class TestFileReceiver(unittest.TestCase):
def setUp(self):
self.file_receiver = FileReceiver()
def test_acquire_input_path_valid(self):
self.file_receiver.acquire_input_path()
self.assertNotEqual(
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\PythonUsage",
self.file_receiver.input_folder_path)
def test_acquire_input_path_invalid(self):
self.file_receiver.acquire_input_path()
self.assertEqual(
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\PythonUsage",
self.file_receiver.input_folder_path)
def test_acquire_output_path_valid(self):
self.file_receiver.acquire_output_path()
self.assertNotEqual(
"D:\\Google_Play_Fraud_Benign_Malware\\Visualizations",
self.file_receiver.output_folder_path)
def test_acquire_output_path_invalid(self):
self.file_receiver.acquire_output_path()
self.assertEqual(
"D:\\Google_Play_Fraud_Benign_Malware\\Visualizations",
self.file_receiver.output_folder_path)
class TestDataAdjustment(unittest.TestCase):
def setUp(self):
self.data_adjuster = DataAdjustment()
self.file_receiver = FileReceiver()
def test_removeStopWords_valid(self):
result = self.data_adjuster.remove_string_stopwords(
["apple", "an", "the"])
self.assertEqual(1, len(result))
print(result)
def test_removeStopWords_invalid(self):
result = self.data_adjuster.remove_string_stopwords(["an", "the"])
self.assertEqual(1, len(result))
print(result)
def test_remove_string_punctuation_valid(self):
test = "this string. has ! a bunch , of ? punctuation "
test = self.data_adjuster.remove_string_punctuation(test)
self.assertEqual(-1, test.find('.'))
print(test)
def test_remove_string_punctuation_invalid(self):
test = "this string has no punctuation"
test = self.data_adjuster.remove_string_punctuation(test)
self.assertNotEqual(-1, test.find(','))
print(test)
def test_create_dict_from_tuple_valid(self):
test = (("lol", 5), ("test", 4), ("trash", 3))
result = self.data_adjuster.get_dict_from_tuple(test)
self.assertNotEqual(0, len(result))
def test_create_dict_from_tuple_invalid(self):
test = (("lol", 5), ("test", 4), ("trash", 3))
result = self.data_adjuster.get_dict_from_tuple(test)
self.assertNotEqual(3, len(result))
def test_remove_duplicate_rows_from_csv(self):
self.file_receiver.acquire_input_path()
self.data_adjuster.remove_duplicate_rows_from_csv(
self.file_receiver.csv_files,
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test')
def main():
wc_generator = WordCloudGenerator()
file_receiver = FileReceiver()
# acquire paths
if len(wc_generator.csv_files) == 0:
file_receiver.acquire_input_path()
file_receiver.acquire_output_path()
# create word clouds
wc_generator.acquire_csv_files(file_receiver.csv_files)
figure_choice = input(
"Single figure-multiple word clouds(M) or each word clouds separate(S)?\n"
)
if figure_choice == 'M':
wc_generator.create_dictionaries_from_topics()
wc_generator.create_figure_with_multiple_word_clouds()
#save word clouds
wc_generator.save_figure(file_receiver.output_folder_path)
else:
column_name = input(
"What is the column name from which you want to extract text frequency?\n"
)
wc_generator.create_dictionaries(column_name)
wc_generator.create_word_cloud()
# save word clouds
wc_generator.save_word_cloud(file_receiver.output_folder_path)
# display word clouds
while True:
input_text = input("Would you like to see the word clouds? (Y/N) :")
if input_text == 'Y':
wc_generator.display_word_cloud()
break
else:
if input_text == 'N':
print("Shutting down.")
break
else:
print("I didn't catch that, try again.")
def main():
lc_generator = LineChartGenerator()
file_receiver = FileReceiver()
file_receiver.acquire_input_path()
file_receiver.acquire_output_path()
line_type = input("Yearly lines(Y) or Character Distribution(W): ")
if line_type == "Y":
lc_generator.acquire_csv_files(file_receiver.csv_files)
lc_generator.calculate_overall_reviews_by_identifiable_individuals()
lc_generator.calculate_reviews_by_identifiable_individuals_per_app()
lc_generator.create_all_year_data_chart()
lc_generator.create_yearly_app_data_charts()
lc_generator.save_yearly_app_charts(file_receiver.output_folder_path)
lc_generator.save_all_year_charts(file_receiver.output_folder_path)
# display line charts
while True:
input_text = input(
"Would you like to see the line charts? (Y/N) :")
if input_text == 'Y':
lc_generator.display_line_charts()
break
else:
if input_text == 'N':
print("Shutting down.")
break
else:
print("I didn't catch that, try again.")
