def test_predict_proba(self, data):
model = VWClassifier()
model.fit(data.x, data.y)
actual = model.predict_proba(data.x)
assert actual.shape[0] == 100
assert np.allclose(actual[0], [0.3997, 0.6003], atol=1e-4)
print(seenMovie)
print(metadata)
print("Data loaded")
print(seenMovie.shape, '\t', metadata.shape)
seenMovie = seenMovie.astype('int')
# split train and test set
X_train, X_test, y_train, y_test = train_test_split(metadata, seenMovie, test_size=0.3, random_state=256)
# build VW logistic regression model
# LogLossVal: 0.013283467177640678
# Mean Square Error of the Log for the 1st model: 0.00018478019510039388
print('Train\n', y_train)
model = VWClassifier(loss_function='logistic')
model.fit(X_train, y_train)
# predict model
y_pred = model.predict_proba(X_test)
print(y_pred)
print("Training complete for model 1...")
print("starting LogLoss...")
# get log loss for linear regression model
logLossVal = log_loss(y_test, y_pred, eps=1e-15, normalize=True, sample_weight=None, labels=None)
# r2_score_nnls = r2_score(y_test, y_pred)
# print("NNLS R2 score", r2_score_nnls)
# mse_1 = calculateMeanSquareError(y_test, y_pred)
# m1_recall = recall_score(y_test, y_pred, average='binary', zero_division=0)
# m1_precision = precision_score(y_test, y_pred, average='binary', zero_division=0)
# accuracy_m1 = accuracy_score(y_test, y_pred);
# print("Model 1 Accuracy: ", accuracy_m1)
print("LogLoss Model 1: ", logLossVal)
# print("Mean Square Error of the Log for the 1st model: ", mse_1)
