Updates code structure and README

Readme.md

+# WASP AS 1 Assigment: Activity Recognition,
+# by Frida Heskebeck, Matthias Mayr, Momina Rizwan and Pontus Andersson
+
+Our activity recognition is based on thresholds.
+The approach is to use the mean of the x,y and z accelerometer data.
+Over a time interval of two seconds, we look at the difference of the max and min values of the mean.
+If the differences is lower than a set threshold, the person is predicted to be standing still.
+If the difference is greater than the still treshold but smaller than a set running threshold, the person is predicted to be walking.
+Otherwise, the person is predicted to be running.
+
+This repository contains three scripts used to perform activity recognition and data visualization.
+The data is stored in the `data` directory. To include your own data, add a subfolder to `data` named Data_YourData.
+We assume the scripts are called from the as1-activity-recognition folder.
+
+* `data_visualization.py` allows you to visualize data. Usage: `python data_visualization.py Name DataType`,
+where `Name` is the name of the person whose data you wish to show, and `DataType` is either `ACC` or `GYR` for accelerometer and
+gyro data, respectively. Red bars are used to separate the data files.
+
+* `get_data.py` is a helper function for `activity_recognition.py`. It collects the data used in the latter script.
+
+* `activity_recognition.py` allows you to do activity recognition. Usage: `python activity_recognition.py Name PresentationMode`,
+where `Name` is as in `data_visualization.py` and `PresentationMode` is either `Text` or `ConfusionMatrix`, with
+`Text` yielding console output of each prediction and corresponding ground truth, and `ConfusionMatrix` yielding a confusion matrix.
+For both options, we print the accuracy in the console.
\ No newline at end of file

src/activity_recognition.py

@@ -9,40 +9,74 @@ Created on Wed Mar 25 07:38:10 2020
 import numpy as np
 import sys
 from get_data import get_data
+import matplotlib.pyplot as plt
 
 #%%
 
 def main():
+    person = sys.argv[1] # Which person's data?
+    presentation = sys.argv[2] # What presentation option? (Text or ConfusionMatrix)
+
     freq = 100 # Assume data was collected at 100 Hz
     still = 2
     walk = 20
 
     # Get mean of accelerometer x,y,z data
-    acc, ground_truth = get_data(sys.argv[1], 'ACC')
-
+    acc, ground_truth = get_data(person, 'ACC')
+    confMat = np.zeros((3,3))
     # Check minimum and maximum value over time interval. Determine activity during time interval based on difference between these
     time_interval = 2 # s
-    correct_guesses = 0
-    total_guesses = 0
+    number_correct_guesses = 0
+    number_total_guesses = 0
     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)
+        
+        classes = ['Still','Walking','Running']
+        true_idx = classes.index(ground_truth[int((2 * i + time_interval) * freq / 2.0)])
 
-        gt = ground_truth[int((2 * i + time_interval) * freq / 2.0)]
-
-        if xMax - xMin < still: # Some limit for still
-            print("At time: {}-{}, the person is - Still ({}, Diff: {:0.2f})".format(i, i + time_interval, gt, xMax - xMin))
-            correct_guesses += int(gt == 'Still')
-        elif xMax - xMin < walk: # Some limit for walk
-            print("At time: {}-{}, the person is - Walking ({}, Diff: {:0.2f})".format(i, i + time_interval, gt, xMax - xMin))
-            correct_guesses += int(gt == 'Walking')
+        if xMax - xMin < still:
+            if presentation == 'Text': print("At time: {}-{}, the person is - Still ({}, Diff: {:0.2f})".format(i, i + time_interval, ground_truth[int((2 * i + time_interval) * freq / 2.0)], xMax - xMin))
+            pred_idx = 0
+        elif xMax - xMin < walk:
+            if presentation == 'Text': print("At time: {}-{}, the person is - Walking ({}, Diff: {:0.2f})".format(i, i + time_interval, ground_truth[int((2 * i + time_interval) * freq / 2.0)], xMax - xMin))
+            pred_idx = 1
         else:
-            print("At time: {}-{}, the person is - Running ({}, Diff: {:0.2f})".format(i, i + time_interval, gt, xMax - xMin))
-            correct_guesses += int(gt == 'Running')
-        total_guesses += 1
-
-    print("#Correct guesses: {}, #Total guesses: {}, Correct%: {:.2f}".format(correct_guesses, total_guesses, correct_guesses / float(total_guesses) * 100))
+            if presentation == 'Text': print("At time: {}-{}, the person is - Running ({}, Diff: {:0.2f})".format(i, i + time_interval, ground_truth[int((2 * i + time_interval) * freq / 2.0)], xMax - xMin))
+            pred_idx = 2
+        number_correct_guesses += int(true_idx == pred_idx)
+        number_total_guesses += 1
+        confMat[true_idx,pred_idx] += 1
+    
+    print("#Correct guesses: {}, #Total guesses: {}, Correct%: {:.2f}".format(number_correct_guesses, number_total_guesses, number_correct_guesses / float(number_total_guesses) * 100))
 