elif line_type == "W":
lc_generator.acquire_csv_files(file_receiver.csv_files)
lc_generator.categorize_text_by_character_count()
lc_generator.create_simple_line_chart()
lc_generator.save_line_chart(file_receiver.output_folder_path)
def setUp(self):
self.wordcloud = WordCloudGenerator()
self.file_receiver = FileReceiver()
def setUp(self):
self.data_adjuster = DataAdjustment()
self.file_receiver = FileReceiver()
def setUp(self):
self.dendrogram_generator = DendrogramGenerator()
self.file_receiver = FileReceiver()
class TestWordCloud(unittest.TestCase):
def setUp(self):
self.wordcloud = WordCloudGenerator()
self.file_receiver = FileReceiver()
def test_display_wordcloud_valid(self):
wc = WordCloud(background_color="white")
wc.generate_from_text(
"this is a word cloud text lmao lmao lmao lmao lo lo lo lol lol lol lol"
)
self.wordcloud.word_clouds.append(wc)
self.wordcloud.display_word_cloud()
def test_display_wordcloud_invalid(self):
self.wordcloud.display_word_cloud()
def test_create_dictionaries_valid(self):
self.file_receiver.acquire_input_path()
self.wordcloud.acquire_csv_files(self.file_receiver.csv_files)
self.wordcloud.create_dictionaries('Text')
self.assertNotEqual(0, len(self.wordcloud.csv_files))
self.assertNotEqual(0, len(self.wordcloud.word_frequency))
def test_create_dictionaries_invalid(self):
self.file_receiver.acquire_input_path()
self.wordcloud.acquire_csv_files(self.file_receiver.csv_files)
self.wordcloud.create_dictionaries('Text')
self.assertEqual(0, len(self.wordcloud.csv_files))
self.assertEqual(0, len(self.wordcloud.word_frequency))
def test_create_word_cloud_valid(self):
test_data = {'Word': ["nice", "very nice"], 'Frequency': [100, 200]}
test_frame = pd.DataFrame(test_data, columns=['Word', 'Frequency'])
self.wordcloud.word_frequency.append(test_frame)
self.wordcloud.create_word_cloud()
self.assertNotEqual(0, len(self.wordcloud.word_clouds))
self.wordcloud.display_word_cloud()
def test_create_word_cloud_invalid(self):
test_data = {'Word': ["nice", "very nice"], 'Frequency': [100, 200]}
test_frame = pd.DataFrame(test_data, columns=['Word', 'Frequency'])
self.wordcloud.word_frequency.append(test_frame)
self.wordcloud.create_word_cloud()
self.assertNotEqual(1, len(self.wordcloud.word_clouds))
self.wordcloud.display_word_cloud()
def test_save_word_cloud_valid(self):
self.wordcloud.acquire_csv_files([
'D:\Google_Play_Fraud_Benign_Malware\Fraud\Test\fraud_apps_640_review_info_final_2012_top_10.csv'
])
self.wordcloud.create_dictionaries('Text')
self.wordcloud.create_word_cloud()
self.assertNotEqual(0, len(self.wordcloud.word_clouds))
self.wordcloud.save_word_cloud(
"D:\\Google_Play_Fraud_Benign_Malware\\Visualizations")
def test_save_word_cloud_invalid(self):
self.wordcloud.acquire_csv_files([
'D:\Google_Play_Fraud_Benign_Malware\Fraud\Test\fraud_apps_640_review_info_final_2012_top_10.csv'
])
self.wordcloud.create_dictionaries('Text')
self.wordcloud.create_word_cloud()
self.assertNotEqual(0, len(self.wordcloud.word_clouds))
self.wordcloud.save_word_cloud(
"D:\\Google_Play_Fraud_Benign_Malware\\Visualizations")
def test_create_sentiment_dictionaries_valid(self):
self.file_receiver.acquire_input_path()
self.wordcloud.acquire_csv_files(self.file_receiver.csv_files)
self.wordcloud.create_sentiment_dictionaries('Text')
self.assertNotEqual(0, len(self.wordcloud.sentiment_word_cloud_data))
def test_create_sentiment_word_cloud_valid(self):
self.wordcloud.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test\\Sentiment_word_cloud\\fraud_apps_640_review_info_final_2012_top_10_including_sentiment_score.csv'
])
self.wordcloud.create_sentiment_dictionaries('Text')
self.assertNotEqual(0, len(self.wordcloud.sentiment_word_cloud_data))
self.wordcloud.create_sentiment_word_cloud()
def test_save_sentiment_word_cloud_valid(self):
self.wordcloud.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test\\Sentiment_word_cloud\\fraud_apps_640_review_info_final_2013_top_10_including_sentiment_score.csv'
])
self.wordcloud.create_sentiment_dictionaries('Text')
