def execute_process(self, key, **kwargs):
logging.info('Commencing caching of fundraiser totals data at: %s' %
self.CACHING_HOME)
end_time = TP.timestamp_from_obj(datetime.datetime.utcnow(), 1, 3)
""" DATA CONFIG """
""" set the metrics to plot """
lttdl = DL.LongTermTrendsLoader(db='db1025')
start_of_2011_fundraiser = '20111116000000'
countries = DL.CiviCRMLoader().get_ranked_donor_countries(
start_of_2011_fundraiser)
countries.append('Total')
""" Dictionary object storing lists of regexes - each expression must pass for a label to persist """
year_groups = dict()
for country in countries:
if cmp(country, 'Total') == 0:
year_groups['2011 Total'] = ['2011.*']
year_groups['2010 Total'] = ['2010.*']
else:
year_groups['2011 ' + country] = ['2011' + country]
year_groups['2010 ' + country] = ['2010' + country]
metrics = 'amount'
weights = ''
groups = year_groups
group_metrics = ['year', 'country']
metric_types = DL.LongTermTrendsLoader._MT_AMOUNT_
include_totals = False
include_others = False
hours_back = 0
time_unit = TP.DAY
""" END CONFIG """
""" For each metric use the LongTermTrendsLoader to generate the data to plot """
dr = DR.DataReporting()
times, counts = lttdl.run_fundrasing_totals(end_time, metric_name=metrics, metric_type=metric_types, groups=groups, group_metric=group_metrics, include_other=include_others, \
include_total=include_totals, hours_back=hours_back, weight_name=weights, time_unit=time_unit)
dict_param = dict()
for country in countries:
key_2011 = '2011 ' + country
key_2010 = '2010 ' + country
new_counts = dict()
new_counts[key_2010] = counts[key_2010]
new_counts[key_2011] = counts[key_2011]
new_times = dict()
new_times[key_2010] = times[key_2010]
new_times[key_2011] = times[key_2011]
dr._counts_ = new_counts
dr._times_ = new_times
empty_data = [0] * len(new_times[new_times.keys()[0]])
data = list()
data.append(dr.get_data_lists([''], empty_data))
dict_param[country] = Hlp.combine_data_lists(data)
self.clear_cached_data(key)
self.cache_data(dict_param, key)
logging.info('Caching complete.')
def execute_process(self, key, **kwargs):
logging.info('Commencing caching of long term trends data at: %s' %
self.CACHING_HOME)
end_time, start_time = TP.timestamps_for_interval(datetime.datetime.utcnow(), 1, \
hours=-self.VIEW_DURATION_HRS, resolution=1)
""" DATA CONFIG """
countries = DL.CiviCRMLoader().get_ranked_donor_countries(start_time)
countries = countries[1:6]
""" set the metrics to plot """
lttdl = DL.LongTermTrendsLoader(db='storage3')
""" Dictionary object storing lists of regexes - each expression must pass for a label to persist """
# country_groups = {'US': ['(US)'], 'CA': ['(CA)'], 'JP': ['(JP)'], 'IN': ['(IN)'], 'NL': ['(NL)']}
payment_groups = {'Credit Card': ['^cc$'], 'Paypal': ['^pp$']}
currency_groups = {
'USD': ['(USD)'],
'CAD': ['(CAD)'],
'JPY': ['(JPY)'],
'EUR': ['(EUR)']
}
lang_cntry_groups = {
'US': ['US..', '.{4}'],
'EN': ['[^U^S]en', '.{4}']
}
top_cntry_groups = dict()
for country in countries:
top_cntry_groups[country] = [country, '.{2}']
# To include click rate
# groups = [ lang_cntry_groups] metrics = ['click_rate'] metrics_index = [3]
# group_metrics = [DL.LongTermTrendsLoader._MT_RATE_] metric_types = ['country', 'language'] include_totals = [True] include_others = [True]
metrics = [
