##############################################################################
# Create CV
# -------------------------------------------
RSKF = RandomStratifiedKFold(n_splits=2, random_state=12, verbose=False)
##############################################################################
# Initialize Random-Forest
# ---------------------------
classifier = RandomForestClassifier()
##############################################################################
# Start learning
# ---------------------------
SL = SuperLearner(classifier=classifier,
param_grid=dict(n_estimators=[10, 100]))
SL.fit(X, y, cv=RSKF)
##############################################################################
# Get kappa from each fold
# ---------------------------
for stats in SL.get_stats_from_cv(confusion_matrix=False, kappa=True):
print(stats['kappa'])
##############################################################################
# Get each confusion matrix from folds
# -----------------------------------------------
cms = []
for stats in SL.get_stats_from_cv(confusion_matrix=True):
cms.append(stats['confusion_matrix'])
# Initialize Random-Forest and metrics # -------------------------------------- classifier = RandomForestClassifier(random_state=12,n_jobs=1) # kappa = metrics.make_scorer(metrics.cohen_kappa_score) f1_mean = metrics.make_scorer(metrics.f1_score,average='micro') scoring = dict(kappa=kappa,f1_mean=f1_mean,accuracy='accuracy') ############################################################################## # Start learning # --------------------------- # sklearn will compute different metrics, but will keep best results from kappa (refit='kappa') SL = SuperLearner(classifier=classifier,param_grid = dict(n_estimators=[10]),n_jobs=1,verbose=1) SL.fit(X,y,cv=SKF,scoring=kappa) # ============================================================================= # ############################################################################## # # Read the model # # ------------------- # print(SL.model) # print(SL.model.cv_results_) # print(SL.model.best_score_) # # ############################################################################## # # Get F1 for every class from best params # # -----------------------------------------------
##############################################################################
# Create list of different CV
# ---------------------------
CVs = [
cross_validation.RandomStratifiedKFold(n_splits=2),
cross_validation.LeavePSubGroupOut(valid_size=0.5),
cross_validation.LeaveOneSubGroupOut(),
StratifiedKFold(n_splits=2, shuffle=True) #from sklearn
]
kappas = []
for cv in CVs:
SL = SuperLearner(classifier=classifier,
param_grid=dict(n_estimators=[50, 100]),
n_jobs=1)
SL.fit(X, y, group=g, cv=cv)
print('Kappa for ' + str(type(cv).__name__))
cvKappa = []
for stats in SL.get_stats_from_cv(confusion_matrix=False, kappa=True):
print(stats['kappa'])
cvKappa.append(stats['kappa'])
kappas.append(cvKappa)
print(20 * '=')
##########################
# Plot example
##############################################################################
# Initialize Random-Forest and metrics
# --------------------------------------
classifier = RandomForestClassifier(random_state=12, n_jobs=1)
kappa = metrics.make_scorer(metrics.cohen_kappa_score)
f1_mean = metrics.make_scorer(metrics.f1_score, average='micro')
scoring = dict(kappa=kappa, f1_mean=f1_mean, accuracy='accuracy')
##############################################################################
# Start learning
# ---------------------------
# sklearn will compute different metrics, but will keep best results from kappa (refit='kappa')
SL = SuperLearner(classifier=classifier,
param_grid=dict(n_estimators=[10]),
n_jobs=1,
verbose=1)
##############################################################################
# Create or use custom function
def reduceBands(X, bandToKeep=[0, 2]):
# this function get the first and the last band
X = X[:, bandToKeep].reshape(-1, len(bandToKeep))
return X
# add this function to learnAndPredict class
SL.customize_array(reduceBands)