File size: 3,617 Bytes
4db667a f1735e2 4db667a f1735e2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 | import streamlit as st
import pandas as pd
import numpy as np
import joblib
import xgboost as xgb
st.set_page_config(
page_title="Customer Satisfaction Prediction",
page_icon="👤",
layout="centered")
st.title("👤 Customer Satisfaction Prediction")
st.markdown("""
Enter the key financial details below to predict if a specific customer will be **Satisfied** or **Unsatisfied**.
*Note: Only the top influential features are shown for manual input. Others are set to default values.*
""")
# Model
@st.cache_resource
def load_model():
try:
model = joblib.load('src/xgb_model.pkl')
return model
except FileNotFoundError:
st.error("Model file (xgb_model.pkl) not found.")
return None
model = load_model()
# Features
if model:
booster = model.get_booster()
all_features = booster.feature_names
importance_map = booster.get_score(importance_type='gain')
sorted_features = sorted(importance_map.items(), key=lambda x: x[1], reverse=True)
top_feature_names = [f[0] for f in sorted_features[:10]] # Top 10 features
if 'var15' not in top_feature_names and 'var15' in all_features:
top_feature_names.insert(0, 'var15')
# User Input
st.sidebar.header("Customer Profile")
st.sidebar.write("Adjust the values below:")
user_inputs = {}
if model:
for col in top_feature_names:
label = col
default_val = 0.0
min_val = 0.0
max_val = 1000000.0
step = 1.0
if col == 'var15':
label = "Customer Age"
default_val = 23.0
min_val = 5.0
max_val = 105.0
elif col == 'saldo_var30':
label = "Account Balance"
default_val = 0.0
elif col == 'var38':
label = "Mortgage Value"
default_val = 117310.97
val = st.sidebar.number_input(
label=label,
min_value=float(min_val) if col == 'var15' else None,
value=float(default_val),
step=step)
user_inputs[col] = val
# Prediction
col1, col2 = st.columns([1, 2])
with col1:
st.image("https://cdn-icons-png.flaticon.com/512/1077/1077114.png", width=150)
with col2:
st.subheader("Predict")
predict_btn = st.button("Calculate Satisfaction Score", type="primary")
if predict_btn and model:
input_data = {feature: 0 for feature in all_features}
for key, value in user_inputs.items():
if key in input_data:
input_data[key] = value
if 'var3' in input_data and 'var3' not in user_inputs:
input_data['var3'] = 2
df_single = pd.DataFrame([input_data])
df_single = df_single[all_features]
with st.spinner("Analyzing customer profile..."):
prob = model.predict_proba(df_single)[:, 1][0]
prediction = (prob > 0.5).astype(int)
st.divider()
col_res1, col_res2 = st.columns(2)
col_res1.metric(
label="Unhappiness Probability",
value=f"{prob:.2%}",
delta="High Risk" if prob > 0.5 else "Low Risk",
delta_color="inverse")
if prediction == 0:
col_res2.success("✅ Prediction: **SATISFIED** (Happy)")
st.balloons()
else:
col_res2.error("⚠️ Prediction: **UNSATISFIED** (Unhappy)")
st.warning("This customer is at high risk of churning or filing a complaint.")
with st.expander("See raw input data used for model"):
st.write(df_single)
elif not model:
st.warning("Please upload the 'xgb_model.pkl' file to the Space.") |