self.assertNotEqual(0, len(self.wordcloud.sentiment_word_cloud_data))
self.wordcloud.create_sentiment_word_cloud()
self.wordcloud.save_sentiment_clouds(
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test\\Sentiment_word_cloud'
)
def test_create_dictionaries_from_text_topics(self):
self.wordcloud.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\LATENT DIRICHLET ALLOCATION\\2016\\Keywords\\topic_keywords_fraud_apps_2016_all_reviews_including_sentiment_score.csv'
])
self.wordcloud.create_dictionaries_from_topics()
def test_create_figure_with_multiple_word_clouds(self):
self.wordcloud.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\LATENT DIRICHLET ALLOCATION\\2016\\Keywords\\topic_keywords_fraud_apps_2016_all_reviews_including_sentiment_score.csv'
])
self.wordcloud.create_dictionaries_from_topics()
self.wordcloud.create_figure_with_multiple_word_clouds()
def setUp(self):
self.barchart_generator = BarChartGenerator()
self.file_receiver = FileReceiver()
def main():
file_receiver = FileReceiver()
pie_chart_generator = PieChartGenerator()
pie_type = input(
"Basic Pie Chart(B), Nested Pie Chart(Sentiment-Rating=SR,Sentiment-Topic=ST, Rating-Topic=RT): "
)
if pie_type == 'B':
file_receiver.acquire_input_path()
file_receiver.acquire_output_path()
pie_chart_generator.acquire_csv_files(file_receiver.csv_files)
pie_chart_generator.get_chart_data_from_csv_files()
pie_chart_generator.create_basic_pie_chart()
pie_chart_generator.save_basic_pie_charts(
file_receiver.output_folder_path)
elif pie_type == 'SR':
file_receiver.acquire_input_path()
file_receiver.acquire_output_path()
pie_chart_generator.acquire_csv_files(file_receiver.csv_files)
pie_chart_generator.get_chart_data_from_csv_files()
pie_chart_generator.create_nested_pie_chart_sentiment_and_rating()
pie_chart_generator.save_nested_pie_chart(
file_receiver.output_folder_path)
elif pie_type == 'ST':
input_folders = [
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\Sentiment & Topic\\2016",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\Sentiment & Topic\\2013",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\Sentiment & Topic\\2014",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\Sentiment & Topic\\2015",
#"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\Sentiment & Topic\\2016"
]
output_folders = [
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\LATENT DIRICHLET ALLOCATION\\2016\\Sentiment-Topic Nested Pie Charts",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\LATENT DIRICHLET ALLOCATION\\2013\\Sentiment-Topic Nested Pie Charts",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\LATENT DIRICHLET ALLOCATION\\2014\\Sentiment-Topic Nested Pie Charts",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\LATENT DIRICHLET ALLOCATION\\2015\\Sentiment-Topic Nested Pie Charts",
#"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\LATENT DIRICHLET ALLOCATION\\2016\\Sentiment-Topic Nested Pie Charts"
]
for i in range(0, len(input_folders)):
filenames = get_csv_files_from_directories(input_folders[i])
file_list = []
for filename in filenames:
file_list.append(filename)
pie_chart_generator.acquire_csv_files(file_list)
pie_chart_generator.get_chart_data_from_csv_files(True)
pie_chart_generator.create_nested_pie_chart_sentiment_and_topic()
pie_chart_generator.save_nested_pie_chart(output_folders[i])
elif pie_type == 'RT':
input_folders = [
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\Sentiment & Topic\\2016",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\Sentiment & Topic\\2013",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\Sentiment & Topic\\2014",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\Sentiment & Topic\\2015" #,
#"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\Sentiment & Topic\\2016"
]
output_folders = [
