def get_percent_of_parallel_sensor_events(number_of_entire_rows, dataset_name, whole_common_time):
'''
count number of events in common time of performed activites
'''
# بعدا اصلاح شود. داده ای که به آن پاس داده میشود اشتباه است.
address_to_read = r"E:\pgmpy\{}\sensor_data_each_row_one_features_is_one_on_and_off+time_ordered.csv".format(dataset_name)
f= open(address_to_read , "r")
counter = 0
print(whole_common_time)
durations_index = 0
for line in f:
cells = line.split(',')
date_time = convert_string_to_datetime(cells[-2], cells[-1].split('\n')[0]) #datetime
if date_time < whole_common_time[durations_index]["start_time"]:
continue
if date_time <= whole_common_time[durations_index]["end_time"]:
counter += 1
if date_time > whole_common_time[durations_index]["end_time"]:
durations_index += 1
if date_time >= whole_common_time[durations_index]["start_time"] and date_time <= whole_common_time[durations_index]["end_time"]:
counter += 1
return counter/number_of_entire_rows
def get_list_of_duration_of_activities(file_address):
f = open(file_address, "r")
_, _, list_of_works = get_list_of_allowed_sensors_and_works_in_dataset(
file_address)
list_of_beginned_activities = [
] # list of dictionaries, each cell contains the activity and personID of beginner
number_of_proccessed_line = -1
list_of_durations = []
PersonNumber, WorkNumber = -1, -1
for line in f:
number_of_proccessed_line += 1
cells = line.split()
if len(cells) > 4:
PersonNumber, WorkString = get_person_and_work(cells[4])
WorkNumber = list_of_works.index(WorkString)
if cells[5] == 'begin':
list_of_beginned_activities.append(
[PersonNumber, WorkNumber, cells[0], cells[1]])
elif cells[5] == 'end':
indices = [
i for i, (first, second,
*_) in enumerate(list_of_beginned_activities)
if (first, second) == (PersonNumber, WorkNumber)
]
print(indices)
index = indices[0]
begin_datetime = convert_string_to_datetime(
list_of_beginned_activities[index][2],
list_of_beginned_activities[index][3])
end_datetime = convert_string_to_datetime(cells[0], cells[1])
timedelta_in_sec = timedelta.total_seconds(end_datetime -
begin_datetime)
list_of_durations.append(timedelta_in_sec)
del (list_of_beginned_activities[index])
return list_of_durations
def convert_casas_dataset_to_pycasas_events_file(file_address_to_read, file_address_to_save_dir):
"""
"""
f = open(file_address_to_read,"r")
list_of_sensors, number_of_allowed_samples, list_of_works = get_list_of_allowed_sensors_and_works_in_dataset(file_address_to_read)
#print(list_of_sensors)
number_of_columns = 7# 6+1 (1 for datetime object used to sort data based on time)
features = [0] * number_of_columns
all_features = np.zeros((number_of_allowed_samples, number_of_columns), dtype= object )
counter = -1
first = True
active_activities = []
active_residents = []
for line in f:
cells = line.split()
try:
feature_column = list_of_sensors.index(cells[2])
except Exception as e:# i.e. the item is not in list
feature_column = -1
if len(cells) > 4:
if cells[5] == 'begin':
if cells[4][0] == 'R':
person = cells[4].split('_')[0]
activity = cells[4][len(person)+1:] # remain of the string is the activity
active_activities.append(activity)
active_residents.append(person)
else:
active_activities.append(cells[4])
if feature_column != -1:
counter +=1
date_details = cells[0].split('-')
date = date_details[1] + '/' + date_details[2] + '/' + date_details[0] # month/day/year
features[0] = date + " " + cells[1] + " " + "-08:00" # date time
features[1] = cells[2] # sensor
features[2] = cells[3] # message
features[3] = ';'.join(sorted(list(set(active_residents))))#residents
features[4] = ';'.join(sorted(list(set(active_activities))))#activities
features[5] = get_sensor_type(cells[2])#sensor_type
features[6] = convert_string_to_datetime(cells[0],cells[1])
if len(cells) > 4 and cells[5] == 'end':
if cells[4][0] == 'R':
person = cells[4].split('_')[0]
activity = cells[4][len(person)+1:] # remain of the string is the activity
active_activities.remove(activity)
active_residents.remove(person)
else:
active_activities.remove(cells[4])
if feature_column != -1:
