File size: 4,968 Bytes
e38bc03 d55626a e38bc03 d55626a e38bc03 f7a8a95 e38bc03 d55626a e38bc03 | 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 | import streamlit as st
import pandas as pd
import numpy as np
import joblib
from huggingface_hub import hf_hub_download
# 1. Load Model from Hugging Face Model Hub
# ============================================================
MODEL_REPO_ID = "Quantum9999/Tourism-Package-Prediction-Model" # Corrected to the new model repo ID
DATASET_REPO_ID = "Quantum9999/Tourism-Package-Prediction" # Repo where preprocessor is stored
MODEL_FILENAME = "xgb_model.pkl"
@st.cache_resource
def load_model():
# Download the model from the MODEL_REPO_ID with repo_type="model"
model_path = hf_hub_download(repo_id=MODEL_REPO_ID, filename=MODEL_FILENAME, repo_type="model")
model = joblib.load(model_path)
return model
model = load_model()
# 2. Streamlit UI
# ============================================================
st.title(" Wellness Tourism Package Purchase Prediction")
st.write("Fill in the customer details below to predict whether they will purchase the new Wellness Tourism Package.")
st.markdown("---")
# 3. User Inputs
# ============================================================
def user_input_form():
Age = st.number_input("Age", min_value=1, max_value=100, value=30)
CityTier = st.selectbox("City Tier", [1, 2, 3])
NumberOfPersonVisiting = st.number_input("Number of People Visiting", min_value=1, max_value=10, value=1)
PreferredPropertyStar = st.selectbox("Preferred Property Star", [3, 4, 5])
NumberOfTrips = st.number_input("Number of Trips per Year", min_value=0, max_value=20, value=2)
NumberOfChildrenVisiting = st.number_input("Children Visiting (Under 5 Years)", min_value=0, max_value=5, value=0)
MonthlyIncome = st.number_input("Monthly Income", min_value=1000, max_value=1000000, value=30000)
PitchSatisfactionScore = st.selectbox("Pitch Satisfaction Score", [1, 2, 3, 4, 5])
NumberOfFollowups = st.number_input("Number of Follow-ups", min_value=1, max_value=10, value=2)
DurationOfPitch = st.number_input("Duration of Pitch (Minutes)", min_value=1, max_value=60, value=15)
TypeofContact = st.selectbox("Type of Contact", ["Company Invited", "Self Enquiry"])
Occupation = st.selectbox("Occupation", ["Salaried", "Self Employed", "Small Business", "Large Business", "Free Lancer"])
Gender = st.selectbox("Gender", ["Male", "Female"])
MaritalStatus = st.selectbox("Marital Status", ["Married", "Single", "Divorced"])
Passport = st.selectbox("Passport", [0, 1])
OwnCar = st.selectbox("Owns Car?", [0, 1])
Designation = st.selectbox("Designation", ["Junior", "Senior", "Manager", "Executive", "Other"])
ProductPitched = st.selectbox("Product Pitched", ["Basic", "Standard", "Deluxe", "Super Deluxe", "King"])
# Create DataFrame
data = pd.DataFrame({
"Age": [Age],
"CityTier": [CityTier],
"NumberOfPersonVisiting": [NumberOfPersonVisiting],
"PreferredPropertyStar": [PreferredPropertyStar],
"NumberOfTrips": [NumberOfTrips],
"NumberOfChildrenVisiting": [NumberOfChildrenVisiting],
"MonthlyIncome": [MonthlyIncome],
"PitchSatisfactionScore": [PitchSatisfactionScore],
"NumberOfFollowups": [NumberOfFollowups],
"DurationOfPitch": [DurationOfPitch],
"TypeofContact": [TypeofContact],
"Occupation": [Occupation],
"Gender": [Gender],
"MaritalStatus": [MaritalStatus],
"Passport": [Passport],
"OwnCar": [OwnCar],
"Designation": [Designation],
"ProductPitched": [ProductPitched]
})
return data
user_data = user_input_form()
st.markdown("---")
# 4. Preprocess User Input → MATCH Training Preprocessing
# ============================================================
# Categorical + numerical split (same as prep.py)
numerical_features = [
'Age', 'CityTier', 'NumberOfPersonVisiting', 'PreferredPropertyStar',
'NumberOfTrips', 'NumberOfChildrenVisiting', 'MonthlyIncome',
'PitchSatisfactionScore', 'NumberOfFollowups', 'DurationOfPitch'
]
categorical_features = [
'TypeofContact', 'Occupation', 'Gender', 'MaritalStatus',
'Passport', 'OwnCar', 'Designation', 'ProductPitched'
]
# Load preprocessors (generated in prep.py) from the DATASET_REPO_ID
preprocessor_path = hf_hub_download(repo_id=DATASET_REPO_ID, filename="preprocessing_pipeline.pkl", repo_type="dataset")
preprocessor = joblib.load(preprocessor_path)
processed_user_data = preprocessor.transform(user_data)
# 5. Make Prediction
# ============================================================
if st.button("Predict"):
prediction = model.predict(processed_user_data)[0]
proba = model.predict_proba(processed_user_data)[0][1]
st.subheader(" Prediction Result")
if prediction == 1:
st.success(f" Customer is LIKELY to purchase the Wellness Tourism Package! (Confidence: {proba:.2f})")
else:
st.error(f" Customer is NOT likely to purchase the package. (Confidence: {proba:.2f})")
|