Debug assignment of segments to rows

data/external/participant_files/p01.yaml

@@ -5,7 +5,7 @@ PHONE:
   START_DATE: 2021-05-21 09:21:24
   END_DATE: 2021-07-12 17:32:07
 EMPATICA:
-  DEVICE_IDS: [empatica1]
+  DEVICE_IDS: [uploader_53573]
-  LABEL: test01
+  LABEL: uploader_53573
-  START_DATE: 
+  START_DATE: 2021-05-21 09:21:24
-  END_DATE: 
+  END_DATE: 2021-07-12 17:32:07

src/data/datetime/assign_to_time_segment.R

@@ -5,15 +5,28 @@ options(scipen=999)
 
 assign_rows_to_segments <- function(data, segments){
   # This function is used by all segment types, we use data.tables because they are fast
+  print(nrow(data))
+  print(ncol(data))
+
   data <- data.table::as.data.table(data)
   data[, assigned_segments := ""]
   for(i in seq_len(nrow(segments))) {
     segment <- segments[i,]
+    print(segment)
+    print(data[segment$segment_start_ts<= timestamp & segment$segment_end_ts >= timestamp])
+
     data[segment$segment_start_ts<= timestamp & segment$segment_end_ts >= timestamp,
          assigned_segments := stringi::stri_c(assigned_segments, segment$segment_id, sep = "|")]
   }
+  
   data[,assigned_segments:=substring(assigned_segments, 2)]
   data
+
+  test <- # print multiple columns
+    data %>%
+    dplyr::filter(is.na(assigned_segments))
+
+  test %>% as_tibble() %>% print(n=50)
 }
 
 assign_to_time_segment <- function(sensor_data, time_segments, time_segments_type, include_past_periodic_segments, most_common_tz){

tests/scripts/test_acc.py

@@ -0,0 +1,38 @@
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+import sys
+
+df = pd.read_csv(f"/rapids/data/raw/p03/empatica_accelerometer_raw.csv")
+
+
+df['date'] = pd.to_datetime(df['timestamp'],unit='ms')
+df.set_index('date', inplace=True)
+print(df)
+df = df['double_values_0'].resample("31ms").mean()
+print(df)
+
+st='2021-05-21 12:28:27'
+en='2021-05-21 12:59:12'
+
+df = df.loc[(df.index > st) & (df.index < en)]
+plt.plot(df)
+
+plt.savefig(f'NaN.png')
+sys.exit()
+
+
+plt.plot(df)
+
+esm = pd.read_csv(f"/rapids/data/raw/p03/phone_esm_raw.csv")
+
+esm['date'] = pd.to_datetime(esm['timestamp'],unit='ms')
+esm = esm[esm['date']]
+esm.set_index('date', inplace=True)
+print(esm)
+
+esm = esm['esm_session'].resample("2900ms").mean()
+
+plt.plot(esm)
+plt.savefig(f'NaN.png')