if first == True:
first = False
if counter < number_of_allowed_samples:
all_features[counter] = features
else:
all_features = np.vstack([all_features,features])
file_address_to_save = os.path.join(file_address_to_save_dir, 'data', 'events.csv')
all_features = all_features[all_features[:,-1].argsort()] # sort all_features based on datetime column
np.savetxt(file_address_to_save, np.delete(all_features, -1 , 1 ), delimiter=',' , fmt='%s')
def get_list_of_durations(number_of_entire_rows, dataset_name):
'''
1. The order of features: sensor events (for each sensor on and off),
Person,
Date,
Time
This function works for every multi-rsident dataset
'''
address_to_read = r"E:\pgmpy\{}\sensor_data_each_row_one_features_is_one_on_and_off+time_ordered.csv".format(dataset_name)
f= open(address_to_read , "r")
all_features = None#np.zeros((number_of_entire_rows, 124), dtype= object )#np.str)1003 +1
counter = -1
first = True
for line in f:
#print(line)
cells = line.split(',')
if first:
number_of_columns = 3 # Person + Activity + datetime
all_features = np.zeros((number_of_entire_rows, number_of_columns), dtype= object )#np.str)1003 +1
converted_cells = []
converted_cells.append(int(cells[-4]))#person
converted_cells.append(int(cells[-3]))#activity
#print(cells[-2], cells[-1])
converted_cells.append(convert_string_to_datetime(cells[-2], cells[-1].split('\n')[0])) #datetime
counter+=1
if first == True:
first = False
if counter < number_of_entire_rows:
all_features[counter] = converted_cells
else:
all_features = np.vstack([all_features,converted_cells])
#seperate each person data in a list (-4 is the index of person column)
person_IDs = list(set(all_features[: , -3]))
#print(person_IDs)
number_of_residents = len(person_IDs)
person_data = np.zeros(number_of_residents, dtype = np.ndarray)
durations = np.zeros(number_of_residents, dtype = np.ndarray)
#print(type(person_data))
for i in range(number_of_residents):
person_data[i] = all_features[np.where(all_features[:,-3] == person_IDs[i])]
#separate each person activities based on start and end time of items
for per in range(number_of_residents):
start_time = person_data[per][0][-1]
activity = person_data[per][0][-2]
durations[per] = []
for i in range(1,len(person_data[per])):
if person_data[per][i][-2] != activity:
durations[per].append({"start_time": start_time, "end_time": person_data[per][i-1][-1]})
start_time = person_data[per][i][-1]
activity = person_data[per][i][-2]
return durations
def return_list_of_activity_durations(number_of_entire_rows, address_to_read):
'''
'''
f= open(address_to_read , "r")
counter = -1
first = True
for line in f:
#print(line)
cells = line.split(',')
if first:
number_of_columns = 3#Person_ID, Activity_ID, +1 is for datetime column
all_features = np.zeros((number_of_entire_rows, number_of_columns), dtype= object )#np.str)1003 +1
converted_cells = []
converted_cells.append(int(cells[-4]))#Person_ID
converted_cells.append(int(cells[-3]))#Activity_ID
converted_cells.append(convert_string_to_datetime(cells[-2], cells[-1].split('\n')[0])) #DateTime. the time has '\n' at end taht should be removed
counter+=1
if first == True:
first = False
if counter < number_of_entire_rows:
all_features[counter] = converted_cells
else:
all_features = np.vstack([all_features,converted_cells])
#seperate each person data in a list (-4 is the index of person column)
person_IDs = list(set(all_features[: , 0]))
#print(person_IDs)
number_of_residents = len(person_IDs)
person_data = np.zeros(number_of_residents, dtype = np.ndarray)
#print(type(person_data))
for i in range(number_of_residents):
person_data[i] = all_features[np.where(all_features[:,0] == person_IDs[i])]
#print("*****************\n {}".format(i))
#print(type(person_data[i]))
#print(person_data[i].shape)
#save bag of features in deltaT for each person
person_durations = np.zeros(number_of_residents, dtype = np.ndarray)
for each_person in range(number_of_residents):
#print("each_line:{}".format(each_line+1))
new_counter = 0
#initialize
person_data_number_of_rows , _ = person_data[each_person].shape
