From f3ca56cdbf22d7eed38f920889c4b19f49da7760 Mon Sep 17 00:00:00 2001
From: Primoz <sisko.primoz@gmail.com>
Date: Fri, 14 Oct 2022 14:46:28 +0000
Subject: [PATCH] Start with ERS logic integration within Snakemake.

---
 config.yaml                                   |  3 +++
 rules/preprocessing.smk                       | 21 +++++++++++++++++++
 .../process_user_event_related_segments.py    | 19 +++++++++++++++++
 3 files changed, 43 insertions(+)
 create mode 100644 src/data/process_user_event_related_segments.py

diff --git a/config.yaml b/config.yaml
index 454f8dae..55a626e8 100644
--- a/config.yaml
+++ b/config.yaml
@@ -24,6 +24,9 @@ TIME_SEGMENTS: &time_segments
   TYPE: EVENT # FREQUENCY, PERIODIC, EVENT
   FILE: "data/external/straw_events.csv"
   INCLUDE_PAST_PERIODIC_SEGMENTS: TRUE # Only relevant if TYPE=PERIODIC, see docs
+  TAILORED_EVENTS: # Only relevant if TYPE=EVENT
+    COMPUTE: True
+    PARAMETER_ONE: "something"
 
 # See https://www.rapids.science/latest/setup/configuration/#timezone-of-your-study
 TIMEZONE: 
diff --git a/rules/preprocessing.smk b/rules/preprocessing.smk
index fb583459..c119434b 100644
--- a/rules/preprocessing.smk
+++ b/rules/preprocessing.smk
@@ -249,3 +249,24 @@ rule empatica_readable_datetime:
         "data/raw/{pid}/empatica_{sensor}_with_datetime.csv"
     script:
         "../src/data/datetime/readable_datetime.R"
+
+
+rule extract_event_information_from_esm:
+    input:
+        esm_raw_input = "data/raw/{pid}/phone_esm_raw.csv"
+    params:
+        stage = "extract"
+    output:
+        "data/raw/ers/{pid}_ers.csv"
+    script:
+        "../src/data/process_user_event_related_segments.py"
+
+rule create_event_related_segments_file:
+    input:
+        ers_files = expand("data/raw/{pid}_ers.csv", pid=config["PIDS"])
+    params:
+        stage = "merge"
+    output:
+        "data/external/straw_events.csv"
+    script:
+        "../src/data/process_user_event_related_segments.py"
\ No newline at end of file
diff --git a/src/data/process_user_event_related_segments.py b/src/data/process_user_event_related_segments.py
new file mode 100644
index 00000000..bb138c7c
--- /dev/null
+++ b/src/data/process_user_event_related_segments.py
@@ -0,0 +1,19 @@
+import pandas as pd
+import numpy as np
+
+import sys
+
+
+input_data_files = dict(snakemake.input)
+
+# TODO: potrebno preveriti kako se izvaja iskanje prek device_id -> na tem temelji tudi proces ekstrahiranja ERS
+
+if snakemake.params["stage"] == "extract": # TODO: najprej preveri ustreznost umeščenosti v RAPIDS pipelineu
+    extracted_ers = extract_ers_from_file(input_data_files[0])
+    extracted_ers.to_csv(snakemake.output[0], index=False)
+elif snakemake.params["stage"] == "merge":
+    pass # TODO: morda ta del raje naredi v drugi skripti (po principu utils/merge_sensor_features_for_all_participants.R)
+
+
+def extract_ers_from_file(esm_file): # TODO: kako se bodo pridobili device_id? Bo torej potreben tudi p0??.yaml?
+    return None
\ No newline at end of file