# 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')
LAP = learnAndPredict(n_jobs=1,verbose=1)
LAP.learnFromRaster(raster,vector,field,cv=SKF,
classifier=classifier,param_grid=dict(n_estimators=[10]),
scoring=kappa)
##############################################################################
# Read the model
# -------------------
print(LAP.model)
print(LAP.model.cv_results_)
print(LAP.model.best_score_)
##############################################################################
# Get F1 for every class from best params
# -------------------------------------------
RSKF = RandomStratifiedKFold(n_splits=2,
random_state=12,verbose=False)
##############################################################################
# Initialize Random-Forest
# ---------------------------
classifier = RandomForestClassifier()
##############################################################################
# Start learning
# ---------------------------
LAP = learnAndPredict()
LAP.learnFromRaster(raster,vector,field,cv=RSKF,
classifier=classifier,param_grid=dict(n_estimators=[10,100]))
##############################################################################
# Get kappa from each fold
# ---------------------------
for stats in LAP.getStatsFromCV(confusionMatrix=False,kappa=True):
print(stats['kappa'])
##############################################################################
# Get each confusion matrix from folds
# -----------------------------------------------
cms = []
for stats in LAP.getStatsFromCV(confusionMatrix=True):
classifier = RandomForestClassifier(random_state=12,n_jobs=1)
##############################################################################
# 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=[]
LAP = learnAndPredict(n_jobs=1)
for cv in CVs :
LAP.learnFromRaster(raster,vector,inField=field,group=group,cv=cv,
classifier=classifier,param_grid=dict(n_estimators=[50,100]))
print('Kappa for '+str(type(cv).__name__))
cvKappa = []
for stats in LAP.getStatsFromCV(confusionMatrix=False,kappa=True):
print(stats['kappa'])
cvKappa.append(stats['kappa'])
kappas.append(cvKappa)
print(20*'=')