def spline_classification_plot(ax, X, y, X_eval, y_eval, gam_ref):
# gam = LogisticGAM(s(0)).gridsearch(X, y)
# documentation of LogisticGAM: https://pygam.readthedocs.io/en/latest/api/logisticgam.html
gam = LogisticGAM(s(0, constraints='monotonic_inc',
n_splines=5)).gridsearch(X, y) # add a linear term
#XX = gam.generate_X_grid(term=0)
XX = np.linspace(0, 1, 100)
ax.plot(XX, gam.predict_proba(XX), c='g')
ax.plot(XX, gam.confidence_intervals(XX, width=0.95), c='r', ls='--')
# compute ece and acc after calibration
y_ = gam.predict_proba(X_eval)
ece = EceEval(np.array([1 - y_, y_]).T, y_eval, num_bins=100)
mce = MceEval(np.array([1 - y_, y_]).T, y_eval, num_bins=100)
brier = BrierEval(np.array([1 - y_, y_]).T, y_eval)
mse = MseEval(gam, gam_ref, num_bins=100)
acc = gam.accuracy(X_eval, y_eval)
ax.text(0.05,
0.75,
'ECE=%.4f\nMCE=%.4f\nBrier=%.4f\nACC=%.4f\nMSE=%.4f' %
(ece, mce, brier, acc, mse),
size=6,
ha='left',
va='center',
bbox={
'facecolor': 'green',
'alpha': 0.5,
'pad': 4
})
ax.set_xlim(0.0, 1.0)
ax.set_ylim(0.0, 1.0)
confi = gam.confidence_intervals(X_eval, width=0.95)
print gam.summary()
return ece, mce, brier, acc, mse, ax, confi
class AdaptiveLogisticGAM(BaseEstimator, RegressorMixin):
def __init__(self, param_grid=None, gam_params=None):
# create GAM
if gam_params is None:
gam_params = {}
self.model = LogisticGAM(**gam_params)
# set grid search parameters
if param_grid is None:
param_grid = GAM_GRID_BASE
self.param_grid = param_grid
def fit(self, X, y):
if isinstance(X, pd.DataFrame):
X = X.values
# fit using grid-search
self.model.gridsearch(X, y, progress=False, **self.param_grid)
def predict(self, X):
if isinstance(X, pd.DataFrame):
X = X.values
return self.model.predict(X)
def predict_proba(self, X):
if isinstance(X, pd.DataFrame):
X = X.values
return self.model.predict_proba(X)
def spline_calibration(X, y):
gam = LogisticGAM(s(0, constraints='monotonic_inc')).gridsearch(
X, y) # add a linear term
# documentation of LogisticGAM: https://pygam.readthedocs.io/en/latest/api/logisticgam.html
# gam = LogisticGAM(s(0, constraints='monotonic_inc')).gridsearch(X, y) # add a linear term
# compute ece and acc after calibration
y_ = gam.predict_proba(X)
return y_
def calibrate_propensities(propensities, treatment):
"""Post-hoc calibration of propensity scores given the true treatments
Args:
propensities: propensity scores
treatment: treatment indicator
Returns:
p: calibrated version of the propensities given
"""
gam = LogisticGAM(s(0)).fit(propensities, treatment)
return gam.predict_proba(propensities)
def calibrate(ps, treatment):
"""Calibrate propensity scores with logistic GAM.