'impressions', 'views', 'donations', 'donations', 'amount',
'amount', 'diff_don', 'diff_don', 'donations', 'conversion_rate'
]
weights = ['', '', '', '', '', '', 'donations', 'donations', '', '']
metrics_index = [0, 1, 2, 2, 2, 4, 5, 5, 6, 6]
groups = [lang_cntry_groups, lang_cntry_groups, lang_cntry_groups, top_cntry_groups, lang_cntry_groups, currency_groups, \
lang_cntry_groups, lang_cntry_groups, payment_groups, payment_groups]
""" The metrics that are used to build a group string to be qualified via regex - the values of the list metrics are concatenated """
group_metrics = [['country', 'language'], ['country', 'language'], ['country', 'language'], \
['country', 'language'], ['country', 'language'], ['currency'], ['country', 'language'], \
['country', 'language'], ['payment_method'], ['payment_method']]
metric_types = [DL.LongTermTrendsLoader._MT_AMOUNT_, DL.LongTermTrendsLoader._MT_AMOUNT_, DL.LongTermTrendsLoader._MT_AMOUNT_, \
DL.LongTermTrendsLoader._MT_AMOUNT_, DL.LongTermTrendsLoader._MT_AMOUNT_, DL.LongTermTrendsLoader._MT_AMOUNT_, \
DL.LongTermTrendsLoader._MT_RATE_WEIGHTED_, DL.LongTermTrendsLoader._MT_RATE_WEIGHTED_, DL.LongTermTrendsLoader._MT_AMOUNT_, \
DL.LongTermTrendsLoader._MT_RATE_]
include_totals = [
True, True, True, False, True, True, False, False, False, True
]
include_others = [
True, True, True, False, True, True, True, True, True, False
]
hours_back = [0, 0, 0, 0, 0, 0, 24, 168, 0, 0]
time_unit = [
TP.HOUR, TP.HOUR, TP.HOUR, TP.HOUR, TP.HOUR, TP.HOUR, TP.HOUR,
TP.HOUR, TP.HOUR, TP.HOUR
]
data = list()
""" END CONFIG """
""" For each metric use the LongTermTrendsLoader to generate the data to plot """
for index in range(len(metrics)):
dr = DR.DataReporting()
times, counts = lttdl.run_query(start_time, end_time, metrics_index[index], metric_name=metrics[index], metric_type=metric_types[index], \
groups=groups[index], group_metric=group_metrics[index], include_other=include_others[index], \
include_total=include_totals[index], hours_back=hours_back[index], weight_name=weights[index], \
time_unit=time_unit[index])
times = TP.normalize_timestamps(times, False, time_unit[index])
dr._counts_ = counts
dr._times_ = times
empty_data = [0] * len(times[times.keys()[0]])
data.append(dr.get_data_lists([''], empty_data))
dict_param = Hlp.combine_data_lists(data)
dict_param['interval'] = self.VIEW_DURATION_HRS
dict_param['end_time'] = TP.timestamp_convert_format(end_time, 1, 2)
self.clear_cached_data(key)
self.cache_data(dict_param, key)
logging.info('Caching complete.')
def generate_summary(request):
try:
err_msg = ''
"""
PROCESS POST DATA
=================
Escape all user input that can be entered in text fields
"""
if 'utm_campaign' in request.POST:
utm_campaign = MySQLdb._mysql.escape_string(
request.POST['utm_campaign'])
if 'start_time' in request.POST:
start_time = MySQLdb._mysql.escape_string(
request.POST['start_time'].strip())
if not (TP.is_timestamp(start_time, 1)) and not (TP.is_timestamp(
start_time, 2)):
err_msg = 'Incorrectly formatted start timestamp.'
raise Exception()
if 'end_time' in request.POST:
end_time = MySQLdb._mysql.escape_string(
request.POST['end_time'].strip())
if not (TP.is_timestamp(end_time, 1)) and not (TP.is_timestamp(
end_time, 2)):
err_msg = 'Incorrectly formatted end timestamp.'
