Download src/streamlit_app.py from sellacio/ml-pr: direct link, hf CLI and curl.
- Browser
- Download file 8.59 kB
-
https://huggingface.co/spaces/sellacio/ml-pr/resolve/main/src/streamlit_app.py
- Command line
-
hf download hf://spaces/sellacio/ml-pr/src/streamlit_app.py
-
curl -L -o streamlit_app.py https://huggingface.co/spaces/sellacio/ml-pr/resolve/main/src/streamlit_app.py
8.59 kB
| import os | |
| import streamlit as st | |
| import pandas as pd | |
| import numpy as np | |
| import joblib | |
| import shap | |
| import matplotlib.pyplot as plt | |
| from sklearn.base import BaseEstimator, TransformerMixin | |
| import xgboost as xgb | |
| # ============================================================================ | |
| # 1. КАСТОМНЫЕ КЛАССЫ C ПОДДЕРЖКОЙ АТРИБУТОВ | |
| # ============================================================================ | |
| class AirlineFeatureEngineer(BaseEstimator, TransformerMixin): | |
| def fit(self, X, y=None): | |
| return self | |
| def transform(self, X): | |
| X = X.copy() | |
| X["ArrivalDelay_missing"] = X["Arrival Delay in Minutes"].isna().astype(int) | |
| dep = X["Departure Delay in Minutes"].fillna(X["Departure Delay in Minutes"].median()) | |
| arr = X["Arrival Delay in Minutes"].fillna(X["Arrival Delay in Minutes"].median()) | |
| X["Total Delay Minutes"] = dep + arr | |
| X = X.drop(columns=["Departure Delay in Minutes", "Arrival Delay in Minutes"]) | |
| return X | |
| class EarlyStoppingXGBClassifier(xgb.XGBClassifier): | |
| def __init__(self, **kwargs): | |
| # Явно задаём атрибуты, которые могут потребоваться при predict | |
| self.verbosity = kwargs.pop('verbosity', 1) | |
| self.enable_categorical = kwargs.pop('enable_categorical', False) | |
| super().__init__(verbosity=self.verbosity, enable_categorical=self.enable_categorical, **kwargs) | |
| # Необходимо для scikit-learn > 1.6 | |
| def __sklearn_tags__(self): | |
| tags = super().__sklearn_tags__() | |
| tags.input_tags.categorical = self.enable_categorical | |
| return tags | |
| def _more_tags(self): | |
| tags = super()._more_tags() | |
| tags["categorical"] = self.enable_categorical | |
| return tags | |
| # ============================================================================ | |
| # 2. ЗАГРУЗКА МОДЕЛЕЙ | |
| # ============================================================================ | |
| def load_models(): | |
| base_dir = os.path.dirname(__file__) # папка src/ | |
| xgb_path = os.path.join(base_dir, 'xgb_pipeline.pkl') | |
| knn_path = os.path.join(base_dir, 'knn_pipeline.pkl') | |
| xgb_model = joblib.load(xgb_path) | |
| knn_model = joblib.load(knn_path) | |
| return xgb_model, knn_model | |
| # ============================================================================ | |
| # 3. ФУНКЦИЯ ДЛЯ SHAP | |
| # ============================================================================ | |
| def get_shap_for_instance(model, input_df_raw): | |
| pre_pipeline = model[:-1] # всё, кроме классификатора | |
| clf = model.named_steps['clf'] | |
| X_trans = pre_pipeline.transform(input_df_raw) | |
| pred = clf.predict(X_trans)[0] | |
| proba = clf.predict_proba(X_trans)[0][1] | |
| # SHAP: TreeExplainer для XGBoost, KernelExplainer для KNN | |
| if hasattr(clf, 'get_booster') or isinstance(clf, xgb.XGBClassifier): | |
| explainer = shap.TreeExplainer(clf) | |
| shap_values = explainer.shap_values(X_trans) | |
| if isinstance(shap_values, list): | |
| shap_vals = shap_values[1][0] if len(shap_values) > 1 else shap_values[0][0] | |
| else: | |
| shap_vals = shap_values[0] if len(shap_values.shape) == 3 else shap_values[0] | |
| base_val = explainer.expected_value | |
| if isinstance(base_val, (list, np.ndarray)): | |
| base_val = base_val[1] if len(base_val) > 1 else base_val[0] | |
| else: | |
| # KNN — KernelExplainer (background = первые 100 объектов) | |
| background = X_trans[:min(100, len(X_trans))] | |
| explainer = shap.KernelExplainer(clf.predict_proba, background) | |
| shap_values = explainer.shap_values(X_trans) | |
| shap_vals = shap_values[1][0] if len(shap_values) == 2 else shap_values[0][0] | |
| base_val = explainer.expected_value[1] if isinstance(explainer.expected_value, (list, np.ndarray)) else explainer.expected_value | |
| # Имена признаков | |
| try: | |
| all_feature_names = model.named_steps['preprocessor'].get_feature_names_out() | |