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\LATENT DIRICHLET ALLOCATION\\2016\\Rating-Topic Nested Pie Charts",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\LATENT DIRICHLET ALLOCATION\\2013\\Rating-Topic Nested Pie Charts",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\LATENT DIRICHLET ALLOCATION\\2014\\Rating-Topic Nested Pie Charts",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\LATENT DIRICHLET ALLOCATION\\2015\\Rating-Topic Nested Pie Charts" #,
#"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\LATENT DIRICHLET ALLOCATION\\2016\\Rating-Topic Nested Pie Charts"
]
for i in range(0, len(input_folders)):
filenames = get_csv_files_from_directories(input_folders[i])
file_list = []
for filename in filenames:
file_list.append(filename)
pie_chart_generator.acquire_csv_files(file_list)
pie_chart_generator.get_chart_data_from_csv_files(True)
pie_chart_generator.create_nested_pie_chart_rating_and_topic()
pie_chart_generator.save_nested_pie_chart(output_folders[i])
def main():
file_receiver = FileReceiver()
sentiment_analyzer = SentimentAnalyzer()
data_adjuster = DataAdjustment()
input_text = input(
"Calculate Sentiment for text in csv(S) or Add column from existing csv file to another(C):"
)
if input_text == 'S':
file_receiver.acquire_input_path()
file_receiver.acquire_output_path()
sentiment_analyzer.acquire_csv_files(file_receiver.csv_files)
sentiment_analyzer.create_data_frames_with_result_columns()
sentiment_analyzer.save_sentiment_csv_file(
file_receiver.output_folder_path)
elif input_text == "C":
print("Input path to initial set:")
file_receiver.acquire_input_path()
first_set = file_receiver.csv_files
print("Input path to second set:")
file_receiver.acquire_input_path()
second_set = file_receiver.csv_files
file_receiver.acquire_output_path()
first_set_files = []
second_set_files = []
first_folder = []
for i in range(0, len(first_set)):
first_head, first_tail = os.path.split(first_set[i])
first_folder = first_head
second_head, second_tail = os.path.split(second_set[i])
first_set_files.append(first_tail)
second_set_files.append(second_tail)
for file in first_set_files:
second_set_index = second_set_files.index(file)
first_data = pd.read_csv(first_folder + '\\' + file)
second_data = pd.read_csv(second_set[second_set_index])
data_adjuster.concatenate_csv_data(
file_receiver.output_folder_path, file, first_data,
second_data, "Topic ID", "Topic Count")
class TestBarChart(unittest.TestCase):
def setUp(self):
self.barchart_generator = BarChartGenerator()
self.file_receiver = FileReceiver()
def test_calculate_text_length_valid(self):
self.file_receiver.acquire_input_path()
self.barchart_generator.acquire_csv_files(self.file_receiver.csv_files)
self.barchart_generator.categorize_text_by_word_count()
self.assertNotEqual(0, len(self.barchart_generator.csv_files))
def test_calculate_text_length_invalid(self):
self.file_receiver.acquire_input_path()
self.barchart_generator.acquire_csv_files(self.file_receiver.csv_files)
self.barchart_generator.categorize_text_by_word_count()
self.assertEqual(0, len(self.barchart_generator.csv_files))
def test_create_horizontal_bar_chart_valid(self):
self.barchart_generator.total_word_count = {
'0-50': 1,
'51-100': 9,
'101-200': 11,
'201-300': 25,
'301-400': 60,
'400+': 5
}
self.barchart_generator.per_file_word_count = (('2012', {
'0-50': 1,
'51-100': 9,
'101-200': 11,
'201-300': 25,
'301-400': 60,
'400+': 5
}), ('2013', {
'0-50': 1,
'51-100': 9,
'101-200': 11,
'201-300': 25,
'301-400': 60,
'400+': 5
}), ('2014', {
'0-50': 1,
'51-100': 9,
'101-200': 11,
'201-300': 25,
'301-400': 60,
'400+': 5
}))
self.barchart_generator.create_overall_bar_charts()
self.barchart_generator.display_bar_charts()
def test_create_horizontal_bar_chart_invalid(self):
self.barchart_generator.total_word_count = {
'0-50': "invalid",
'51-100': 9,
'101-200': 11,
'201-300': 25,
'301-400': 60,
'400+': 5
}
self.barchart_generator.per_file_word_count = (('2012', {
'0-50': 1,
'51-100': 9,
'101-200': 11,
'201-300': 25,
'301-400': 60,
'400+': 5
}), ('2013', {
'0-50': 1,
'51-100': 9,
'101-200': 11,
'201-300': 25,
'301-400': 60,
'400+': 5
}), ('2014', {
'0-50': 1,
'51-100': 9,
'101-200': 11,
'201-300': 25,
'301-400': 60,