raise Exception()
if 'iso_filter' in request.POST:
country = MySQLdb._mysql.escape_string(request.POST['iso_filter'])
else:
country = '.{2}'
if 'measure_confidence' in request.POST:
if cmp(request.POST['measure_confidence'], 'yes') == 0:
measure_confidence = True
else:
measure_confidence = False
else:
measure_confidence = False
if 'one_step' in request.POST:
if cmp(request.POST['one_step'], 'yes') == 0:
use_one_step = True
else:
use_one_step = False
else:
use_one_step = False
if 'donations_only' in request.POST:
if cmp(request.POST['donations_only'], 'yes') == 0:
donations_only = True
else:
donations_only = False
else:
donations_only = False
""" Convert timestamp format if necessary """
if TP.is_timestamp(start_time, 2):
start_time = TP.timestamp_convert_format(start_time, 2, 1)
if TP.is_timestamp(end_time, 2):
end_time = TP.timestamp_convert_format(end_time, 2, 1)
""" =============================================== """
"""
GENERATE A REPORT SUMMARY TABLE
===============================
"""
if donations_only:
srl = DL.SummaryReportingLoader(
query_type=FDH._TESTTYPE_DONATIONS_)
else:
srl = DL.SummaryReportingLoader(
query_type=FDH._TESTTYPE_BANNER_LP_)
srl.run_query(start_time,
end_time,
utm_campaign,
min_views=-1,
country=country)
column_names = srl.get_column_names()
summary_results = srl.get_results()
if not (summary_results):
html_table = '<h3>No artifact summary data available for %s.</h3>' % utm_campaign
else:
summary_results_list = list()
for row in summary_results:
summary_results_list.append(list(row))
summary_results = summary_results_list
"""
Format results to encode html table cell markup in results
"""
if measure_confidence:
ret = DR.ConfidenceReporting(
query_type='', hyp_test='').get_confidence_on_time_range(
start_time,
end_time,
utm_campaign,
one_step=use_one_step,
country=country) # first get color codes on confidence
conf_colour_code = ret[0]
for row_index in range(len(summary_results)):
artifact_index = summary_results[row_index][
0] + '-' + summary_results[row_index][
1] + '-' + summary_results[row_index][2]
for col_index in range(len(column_names)):
is_coloured_cell = False
if column_names[col_index] in conf_colour_code.keys():
if artifact_index in conf_colour_code[
column_names[col_index]].keys():
summary_results[row_index][
col_index] = '<td style="background-color:' + conf_colour_code[
column_names[col_index]][
artifact_index] + ';">' + str(
summary_results[row_index]
[col_index]) + '</td>'
is_coloured_cell = True
if not (is_coloured_cell):
summary_results[row_index][
col_index] = '<td>' + str(
summary_results[row_index]
[col_index]) + '</td>'
html_table = DR.DataReporting()._write_html_table(
summary_results,
column_names,
use_standard_metric_names=True,
omit_cell_markup=True)
else:
html_table = DR.DataReporting()._write_html_table(
summary_results,
column_names,
use_standard_metric_names=True)
""" Generate totals only if it's a non-donation-only query """
if donations_only:
srl = DL.SummaryReportingLoader(
query_type=FDH._QTYPE_TOTAL_DONATIONS_)
else:
srl = DL.SummaryReportingLoader(query_type=FDH._QTYPE_TOTAL_)
srl.run_query(start_time,
end_time,
utm_campaign,
min_views=-1,
country=country)
total_summary_results = srl.get_results()
if not (total_summary_results):
html_table = html_table + '<div class="spacer"></div><div class="spacer"></div><h3>No data available for %s Totals.</h3>' % utm_campaign
else:
html_table = html_table + '<div class="spacer"></div><div class="spacer"></div>' + DR.DataReporting(
)._write_html_table(total_summary_results,
srl.get_column_names(),
use_standard_metric_names=True)
metric_legend_table = DR.DataReporting().get_standard_metrics_legend()
conf_legend_table = DR.ConfidenceReporting(
query_type='bannerlp',
hyp_test='TTest').get_confidence_legend_table()
html_table = '<h4><u>Metrics Legend:</u></h4><div class="spacer"></div>' + metric_legend_table + \
'<div class="spacer"></div><h4><u>Confidence Legend for Hypothesis Testing:</u></h4><div class="spacer"></div>' + conf_legend_table + '<div class="spacer"></div><div class="spacer"></div>' + html_table
"""
DETERMINE PAYMENT METHODS
=========================
"""
ccl = DL.CiviCRMLoader()
pm_data_counts, pm_data_conversions = ccl.get_payment_methods(
utm_campaign, start_time, end_time, country=country)
html_table_pm_counts = DR.IntervalReporting(
).write_html_table_from_rowlists(
pm_data_counts, ['Payment Method', 'Portion of Donations (%)'],
'Landing Page')
html_table_pm_conversions = DR.IntervalReporting(
).write_html_table_from_rowlists(pm_data_conversions, [
'Payment Method', 'Visits', 'Conversions', 'Conversion Rate (%)',
'Amount', 'Amount 25'
], 'Landing Page')
html_table = html_table + '<div class="spacer"></div><h4><u>Payment Methods Breakdown:</u></h4><div class="spacer"></div>' + html_table_pm_counts + \
'<div class="spacer"></div><div class="spacer"></div>' + html_table_pm_conversions + '<div class="spacer"></div><div class="spacer"></div>'
return render_to_response('tests/table_summary.html', {
'html_table': html_table,
'utm_campaign': utm_campaign
},
context_instance=RequestContext(request))
except Exception as inst:
if cmp(err_msg, '') == 0:
err_msg = 'Could not generate campaign tabular results.'
