stress_at_work_analysis/features/communication.py

191 lines
6.5 KiB
Python
Raw Normal View History

from collections.abc import Collection
import pandas as pd
from config.models import SMS, Call, Participant
from setup import db_engine, session
call_types = {1: "incoming", 2: "outgoing", 3: "missed"}
sms_types = {1: "received", 2: "sent"}
def get_call_data(usernames: Collection) -> pd.DataFrame:
2021-04-06 14:32:18 +02:00
"""
Read the data from the calls table and return it in a dataframe.
Parameters
----------
usernames: Collection
2021-04-06 14:32:18 +02:00
A list of usernames to put into the WHERE condition.
Returns
-------
df_calls: pd.DataFrame
A dataframe of call data.
"""
query_calls = (
session.query(Call, Participant.username)
.filter(Participant.id == Call.participant_id)
.filter(Participant.username.in_(usernames))
)
with db_engine.connect() as connection:
df_calls = pd.read_sql(query_calls.statement, connection)
return df_calls
def get_sms_data(usernames: Collection) -> pd.DataFrame:
"""
Read the data from the sms table and return it in a dataframe.
Parameters
----------
usernames: Collection
A list of usernames to put into the WHERE condition.
Returns
-------
df_sms: pd.DataFrame
A dataframe of call data.
"""
query_sms = (
session.query(SMS, Participant.username)
.filter(Participant.id == SMS.participant_id)
.filter(Participant.username.in_(usernames))
)
with db_engine.connect() as connection:
df_sms = pd.read_sql(query_sms.statement, connection)
return df_sms
def enumerate_contacts(comm_df: pd.DataFrame) -> pd.DataFrame:
2021-04-06 14:32:18 +02:00
"""
Count contacts (callers, senders) and enumerate them by their frequency.
Parameters
----------
comm_df: pd.DataFrame
A dataframe of calls or SMSes.
Returns
-------
comm_df: pd.DataFrame
The altered dataframe with the column contact_id, arranged by frequency.
"""
2021-04-06 11:48:37 +02:00
contact_counts = (
comm_df.groupby(
["participant_id", "trace"]
) # We want to count rows by participant_id and trace
.size() # Count rows
.reset_index() # Make participant_id a regular column.
.rename(columns={0: "freq"})
.sort_values(["participant_id", "freq"], ascending=False)
# First sort by participant_id and then by call frequency.
2021-04-06 11:48:37 +02:00
)
# We now have a frequency table of different traces (contacts) *within* each participant_id.
# Next, enumerate these contacts.
# In other words, recode the contacts into integers from 0 to n_contacts,
# so that the first one is contacted the most often.
contact_ids = (
2021-05-04 17:23:52 +02:00
contact_counts.groupby("participant_id") # Group again for enumeration.
.cumcount() # Enumerate (count) rows *within* participants.
.to_frame("contact_id")
)
contact_counts = contact_counts.join(contact_ids)
# Add these contact_ids to the temporary (grouped) data frame.
comm_df = comm_df.merge(contact_counts, on=["participant_id", "trace"])
# Add these contact_ids to the original data frame.
return comm_df
def count_comms(comm_df: pd.DataFrame) -> pd.DataFrame:
"""
Calculate frequencies (and duration) of messages (or calls), grouped by their types.
Parameters
----------
comm_df: pd.DataFrame
A dataframe of calls or SMSes.
Returns
-------
comm_features: pd.DataFrame
A list of communication features for every participant.
2021-04-09 15:33:52 +02:00
These are:
* the number of calls by type (incoming, outgoing missed) and in total,
* the ratio of incoming and outgoing calls to the total number of calls,
* the total and maximum duration of calls by type, and
* the number of messages by type (received, sent).
"""
if "call_type" in comm_df:
comm_counts = (
comm_df.value_counts(subset=["participant_id", "call_type"])
.unstack()
.rename(columns=call_types)
.add_prefix("no_")
)
# Count calls by type.
comm_counts["no_all"] = comm_counts.sum(axis=1)
# Add a total count of calls.
comm_counts = comm_counts.assign(
no_incoming_ratio=lambda x: x.no_incoming / x.no_all,
no_outgoing_ratio=lambda x: x.no_outgoing / x.no_all,
)
# Ratio of incoming and outgoing calls to all calls.
comm_duration_total = (
comm_df.groupby(["participant_id", "call_type"])
.sum()["call_duration"]
.unstack()
.rename(columns=call_types)
.add_prefix("duration_total_")
)
# Total call duration by type.
comm_duration_max = (
comm_df.groupby(["participant_id", "call_type"])
.max()["call_duration"]
.unstack()
.rename(columns=call_types)
.add_prefix("duration_max_")
)
# Max call duration by type
comm_features = comm_counts.join(comm_duration_total)
comm_features = comm_features.join(comm_duration_max)
try:
comm_features.drop(columns="duration_total_" + call_types[3], inplace=True)
comm_features.drop(columns="duration_max_" + call_types[3], inplace=True)
# The missed calls are always of 0 duration.
except KeyError:
pass
# If there were no missed calls, this exception is raised.
# But we are dropping the column anyway, so no need to deal with the exception.
elif "message_type" in comm_df:
comm_counts = (
comm_df.value_counts(subset=["participant_id", "message_type"])
.unstack()
.rename(columns=sms_types)
.add_prefix("no_")
)
comm_counts["no_all"] = comm_counts.sum(axis=1)
# Add a total count of messages.
comm_features = comm_counts.assign(
no_received_ratio=lambda x: x.no_received / x.no_all,
no_sent_ratio=lambda x: x.no_sent / x.no_all,
)
# Ratio of incoming and outgoing messages to all messages.
else:
raise KeyError("The dataframe contains neither call_type or message_type")
return comm_features
def contact_features():
# TODO Implement a method that takes a DF with enumerated contacts as argument and calculates:
# * Duration of calls per caller (for most common callers)
# * Determine work vs non-work contacts by work hours heuristics
# * Numer of people contacted
# And similarly for SMS.
pass
def calls_sms_features():
# TODO Relate the calls and sms data, such as comparing the number of (missed) calls and messages.
pass