at normal cadence.",
+    "WALKING": "Rhythmic periodic acceleration with peaks on the vertical axis: consistent with level walking at normal cadence.",
     "WALKING_DOWNSTAIRS": "Downward gravitational shift with higher impact peaks characteristic of descending a staircase.",
-    "WALKING_UPSTAIRS": "Elevated vertical acceleration effort with upward body displacement — consistent with climbing stairs.",
+    "WALKING_UPSTAIRS": "Elevated vertical acceleration effort with upward body displacement: consistent with climbing stairs.",
 }
 
 # ── Model loader ────────────────────────────────────────────────────────────
@@ -84,11 +84,11 @@ with st.sidebar:
     st.markdown("---")
     st.markdown("**Models**")
     st.markdown("""
-    **FFN** — Feedforward Network
+    **FFN**: Feedforward Network
     Dense(512) → Dense(256) → Dense(128)
     BatchNorm + Dropout(0.3) per layer
 
-    **CNN** — 1D Convolutional Network
+    **CNN**: 1D Convolutional Network
     Conv1D(64) → Conv1D(128) → Conv1D(256)
     GlobalAvgPool → Dense(128)
     """)
@@ -102,9 +102,9 @@ cnn_model, cnn_status = load_model("har_cnn.keras")
 
 if ffn_status != "ready" or cnn_status != "ready":
     if ffn_status != "ready":
-        st.warning(f"FFN not loaded — {ffn_status}")
+        st.warning(f"FFN not loaded: {ffn_status}")
     if cnn_status != "ready":
-        st.warning(f"CNN not loaded — {cnn_status}")
+        st.warning(f"CNN not loaded: {cnn_status}")
 
 # ── Tabs ─────────────────────────────────────────────────────────────────────
 
@@ -124,7 +124,7 @@ with tab1:
         feature_cols = [c for c in samples_df.columns if c not in ["Activity", "subject"]]
 
         sample_labels = [
-            f"Sample {i+1}  —  {row['Activity']}"
+            f"Sample {i+1} :  {row['Activity']}"
             for i, (_, row) in enumerate(samples_df.iterrows())
         ]
 
@@ -142,7 +142,7 @@ with tab1:
 
         if st.button("Classify this sample", type="primary"):
             if ffn_status != "ready" or cnn_status != "ready":
-                st.error("One or both models not loaded — cannot predict yet.")
+                st.error("One or both models not loaded: cannot predict yet.")
             else:
                 arr = feature_vector.reshape(1, -1)