""":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"]]
#Check if user has a history
number_times_clicked = row["UserClicksAd"]
#For users with no history pick the most popular item
if number_times_clicked == 0:
""" Prepare data for trianing and testing # """ fileNameTrainData = "data/train.csv" fileNameTermVectors = "data/termVectorsPerPublisher.json" # 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) # Feature Extraction part # Running feature extraction to create word dictionary, word counts, article grouping (distances) feature_extraction = FeatureExtraction() [train_data, article_popularity, os_list, publisher_list] = feature_extraction.prepare_features(train_data, termVectors) #Taking only users that have historically clicked into training. train_data = train_data.loc[train_data['UserClicksAd'] > 0] #Balancing training data #Since the dataset is imbalanced, we balance negative and positive samples for training. # positive_samples = train_data.loc[train_data['Output'] == 1] # positive_samples_count = train_data.loc[train_data['Output'] == 1].shape[0] # negative_samples = train_data.loc[train_data['Output'] == 0] # rows = random.sample(negative_samples.index, positive_samples_count) # negative_samples = negative_samples.ix[rows] # train_data = pd.concat([positive_samples, negative_samples]) """
""":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)
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"]]
#Check if user has a history
number_times_clicked = row["UserClicksAd"]
#For users with no history pick the most popular item
if number_times_clicked == 0:
#Pick top 20 articles
top_article_popularity = heapq.nlargest(20, enumerate(article_popularity), key=lambda x: x[1])