From aed73bb7ed0adb4da4f05aadfa30cae95460b7bd Mon Sep 17 00:00:00 2001
From: junos <junos.lukan@ijs.si>
Date: Sat, 21 Aug 2021 18:12:02 +0200
Subject: [PATCH] Add fill values for communication for rows with no
 calls/smses.

---
 features/communication.py | 51 +++++++++++++++++++++++++++------------
 1 file changed, 35 insertions(+), 16 deletions(-)

diff --git a/features/communication.py b/features/communication.py
index d92bd29..e9d5c37 100644
--- a/features/communication.py
+++ b/features/communication.py
@@ -8,14 +8,21 @@ from setup import db_engine, session
 call_types = {1: "incoming", 2: "outgoing", 3: "missed"}
 sms_types = {1: "received", 2: "sent"}
 
-FEATURES_CALLS = (
-    ["no_calls_all"]
-    + ["no_" + call_type for call_type in call_types.values()]
-    + ["duration_total_" + call_types.get(1), "duration_total_" + call_types.get(2)]
-    + ["duration_max_" + call_types.get(1), "duration_max_" + call_types.get(2)]
-    + ["no_" + call_types.get(1) + "_ratio", "no_" + call_types.get(2) + "_ratio"]
-    + ["no_contacts_calls"]
-)
+FILL_NA_CALLS = {
+    "no_calls_all": 0,
+    "no_" + call_types.get(1): 0,
+    "no_" + call_types.get(2): 0,
+    "no_" + call_types.get(3): 0,
+    "duration_total_" + call_types.get(1): 0,
+    "duration_total_" + call_types.get(2): 0,
+    "duration_max_" + call_types.get(1): 0,
+    "duration_max_" + call_types.get(2): 0,
+    "no_" + call_types.get(1) + "_ratio": 1 / 3,  # Three different types
+    "no_" + call_types.get(2) + "_ratio": 1 / 3,
+    "no_contacts_calls": 0,
+}
+
+FEATURES_CALLS = list(FILL_NA_CALLS.keys())
 
 # FEATURES_CALLS =
 # ["no_calls_all",
@@ -23,19 +30,24 @@ FEATURES_CALLS = (
 # "duration_total_incoming", "duration_total_outgoing",
 # "duration_max_incoming", "duration_max_outgoing",
 # "no_incoming_ratio", "no_outgoing_ratio",
-# "no_contacts"]
+# "no_contacts_calls"]
+
+FILL_NA_SMS = {
+    "no_sms_all": 0,
+    "no_" + sms_types.get(1): 0,
+    "no_" + sms_types.get(2): 0,
+    "no_" + sms_types.get(1) + "_ratio": 1 / 2,  # Two different types
+    "no_" + sms_types.get(2) + "_ratio": 1 / 2,
+    "no_contacts_sms": 0,
+}
+
+FEATURES_SMS = list(FILL_NA_SMS.keys())
 
-FEATURES_SMS = (
-    ["no_sms_all"]
-    + ["no_" + sms_type for sms_type in sms_types.values()]
-    + ["no_" + sms_types.get(1) + "_ratio", "no_" + sms_types.get(2) + "_ratio"]
-    + ["no_contacts_sms"]
-)
 # FEATURES_SMS =
 # ["no_sms_all",
 #  "no_received", "no_sent",
 #  "no_received_ratio", "no_sent_ratio",
-#  "no_contacts"]
+#  "no_contacts_sms"]
 
 FEATURES_CALLS_SMS_PROP = [
     "proportion_calls_all",
@@ -45,8 +57,15 @@ FEATURES_CALLS_SMS_PROP = [
     "proportion_calls_missed_sms_received",
 ]
 
+FILL_NA_CALLS_SMS_PROP = {
+    key: 1 / 2 for key in FEATURES_CALLS_SMS_PROP
+}  # All of the form of a / (a + b).
+
 FEATURES_CALLS_SMS_ALL = FEATURES_CALLS + FEATURES_SMS + FEATURES_CALLS_SMS_PROP
 
+FILL_NA_CALLS_SMS_ALL = FILL_NA_CALLS | FILL_NA_SMS | FILL_NA_CALLS_SMS_PROP
+# As per PEP-584 a union for dicts was implemented in Python 3.9.0.
+
 
 def get_call_data(usernames: Collection) -> pd.DataFrame:
     """