class BasePredictions:
def __init__(self, **kwargs):
self.X = kwargs.get("X")
self.y = kwargs.get("y")
self.combs = kwargs.get("combs")
self.clf = kwargs.get("clf")
# arguments with default values
self.top = kwargs.get("top", 20)
self.mean_fpr = np.linspace(0, 1, 100)
self.n_estimators = kwargs.get("n_estimators", 500)
self.class_weight = kwargs.get("class_weight", "balanced")
self.min_samples_split = kwargs.get("min_samples_split", 3)
self.min_samples_leaf = kwargs.get("min_samples_leaf", 3)
self.colsample_bytree = kwargs.get("colsample_bytree", 0.6)
self.learning_rate = kwargs.get("learning_rate", 0.1)
self.random_state = kwargs.get("random_state", 125)
self.max_depth = kwargs.get("max_depth", None)
self.objective = kwargs.get("objective", 'binary:logistic')
self.scale_pos_weight = kwargs.get("scale_pos_weight", 1)
#for neural net
self.layers = kwargs.get("layers", 1)
self.dropout = kwargs.get("dropout", 0.1)
self.nodes = kwargs.get("nodes", 128)
self.epochs = kwargs.get("epochs", 400)
self.steps = kwargs.get("steps", 64)
self.learning_rate_deep = kwargs.get("learning_rate_deep", 0.001)
self.beta_1 = kwargs.get("beta_1", 0.9)
self.beta_2 = kwargs.get("beta_2", 0.999)
self._set_classifier()
self.predicted = dict()
self.topfeat = dict()
self.fpr = dict()
self.tpr = dict()
self.tprs = dict()
self.auc = dict()
self.precision = dict()
self.recall = dict()
self.avprec = dict()
def _set_classifier(self):
if self.clf.lower() == "randomforest":
self.clf = RandomForestClassifier(
bootstrap=True,
class_weight=self.class_weight,
max_depth=self.max_depth,
n_estimators=self.n_estimators,
max_features='sqrt',
min_samples_split=self.min_samples_split,
min_samples_leaf=self.min_samples_leaf,
random_state=self.random_state,
n_jobs=-1)
elif self.clf.lower() == "xgboost":
if self.max_depth is None:
self.max_depth = 5
self.clf = xgb.XGBClassifier(
learning_rate=self.learning_rate,
colsample_bytree=self.colsample_bytree,
random_state=self.random_state,
max_depth=self.max_depth,
n_estimators=self.n_estimators,
scale_pos_weight=self.scale_pos_weight,
objective=self.objective,
n_jobs=-1)
elif self.clf.lower() == "neural_network":
def Neural_network(dropout=0.1,
nodes=128,
layers=1,
learning_rate_deep=0.001,
beta_1=0.99,
beta_2=0.99):
clf = Sequential()
for i in range(self.layers):
#With BN
#clf.add(Dense(self.nodes, activation="linear", use_bias="False"))
#clf.add(BatchNormalization())
#clf.add(Activation("relu"))
#clf.add(Dropout(self.dropout))
#Without BN
#LeakyReLU
#clf.add(Dense(self.nodes))
#clf.add(LeakyReLU())
#ReLU
clf.add(Dense(self.nodes, activation="relu"))
clf.add(Dropout(self.dropout))
clf.add(Dense(3, activation="softmax"))
opt = keras.optimizers.Adam(
learning_rate=self.learning_rate_deep,
beta_1=self.beta_1,
beta_2=self.beta_2)
clf.compile(
loss=tf.keras.losses.SparseCategoricalCrossentropy(),
optimizer=opt,
metrics=["accuracy"
]) #other option loss = "binary_crossentropy"
return clf
self.clf = KerasClassifier(
Neural_network,
epochs=self.epochs,
steps_per_epoch=self.steps,
dropout=self.dropout,
nodes=self.nodes,
layers=self.layers,
learning_rate_deep=self.learning_rate_deep,
beta_1=self.beta_1,
beta_2=self.beta_2) #class_weight=self.class_weight
else:
raise ValueError(
"only randomforest, xgboost and neural_network are supported")