'400+': 5
}))
self.barchart_generator.create_overall_bar_charts()
self.barchart_generator.display_bar_charts()
def test_save_bar_charts_valid(self):
self.file_receiver.acquire_input_path()
self.barchart_generator.acquire_csv_files(self.file_receiver.csv_files)
self.barchart_generator.categorize_text_by_word_count()
self.barchart_generator.create_overall_bar_charts()
self.barchart_generator.display_bar_charts()
self.barchart_generator.save_overall_bar_charts(
"D:\\Google_Play_Fraud_Benign_Malware\\Visualizations")
def test_save_bar_charts_invalid(self):
self.file_receiver.acquire_input_path()
self.barchart_generator.acquire_csv_files(self.file_receiver.csv_files)
self.barchart_generator.categorize_text_by_word_count()
self.barchart_generator.create_overall_bar_charts()
self.barchart_generator.display_bar_charts()
self.barchart_generator.save_overall_bar_charts(
"D:\\Google_Play_Fraud_Benign_Malware\\Visualizations")
def test_calculate_word_occurrence_valid(self):
self.barchart_generator.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test\\PieChartTest\\fraud_apps_640_review_info_final_2012_top_10.csv'
])
self.barchart_generator.categorize_words_by_valence()
self.assertNotEqual(0, len(self.barchart_generator.file_valence_data))
# missing text column
def test_calculate_word_occurence_invalid(self):
self.barchart_generator.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test\\fraud_apps_640_review_info_final_2016_top_10_missing_text_column.csv'
])
self.barchart_generator.categorize_words_by_valence()
self.assertNotEqual(0, len(self.barchart_generator.file_valence_data))
def test_create_divergent_valence_bar_chart_valid(self):
self.barchart_generator.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test\\PieChartTest\\fraud_apps_640_review_info_final_2012_top_10.csv'
])
self.barchart_generator.categorize_words_by_valence()
self.barchart_generator.create_divergent_valence_bar_chart()
self.assertNotEqual(0, len(self.barchart_generator.file_valence_data))
def test_create_divergent_valence_bar_chart_invalid(self):
self.barchart_generator.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test\\PieChartTest\\fraud_apps_640_review_info_final_2012_top_10.csv'
])
self.barchart_generator.categorize_words_by_valence()
self.barchart_generator.file_valence_data = None
self.barchart_generator.create_divergent_valence_bar_chart()
self.assertNotEqual(0, len(self.barchart_generator.file_valence_data))
def test_categorize_rating(self):
self.barchart_generator.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test\\PieChartTest\\fraud_apps_640_review_info_final_2012_top_10.csv'
])
self.barchart_generator.categorize_ratings()
def test_create_rating_bar_charts(self):
self.barchart_generator.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\2012\\sentiment\\fraud_apps_2012_all_anon_reviews_including_sentiment_score.csv'
])
self.barchart_generator.categorize_ratings()
self.barchart_generator.create_rating_bar_charts()
def setUp(self):
self.file_receiver = FileReceiver()
class TestLineChart(unittest.TestCase):
def setUp(self):
self.file_receiver = FileReceiver()
self.line_chart_generator = LineChartGenerator()
def test_categorize_text_by_word_count(self):
self.line_chart_generator.acquire_csv_files([
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\2013\\sentiment\\fraud_apps_2013_all_anon_reviews_including_sentiment_score.csv"
])
self.line_chart_generator.categorize_text_by_character_count()
self.assertNotEqual(
0, len(self.line_chart_generator.per_file_character_count))
def test_create_simple_line_chart(self):
self.line_chart_generator.acquire_csv_files([
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\2012\\sentiment\\fraud_apps_2012_all_anon_reviews_including_sentiment_score.csv",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\2013\\sentiment\\fraud_apps_2013_all_anon_reviews_including_sentiment_score.csv",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\2014\\sentiment\\fraud_apps_2014_all_anon_including_sentiment_score.csv",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\2015\\sentiment\\fraud_apps_2015_all_anon_reviews_including_sentiment_score.csv",
