def generate_assets():
X_train, y_train, X_test, y_test = titanic_survive()
model = RandomForestClassifier(n_estimators=5, max_depth=2)
model.fit(X_train, y_train)
explainer = ClassifierExplainer(
model, X_test, y_test,
cats=[{'Gender': ['Sex_female', 'Sex_male', 'Sex_nan']},
'Deck', 'Embarked'],
labels=['Not survived', 'Survived'])
dashboard = ExplainerDashboard(explainer,
[
ShapDependenceComposite(explainer, title="Test Tab!"),
ShapDependenceComposite,
"importances"
], title="Test Title!")
pkl_dir = Path.cwd() / "tests" / "cli_assets"
explainer.dump(pkl_dir / "explainer.joblib")
explainer.to_yaml(pkl_dir / "explainer.yaml")
dashboard.to_yaml(pkl_dir / "dashboard.yaml",
explainerfile=str(pkl_dir / "explainer.joblib"))
return None
class DashboardTests(unittest.TestCase):
def setUp(self):
X_train, y_train, X_test, y_test = titanic_survive()
train_names, test_names = titanic_names()
self.model = RandomForestClassifier(n_estimators=5, max_depth=2)
self.model.fit(X_train, y_train)
self.explainer = ClassifierExplainer(
self.model, X_test, y_test,
cats=[{'Gender': ['Sex_female', 'Sex_male', 'Sex_nan']},
'Deck', 'Embarked'],
labels=['Not survived', 'Survived'])
self.dashboard = ExplainerDashboard(self.explainer,
[
ShapDependenceTab(self.explainer, title="Test Tab!"),
ShapDependenceTab,
"importances"
], title="Test Title!")
self.pkl_dir = Path.cwd() / "tests" / "cli_assets"
self.explainer.dump(self.pkl_dir / "explainer.joblib")
self.explainer.to_yaml(self.pkl_dir / "explainer.yaml")
self.dashboard.to_yaml(self.pkl_dir / "dashboard.yaml",
explainerfile=str(self.pkl_dir / "explainer.joblib"))
def test_yaml(self):
yaml = self.dashboard.to_yaml()
self.assertIsInstance(yaml, str)
def test_yaml_dict(self):
yaml_dict = self.dashboard.to_yaml(return_dict=True)
self.assertIsInstance(yaml_dict, dict)
self.assertIn("dashboard", yaml_dict)
def test_load_config_joblib(self):
db = ExplainerDashboard.from_config(
self.pkl_dir / "explainer.joblib",
self.pkl_dir / "dashboard.yaml")
self.assertIsInstance(db, ExplainerDashboard)
def test_load_config_yaml(self):
db = ExplainerDashboard.from_config(
self.pkl_dir / "dashboard.yaml")
self.assertIsInstance(db, ExplainerDashboard)
def test_load_config_explainer(self):
db = ExplainerDashboard.from_config(
self.explainer, self.pkl_dir / "dashboard.yaml")
self.assertIsInstance(db, ExplainerDashboard)
model = pickle.load(open(MODELS_DIR / 'general_model.pkl', 'rb'))
y = pd.read_csv(DATA_DIR / 'general_target.csv',
index_col=['Ticker']).drop(columns=['Date'])
X = pd.read_csv(DATA_DIR / f'general_features.csv',
index_col=['Ticker']).drop(columns=['Date'])
# Dashboard Explainer is fussy about Column Names
X.columns = X.columns.str.replace('.', '')
feature_names = model.get_booster().feature_names
feature_names = [x.replace('.', '') for x in feature_names]
model.get_booster().feature_names = feature_names
explainer = RegressionExplainer(model, X, y)
db = ExplainerDashboard(
explainer,
title="Stock Valuation Explainer",
description=
"Visit https://share.streamlit.io/gardnmi/fundamental-stock-prediction to see the model in use,",
shap_interaction=False,
precision='float32',
decision_trees=False)
db.to_yaml("dashboard.yaml",
explainerfile="explainer.joblib",
dump_explainer=True)
db = ExplainerDashboard.from_config("dashboard.yaml")
app = db.flask_server()
from explainerdashboard import RegressionExplainer, ExplainerDashboard
from explainerdashboard.custom import *
from joblib import load
import pandas as pd
from sklearn.model_selection import train_test_split
# Load model & data
dec_tree = load('dec_tree_v3.joblib')
df_data = pd.read_csv('data_v3_enc.csv')
# Prepare & split data
X = df_data.drop(['Duration', 'Timestamp'], axis=1)
y = df_data.Duration
Xt, X_small, yt, y_small = train_test_split(X, y, test_size=0.01, random_state=0)
exp = RegressionExplainer(dec_tree, X_small, y_small, cats=['Day_of_week', 'Hour', 'Vehicle', 'Position'])
# Build
db = ExplainerDashboard(exp, [ShapDependenceComposite, WhatIfComposite], hide_whatifpdp=True)
# Save
exp.dump("explainer.joblib")
db.to_yaml("dashboard.yaml")