Compile a list of contact features and add a test.
parent
c88336481e
commit
2d78aacd18
|
@ -37,6 +37,14 @@ FEATURES_SMS = (
|
|||
# "no_received_ratio", "no_sent_ratio",
|
||||
# "no_contacts"]
|
||||
|
||||
FEATURES_CONTACT = [
|
||||
"proportion_calls_all",
|
||||
"proportion_calls_incoming",
|
||||
"proportion_calls_outgoing",
|
||||
"proportion_calls_contacts",
|
||||
"proportion_calls_missed_sms_received",
|
||||
]
|
||||
|
||||
|
||||
def get_call_data(usernames: Collection) -> pd.DataFrame:
|
||||
"""
|
||||
|
@ -287,38 +295,26 @@ def calls_sms_features(df_calls: pd.DataFrame, df_sms: pd.DataFrame) -> pd.DataF
|
|||
"""
|
||||
count_calls = count_comms(df_calls)
|
||||
count_sms = count_comms(df_sms)
|
||||
count_joined = (
|
||||
count_calls.merge(
|
||||
count_sms, on="participant_id", suffixes=("_calls", "_sms")
|
||||
) # Merge calls and sms features
|
||||
.reset_index() # Make participant_id a regular column
|
||||
.assign(
|
||||
proportion_calls=(
|
||||
lambda x: x.no_calls_all / (x.no_calls_all + x.no_sms_all)
|
||||
),
|
||||
proportion_calls_incoming=(
|
||||
lambda x: x.no_incoming / (x.no_incoming + x.no_received)
|
||||
),
|
||||
proportion_calls_missed_sms_received=(
|
||||
lambda x: x.no_missed / (x.no_missed + x.no_received)
|
||||
),
|
||||
proportion_calls_outgoing=(
|
||||
lambda x: x.no_outgoing / (x.no_outgoing + x.no_sent)
|
||||
),
|
||||
proportion_calls_contacts=(
|
||||
lambda x: x.no_contacts_calls
|
||||
/ (x.no_contacts_calls + x.no_contacts_sms)
|
||||
)
|
||||
# Calculate new features and create additional columns
|
||||
)[
|
||||
[
|
||||
"participant_id",
|
||||
"proportion_calls",
|
||||
"proportion_calls_incoming",
|
||||
"proportion_calls_outgoing",
|
||||
"proportion_calls_contacts",
|
||||
"proportion_calls_missed_sms_received",
|
||||
]
|
||||
] # Filter out only the relevant features
|
||||
)
|
||||
count_joined = count_calls.merge(
|
||||
count_sms, on="participant_id", suffixes=("_calls", "_sms")
|
||||
).assign( # Merge calls and sms features
|
||||
proportion_calls_all=(
|
||||
lambda x: x.no_calls_all / (x.no_calls_all + x.no_sms_all)
|
||||
),
|
||||
proportion_calls_incoming=(
|
||||
lambda x: x.no_incoming / (x.no_incoming + x.no_received)
|
||||
),
|
||||
proportion_calls_missed_sms_received=(
|
||||
lambda x: x.no_missed / (x.no_missed + x.no_received)
|
||||
),
|
||||
proportion_calls_outgoing=(
|
||||
lambda x: x.no_outgoing / (x.no_outgoing + x.no_sent)
|
||||
),
|
||||
proportion_calls_contacts=(
|
||||
lambda x: x.no_contacts_calls / (x.no_contacts_calls + x.no_contacts_sms)
|
||||
)
|
||||
# Calculate new features and create additional columns
|
||||
)[
|
||||
FEATURES_CONTACT
|
||||
] # Filter out only the relevant features
|
||||
return count_joined
|
||||
|
|
|
@ -86,5 +86,8 @@ class CallsFeatures(unittest.TestCase):
|
|||
|
||||
def test_calls_sms_features(self):
|
||||
self.features_call_sms = calls_sms_features(self.calls, self.sms)
|
||||
print(self.features_call_sms.columns)
|
||||
print(self.features_call_sms)
|
||||
self.assertIsInstance(self.features_call_sms, pd.DataFrame)
|
||||
self.assertCountEqual(
|
||||
self.features_call_sms.columns.to_list(), FEATURES_CONTACT
|
||||
)
|
||||
|
|
Loading…
Reference in New Issue