"D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\All Data\\2016\\sentiment\\fraud_apps_2016_all_anon_reviews_including_sentiment_score.csv"
])
self.line_chart_generator.categorize_text_by_character_count()
self.line_chart_generator.create_simple_line_chart()
self.assertNotEqual(0, len(self.line_chart_generator.line_charts))
def test_calculate_monthly_app_reviews_valid(self):
self.line_chart_generator.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test\\fraud_apps_640_review_info_final_2014_top_10.csv'
])
self.line_chart_generator.calculate_reviews_by_identifiable_individuals_per_app(
)
# missing data column - month
def test_calculate_monthly_app_reviews_invalid(self):
self.line_chart_generator.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test\\fraud_apps_640_review_info_final_2014_top_10_no_month_column.csv'
])
self.line_chart_generator.calculate_reviews_by_identifiable_individuals_per_app(
)
def test_create_charts_valid(self):
self.line_chart_generator.create_charts([
('APP_1', [(1, 47), (2, 51), (3, 30), (4, 34), (5, 18), (6, 22),
(7, 11), (8, 14), (9, 11), (10, 343), (11, 142),
(12, 121)]),
('APP_2', [(1, 22), (2, 22), (3, 26), (4, 6), (5, 26), (6, 61),
(7, 22), (8, 34), (9, 26), (10, 174), (11, 148),
(12, 22)]),
('APP_3', [(1, 25), (2, 34), (3, 14), (4, 22), (5, 20), (6, 119),
(7, 72), (8, 24), (9, 17), (10, 61), (11, 13),
(12, 24)]),
('APP_4', [(1, 10), (2, 16), (3, 6), (4, 34), (5, 36), (6, 30),
(7, 30), (8, 18), (9, 36), (10, 138), (11, 112),
(12, 22)]),
('APP_5', [(1, 132), (2, 162), (3, 136), (4, 104), (5, 110),
(6, 144), (7, 141), (8, 156), (9, 122), (10, 78),
(11, 102), (12, 118)]),
('APP_6', [(1, 17), (2, 13), (3, 17), (4, 40), (5, 44), (6, 46),
(7, 47), (8, 58), (9, 52), (10, 59), (11, 80),
(12, 168)]),
('APP_7', [(1, 32), (2, 88), (3, 162), (4, 121), (5, 165),
(6, 112), (7, 149), (8, 145), (9, 83), (10, 259),
(11, 212), (12, 221)]),
('APP_8', [(1, 247), (2, 178), (3, 226), (4, 182), (5, 160),
(6, 121), (7, 82), (8, 130), (9, 152), (10, 104),
(11, 143), (12, 112)]),
('APP_9', [(1, 27), (2, 33), (3, 19), (4, 68), (5, 31), (6, 17),
(7, 30), (8, 37), (9, 52), (10, 149), (11, 89),
(12, 53)]),
('APP_10', [(1, 96), (2, 56), (3, 142), (4, 172), (5, 219),
(6, 211), (7, 130), (8, 140), (9, 186), (10, 147),
(11, 138), (12, 98)])
])
# missing APP_2 in the second element
def test_create_charts_invalid(self):
self.line_chart_generator.create_charts([
('APP_1', [(1, 47), (2, 51), (3, 30), (4, 34), (5, 18), (6, 22),
(7, 11), (8, 14), (9, 11), (10, 343), (11, 142),
(12, 121)]),
([(1, 22), (2, 22), (3, 26), (4, 6), (5, 26), (6, 61), (7, 22),
(8, 34), (9, 26), (10, 174), (11, 148), (12, 22)]),
('APP_3', [(1, 25), (2, 34), (3, 14), (4, 22), (5, 20), (6, 119),
(7, 72), (8, 24), (9, 17), (10, 61), (11, 13),
(12, 24)]),
('APP_4', [(1, 10), (2, 16), (3, 6), (4, 34), (5, 36), (6, 30),
(7, 30), (8, 18), (9, 36), (10, 138), (11, 112),
(12, 22)]),
('APP_5', [(1, 132), (2, 162), (3, 136), (4, 104), (5, 110),
(6, 144), (7, 141), (8, 156), (9, 122), (10, 78),
(11, 102), (12, 118)]),
('APP_6', [(1, 17), (2, 13), (3, 17), (4, 40), (5, 44), (6, 46),
(7, 47), (8, 58), (9, 52), (10, 59), (11, 80),
(12, 168)]),
('APP_7', [(1, 32), (2, 88), (3, 162), (4, 121), (5, 165),
(6, 112), (7, 149), (8, 145), (9, 83), (10, 259),
(11, 212), (12, 221)]),
('APP_8', [(1, 247), (2, 178), (3, 226), (4, 182), (5, 160),
(6, 121), (7, 82), (8, 130), (9, 152), (10, 104),
(11, 143), (12, 112)]),
('APP_9', [(1, 27), (2, 33), (3, 19), (4, 68), (5, 31), (6, 17),
(7, 30), (8, 37), (9, 52), (10, 149), (11, 89),
(12, 53)]),
('APP_10', [(1, 96), (2, 56), (3, 142), (4, 172), (5, 219),
(6, 211), (7, 130), (8, 140), (9, 186), (10, 147),
(11, 138), (12, 98)])
])
def test_create_yearly_app_data_charts_valid(self):
self.line_chart_generator.yearly_app_data = [[('APP_1', [(1, 47),
(2, 51),
(3, 30),
(4, 34),
(5, 18),
(6, 22),
(7, 11),
