def predict(self, X):
'''
This function should provide predictions of labels on (test) data.
Here we just return zeros...
Make sure that the predicted values are in the correct format for the scoring
metric. For example, binary classification problems often expect predictions
in the form of a discriminant value (if the area under the ROC curve it the metric)
rather that predictions of the class labels themselves. For multi-class or multi-labels
problems, class probabilities are often expected if the metric is cross-entropy.
Scikit-learn also has a function predict-proba, we do not require it.
The function predict eventually can return probabilities.
'''
Prepro = Preprocessor()
Prepro.pip0(10)
Prepro.fit_transform(X,y=None)
num_test_samples = len(X)
if X.ndim>1: num_feat = len(X[0])
print("PREDICT: dim(X)= [{:d}, {:d}]".format(num_test_samples, num_feat))
if (self.num_feat != num_feat):
print("ARRGH: number of features in X does not match training data!")
print("PREDICT: dim(y)= [{:d}, {:d}]".format(num_test_samples, self.num_labels))
output= self.clf.predict(X)
return output
def fit(self, X, y):
'''
This function should train the model parameters.
Here we do nothing in this example...
Args:
X: Training data matrix of dim num_train_samples * num_feat.
y: Training label matrix of dim num_train_samples * num_labels.
Both inputs are numpy arrays.
For classification, labels could be either numbers 0, 1, ... c-1 for c classe
or one-hot encoded vector of zeros, with a 1 at the kth position for class k.
The AutoML format support on-hot encoding, which also works for multi-labels problems.
Use data_converter.convert_to_num() to convert to the category number format.
For regression, labels are continuous values.
'''
Prepro = Preprocessor()
Prepro.pip0(10)
Prepro.fit_transform(X, y)
self.num_train_samples = len(X)
if X.ndim>1: self.num_feat = len(X[0])
print("FIT: dim(X)= [{:d}, {:d}]".format(self.num_train_samples, self.num_feat))
num_train_samples = len(y)
if y.ndim>1: self.num_labels = len(y[0])
print("FIT: dim(y)= [{:d}, {:d}]".format(num_train_samples, self.num_labels))
if (self.num_train_samples != num_train_samples):
print("ARRGH: number of samples in X and y do not match!")
###### Baseline models ######
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import LinearRegression
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.svm import SVR
# Comment and uncomment right lines in the following to choose the model
#self.clf = GaussianNB()
#self.clf = LinearRegression()
#self.clf = DecisionTreeRegressor()
#self.clf = RandomForestRegressor()
#self.clf = KNeighborsRegressor()
#self.clf = SVR(C=1.0, epsilon=0.2)
if self.is_trained==False:
self.clf=self.selection_hyperparam(X, y)
# self.clf=self.selection_hyperparam__(X, y)
self.is_trained=True