Adds ground truth to output, and cleans up a bit

src/activity_recognition.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Mar 25 07:38:10 2020
+
+@author: frida
+"""
+
+import numpy as np
+import sys
+from get_data import get_data
+
+#%%
+
+def main():
+    freq = 100 # Assume data was collected at 100 Hz
+    still = 3
+    walk = 15
+
+    # Get mean of accelerometer x,y,z data
+    acc, ground_truth = get_data(sys.argv[1], 'ACC')
+
+    # Check minimum and maximum value over time interval. Determine activity during time interval based on difference between these
+    time_interval = 2 # s
+    for i in np.arange(0, len(acc)//freq - time_interval, time_interval):
+        acc_one_sec = acc[i * freq:(i + time_interval) * freq]
+        xMin = min(acc_one_sec)
+        xMax = max(acc_one_sec)
+
+        if xMax - xMin < still: # Some limit for still
+            print("At time: {}-{}, the person is - Still ({})".format(i, i + time_interval, ground_truth[int((2 * i + time_interval) * freq / 2.0)]))
+        elif xMax - xMin < walk: # Some limit for walk
+            print("At time: {}-{}, the person is - Walking ({})".format(i, i + time_interval, ground_truth[int((2 * i + time_interval) * freq / 2.0)]))
+        else:
+            print("At time: {}-{}, the person is - Running ({})".format(i, i + time_interval, ground_truth[int((2 * i + time_interval) * freq / 2.0)]))
+    
+if __name__ == "__main__":
+    main()
\ No newline at end of file

src/data_visualization.py

@@ -7,12 +7,11 @@ import sys
 import numpy as np
 
 def main():
-    person = sys.argv[1] # Frida or Momina
-    visualization = sys.argv[2] # ACC or GYR
+    person = sys.argv[1] # Frida, Matthias or Momina
+    data_type = sys.argv[2] # ACC or GYR
     verbose = True if len(sys.argv) > 3 else False
 
     data_path = '../Data_' + person + '/'
-
     data_paths = (glob.glob(data_path + '/*.txt'))
 
     data_x = []
@@ -21,13 +20,15 @@ def main():
 
     all_nbr_measurements = []
 
+    # Read each file in person's directory
     for path in data_paths:
         nbr_measurements = 0
 
         with open(path, 'r') as f:
+            # Retrieve data of type data_type, and store the activity and the number of measurements
             for l in f:
                 l = l.split('\t')
-                if visualization == l[1]:
+                if data_type == l[1]:
                     data_x.append(float(l[2]))
                     data_y.append(float(l[3]))
                     data_z.append(float(l[4][:-1])) # don't include newline
@@ -40,9 +41,10 @@ def main():
         all_nbr_measurements.append(nbr_measurements)
         print("Mean of means for file {:s}: {:0.3f}".format(path, (statistics.mean(data_x) + statistics.mean(data_y) + statistics.mean(data_z)) / 3))
 
+    # Plot x, y, z, and the mean of those, together with delimeters for the different files
     cumulative_all_nbr_measurements = np.cumsum(all_nbr_measurements)
     plt.figure(figsize=(24, 9))
-    plt.suptitle(visualization + ' data visualization')
+    plt.suptitle(data_type + ' data visualization')
     plt.subplot(411)
     plt.plot(data_x)
     for nbr in cumulative_all_nbr_measurements:

src/data_visualization_copy.py → src/get_data.py

@@ -6,75 +6,48 @@ import glob
 import sys
 import numpy as np
 
-def get_data(person,visualization):
-    #person = sys.argv[1] # Frida or Momina
-    #visualization = sys.argv[2] # ACC or GYR
-    #verbose = True if len(sys.argv) > 3 else False
-    verbose= False
+def get_data(person, data_type):
     freq = 100
 
     data_path = '../Data_' + person + '/'
-
     data_paths = (glob.glob(data_path + '/*.txt'))
 
     data_x = []
     data_y = []
     data_z = []
+    data_GT = []
 
     all_nbr_measurements = []
 