(8, 14),
(9, 11),
(10, 343),
(11, 142),
(12, 121)]),
('APP_2', [(1, 22),
(2, 22),
(3, 26),
(4, 6),
(5, 26),
(6, 61),
(7, 22),
(8, 34),
(9, 26),
(10, 174),
(11, 148),
(12, 22)]),
('APP_3', [(1, 25),
(2, 34),
(3, 14),
(4, 22),
(5, 20),
(6, 119),
(7, 72),
(8, 24),
(9, 17),
(10, 61),
(11, 13),
(12, 24)]),
('APP_4', [(1, 10),
(2, 16),
(3, 6),
(4, 34),
(5, 36),
(6, 30),
(7, 30),
(8, 18),
(9, 36),
(10, 138),
(11, 112),
(12, 22)]),
('APP_5', [(1, 132),
(2, 162),
(3, 136),
(4, 104),
(5, 110),
(6, 144),
(7, 141),
(8, 156),
(9, 122),
(10, 78),
(11, 102),
(12, 118)]),
('APP_6', [(1, 17),
(2, 13),
(3, 17),
(4, 40),
(5, 44),
(6, 46),
(7, 47),
(8, 58),
(9, 52),
(10, 59),
(11, 80),
(12, 168)]),
('APP_7', [(1, 32),
(2, 88),
(3, 162),
(4, 121),
(5, 165),
(6, 112),
(7, 149),
(8, 145),
(9, 83),
(10, 259),
(11, 212),
(12, 221)]),
('APP_8', [(1, 247),
(2, 178),
(3, 226),
(4, 182),
(5, 160),
(6, 121),
(7, 82),
(8, 130),
(9, 152),
(10, 104),
(11, 143),
(12, 112)]),
('APP_9', [(1, 27),
(2, 33),
(3, 19),
(4, 68),
(5, 31),
(6, 17),
(7, 30),
(8, 37),
(9, 52),
(10, 149),
(11, 89),
(12, 53)]),
('APP_10', [(1, 96),
(2, 56),
(3, 142),
(4, 172),
(5, 219),
(6, 211),
(7, 130),
(8, 140),
(9, 186),
(10, 147),
(11, 138),
(12, 98)])],
[
('APP_1', [(1, 0),
(2, 0),
(3, 0),
(4, 0),
(5, 0),
(6, 0),
(7, 0),
(8, 0),
(9, 0),
(10, 0),
(11, 0),
(12, 2)]),
('APP_2', [(1, 0),
(2, 0),
(3, 0),
(4, 0),
(5, 0),
(6, 0),
(7, 0),
(8, 0),
(9, 2),
(10, 0),
(11, 0),
(12, 2)]),
('APP_3', [(1, 0),
(2, 0),
(3, 0),
(4, 0),
(5, 2),
(6, 0),
(7, 2),
(8, 0),
(9, 2),
(10, 2),
(11, 4),
(12, 24)]),
('APP_4', [(1, 0),
(2, 0),
(3, 1),
(4, 0),
(5, 0),
(6, 0),
(7, 0),
(8, 0),
(9, 0),
(10, 0),
(11, 0),
(12, 1)]),
('APP_5', [(1, 0),
(2, 0),
(3, 0),
(4, 0),
(5, 0),
(6, 0),
(7, 0),
(8, 0),
(9, 0),
(10, 0),
(11, 2),
(12, 0)]),
('APP_6', [(1, 0),
(2, 0),
(3, 0),
(4, 0),
(5, 0),
(6, 2),
(7, 0),
(8, 2),
(9, 0),
(10, 2),
(11, 4),
(12, 4)]),
('APP_7', [(1, 0),
(2, 0),
(3, 0),
(4, 0),
(5, 0),
(6, 0),
(7, 0),
(8, 0),
(9, 0),
(10, 0),
(11, 0),
(12, 1)])
]]
self.line_chart_generator.create_yearly_app_data_charts()
# missing second element in the list
def test_create_yearly_app_data_charts_invalid(self):
self.line_chart_generator.yearly_app_data = [[('APP_1', [(1, 47),
(2, 51),
(3, 30),
(4, 34),
(5, 18),
(6, 22),
(7, 11),
(8, 14),
(9, 11),
(10, 343),
(11, 142),
(12, 121)]),
('APP_2', [(1, 22),
(2, 22),
(3, 26),
(4, 6),
(5, 26),
(6, 61),
(7, 22),
(8, 34),
(9, 26),
(10, 174),
(11, 148),
(12, 22)]),
('APP_3', [(1, 25),
(2, 34),
(3, 14),
(4, 22),
(5, 20),
(6, 119),
(7, 72),
(8, 24),
(9, 17),
(10, 61),
(11, 13),
(12, 24)]),
('APP_4', [(1, 10),
(2, 16),
(3, 6),
(4, 34),
(5, 36),
(6, 30),
(7, 30),
(8, 18),
(9, 36),
(10, 138),
(11, 112),
(12, 22)]),
('APP_5', [(1, 132),
(2, 162),
(3, 136),
(4, 104),
(5, 110),
(6, 144),
(7, 141),
(8, 156),
(9, 122),
(10, 78),
(11, 102),
(12, 118)]),
('APP_6', [(1, 17),
(2, 13),
(3, 17),
(4, 40),
(5, 44),
(6, 46),
(7, 47),
(8, 58),
(9, 52),
(10, 59),
(11, 80),
(12, 168)]),
('APP_7', [(1, 32),
(2, 88),
(3, 162),
(4, 121),
(5, 165),
(6, 112),
(7, 149),
(8, 145),
(9, 83),
(10, 259),
(11, 212),
(12, 221)]),
('APP_8', [(1, 247),
(2, 178),
(3, 226),
(4, 182),
(5, 160),
(6, 121),
(7, 82),
(8, 130),
(9, 152),
(10, 104),
(11, 143),
(12, 112)]),
('APP_9', [(1, 27),
(2, 33),
(3, 19),
(4, 68),
(5, 31),
(6, 17),
(7, 30),
(8, 37),
(9, 52),
(10, 149),
(11, 89),
(12, 53)]),
('APP_10', [(1, 96),
(2, 56),
(3, 142),
(4, 172),
(5, 219),
(6, 211),
(7, 130),
(8, 140),
(9, 186),
(10, 147),
(11, 138),
(12, 98)])],
[]]
self.line_chart_generator.create_yearly_app_data_charts()
def test_calculate_all_year_data_valid(self):
self.line_chart_generator.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test\\fraud_apps_640_review_info_final_2014_top_10.csv'
])
self.line_chart_generator.calculate_overall_reviews_by_identifiable_individuals(
)
def test_calculate_all_year_data_invalid(self):
self.line_chart_generator.acquire_csv_files([
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test\\fraud_apps_640_review_info_final_2014_top_10_no_month_column.csv'