return index(request, err_msg=err_msg)
def show_campaigns(request, utm_campaign, **kwargs):
"""
PROCESS POST KWARGS
===================
"""
err_msg = ''
try:
err_msg = str(kwargs['kwargs']['err_msg'])
except:
pass
test_type_override = ''
try:
test_type_override = MySQLdb._mysql.escape_string(
request.POST['test_type_override'])
if test_type_override == 'Banner':
test_type_var = FDH._TESTTYPE_BANNER_
elif test_type_override == 'Landing Page':
test_type_var = FDH._TESTTYPE_LP_
elif test_type_override == 'Banner and LP':
test_type_var = FDH._TESTTYPE_BANNER_LP_
except:
test_type_var = ''
pass
try:
""" Find the earliest and latest page views for a given campaign """
lptl = DL.LandingPageTableLoader()
ccrml = DL.CiviCRMLoader()
start_time = ccrml.get_earliest_donation(utm_campaign)
end_time = ccrml.get_latest_donation(utm_campaign)
one_step = lptl.is_one_step(start_time, end_time, utm_campaign)
if not (one_step):
start_time = lptl.get_earliest_campaign_view(utm_campaign)
end_time = lptl.get_latest_campaign_view(utm_campaign)
interval = 1
""" Create reporting object to retrieve campaign data and write plots to image repo on disk """
ir = DR.IntervalReporting(was_run=False,
use_labels=False,
font_size=20,
plot_type='line',
query_type='campaign',
file_path=projSet.__web_home__ +
'campaigns/static/images/')
""" Produce analysis on the campaign view data """
ir.run(start_time,
end_time,
interval,
'views',
utm_campaign, {},
one_step=one_step)
"""
ESTIMATE THE START AND END TIME OF THE CAMPAIGN
===============================================
Search for the first instance when more than 10 views are observed over a sampling period
"""
col_names = ir._data_loader_.get_column_names()
views_index = col_names.index('views')
ts_index = col_names.index('ts')
row_list = list(ir._data_loader_._results_) # copy the query results
for row in row_list:
if row[views_index] > 100:
start_time_est = row[ts_index]
break
row_list.reverse()
for row in row_list:
if row[views_index] > 100:
end_time_est = row[ts_index]
break
"""
BUILD THE VISUALIZATION FOR THE TEST VIEWS OF THIS CAMAPAIGN
============================================================
"""
""" Read the test name """
ttl = DL.TestTableLoader()
row = ttl.get_test_row(utm_campaign)
test_name = ttl.get_test_field(row, 'test_name')
""" Regenerate the data using the estimated start and end times """
ir = DR.IntervalReporting(was_run=False,
use_labels=False,
font_size=20,
plot_type='line',
query_type='campaign',
file_path=projSet.__web_home__ +
'campaigns/static/images/')
ir.run(start_time_est,
end_time_est,
interval,
'views',
utm_campaign, {},
one_step=one_step)
""" Determine the type of test (if not overridden) and retrieve the artifacts """
test_type, artifact_name_list = FDH.get_test_type(
utm_campaign, start_time, end_time,
DL.CampaignReportingLoader(query_type=''), test_type_var)
return render_to_response('campaigns/show_campaigns.html', {'utm_campaign' : utm_campaign, 'test_name' : test_name, 'start_time' : start_time_est, 'end_time' : end_time_est, 'one_step' : one_step, \
'artifacts' : artifact_name_list, 'test_type' : test_type, 'err_msg' : err_msg}, context_instance=RequestContext(request))
except Exception as inst:
logging.error('Failed to correctly produce campaign diagnostics.')