# create a ndarray with size of all data of the person
person_durations[each_person] = np.ndarray(shape = (person_data_number_of_rows , 2), dtype = int)#just save activityID and its duration
last_activity = person_data[each_person][0][1]
last_start_datetime = person_data[each_person][0][2]
for offset in range(1, len(person_data[each_person]), 1): # range(start, end, step) sharte end ine k bozorgtar bashe pas bayad yeki az akhari kamtar begiram
# compare delta time in minutes
if person_data[each_person][offset][1] == last_activity:
continue
else:
# save activity column
person_durations[each_person][new_counter][0] = last_activity
#add person column value
person_durations[each_person][new_counter][1] = timedelta.total_seconds(person_data[each_person][offset-1][2] - last_start_datetime) / 60
last_start_datetime = person_data[each_person][offset][2]
last_activity = person_data[each_person][offset][1]
new_counter += 1
#update last row column and activity number
person_durations[each_person][new_counter][0] = last_activity
person_durations[each_person][new_counter][1] = timedelta.total_seconds(person_data[each_person][offset][2] - last_start_datetime)/60
#remove additional items (because when i created the person_bag[each_person], the size was number of rows )
person_durations[each_person] = np.delete(person_durations[each_person] , range(new_counter + 1 , person_data_number_of_rows) , axis = 0)
for i in range(number_of_residents):
print("resident number:", person_IDs[i] , "\n---------------------------\n")
#print(sorted(list(set(person_durations[i][:,1]))))
print(person_durations[i][:,1])
print("average activity duration:" , np.average(person_durations[i][:,1]))
#for j in range(len(person_durations[i])):
# print(person_durations[i])
return person_durations
def convert_data_to_each_row_one_feature_is_on(in_file, out_file,
person_number, hasHeader):
'''
this function adds the person number to file as well
there is a mistake that this code ignores the first activity if the activity does not change any sesnor status
'''
f = open(in_file, "r")
#read the first line to get the sensor names
seprators_pattern = ',| |\n'
first_line = re.split(
seprators_pattern,
f.readline()) # the last element should be ''. do ont count it
#-3 for Activity,timestamp,''
#+5 for Person + work + 1 date + 1 time + 1 datetime for ordering data
number_of_columns = (len(first_line) - 3) * 2 + 5
number_of_sensors_plus_activity = len(first_line) - 2
list_of_sensor_names = first_line[0:(number_of_sensors_plus_activity - 1)]
features = [0] * number_of_columns
features[-5] = person_number
number_of_samples = get_number_of_lines_in_file(in_file, hasHeader)
all_features = np.zeros((number_of_samples, number_of_columns),
dtype=object)
counter = -1
#first = True
previous_cells = re.split(seprators_pattern,
f.readline()) #first line of samples
for line in f:
#search for the first change in sensor states
cells = re.split(seprators_pattern, line)
if cells[0:number_of_sensors_plus_activity] != previous_cells[
0:number_of_sensors_plus_activity]:
counter += 1
#find the sensor whose status is changed
for i in range(number_of_sensors_plus_activity - 1):
if cells[i] != previous_cells[i]:
if cells[i] == '1':
changed_index = i * 2
elif cells[i] == '0':
changed_index = i * 2 + 1
break
#set_of_changed_index.add(changed_index)
features[changed_index] = 1
features[-4] = openshs_activities[cells[-4]]
features[-3] = cells[-3]
features[-2] = cells[-2]
features[-1] = convert_string_to_datetime(cells[-3], cells[-2])
previous_cells = cells
if counter < number_of_samples:
all_features[counter] = features
else:
all_features = np.vstack([all_features, features])
#reset changed_index to 0
features[changed_index] = 0
all_features = np.delete(all_features,
range(counter + 1, number_of_samples),
axis=0)
#print(all_features[:,-1])
all_features = all_features[all_features[:, -1].argsort(
)] # sort all_features based on datetime column
rows, cols = all_features.shape
print("rows:", rows, "cols:", cols)
np.savetxt(out_file,
np.delete(all_features, -1, 1),
delimiter=',',
fmt='%s')