def test_amazon_pulling():
df = pulling_logic.pulling_amazon(
resource_filename("vadertester", "json/Amazon_githubdata.json.gz"))
errors = []
github_line_amount = 37
# First checks if the data is being put into a form properly
if not len(df.columns) == 3:
errors.append("incorrect column amount")
# This error needs to be asserted because the key is used later on in the test
assert df.columns[0] == "ID", "ID incorrectly labeled"
if not df.columns[1] == "ReviewText":
errors.append("ReviewText Column incorrectly labeled")
# This error needs to be asserted because the key is used later on in the test
assert df.columns[
2] == "ReviewScore", "ReviewScore Column incorrectly labeled"
# Checks if the IDs are Unique (test may take a long time on large data)
if not df['ID'].is_unique:
errors.append("ID column values are not unique")
# Check if ReviewScore is all numeric
if not df['ReviewScore'].dtype == "float64":
errors.append("Rating column not numeric")
# Checks if all lines from github data imported (github data contains 37 lines)
if not len(df.index) == github_line_amount:
errors.append("Not All data is imported correctly")
assert not errors, "errors occurred:\n{}".format("\n".join(errors))
def main():
saved = sys.stdout
with open('output.txt', 'w') as fout:
sys.stdout = writer(sys.stdout, fout)
print("Vader tester started")
parser = create_parser()
args = parser.parse_args()
print("Loading test data from '" + args.file_input + "'")
all_df = pulling_amazon(args.file_input)
print("Getting " + str(args.amount) + " random rows from data")
if len(all_df.index) < args.amount:
raise Exception(
"Sample cannot be bigger than dataset amount which is " +
str(len(all_df.index)) + " rows")
random_sample_df = random_sample(all_df, args.amount)
print("Finished loading test data")
print("Running tests")
run_tests(random_sample_df)
print("Finished running tests")
print("Displaying output")
report_generation(random_sample_df)
print("Vader tester finished")
sys.stdout = saved
def tested_data_frame():
df = pulling_amazon(resource_filename("vadertester", "json/Amazon_githubdata.json.gz"))
testing_logic.run_tests(df)
return df
def amazon_data_frame_tested():
df = pulling_amazon(
resource_filename("vadertester", "json/Amazon_githubdata.json.gz"))
df = random_sample(df, 30)
run_tests(df)
return df
def amazon_data_frame():
return pulling_amazon(
resource_filename("vadertester", "json/Amazon_githubdata.json.gz"))