def main(arguments):
print('\n\n<< Starting pipeline >>\n')
# Data acquisition
mac.acquire_db_data(arguments.path)
# mac.api_request_job_codes()
mac.country_codes()
# Data wrangling
mwr.wrangle()
# Data analysis
df_poll = man.analysis_settings(arguments.country)
man.analyze_ch1(df_poll)
man.analysis_ch2(df_poll)
man.analysis_ch3(df_poll)
# Data reporting
mre.graph_reporting(arguments.country)
mre.pdf_reporting()
mre.email_reporting(arguments.email)
mre.tweets(arguments.hashtag)
print(
'\n\n========== Pipeline is complete. You may find the results in the folder ./data/results ========='
)
def main(country):
print('Starting pipe line')
df_acq = m_acquisition.data_df()
print('Cleaning retrieved data!')
df_wrang= m_wrangling.wrangle(df_acq)
print('Analysing data!')
df_analysis=m_analysis.analyze(df_wrang,country)
def main(some_args):
data = mac.acquire()
filtered = mwr.wrangle(data, year)
results = man.analyze(filtered)
fig = mre.plotting_function(results, title, arguments)
mre.save_viz(fig, title)
print(
'========================= Pipeline is complete. You may find the results in the folder ./data/results ========================='
)
def main(path, country, unknown):
print('Starting Pipeline...')
df_with_dates_raw = mac.acquire(path)
df_with_dates_clean = mwr.wrangle(df_with_dates_raw, country, unknown)
df_analyze = man.analyze(df_with_dates_clean)
mre.save_df(df_analyze, country, unknown)
print(f'The results of the country -{country}- are: ')
print(df_analyze)
print('Finished Pipeline')
def main(country=None):
start = time.time()
print(f'Starting pipeline for {country}')
df = m_acquisition.acquire()
print('This may take around 80 seconds..')
wrangling_ = m_wrangling.wrangle(df)
print('Wrangling done, lets save the table')
analysis_ = m_analysis.analyse(wrangling_, country)
print(analysis_)
print(f'Task {country} done')
end = time.time()
print(end - start, str("seconds"))
def main(arguments):
data = mac.acquire(arguments.path)
filtered = mwr.wrangle(data, arguments.unemployed)
results = man.analyze(filtered)
reporting = mre.reporting(results, arguments.country)
reporting.to_csv('./data/results/Results.csv')
print(reporting)
print(
'\n\n======================| Pipeline is complete. You may find the results in the folder ./data/results |==============================\n\n'
)
def main():
print('======== Starting pipeline... ========')
assets, cf_liabs = mac.acquire_inputs()
combined_orig_cf, cf_liabs = mwr.wrangle(assets, cf_liabs)
assets_sell, assets_purchase, final_cf_combined = man.analyze_gaps(
assets, combined_orig_cf, cf_liabs)
mre.save_results(assets_sell, assets_purchase, final_cf_combined)
print(
'========================= Pipeline is complete. You may find the results in the folder ./data/results ========================='
)
def main(arg1, arg2):
data_personal_info = mac.acquire_personal_info(arg1)
print('A dataframe with personal info was created')
clean_gender = mwr.wrangle(data_personal_info)
country_names = mac.fetch_country()
print('A dataframe with country info was created')
career_info = mac.acquire_career_info(arg1)
print('A dataframe with career info was created')
job_titles = mac.fetch_job_titles(career_info)
print('Job titles successfully retrieved')
country_info = mac.acquire_country_info(arg1)
main_df = mwr.merge_dfs(country_info, career_info, clean_gender,
job_titles, country_names)
print('Main dataframe retreived')
final_table = man.analyze(main_df)
print(
'Final table with the results has been created in /data/results folder'
)
table_country = man.filter_country(arg2, final_table)
table_country.to_csv(r'data/results/final_table.csv',
index=False,
header=True)
def main(scrape):
print('Starting Pipeline...')
mac.acquire(scrape)
mwr.wrangle(scrape)
print('Finished Pipeline')
def main(scrape, download, model):
print('Starting Pipeline...')
mac.acquire(scrape)
mwr.wrangle(scrape, download)
man.analyze(model)
print('Finished Pipeline')