+    # Read each txt file in the folder
     for path in data_paths:
         nbr_measurements = 0
 
         with open(path, 'r') as f:
+            print("Reading file {}: ".format(path))
+            
+            # Retrieve data of type data_type, and store the activity and the number of measurements
             for l in f:
                 l = l.split('\t')
-                if visualization == l[1]:
+                if data_type == l[1]:
                     data_x.append(float(l[2]))
                     data_y.append(float(l[3]))
                     data_z.append(float(l[4][:-1])) # don't include newline
+                    path_str_lower_case = path.lower()
+                    if 'running' in path_str_lower_case:
+                        data_GT.append('Running')
+                    elif 'walking' in path_str_lower_case:
+                        data_GT.append('Walking')
+                    else:
+                        data_GT.append('Still')
                     nbr_measurements += 1
 
-        if verbose:
-            print("Mean value x: {:0.3f}".format(statistics.mean(data_x)))
-            print("Mean value y: {:0.3f}".format(statistics.mean(data_y)))
-            print("Mean value z: {:0.3f}".format(statistics.mean(data_z)))
         all_nbr_measurements.append(nbr_measurements)
-        print("Mean of means for file {:s}: {:0.3f}".format(path, (statistics.mean(data_x) + statistics.mean(data_y) + statistics.mean(data_z)) / 3))
 
-    cumulative_all_nbr_measurements = np.cumsum(all_nbr_measurements)
-    plt.figure(figsize=(24, 9))
-    plt.suptitle(visualization + ' data visualization')
-    plt.subplot(411)
-    #plt.plot(data_x)
-    plt.plot(np.array(range(len(data_x)))/freq,data_x)
-    for nbr in cumulative_all_nbr_measurements:
-        plt.axvline(nbr/freq, color='r')
-    plt.ylabel('x')
-    plt.subplot(412)
-    #plt.plot(data_y)
-    plt.plot(np.array(range(len(data_y)))/freq,data_y)
-    for nbr in cumulative_all_nbr_measurements:
-        plt.axvline(nbr/freq, color='r')
-    plt.ylabel('y')
-    plt.subplot(413)
-    #plt.plot(data_z)
-    plt.plot(np.array(range(len(data_z)))/freq,data_z)
-    for nbr in cumulative_all_nbr_measurements:
-        plt.axvline(nbr/freq, color='r')
-    plt.ylabel('z')
-    plt.subplot(414)
+    # Compute mean of x, y and z components of the data
     data_mean = (np.asarray(data_x) + np.asarray(data_y) + np.asarray(data_z)) / 3.0
-    #plt.plot(data_mean)
-    plt.plot(np.array(range(len(data_mean)))/freq,data_mean)
-    for nbr in cumulative_all_nbr_measurements:
-        plt.axvline(nbr/freq, color='r')
-    plt.ylabel('mean')
-    plt.show()
-    return data_mean
-
-#if __name__ == "__main__":
-#    main()
+    
+    return data_mean, data_GT
 
 
 

src/script_frida.py

-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Wed Mar 25 07:38:10 2020
-
-@author: frida
-"""
-
-import numpy as np
-from data_visualization_copy import get_data
-
-
-
-#%%
-
-x = 1
-freq = 100 # Hz ?
-time_interval = 1 # s
-xMin = np.inf
-xMax = -np.inf
-still = 3 # Tune these
-walk = 15  # Tune these
-
-xMin = np.inf
-xMax = -np.inf
-acc = get_data('Frida','ACC')
-#acc = get_data('Momina','ACC')
-
-time_interval = 2
-for i in np.arange(0,len(acc)//freq-time_interval,time_interval):
-#for i in range(150,180):
-    acc_one_sec = acc[(i)*freq:(i+time_interval)*freq]
-    xMin = min(acc_one_sec)
-    
-    xMax = max(acc_one_sec)
-    #print(xMax-xMin)
-
-    if xMax-xMin < still: # Some limit for still
-        print("At time: {}-{}, the person is - Still".format(i,i+time_interval))
-    elif xMax-xMin < walk: # Some limit for walk
-        print("At time: {}-{}, the person is - Walking".format(i,i+time_interval))
-    else:
-        print("At time: {}-{}, the person is - Running".format(i,i+time_interval))
-
-    
-    
\ No newline at end of file