logging.error(type(inst))
logging.error(inst.args)
logging.error(inst)
""" Return to the index page with an error """
err_msg = 'There is insufficient data to analyze this campaign: %s. Check to see if the <a href="/LML/">impressions have been loaded</a>. <br><br>ERROR:<br><br>%s' % (
utm_campaign, inst.__str__())
return index(request, kwargs={'err_msg': err_msg})
def generate_reporting_objects(test_name, start_time, end_time, campaign,
label_dict, label_dict_full, sample_interval,
test_interval, test_type, metric_types,
one_step_var, country):
""" Labels will always be metric names in this case """
# e.g. labels = {'Static banner':'20101227_JA061_US','Fading banner':'20101228_JAFader_US'}
use_labels_var = True
""" Build reporting objects """
ir_cmpgn = DR.IntervalReporting(use_labels=False,
font_size=20,
plot_type='line',
query_type='campaign',
file_path=projSet.__web_home__ +
'campaigns/static/images/')
"""
DETERMINE DONOR DOLLAR BREAKDOWN
================================
"""
try:
logging.info('')
logging.info('Determining Donations Distribution:')
logging.info('===================================\n')
DR.DonorBracketReporting(query_type=FDH._QTYPE_LP_,
file_path=projSet.__web_home__ +
'tests/static/images/').run(
start_time, end_time, campaign)
except:
pass
"""
DETERMINE CATEGORY DISTRIBUTION
===============================
"""
if (0):
DR.CategoryReporting(file_path=projSet.__web_home__ +
'tests/static/images/').run(
start_time, end_time, campaign)
"""
DETERMINE LANGUAGE BREAKDOWN
============================
"""
html_language = ''
if (1):
logging.info('')
logging.info('Determining Languages Distribution:')
logging.info('===================================\n')
columns, data = DL.CiviCRMLoader().get_donor_by_language(
campaign, start_time, end_time)
html_language = DR.DataReporting()._write_html_table(data, columns)
"""
DETERMINE PAYMENT METHODS
=========================
"""
logging.info('')
logging.info('Determining Payment Methods:')
logging.info('============================\n')
ccl = DL.CiviCRMLoader()
pm_data_counts, pm_data_conversions = ccl.get_payment_methods(
campaign, start_time, end_time, country=country)
html_table_pm_counts = DR.IntervalReporting(
).write_html_table_from_rowlists(
pm_data_counts, ['Payment Method', 'Portion of Donations (%)'],
'Landing Page')
html_table_pm_conversions = DR.IntervalReporting(
).write_html_table_from_rowlists(pm_data_conversions, [
'Payment Method', 'Visits', 'Conversions', 'Conversion Rate (%)',
'Amount', 'Amount 25'
], 'Landing Page')
"""
BUILD REPORTING OBJECTS
=======================
"""
if test_type == FDH._TESTTYPE_BANNER_:
ir = DR.IntervalReporting(use_labels=use_labels_var,
font_size=20,
plot_type='step',
query_type=FDH._QTYPE_BANNER_,
file_path=projSet.__web_home__ +
'tests/static/images/')
link_item = '<a href="http://meta.wikimedia.org/w/index.php?title=Special:NoticeTemplate/view&template=%s">%s</a>'
measured_metric = ['don_per_imp', 'amt_norm_per_imp', 'click_rate']
elif test_type == FDH._TESTTYPE_LP_:
ir = DR.IntervalReporting(use_labels=use_labels_var,
font_size=20,
plot_type='step',
query_type=FDH._QTYPE_LP_,
file_path=projSet.__web_home__ +
'tests/static/images/')
link_item = '<a href="http://meta.wikimedia.org/w/index.php?title=Special:NoticeTemplate/view&template=%s">%s</a>'
measured_metric = ['don_per_view', 'amt_norm_per_view']
elif test_type == FDH._TESTTYPE_BANNER_LP_:
ir = DR.IntervalReporting(use_labels=use_labels_var,
font_size=20,
plot_type='step',
query_type=FDH._QTYPE_BANNER_LP_,
file_path=projSet.__web_home__ +
'tests/static/images/')
link_item = '<a href="http://meta.wikimedia.org/w/index.php?title=Special:NoticeTemplate/view&template=%s">%s</a>'
