def predict_prob(self, data, load_classifier=False):
if load_classifier:
self.classifier = DataHandling.load_data(Constants.model_path + 'classifier_NB.pickle')
return self.classifier.predict_prob(data)
# fileNameTestData = "data/test.csv" # well. obviously we dont hand this one out
topN = 5
termVectors = json.load(open(fileNameTermVectors))
train_data = pd.read_csv(fileNameTrainData)
""":type: pd.DataFrame"""
# testData = pd.read_csv(fileNameTestData)
"""
Test model on unseen data. After each prediction step, you may update you model. This is not mandatory though.
"""
# Loading the trained model in case we do not want to train on new data
model = DataHandling.load_data(Constants.model_path + 'Model_NB.pickle')
os_list = DataHandling.load_data(Constants.model_path + 'os_list.pickle')
publisher_list = DataHandling.load_data(Constants.model_path + 'publisher_list.pickle')
#In case there is a new termVectors file we use this to extract features, I assume it is because articles will be updated.
feature_extraction = FeatureExtraction()
[article_word_count, word_tfidf, publishers, article_numbers] = feature_extraction.prepare_dictionary_article(termVectors)
# #For testing train data the same as test data
testData = train_data
article_popularity = DataHandling.load_data(Constants.model_path + 'article_popularity.pickle')
train_data = DataHandling.load_data(Constants.model_path + 'train_data_with_article_distances.pickle')
for (rowNum, row) in testData.iterrows():
inputFeatures = row[["Publisher", "Osfamily", "ItemSrc", "UserID", "UserClicksAd"]]