Ref: https://pygam.readthedocs.io/en/latest/api/logisticgam.html
Args:
ps (numpy.array): a propensity score vector
treatment (numpy.array): a binary treatment vector (0: control, 1: treated)
Returns:
(numpy.array): a calibrated propensity score vector
"""
gam = LogisticGAM(s(0)).fit(ps, treatment)
return gam.predict_proba(ps)
def spline_classification(X, y, X_eval, y_eval, gam_ref):
# gam = LogisticGAM(s(0)).gridsearch(X, y)
# documentation of LogisticGAM: https://pygam.readthedocs.io/en/latest/api/logisticgam.html
gam = LogisticGAM(s(0, constraints='monotonic_inc',
n_splines=5)).gridsearch(X, y) # add a linear term
#XX = gam.generate_X_grid(term=0)
# compute ece and acc after calibration
y_ = gam.predict_proba(X_eval)
ece = EceEval(np.array([1 - y_, y_]).T, y_eval, num_bins=100)
mce = MceEval(np.array([1 - y_, y_]).T, y_eval, num_bins=100)
brier = BrierEval(np.array([1 - y_, y_]).T, y_eval)
mse = MseEval(gam, gam_ref, num_bins=100)
acc = gam.accuracy(X_eval, y_eval)
# compute the confidence on datapoints of X_eval
confi = gam.confidence_intervals(X_eval, width=0.95)
return ece, mce, brier, acc, mse, confi
rfc_predictions_2020
rfc_predictions_2020.to_csv("rfc_predictions.csv")
##### ----- ##### ----- ##### ----- ##### -----# #### ----- ##### ----- ##### ----- ##### ----- #####
# Model 1.3 - Generalized Additive Models
from pygam import LogisticGAM
#Fit a GAM model with the default parameters
gam_model = LogisticGAM()
gam_model.fit(X_train, y_train)
gam_pred_prob = gam_model.predict_proba(X_test)
gam_preds, complete_gam_dat = top_15_predictions(entire_test_data, gam_pred_prob )
gam_performance = all_nba_test_report(complete_gam_dat)
players_missed(complete_gam_dat)
gam_predict_probs_2020 = gam_model.predict_proba(features_2020)
gam_predict_binary_2020 = gam_model.predict(features_2020)
ds = load_breast_cancer()
X, y = ds.data, ds.target
#select first 6 features only
X = X[:, 0:6]
selected_features = ds.feature_names[0:6]
#-----------------------------------------------------
#Fit a model with the default parameters
gam = LogisticGAM().fit(X, y)
gam.summary()
roc_auc_score(y, gam.predict_proba(X)) #0.994173140954495
gam.accuracy(X, y) #0.9560632688927944
#-----------------------------------------------------
# Explore and interpret individual features
plt.ion()
plt.rcParams['figure.figsize'] = (28, 8)
fig, axs = plt.subplots(1, X.shape[1])
for i, ax in enumerate(axs):
XX = gam.generate_X_grid(term=i, meshgrid=True)
pdep, confi = gam.partial_dependence(term=i,
X=XX,
meshgrid=True,
acc_loggamc = cross_val_score(gam, X_train_scaled, Y_train, cv=10, scoring='accuracy').mean()
print('acc_loggam_cross-validation, train_scaled',acc_loggamc)
# make predictions for testing set
Y_scaler_pred_class = logreg.predict(X_test_scaled)
# calculate testing accuracy
from sklearn import metrics
print('\n ------------------------------------------------------------------')
print("\n calculate testing accuracy (M1. X_train_scaled):", metrics.accuracy_score(Y_test, Y_scaler_pred_class))
print('\n ------------------------------------------------------------------')
# ROC curves and AUC
# https://www.medcalc.org/manual/roc-curves.php
# predict probability of survival
Y_scaler_pred_prob_GAM = gam.predict_proba(X_test_scaled)[:, 1]
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = (8, 6)
plt.rcParams['font.size'] = 14
# plot ROC curve. Receiver Operating Characteristic (ROC) curve the true positive rate (Sensitivity)
fpr, tpr, thresholds = metrics.roc_curve(Y_test, Y_scaler_pred_prob_GAM)
plt.rcParams['figure.figsize'] = (8, 6)
plt.rcParams['font.size'] = 14
# plot ROC curve. Receiver Operating Characteristic (ROC) curve the true positive rate (Sensitivity)
fpr, tpr, thresholds = metrics.roc_curve(Y_test, Y_scaler_pred_prob)
fig = plt.figure()
fig.subplots_adjust(bottom=0)
fig.subplots_adjust(top=1)
