def test_joined_median_aggregate(self):
"""
Test join with median aggregate.
"""
mfl = MostFrequentLocation("2016-01-01", "2016-01-04", level="admin3")
rog = RadiusOfGyration("2016-01-01", "2016-01-04")
joined = mfl.join_aggregate(rog, method="median")
rawus_avg = (rog.get_dataframe().set_index("subscriber").join(
mfl.get_dataframe().set_index("subscriber")).set_index(
"name").ix["Rasuwa"].rog.median())
self.assertAlmostEqual(
joined.get_dataframe().set_index("name").ix["Rasuwa"].rog,
rawus_avg)
def test_query_can_be_subscriber_set_restricted(self):
"""Test that some queries can be limited to only a subset of subscribers."""
# Create a temporary table in the DB
con = Table.connection.engine
sql = "DROP TABLE IF EXISTS subscriber_list"
con.execute(sql)
sql = """CREATE TABLE subscriber_list (subscriber TEXT)"""
con.execute(sql)
formatted_subscribers = ",".join("('{}')".format(u)
for u in self.subscriber_list)
sql = """INSERT INTO subscriber_list (subscriber) VALUES {}""".format(
formatted_subscribers)
con.execute(sql)
rog = RadiusOfGyration("2016-01-01",
"2016-01-03",
subscriber_subset=Table("subscriber_list"))
hl = HomeLocation(*[
daily_location(d, subscriber_subset=Table("subscriber_list"))
for d in list_of_dates("2016-01-01", "2016-01-03")
])
rog_df = rog.get_dataframe()
hl_df = hl.get_dataframe()
sql = "DROP TABLE IF EXISTS subscriber_list"
con.execute(sql)
# Get the set of subscribers present in the dataframe, we need to handle the logic
# of msisdn_from/msisdn_to
calculated_subscriber_set = set(rog_df.subscriber)
self.assertEqual(calculated_subscriber_set, set(self.subscriber_list))
calculated_subscriber_set = set(hl_df.subscriber)
self.assertEqual(calculated_subscriber_set, set(self.subscriber_list))
class TestNumericSubsetting(TestCase):
def setUp(self):
self.rog = RadiusOfGyration("2016-01-01", "2016-01-02")
self.low = 150
self.high = 155
self.rog_df = self.rog.get_dataframe().query(
"{low} <= rog <= {high}".format(low=self.low, high=self.high))
self.sub = self.rog.numeric_subset(col="rog",
low=self.low,
high=self.high)
def _query_has_values(self, Q, expected_df):
"""
Test if the values of a dataframes columns are equal
to certain values.
"""
query_df = Q.get_dataframe()
assert_array_equal(expected_df.values, query_df.values)
def test_can_numsubset_with_low_and_high(self):
"""
flowmachine.RadiusOfGyration can be subset within a range
"""
self._query_has_values(self.sub, self.rog_df)
def test_can_numsubset_with_inf(self):
"""
flowmachine.RadiusOfGyration can be subset between -Inf and Inf
"""
low = -float("Infinity")
high = float("Infinity")
sub = self.rog.numeric_subset(col="rog", low=low, high=high)
df = self.rog.get_dataframe().query("{low} <= rog <= {high}".format(
low=low, high=high))
self._query_has_values(sub, df)
def test_call_with_str_raises_error(self):
"""
Numeric subset can't be called with a string in arguments low and high
"""
with self.assertRaises(TypeError):
self.rog.numeric_subset(col="rog", low="foo", high=self.high)
with self.assertRaises(TypeError):
self.rog.numeric_subset(col="rog", low=self.low, high="bar")
def test_can_be_stored(self):
"""
Test that flowmachine.NumericSubset can be stored.
"""
self.sub.store().result()
self.assertTrue(self.sub.is_stored)
# Test that the store is of the right length
sub = self.rog.numeric_subset(col="rog", low=self.low, high=self.high)
self.assertEqual(len(sub.get_dataframe()), len(self.rog_df))
def tearDown(self):
"""
Remove stored table from "can_be_stored" test.
"""
self.sub.invalidate_db_cache()
