streamlit-shap
This component provides a wrapper to display SHAP plots in Streamlit.
Installation
pip install git+https://github.com/snehankekre/streamlit-shap
Example
import streamlit as st
from streamlit_shap import st_shap
import shap
from sklearn.model_selection import train_test_split
import xgboost
import numpy as np
import pandas as pd
@st.experimental_memo
def load_data():
return shap.datasets.adult()
@st.experimental_memo
def load_model(X, y):
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=7)
d_train = xgboost.DMatrix(X_train, label=y_train)
d_test = xgboost.DMatrix(X_test, label=y_test)
params = {
"eta": 0.01,
"objective": "binary:logistic",
"subsample": 0.5,
"base_score": np.mean(y_train),
"eval_metric": "logloss",
"tree_method": "gpu_hist"
}
model = xgboost.train(params, d_train, 10, evals = [(d_test, "test")], verbose_eval=100, early_stopping_rounds=20)
return model
st.title("SHAP in Streamlit")
# train XGBoost model
X,y = load_data()
X_display,y_display = shap.datasets.adult(display=True)
model = load_model(X, y)
# compute SHAP values
explainer = shap.Explainer(model, X)
shap_values = explainer(X)
st_shap(shap.plots.waterfall(shap_values[0]), height=300)
st_shap(shap.plots.beeswarm(shap_values), height=300)
explainer = shap.TreeExplainer(model)
shap_values = explainer.shap_values(X)
st_shap(shap.force_plot(explainer.expected_value, shap_values[0,:], X_display.iloc[0,:]), height=200, width=1000)
st_shap(shap.force_plot(explainer.expected_value, shap_values[:1000,:], X_display.iloc[:1000,:]), height=400, width=1000)
205 Jan 7, 2023
9 Jul 15, 2022
7 Sep 9, 2022
4 Dec 2, 2022
162 Nov 11, 2022
2 Nov 29, 2021
4 Jun 12, 2022
0 Jul 9, 2022
38 Dec 20, 2022
2 May 05, 2022
17 Dec 08, 2022
1 Jan 22, 2022
1k Jan 01, 2023
3 Dec 15, 2022
1 Aug 04, 2021
13.1k Jan 03, 2023
3 Jan 27, 2022
3.1k Jan 06, 2023
234 Dec 31, 2022
36 Dec 21, 2022
15 Oct 12, 2022
4 Oct 12, 2022
6.7k Jan 09, 2023
149 Dec 29, 2022
4 Jun 20, 2022
9 Aug 03, 2022
22 Oct 31, 2022
76 Dec 16, 2022