From 12302a9486a90765b0fe4d4ad7e669b2d334ce63 Mon Sep 17 00:00:00 2001
From: Meng Li <34143965+Meng6@users.noreply.github.com>
Date: Fri, 15 May 2020 18:10:36 -0400
Subject: [PATCH] Change path of cleaned features in Snakefile

---
 Snakefile | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/Snakefile b/Snakefile
index 22307b61..8cdde971 100644
--- a/Snakefile
+++ b/Snakefile
@@ -83,11 +83,21 @@ rule all:
         expand("data/processed/data_for_population_model/{source}_{day_segment}_original.csv",
                             source = config["PARAMS_FOR_ANALYSIS"]["SOURCES"],
                             day_segment = config["PARAMS_FOR_ANALYSIS"]["DAY_SEGMENTS"]),
-        expand("data/processed/{pid}/data_for_individual_model/{source}_{day_segment}_clean.csv",
+        expand("data/processed/{pid}/data_for_individual_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_clean.csv",
                             pid = config["PIDS"],
+                            rows_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["ROWS_NAN_THRESHOLD"],
+                            cols_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_NAN_THRESHOLD"],
+                            days_before_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_BEFORE_THRESHOLD"],
+                            days_after_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_AFTER_THRESHOLD"],
+                            cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
                             source = config["PARAMS_FOR_ANALYSIS"]["SOURCES"],
                             day_segment = config["PARAMS_FOR_ANALYSIS"]["DAY_SEGMENTS"]),
-        expand("data/processed/data_for_population_model/{source}_{day_segment}_clean.csv",
+        expand("data/processed/data_for_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_clean.csv",
+                            rows_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["ROWS_NAN_THRESHOLD"],
+                            cols_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_NAN_THRESHOLD"],
+                            days_before_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_BEFORE_THRESHOLD"],
+                            days_after_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_AFTER_THRESHOLD"],
+                            cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
                             source = config["PARAMS_FOR_ANALYSIS"]["SOURCES"],
                             day_segment = config["PARAMS_FOR_ANALYSIS"]["DAY_SEGMENTS"]),
         expand("data/processed/data_for_population_model/demographic_features.csv"),