])
self.line_chart_generator.calculate_overall_reviews_by_identifiable_individuals(
)
def test_create_all_year_data_chart_valid(self):
self.line_chart_generator.all_year_data = [('2014',
[(1, 655), (2, 653),
(3, 778), (4, 783),
(5, 829), (6, 883),
(7, 714), (8, 756),
(9, 737), (10, 1512),
(11, 1179), (12, 959)])]
self.line_chart_generator.create_all_year_data_chart()
# missing year tag
def test_create_all_year_data_chart_invalid(self):
self.line_chart_generator.all_year_data = [([(1, 655), (2, 653),
(3, 778), (4, 783),
(5, 829), (6, 883),
(7, 714), (8, 756),
(9, 737), (10, 1512),
(11, 1179), (12, 959)])]
self.line_chart_generator.create_all_year_data_chart()
def test_save_all_year_charts_valid(self):
self.file_receiver.acquire_input_path()
self.line_chart_generator.acquire_csv_files(
self.file_receiver.csv_files)
self.line_chart_generator.calculate_overall_reviews_by_identifiable_individuals(
)
self.line_chart_generator.calculate_reviews_by_identifiable_individuals_per_app(
)
self.line_chart_generator.create_all_year_data_chart()
self.line_chart_generator.create_yearly_app_data_charts()
self.line_chart_generator.save_all_year_charts(
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test')
self.line_chart_generator.save_yearly_app_charts(
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test')
#invalid output path
def test_save_all_year_charts_invalid(self):
self.file_receiver.acquire_input_path()
self.line_chart_generator.acquire_csv_files(
self.file_receiver.csv_files)
self.line_chart_generator.calculate_overall_reviews_by_identifiable_individuals(
)
self.line_chart_generator.calculate_reviews_by_identifiable_individuals_per_app(
)
self.line_chart_generator.create_all_year_data_chart()
self.line_chart_generator.create_yearly_app_data_charts()
self.line_chart_generator.save_all_year_charts('')
self.line_chart_generator.save_yearly_app_charts(
'D:\\Google_Play_Fraud_Benign_Malware\\Fraud\\Test')
def main():
bc_generator = BarChartGenerator()
file_receiver = FileReceiver()
file_receiver.acquire_input_path()
file_receiver.acquire_output_path()
bc_generator.acquire_csv_files(file_receiver.csv_files)
chart_type = input(
"Sentiment Divergent bar chart(S) or Character count bar chart(W) or Rating bar charts(R) or Topic bar charts(T)?"
)
if chart_type == 'W':
bc_generator.categorize_text_by_word_count()
bc_generator.create_overall_bar_charts()
# display bar charts
while True:
input_text = input("Would you like to see the bar charts? (Y/N) :")
if input_text == 'Y':
bc_generator.display_bar_charts()
break
else:
if input_text == 'N':
print("Shutting down.")
break
else:
print("I didn't catch that, try again.")
bc_generator.save_overall_bar_charts(file_receiver.output_folder_path)
elif chart_type == 'S':
bc_generator.categorize_words_by_valence()
bc_generator.create_divergent_valence_bar_chart()
# display bar charts
while True:
input_text = input("Would you like to see the bar charts? (Y/N) :")
if input_text == 'Y':
bc_generator.display_divergent_bar_charts()
break
else:
if input_text == 'N':
print("Shutting down.")
break
else:
print("I didn't catch that, try again.")
bc_generator.save_divergent_bar_charts(
file_receiver.output_folder_path)
elif chart_type == 'R':
bc_generator.categorize_ratings()
bc_generator.create_rating_bar_charts()
while True:
input_text = input("Would you like to see the bar charts? (Y/N) :")
if input_text == 'Y':
bc_generator.display_bar_charts()
break
else:
if input_text == 'N':
print("Shutting down.")
break
else:
print("I didn't catch that, try again.")
bc_generator.save_rating_charts(file_receiver.output_folder_path)
elif chart_type == 'T':
topic_data = bc_generator.categorize_topic_distribution()
bc_generator.create_bar_charts(topic_data)
bc_generator.save_bar_charts(file_receiver.output_folder_path)
def setUp(self):
self.file_receiver = FileReceiver()
self.sentiment_analyzer = SentimentAnalyzer()
def setUp(self):
self.file_receiver = FileReceiver()
self.line_chart_generator = LineChartGenerator()