Spaces:
Sleeping
Sleeping
Update src/streamlit_app.py
Browse files- src/streamlit_app.py +71 -38
src/streamlit_app.py
CHANGED
|
@@ -1,40 +1,73 @@
|
|
| 1 |
-
import altair as alt
|
| 2 |
-
import numpy as np
|
| 3 |
-
import pandas as pd
|
| 4 |
import streamlit as st
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
|
| 6 |
-
""
|
| 7 |
-
# Welcome to Streamlit!
|
| 8 |
-
|
| 9 |
-
Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
|
| 10 |
-
If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
|
| 11 |
-
forums](https://discuss.streamlit.io).
|
| 12 |
-
|
| 13 |
-
In the meantime, below is an example of what you can do with just a few lines of code:
|
| 14 |
-
"""
|
| 15 |
-
|
| 16 |
-
num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
|
| 17 |
-
num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
|
| 18 |
-
|
| 19 |
-
indices = np.linspace(0, 1, num_points)
|
| 20 |
-
theta = 2 * np.pi * num_turns * indices
|
| 21 |
-
radius = indices
|
| 22 |
-
|
| 23 |
-
x = radius * np.cos(theta)
|
| 24 |
-
y = radius * np.sin(theta)
|
| 25 |
-
|
| 26 |
-
df = pd.DataFrame({
|
| 27 |
-
"x": x,
|
| 28 |
-
"y": y,
|
| 29 |
-
"idx": indices,
|
| 30 |
-
"rand": np.random.randn(num_points),
|
| 31 |
-
})
|
| 32 |
-
|
| 33 |
-
st.altair_chart(alt.Chart(df, height=700, width=700)
|
| 34 |
-
.mark_point(filled=True)
|
| 35 |
-
.encode(
|
| 36 |
-
x=alt.X("x", axis=None),
|
| 37 |
-
y=alt.Y("y", axis=None),
|
| 38 |
-
color=alt.Color("idx", legend=None, scale=alt.Scale()),
|
| 39 |
-
size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
|
| 40 |
-
))
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import streamlit as st
|
| 2 |
+
import pandas as pd
|
| 3 |
+
import joblib
|
| 4 |
+
|
| 5 |
+
st.set_page_config(page_title="Payment Fraud Detection", page_icon="💳", layout="centered")
|
| 6 |
+
|
| 7 |
+
@st.cache_resource
|
| 8 |
+
def load_artifacts():
|
| 9 |
+
model = joblib.load("src/randomforest_model.pkl")
|
| 10 |
+
try:
|
| 11 |
+
features = joblib.load("model_features.pkl")
|
| 12 |
+
except Exception:
|
| 13 |
+
features = None
|
| 14 |
+
return model, features
|
| 15 |
+
|
| 16 |
+
model, model_features = load_artifacts()
|
| 17 |
+
|
| 18 |
+
st.title("💳 Payment Fraud Detection")
|
| 19 |
+
st.write("Enter transaction details and get a fraud prediction (0 = Not Fraud, 1 = Fraud).")
|
| 20 |
+
|
| 21 |
+
with st.sidebar:
|
| 22 |
+
st.header("ℹ️ Info")
|
| 23 |
+
st.write("**Model:** Random Forest")
|
| 24 |
+
if model_features is None:
|
| 25 |
+
st.warning("`model_features.pkl` not found. App will try to predict without reindexing columns.")
|
| 26 |
+
else:
|
| 27 |
+
st.caption(f"Loaded {len(model_features)} feature columns.")
|
| 28 |
+
|
| 29 |
+
st.subheader("Transaction Input")
|
| 30 |
+
|
| 31 |
+
col1, col2 = st.columns(2)
|
| 32 |
+
with col1:
|
| 33 |
+
accountAgeDays = st.number_input("accountAgeDays", min_value=0, value=30, step=1)
|
| 34 |
+
numItems = st.number_input("numItems", min_value=1, value=1, step=1)
|
| 35 |
+
with col2:
|
| 36 |
+
localTime = st.number_input("localTime (e.g., 0–24)", min_value=0.0, value=12.0, step=0.5)
|
| 37 |
+
paymentMethodAgeDays = st.number_input("paymentMethodAgeDays", min_value=0, value=10, step=1)
|
| 38 |
+
|
| 39 |
+
paymentMethod = st.selectbox("paymentMethod", ["paypal", "creditcard", "storecredit"])
|
| 40 |
+
|
| 41 |
+
if st.button("Predict", type="primary"):
|
| 42 |
+
# Build one-row dataframe exactly like training input BEFORE get_dummies
|
| 43 |
+
input_df = pd.DataFrame([{
|
| 44 |
+
"accountAgeDays": accountAgeDays,
|
| 45 |
+
"numItems": numItems,
|
| 46 |
+
"localTime": localTime,
|
| 47 |
+
"paymentMethodAgeDays": paymentMethodAgeDays,
|
| 48 |
+
"paymentMethod": paymentMethod
|
| 49 |
+
}])
|
| 50 |
+
|
| 51 |
+
# One-hot encode like training
|
| 52 |
+
X = pd.get_dummies(input_df, drop_first=True)
|
| 53 |
+
|
| 54 |
+
# Align columns to training columns (important!)
|
| 55 |
+
if model_features is not None:
|
| 56 |
+
X = X.reindex(columns=model_features, fill_value=0)
|
| 57 |
+
|
| 58 |
+
# Predict
|
| 59 |
+
pred = model.predict(X)[0]
|
| 60 |
+
proba = None
|
| 61 |
+
if hasattr(model, "predict_proba"):
|
| 62 |
+
proba = model.predict_proba(X)[0][1]
|
| 63 |
+
|
| 64 |
+
st.divider()
|
| 65 |
+
if pred == 1:
|
| 66 |
+
st.error("🚨 Prediction: FRAUD (1)")
|
| 67 |
+
else:
|
| 68 |
+
st.success("✅ Prediction: NOT FRAUD (0)")
|
| 69 |
+
|
| 70 |
+
if proba is not None:
|
| 71 |
+
st.metric("Fraud Probability", f"{proba:.2%}")
|
| 72 |
|
| 73 |
+
st.caption("Tip: If you get column mismatch issues, create `model_features.pkl` (see README).")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|