def test_os_distribution_country_list(spark, main_summary_data):
main_summary = spark.createDataFrame(*main_summary_data)
with_country_list = os_on_date(main_summary,
'20180201',
country_list=['DE'])
expected = [{
"country": "All",
"submission_date_s3": "20180201",
"os": "Windows 10",
"pct_on_os": 50.0
}, {
"country": "All",
"submission_date_s3": "20180201",
"os": "Mac OS X",
"pct_on_os": 50.0
}, {
"country": "DE",
"submission_date_s3": "20180201",
"os": "Mac OS X",
"pct_on_os": 50.0
}, {
"country": "DE",
"submission_date_s3": "20180201",
"os": "Windows 10",
"pct_on_os": 50.0
}]
is_same(spark, with_country_list, expected)
def test_locale_country_list(spark, main_summary_data):
main_summary = spark.createDataFrame(*main_summary_data)
with_country_list = locale_on_date(main_summary,
'20180201',
4,
country_list=['DE'])
expected = [{
"country": "All",
"submission_date_s3": "20180201",
"locale": "en-US",
"pct_on_locale": 50.0
}, {
"country": "All",
"submission_date_s3": "20180201",
"locale": "DE",
"pct_on_locale": 50.0
}, {
"country": "DE",
"submission_date_s3": "20180201",
"locale": "en-US",
"pct_on_locale": 50.0
}, {
"country": "DE",
"submission_date_s3": "20180201",
"locale": "DE",
"pct_on_locale": 50.0
}]
is_same(spark, with_country_list, expected)
def test_get_avg_daily_usage_no_country_list(spark, main_summary_data):
main_summary = spark.createDataFrame(*main_summary_data)
without_country_list = get_daily_avg_session(main_summary, "20180201")
expected = [{
"country": "All",
"submission_date_s3": "20180201",
"avg_daily_usage(hours)": 300.0 / 3600 / 2.0
}]
is_same(spark, without_country_list, expected)
def test_get_avg_intensity_no_country_list(spark, main_summary_data):
main_summary = spark.createDataFrame(*main_summary_data)
without_country_list = get_avg_intensity(main_summary, "20180201")
expected = [{
"country": "All",
"submission_date_s3": "20180201",
"avg_intensity": 1.0
}]
is_same(spark, without_country_list, expected)
def test_pct_tracking_protection_no_country_list(spark, main_summary_data):
main_summary = spark.createDataFrame(*main_summary_data)
without_country_list = pct_tracking_protection(main_summary, '20180201')
expected = [{
"submission_date_s3": "20180201",
"country": "All",
"pct_TP": 50.0
}]
is_same(spark, without_country_list, expected)
def test_has_addons_no_country_list(spark, main_summary_data):
main_summary = spark.createDataFrame(*main_summary_data)
without_country_list = get_addon(main_summary, '20180201')
expected = [{
"country": "All",
"submission_date_s3": "20180201",
"pct_addon": 100.0
}]
is_same(spark, without_country_list, expected)
def test_new_users_no_country_list(spark, main_summary_data):
main_summary = spark.createDataFrame(*main_summary_data)
without_country_list = new_users(main_summary, '20180201')
expected = [{
"country": "All",
"submission_date_S3": "20180201",
"pct_new_user": 50.0
}]
is_same(spark, without_country_list, expected)
def test_pct_latest_version_no_country_list(spark, main_summary_data):
main_summary = spark.createDataFrame(*main_summary_data)
without_country_list = pct_new_version(main_summary, "20180201")
expected = [{
"country": "All",
"submission_date_s3": "20180201",
"pct_latest_version": 50.0
}]
is_same(spark, without_country_list, expected)
def test_top_10_addons_no_country_list(spark, main_summary_data):
main_summary = spark.createDataFrame(*main_summary_data)
without_country_list = top_10_addons_on_date(main_summary, '20180201', 5)
expected = [{
"country": "All",
"submission_date_s3": "20180201",
"addon_id": 'disableSHA1rollout',
"addon_name": 'SHA-1 deprecation staged rollout',
"pct_with_addon": 100.0
}]
is_same(spark, without_country_list, expected)
def test_YAU_no_country_list(spark, main_summary_data):
main_summary = spark.createDataFrame(*main_summary_data)
without_country_list = getYAU(main_summary,
'20180201',
sample_factor=100.0 / 1)
expected = [{
"country": "All",
"MAU": 200,
"submission_date_s3": "20180201"
}]
is_same(spark, without_country_list, expected)
def test_MAU_no_country_list(spark, main_summary_data):
main_summary = spark.createDataFrame(*main_summary_data)
without_country_list = getMAU(main_summary,
date='20180201',
sample_factor=100.0 / 1)
expected = [{
"country": "All",
"active_users": 200,
"submission_date_s3": "20180201"
}]
is_same(spark, without_country_list, expected, verbose=True)
def test_integration_missing_fields_no_country_list(
