Calculate common features outside if...else.
parent
4740e94d37
commit
a2a44c202a
|
@ -164,16 +164,8 @@ def count_comms(comm_df: pd.DataFrame) -> pd.DataFrame:
|
||||||
.add_prefix("duration_max_")
|
.add_prefix("duration_max_")
|
||||||
)
|
)
|
||||||
# Max call duration by type
|
# Max call duration by type
|
||||||
comm_contacts_counts = (
|
|
||||||
enumerate_contacts(comm_df)
|
|
||||||
.groupby(["participant_id"])
|
|
||||||
.nunique()["contact_id"]
|
|
||||||
.rename("no_contacts")
|
|
||||||
)
|
|
||||||
# Number of communication contacts
|
|
||||||
comm_features = comm_counts.join(comm_duration_total)
|
comm_features = comm_counts.join(comm_duration_total)
|
||||||
comm_features = comm_features.join(comm_duration_max)
|
comm_features = comm_features.join(comm_duration_max)
|
||||||
comm_features = comm_features.join(comm_contacts_counts)
|
|
||||||
try:
|
try:
|
||||||
comm_features.drop(columns="duration_total_" + call_types[3], inplace=True)
|
comm_features.drop(columns="duration_total_" + call_types[3], inplace=True)
|
||||||
comm_features.drop(columns="duration_max_" + call_types[3], inplace=True)
|
comm_features.drop(columns="duration_max_" + call_types[3], inplace=True)
|
||||||
|
@ -196,16 +188,16 @@ def count_comms(comm_df: pd.DataFrame) -> pd.DataFrame:
|
||||||
no_sent_ratio=lambda x: x.no_sent / x.no_all,
|
no_sent_ratio=lambda x: x.no_sent / x.no_all,
|
||||||
)
|
)
|
||||||
# Ratio of incoming and outgoing messages to all messages.
|
# Ratio of incoming and outgoing messages to all messages.
|
||||||
comm_contacts_counts = (
|
|
||||||
enumerate_contacts(comm_df)
|
|
||||||
.groupby(["participant_id"])
|
|
||||||
.nunique()["contact_id"]
|
|
||||||
.rename("no_contacts")
|
|
||||||
)
|
|
||||||
# Number of communication contacts
|
|
||||||
comm_features = comm_features.join(comm_contacts_counts)
|
|
||||||
else:
|
else:
|
||||||
raise KeyError("The dataframe contains neither call_type or message_type")
|
raise KeyError("The dataframe contains neither call_type or message_type")
|
||||||
|
comm_contacts_counts = (
|
||||||
|
enumerate_contacts(comm_df)
|
||||||
|
.groupby(["participant_id"])
|
||||||
|
.nunique()["contact_id"]
|
||||||
|
.rename("no_contacts")
|
||||||
|
)
|
||||||
|
# Number of communication contacts
|
||||||
|
comm_features = comm_features.join(comm_contacts_counts)
|
||||||
return comm_features
|
return comm_features
|
||||||
|
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue