def automate():
number_of_zipped_files = len(get_all_files_in_directory(zipped_data_path))
number_of_raw_files = len(get_all_files_in_directory(raw_data_path))
number_of_filtered_files = len(get_all_files_in_directory(filtered_data_path))
number_of_individual_files = len(get_all_files_in_directory(individual_data_path))
if number_of_zipped_files == 0:
logger.raise_exception('There are no .zip files to work with.', logger.LogicError)
if number_of_raw_files == 0:
extract_zip_files()
if number_of_filtered_files == 0:
filter_the_stock_files(raw_data_path, filtered_data_path)
if number_of_individual_files == 0:
combined_data_frame = load_all_stock_files()
all_unique_names = combined_data_frame.symbol.values
timer = Timer()
for n in all_unique_names:
timer.start_timer()
local_data_frame = combined_data_frame[combined_data_frame.symbol == n]
if len(local_data_frame) != 0:
local_stock_path = str(str(individual_data_path) + n + '.csv')
if not os.path.isfile(local_stock_path):
local_data_frame.drop(local_data_frame.columns[0], axis=1, inplace=True)
local_data_frame['date'] = pd.to_datetime(local_data_frame['date'])
local_data_frame = local_data_frame.sort_values(by='date')
create_csv_file(local_data_frame, local_stock_path)
print('Length of local data frame: ' + str(len(local_data_frame)) + '\tLength of combined data: ' + str(len(combined_data_frame)))
combined_data_frame = combined_data_frame[combined_data_frame.symbol != n]
timer.end_timer()
timer.print_time()
def code_to_test_01():
my_list = []
my_set = set()
for x in range(10000):
my_list.append(x)
my_set.add(x)
timer = Timer()
timer.start_timer()
z = 0
for y in range(10000):
if my_list.__contains__(y):
z += y
timer.end_timer()
timer.print_time()
timer.start_timer()
z = 0
for y in range(10000):
if my_set.__contains__(y):
z += y
timer.end_timer()
timer.print_time()
for un in list_of_all_unique_names:
print(un)
logger.log('Finished seperating all the data_xv for individual stocks.')
exit(0)
'''
logger.log('There are: ' + str(len(list_of_all_unique_names)) + ' unique stocks.')
all_earnings = []
timer = Timer()
inner_timer = Timer()
logger.log('Starting the timer for the math code.')
timer.start_timer()
index = 0
bad_stocks = []
def perform_splits_on_stock(sl, data_frame):
for s in sl:
split_date = s.get_date()
split_date = pd.to_datetime(split_date)
data_frame.ix[data_frame.date <= split_date, 'open'] *= s.get_multiplier()
data_frame.ix[data_frame.date <= split_date, 'high'] *= s.get_multiplier()
data_frame.ix[data_frame.date <= split_date, 'low'] *= s.get_multiplier()