spark, main_summary_data_null_value):
''' tests without country list for data with all/some of a given field are null, '', or zero
'''
main_summary = spark.createDataFrame(*main_summary_data_null_value)
usage, os, locales, top10addon = agg_usage(main_summary,
date='20180201',
period=7,
sample_factor=100.0 / 1,
country_list=None)
expected_usage = [{
"submission_date_s3": "20180201",
"country": "All",
"avg_daily_usage(hours)": 500.0 / 3600 / 4.0,
"avg_intensity": 0.75,
"pct_latest_version": 0.0,
"pct_TP": 25.0,
"MAU": 400,
"YAU": 400,
"pct_new_user": 25.0,
"pct_addon": 100.0
}]
expected_os = [{
"country": "All",
"submission_date_s3": "20180201",
"os": "Windows 10",
"pct_on_os": 25.0
}, {
"country": "All",
"submission_date_s3": "20180201",
"os": "Mac OS X",
"pct_on_os": 75.0
}]
expected_locales = [{
"country": "All",
"submission_date_s3": "20180201",
"locale": "en-US",
"pct_on_locale": 50.0
}, {
"country": "All",
"submission_date_s3": "20180201",
"locale": "DE",
"pct_on_locale": 50.0
}]
expected_addons = [{
"country": "All",
"submission_date_s3": "20180201",
"addon_id": u'disableSHA1rollout',
"addon_name": u'SHA-1 deprecation staged rollout',
"pct_with_addon": 100.0
}]
is_same(spark, usage, expected_usage)
is_same(spark, os, expected_os)
is_same(spark, locales, expected_locales)
is_same(spark, top10addon, expected_addons)
def test_integration_no_country_list(spark, main_summary_data):
main_summary = spark.createDataFrame(*main_summary_data)
usage, os, locales, top10addon = agg_usage(main_summary,
date='20180201',
period=1,
sample_factor=100.0 / 1,
country_list=None)
expected_usage = [{
"submission_date_s3": "20180201",
"country": "All",
"avg_daily_usage(hours)": 300.0 / 3600 / 2.0,
"avg_intensity": 1.0,
"pct_latest_version": 50.0,
"pct_TP": 50.0,
"MAU": 200,
"YAU": 200,
"pct_new_user": 50.0,
"pct_addon": 100.0
}]
expected_os = [{
"country": "All",
"submission_date_s3": "20180201",
"os": "Windows 10",
"pct_on_os": 50.0
}, {
"country": "All",
"submission_date_s3": "20180201",
"os": "Mac OS X",
"pct_on_os": 50.0
}]
expected_locales = [{
"country": "All",
"submission_date_s3": "20180201",
"locale": "en-US",
"pct_on_locale": 50.0
}, {
"country": "All",
"submission_date_s3": "20180201",
"locale": "DE",
"pct_on_locale": 50.0
}]
expected_addons = [{
"country": "All",
"submission_date_s3": "20180201",
"addon_id": u'disableSHA1rollout',
"addon_name": u'SHA-1 deprecation staged rollout',
"pct_with_addon": 100.0
}]
is_same(spark, usage, expected_usage)
is_same(spark, os, expected_os)
is_same(spark, locales, expected_locales)
is_same(spark, top10addon, expected_addons)
def test_MAU_country_list(spark, main_summary_data):
main_summary = spark.createDataFrame(*main_summary_data)
with_country_list = getMAU(main_summary,
date='20180201',
sample_factor=100.0 / 1,
country_list=["DE"])
expected = [{
"country": "All",
"MAU": 200,
"submission_date_s3": "20180201"
}, {
"country": "DE",
"MAU": 200,
"submission_date_s3": "20180201"
}]
is_same(spark, with_country_list, expected)
def test_integration_multiple_countries_and_days_no_country_list(
spark, main_summary_data_multiple):
''' tests without country list for data including the following cases:
- multiple countries
a)include countries that are not in country list
b)include countries into country_list that are not in data
- clients with only pings from outside date range
- clients with some pings from outside date range
'''
main_summary = spark.createDataFrame(*main_summary_data_multiple)
usage, locales, top10addon = agg_usage(main_summary,
date='20180201',
period=7,
sample_factor=100.0 / 1,
country_list=None)
expected_usage = [{
"submission_date_s3": "20180201",
"country": "All",
"avg_daily_usage(hours)": 600.0 / 3600 / 5.0,
"avg_intensity": 1.0,
"pct_latest_version": 80.0,
"pct_TP": 20.0,
"MAU": 500,
"YAU": 600,
"pct_new_user": 40.0,
"pct_addon": 100.0
}]
expected_locales = [{
"country": "All",
"submission_date_s3": "20180201",
"locale": "en-US",
"pct_on_locale": 60.0
}, {
"country": "All",
"submission_date_s3": "20180201",
"locale": "DE",
"pct_on_locale": 40.0
}]
expected_addons = [{
"country": "All",
"submission_date_s3": "20180201",
"addon_id": u'disableSHA1rollout',
"addon_name": u'SHA-1 deprecation staged rollout',
"pct_with_addon": 100.0
}]
is_same(spark, usage, expected_usage)
is_same(spark, locales, expected_locales)
is_same(spark, top10addon, expected_addons)
