junos
/
stress_at_work_analysis
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Clarify names for no_all calls/sms feature. 

Add another test.
communication
junos 2021-08-18 15:23:30 +02:00
parent a2a44c202a
commit 1bc996413e
2 changed files with 14 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
features/communication.py
View File

@ -141,11 +141,11 @@ def count_comms(comm_df: pd.DataFrame) -> pd.DataFrame:
.add_prefix("no_") .add_prefix("no_")
) )
# Count calls by type. # Count calls by type.
comm_counts["no_all"] = comm_counts.sum(axis=1) comm_counts["no_calls_all"] = comm_counts.sum(axis=1)
# Add a total count of calls. # Add a total count of calls.
comm_counts = comm_counts.assign( comm_counts = comm_counts.assign(
no_incoming_ratio=lambda x: x.no_incoming / x.no_all, no_incoming_ratio=lambda x: x.no_incoming / x.no_calls_all,
no_outgoing_ratio=lambda x: x.no_outgoing / x.no_all, no_outgoing_ratio=lambda x: x.no_outgoing / x.no_calls_all,
) )
# Ratio of incoming and outgoing calls to all calls. # Ratio of incoming and outgoing calls to all calls.
comm_duration_total = ( comm_duration_total = (
@ -181,11 +181,11 @@ def count_comms(comm_df: pd.DataFrame) -> pd.DataFrame:
.rename(columns=sms_types) .rename(columns=sms_types)
.add_prefix("no_") .add_prefix("no_")
) )
comm_counts["no_all"] = comm_counts.sum(axis=1) comm_counts["no_sms_all"] = comm_counts.sum(axis=1)
# Add a total count of messages. # Add a total count of messages.
comm_features = comm_counts.assign( comm_features = comm_counts.assign(
no_received_ratio=lambda x: x.no_received / x.no_all, no_received_ratio=lambda x: x.no_received / x.no_sms_all,
no_sent_ratio=lambda x: x.no_sent / x.no_all, no_sent_ratio=lambda x: x.no_sent / x.no_sms_all,
) )
# Ratio of incoming and outgoing messages to all messages. # Ratio of incoming and outgoing messages to all messages.
else: else:
@ -280,7 +280,7 @@ def calls_sms_features(df_calls: pd.DataFrame, df_sms: pd.DataFrame) -> pd.DataF
.reset_index() # Make participant_id a regular column .reset_index() # Make participant_id a regular column
.assign( .assign(
proportion_calls=( proportion_calls=(
lambda x: x.no_all_calls / (x.no_all_calls + x.no_all_sms) lambda x: x.no_calls_all / (x.no_calls_all + x.no_sms_all)
), ),
proportion_calls_incoming=( proportion_calls_incoming=(
lambda x: x.no_incoming / (x.no_incoming + x.no_received) lambda x: x.no_incoming / (x.no_incoming + x.no_received)

8
test/test_communication.py
View File

@ -5,7 +5,7 @@ import pandas as pd
from numpy.random import default_rng from numpy.random import default_rng
from pandas.testing import assert_series_equal from pandas.testing import assert_series_equal
from features.communication import count_comms, enumerate_contacts, get_call_data from features.communication import *
rng = default_rng() rng = default_rng()
@ -78,8 +78,14 @@ class CallsFeatures(unittest.TestCase):
self.features = count_comms(self.calls) self.features = count_comms(self.calls)
print(self.features) print(self.features)
self.assertIsInstance(self.features, pd.DataFrame) self.assertIsInstance(self.features, pd.DataFrame)
self.assertCountEqual(self.features.columns.to_list(), FEATURES_CALLS)
def test_count_comms_sms(self): def test_count_comms_sms(self):
self.features = count_comms(self.sms) self.features = count_comms(self.sms)
print(self.features) print(self.features)
self.assertIsInstance(self.features, pd.DataFrame) self.assertIsInstance(self.features, pd.DataFrame)
def test_calls_sms_features(self):
self.features_call_sms = calls_sms_features(self.calls, self.sms)
print(self.features_call_sms.columns)
self.assertIsInstance(self.features_call_sms, pd.DataFrame)