measured_metric = [
'don_per_imp', 'amt_norm_per_imp', 'don_per_view',
'amt_norm_per_view', 'click_rate'
]
"""
GENERATE PLOTS FOR EACH METRIC OF INTEREST
==========================================
"""
logging.info('')
logging.info('Determining Metric Minutely Counts:')
logging.info('==================================\n')
for metric in metric_types:
ir.run(start_time,
end_time,
sample_interval,
metric,
campaign,
label_dict,
one_step=one_step_var,
country=country)
"""
CHECK THE CAMPAIGN VIEWS AND DONATIONS
======================================
"""
ir_cmpgn.run(start_time,
end_time,
sample_interval,
'views',
campaign, {},
one_step=one_step_var,
country=country)
ir_cmpgn.run(start_time,
end_time,
sample_interval,
'donations',
campaign, {},
one_step=one_step_var,
country=country)
"""
PERFORM HYPOTHESIS TESTING
==========================
"""
logging.info('')
logging.info('Executing Confidence Queries:')
logging.info('============================\n')
column_colours = dict()
confidence = list()
cr = DR.ConfidenceReporting(use_labels=use_labels_var,
font_size=20,
plot_type='line',
hyp_test='t_test',
query_type=test_type,
file_path=projSet.__web_home__ +
'tests/static/images/')
for metric in measured_metric:
ret = cr.run(test_name,
campaign,
metric,
label_dict,
start_time,
end_time,
sample_interval,
one_step=one_step_var,
country=country)
confidence.append(ret[0])
column_colours[metric] = ret[1]
"""
GENERATE A REPORT SUMMARY TABLE
===============================
"""
logging.info('')
logging.info('Generating Summary Report:')
logging.info('=========================\n')
"""
if one_step_var == True:
summary_start_time = DL.CiviCRMLoader().get_earliest_donation(campaign)
else:
summary_start_time = DL.LandingPageTableLoader().get_earliest_campaign_view(campaign)
summary_end_time = DL.CiviCRMLoader().get_latest_donation(campaign)
"""
srl = DL.SummaryReportingLoader(query_type=test_type)
srl.run_query(start_time,
end_time,
campaign,
one_step=one_step_var,
country=country)
columns = srl.get_column_names()
summary_results = srl.get_results()
"""
REMOVED - links to pipeline artifacts, this was broken and should be implemented properly later
"""
""" Get Winners, Losers, and percent increase """
winner = list()
loser = list()
percent_increase = list()
labels = list()
for item_long_name in label_dict:
labels.append(label_dict[item_long_name])
for metric in measured_metric:
ret = srl.compare_artifacts(label_dict.keys(), metric, labels=labels)
winner.append(ret[0])
loser.append(ret[1])
percent_increase.append(ret[2])
""" Compose table for showing artifact """
html_table = DR.DataReporting()._write_html_table(
summary_results,
columns,
coloured_columns=column_colours,
use_standard_metric_names=True)
metric_legend_table = DR.DataReporting().get_standard_metrics_legend()
conf_legend_table = DR.ConfidenceReporting(
query_type='bannerlp', hyp_test='TTest').get_confidence_legend_table()
html_table = '<h4><u>Metrics Legend:</u></h4><div class="spacer"></div>' + metric_legend_table + \
'<div class="spacer"></div><h4><u>Confidence Legend for Hypothesis Testing:</u></h4><div class="spacer"></div>' + conf_legend_table + '<div class="spacer"></div><div class="spacer"></div>' + html_table
""" Generate totals for the test summary """
srl = DL.SummaryReportingLoader(query_type=FDH._QTYPE_TOTAL_)
srl.run_query(start_time,
end_time,
campaign,
one_step=one_step_var,
country=country)
html_table = html_table + '<br><br>' + DR.DataReporting(
)._write_html_table(srl.get_results(),
srl.get_column_names(),
use_standard_metric_names=True)
return [
measured_metric, winner, loser, percent_increase, confidence,
html_table_pm_counts, html_table_pm_conversions, html_language,
html_table
]