Create app.py

app.py

@@ -0,0 +1,87 @@
+# streamlit_app.py
+import streamlit as st
+import pandas as pd
+import numpy as np
+import joblib
+import tensorflow as tf
+
+# ─── Caching loaders so they only run once ───────────────────────────────────
+@st.cache(allow_output_mutation=True)
+def load_preprocessor(path="preprocessor.pkl"):
+    return joblib.load(path)
+
+@st.cache(allow_output_mutation=True)
+def load_label_encoder(path="label_encoder.pkl"):
+    return joblib.load(path)
+
+@st.cache(allow_output_mutation=True)
+def load_model(path="keystroke_dnn.h5"):
+    return tf.keras.models.load_model(path)
+
+# ─── Prediction function ────────────────────────────────────────────────────
+def predict_subjects(df_raw):
+    """
+    Takes a DataFrame of raw keystroke features, drops any
+    'subject'/'sessionIndex'/'rep' columns, re-orders to the
+    exact list the preprocessor saw at train-time, scales,
+    runs the DNN, and returns predicted IDs + probabilities.
+    """
+    preprocessor  = load_preprocessor()
+    label_encoder = load_label_encoder()
+    model         = load_model()
+
+    # 1) Drop unused cols if present
+    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
+    feature_cols = preprocessor.transformers_[0][2]
+    df_features  = df_raw[feature_cols]
+
+    # 3) Scale
+    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
+    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 ──────────────────────────────────────────────────────────
+def main():
+    st.set_page_config(page_title="Keystroke Dynamics Auth", layout="wide")
+    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."
+    )
+
+    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}")
+
+if __name__ == "__main__":
+    main()