Update app.py

app.py

@@ -2,7 +2,7 @@
 
 import streamlit as st
 
-# ─── THIS MUST BE FIRST ───────────────────────────────────────────────────────
+# ─── MUST BE FIRST ───────────────────────────────────────────────────────────
 st.set_page_config(page_title="Keystroke Dynamics Auth", layout="wide")
 
 import pandas as pd
@@ -10,7 +10,7 @@ import numpy as np
 import joblib
 import tensorflow as tf
 
-# ─── Caching loaders so they only run only once per session ──────────────────
+# ─── Caching loaders so they only run once per session ───────────────────────
 @st.cache_resource
 def load_preprocessor(path="preprocessor.pkl"):
     return joblib.load(path)
@@ -23,63 +23,69 @@ def load_label_encoder(path="label_encoder.pkl"):
 def load_model(path="keystroke_dnn.h5"):
     return tf.keras.models.load_model(path)
 
-# ─── Prediction function ────────────────────────────────────────────────────
+# ─── Prediction helper ───────────────────────────────────────────────────────
 def predict_subjects(df_raw):
     preprocessor  = load_preprocessor()
     label_encoder = load_label_encoder()
     model         = load_model()
 
-    # 1) Drop unused cols if present
+    # Drop any stray columns
     for c in ("subject", "sessionIndex", "rep"):
         if c in df_raw.columns:
             df_raw = df_raw.drop(columns=[c])
 
-    # 2) Re-order columns exactly as during training
+    # Re-order to exact feature list
     feature_cols = preprocessor.transformers_[0][2]
     df_features  = df_raw[feature_cols]
 
-    # 3) Scale
+    # Scale, predict, decode
     X_scaled = preprocessor.transform(df_features)
-
-    # 4) Model inference
     y_prob   = model.predict(X_scaled)
     idx_pred = np.argmax(y_prob, axis=1)
-
-    # 5) Decode one‐hot back to original labels
     labels   = label_encoder.categories_[0][idx_pred]
 
-    # 6) Build output
+    # Build output table
     df_out = pd.DataFrame({"predicted_subject": labels})
     for i, cls in enumerate(label_encoder.categories_[0]):
         df_out[f"prob_{cls}"] = y_prob[:, i]
-
     return df_out
 
-# ─── Streamlit UI ──────────────────────────────────────────────────────────
+# ─── Streamlit App ──────────────────────────────────────────────────────────
 def main():
     st.title("🔑 Keystroke Dynamics Authentication")
     st.markdown(
-        "Upload a CSV of raw keystroke‐feature vectors (one row per sample). "
-        "The app will drop any `subject`/`sessionIndex`/`rep` columns, scale, "
-        "run through the DNN, and return predicted subject IDs + confidence scores."
+        "Use the sidebar to enter one row of raw keystroke features, then click **Predict**. "
+        "The model will return the predicted subject ID plus per-class probabilities."
     )
 
-    uploaded = st.file_uploader("Choose CSV file", type="csv")
-    if not uploaded:
-        return
-
-    df = pd.read_csv(uploaded)
-    st.write("### Raw feature preview (first 5 rows)")
-    st.dataframe(df.head(), use_container_width=True)
-
-    try:
-        df_preds = predict_subjects(df)
-        st.write("### Predictions")
-        st.dataframe(df_preds, use_container_width=True)
-    except KeyError as e:
-        st.error(f"Missing expected feature column: {e}")
-    except Exception as e:
-        st.error(f"Error during prediction: {e}")
+    # Load the feature‐list so we can build inputs
+    preprocessor = load_preprocessor()
+    feature_cols = preprocessor.transformers_[0][2]
+
+    st.sidebar.header("Enter keystroke features")
+    user_vals = {}
+    # one number_input per feature
+    for col in feature_cols:
+        # you can tweak min/max/default as appropriate
+        user_vals[col] = st.sidebar.number_input(col, value=0.0, format="%.4f")
+
+    if st.sidebar.button("Predict"):
+        # pack into single-row DataFrame
+        df_input = pd.DataFrame([user_vals], columns=feature_cols)
+
+        # Show what we're about to send
+        st.write("### Your input")
+        st.dataframe(df_input, use_container_width=True)
+
+        # Do prediction
+        try:
+            df_pred = predict_subjects(df_input)
+            st.write("### Prediction")
+            st.dataframe(df_pred, use_container_width=True)
+        except KeyError as e:
+            st.error(f"Missing feature (typo?): {e}")
+        except Exception as e:
+            st.error(f"Prediction error: {e}")
 
 if __name__ == "__main__":
     main()