def setUp(self):
X_train, y_train, X_test, y_test = titanic_fare()
self.test_len = len(X_test)
train_names, test_names = titanic_names()
_, self.names = titanic_names()
model = CatBoostRegressor(iterations=5, verbose=0).fit(X_train, y_train)
explainer = RegressionExplainer(model, X_test, y_test, cats=['Deck', 'Embarked'])
X_cats, y_cats = explainer.X_merged, explainer.y
model = CatBoostRegressor(iterations=5, verbose=0).fit(X_cats, y_cats, cat_features=[8, 9])
self.explainer = RegressionExplainer(model, X_cats, y_cats, cats=['Sex'], idxs=X_test.index)
def dashboard_exp(model, X_data, y_data):
import dash_bootstrap_components as dbc
from explainerdashboard import RegressionExplainer, ExplainerDashboard
ExplainerDashboard(
RegressionExplainer(model, X_data, y_data),
bootstrap=dbc.themes.SANDSTONE,
importances=True,
model_summary=False,
contributions=True,
whatif=True,
shap_dependence=False,
shap_interaction=False,
decision_trees=False,
hide_whatifindexselector=True,
hide_whatifprediction=True,
hide_inputeditor=False,
hide_whatifcontributiongraph=False,
hide_whatifcontributiontable=True,
hide_whatifpdp=False,
hide_predindexselector=True,
hide_predictionsummary=True,
hide_contributiongraph=False,
hide_pdp=False,
hide_contributiontable=True,
hide_dropna=True,
hide_range=True,
hide_depth=True,
hide_sort=True,
hide_sample=True, # hide sample size input on pdp component
hide_gridlines=True, # hide gridlines on pdp component
hide_gridpoints=True,
hide_cats_sort=
True, # hide the sorting option for categorical features
hide_cutoff=
True, # hide cutoff selector on classification components
hide_percentage=
True, # hide percentage toggle on classificaiton components
hide_log_x=
True, # hide x-axis logs toggle on regression plots
hide_log_y=
True, # hide y-axis logs toggle on regression plots
hide_ratio=True, # hide the residuals type dropdown
hide_points=
True, # hide the show violin scatter markers toggle
hide_winsor=True, # hide the winsorize input
hide_wizard=
True, # hide the wizard toggle in lift curve component
hide_star_explanation=True,
).run()
if days_since_update > 7:
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")
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")
n_jobs=8,
num_parallel_tree=1,
objective='reg:squarederror',
random_state=42,
reg_alpha=1,
reg_lambda=0,
scale_pos_weight=1.0,
seed=42,
subsample=0.6000000000000001,
tree_method='exact',
validate_parameters=1,
verbosity=None)
X, Y = pd.read_csv('X.csv', index_col=0), pd.read_csv('Y.csv', index_col=0)
REmodel = model.fit(X, Y)
explainer = RegressionExplainer(REmodel,
X,
Y,
cats=cats,
descriptions=feature_descriptions,
units="$")
ExplainerDashboard(
explainer,
title='XGBoost Regression Model Explainer: Predicting House Prices',
description=
'This dashboard shows the inner workings of a fitted machine learning model, and explains its predictions.',
shap_interaction=False,
decision_trees=False).run(port=int(os.environ.get('PORT', 5000)))
clas_explainer = ClassifierExplainer(model,
X_test,
y_test,
cats=['Sex', 'Deck', 'Embarked'],
descriptions=feature_descriptions,
labels=['Not survived', 'Survived'])
_ = ExplainerDashboard(clas_explainer)
clas_explainer.dump(pkl_dir / "clas_explainer.joblib")
# regression
X_train, y_train, X_test, y_test = titanic_fare()
model = RandomForestRegressor(n_estimators=50,
max_depth=5).fit(X_train, y_train)
reg_explainer = RegressionExplainer(model,
X_test,
y_test,
cats=['Sex', 'Deck', 'Embarked'],
descriptions=feature_descriptions,
units="$")
_ = ExplainerDashboard(reg_explainer)
reg_explainer.dump(pkl_dir / "reg_explainer.joblib")
# multiclass
X_train, y_train, X_test, y_test = titanic_embarked()
model = RandomForestClassifier(n_estimators=50,
max_depth=5).fit(X_train, y_train)
multi_explainer = ClassifierExplainer(
model,
X_test,
y_test,
cats=['Sex', 'Deck'],
descriptions=feature_descriptions,
from explainerdashboard.explainers import RandomForestRegressionExplainer
from sklearn.ensemble import RandomForestRegressor
from sklearn import tree
from explainerdashboard import ClassifierExplainer, ExplainerDashboard, RegressionExplainer
from explainerdashboard.datasets import titanic_survive, feature_descriptions
from sklearn.model_selection import train_test_split
import pandas as pd
import numpy as np
imdb = pd.read_csv("Amélioration/Data/movies2.csv", encoding="latin-1")
imdb = imdb.rename(columns = {'11:14' :'film','7.2' : 'metascore','Crime' : 'genre', 'Greg Marcks':'realisateur', 'Henry Thomas' : 'acteur_1', 'Colin Hanks':'acteur_2' ,'6000000' : 'budget', '0': 'votes2', '0.1': 'vote', 'Aug 12, 2005': 'date'})
colonne = ['genre','acteur_1', 'acteur_2', 'realisateur']
imdb = pd.get_dummies(imdb, columns= colonne)
imdb = imdb.drop(columns= ['film', 'budget', 'votes2', 'vote', 'date'], axis = 1 )
X = imdb.loc[:, imdb.columns != 'metascore' ]
y = imdb.loc[:, imdb.columns == 'metascore' ]
X_train, X_test, y_train, y_test = train_test_split(X,y, test_size = 0.3, random_state=42)
model = RandomForestRegressor().fit(X_train, y_train)
explainer = RegressionExplainer(model, X_test, y_test)
db = ExplainerDashboard(explainer, title="Metascore de film",
whatif=False, # you can switch off tabs with bools
shap_interaction=False,
decision_trees=False)
ExplainerDashboard(explainer).run()