+    if presentation == 'ConfusionMatrix':
+        fig, ax = plt.subplots()
+        im = ax.imshow(confMat,cmap='rainbow')
+        
+        # We want to show all ticks...
+        #ax.set_xticks(np.arange(len(classes)))
+        #ax.set_yticks(np.arange(len(classes)))
+        # ... and label them with the respective list entries
+        classes_tick = [' ','Still',' ','Walking',' ','Running',' ']
+        ax.set_xticklabels(classes_tick)
+        ax.set_yticklabels(classes_tick)
+        
+        # Rotate the tick labels and set their alignment.
+        plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
+                rotation_mode="anchor")
+        
+        # Loop over data dimensions and create text annotations.
+        for i in range(len(classes)):
+            for j in range(len(classes)):
+                text = ax.text(j, i, confMat[i, j],
+                            ha="center", va="center", color="k")
+        
+        ax.set_title("Confusion matrix {}, \nrows - true activity, cols - predicted activity".format(person))
+        #fig.tight_layout()
+        fig.colorbar(im)
+        plt.show()
+    
 if __name__ == "__main__":
     main()
\ No newline at end of file

src/activity_recognition_copy.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
-import matplotlib.pyplot as plt
-
-#%%
-
-def main(person):
-    freq = 100 # Assume data was collected at 100 Hz
-    still = 2
-    walk = 20
-
-    # Get mean of accelerometer x,y,z data
-    acc, ground_truth = get_data(person, 'ACC')
-    confMat = np.zeros((3,3))
-    # 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)
-        
-        classes = ['Still','Walking','Running']
-        true_idx = classes.index(ground_truth[int((2 * i + time_interval) * freq / 2.0)])
-
-        if xMax - xMin < still: # Some limit for still
-            print("At time: {}-{}, the person is - Still ({}, Diff: {:0.2f})".format(i, i + time_interval, ground_truth[int((2 * i + time_interval) * freq / 2.0)], xMax - xMin))
-            pred_idx = 0
-        elif xMax - xMin < walk: # Some limit for walk
-            print("At time: {}-{}, the person is - Walking ({}, Diff: {:0.2f})".format(i, i + time_interval, ground_truth[int((2 * i + time_interval) * freq / 2.0)], xMax - xMin))
-            pred_idx = 1
-        else:
-            print("At time: {}-{}, the person is - Running ({}, Diff: {:0.2f})".format(i, i + time_interval, ground_truth[int((2 * i + time_interval) * freq / 2.0)], xMax - xMin))
-            pred_idx = 2
-        confMat[true_idx,pred_idx] += 1
-    
-    fig, ax = plt.subplots()
-    im = ax.imshow(confMat,cmap='rainbow')
-    
-    # We want to show all ticks...
-    #ax.set_xticks(np.arange(len(classes)))
-    #ax.set_yticks(np.arange(len(classes)))
-    # ... and label them with the respective list entries
-    classes_tick = [' ','Still',' ','Walking',' ','Running',' ']
-    ax.set_xticklabels(classes_tick)
-    ax.set_yticklabels(classes_tick)
-    
-    # Rotate the tick labels and set their alignment.
-    plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
-             rotation_mode="anchor")
-    
-    # Loop over data dimensions and create text annotations.
-    for i in range(len(classes)):
-        for j in range(len(classes)):
-            text = ax.text(j, i, confMat[i, j],
-                           ha="center", va="center", color="k")
-    
-    ax.set_title("Confusion matrix {}, \nrows - true activity, cols - predicted activity".format(person))
-    #fig.tight_layout()
-    fig.colorbar(im)
-    plt.show()
-    
-if __name__ == "__main__":
-    main()
\ No newline at end of file

src/data_visualization.py

@@ -9,9 +9,8 @@ import numpy as np
 def main():
     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_path = 'data/Data_' + person + '/'
     data_paths = (glob.glob(data_path + '/*.txt'))
 
     data_x = []
@@ -34,12 +33,7 @@ def main():
                     data_z.append(float(l[4][:-1])) # don't include newline
                     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))
 
     # 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)

src/get_data.py

@@ -9,7 +9,7 @@ import numpy as np
 def get_data(person, data_type):
     freq = 100
 
-    data_path = '../Data_' + person + '/'
+    data_path = 'data/Data_' + person + '/'
     data_paths = (glob.glob(data_path + '/*.txt'))
 
     data_x = []