| selector_mask = model.named_steps['selector'].get_support() | |
| feature_names = all_feature_names[selector_mask] | |
| except: | |
| feature_names = [f"feature_{i}" for i in range(X_trans.shape[1])] | |
| return pred, proba, shap_vals, base_val, feature_names, X_trans[0] | |
| # ============================================================================ | |
| # 4. ИНТЕРФЕЙС STREAMLIT | |
| # ============================================================================ | |
| st.set_page_config(page_title="✈️ Passenger Satisfaction", layout="wide") | |
| st.title("✈️ Airline Passenger Satisfaction Prediction") | |
| st.markdown("Compare **XGBoost** and **K-Nearest Neighbors**.") | |
| with st.spinner("Loading models..."): | |
| xgb_model, knn_model = load_models() | |
| model_choice = st.radio("Select model", ["XGBoost", "KNN"], horizontal=True) | |
| with st.form("input_form"): | |
| col1, col2 = st.columns(2) | |
| with col1: | |
| gender = st.selectbox("Gender", ["Male", "Female"]) | |
| customer_type = st.selectbox("Customer Type", ["Loyal Customer", "disloyal Customer"]) | |
| age = st.slider("Age", 0, 100, 30) | |
| travel_type = st.selectbox("Type of Travel", ["Personal Travel", "Business travel"]) | |
| flight_class = st.selectbox("Class", ["Eco", "Eco Plus", "Business"]) | |
| flight_distance = st.number_input("Flight Distance", 0, 5000, 500) | |
| with col2: | |
| inflight_wifi = st.slider("Inflight wifi service", 0, 5, 3) | |
| dep_arr_convenient = st.slider("Departure/Arrival time convenient", 0, 5, 3) | |
| ease_booking = st.slider("Ease of Online booking", 0, 5, 3) | |
| gate_loc = st.slider("Gate location", 0, 5, 3) | |
| food_drink = st.slider("Food and drink", 0, 5, 3) | |
| online_boarding = st.slider("Online boarding", 0, 5, 3) | |
| seat_comfort = st.slider("Seat comfort", 0, 5, 3) | |
| inflight_entertainment = st.slider("Inflight entertainment", 0, 5, 3) | |
| onboard_service = st.slider("On-board service", 0, 5, 3) | |
| leg_room = st.slider("Leg room service", 0, 5, 3) | |
| baggage_handling = st.slider("Baggage handling", 0, 5, 3) | |
| checkin_service = st.slider("Checkin service", 0, 5, 3) | |
| inflight_service = st.slider("Inflight service", 0, 5, 3) | |
| cleanliness = st.slider("Cleanliness", 0, 5, 3) | |
| dep_delay = st.number_input("Departure Delay (min)", 0.0, 500.0, 0.0) | |
| arr_delay = st.number_input("Arrival Delay (min)", 0.0, 500.0, 0.0) | |
| submitted = st.form_submit_button("Predict") | |
| if submitted: | |
| input_data = { | |
| "Gender": gender, "Customer Type": customer_type, "Age": age, | |
| "Type of Travel": travel_type, "Class": flight_class, | |
| "Flight Distance": flight_distance, | |
| "Inflight wifi service": inflight_wifi, | |
| "Departure/Arrival time convenient": dep_arr_convenient, | |
| "Ease of Online booking": ease_booking, "Gate location": gate_loc, | |
| "Food and drink": food_drink, "Online boarding": online_boarding, | |
| "Seat comfort": seat_comfort, "Inflight entertainment": inflight_entertainment, | |
| "On-board service": onboard_service, "Leg room service": leg_room, | |
| "Baggage handling": baggage_handling, "Checkin service": checkin_service, | |
| "Inflight service": inflight_service, "Cleanliness": cleanliness, | |
| "Departure Delay in Minutes": dep_delay, "Arrival Delay in Minutes": arr_delay | |
| } | |
| input_df = pd.DataFrame([input_data]) | |
| model = xgb_model if model_choice == "XGBoost" else knn_model | |
| model_name = model_choice | |
| pred, proba, shap_vals, base_val, feat_names, _ = get_shap_for_instance(model, input_df) | |
| st.subheader(f"🔮 Prediction ({model_name})") | |
| st.success(f"✅ Satisfied (prob: {proba:.2f})" if pred == 1 else f"❌ Not satisfied (prob: {1-proba:.2f})") | |
| st.subheader("📊 SHAP Explanation") | |
| exp = shap.Explanation(values=shap_vals, base_values=base_val, data=np.zeros(len(feat_names)), feature_names=feat_names) | |
| fig, ax = plt.subplots(figsize=(10, 6)) | |
| shap.plots.waterfall(exp, max_display=12, show=False) | |
| plt.tight_layout() | |
| st.pyplot(fig) | |
| plt.close() | |
| with st.expander("Compare with other model"): | |
| other = knn_model if model_name == "XGBoost" else xgb_model | |
| other_pred = other.predict(input_df)[0] | |
| other_proba = other.predict_proba(input_df)[0][1] | |
| st.write(f"**{other_name}** predicts: {'Satisfied' if other_pred==1 else 'Not satisfied'} (prob: {other_proba:.2f})") | |