def generate_words(array, window, shift, file_id, sensor_id, output_file,
file_handle):
file = file_handle
bucket_size = window
overlap_count = window - shift
slider = Slider(bucket_size, overlap_count)
slider.fit(array)
sensor_word_tf_map = {}
#change refactor
t = 0
while True:
window_data = slider.slide()
if len(window_data) == window:
file_output_line = str([file_id, sensor_id, t]) + '|' + str(
list(window_data)) + '\n'
file.write(file_output_line)
t += shift
word = str(list(window_data)).split('[')[1]
word = word.split(']')[0]
if word in sensor_word_tf_map:
sensor_word_tf_map[word] += 1
else:
sensor_word_tf_map[word] = 1
if slider.reached_end_of_list(): break
return sensor_word_tf_map
def tag_slider(tag_list, bucket_size=10, overlap_count=9):
window_tag = []
tag_array = np.array(tag_list)
if len(tag_array) < bucket_size:
return [tag_array]
slider = Slider(bucket_size, overlap_count)
slider.fit(tag_array)
while True:
window_data = slider.slide()
window_tag.append(window_data)
if slider.reached_end_of_list(): return window_tag
def generate_words(array, window, shift):
bucket_size = window
overlap_count = window - shift
slider = Slider(bucket_size, overlap_count)
slider.fit(array)
#change refactor
words = {}
t = 0
while True:
window_data = slider.slide()
if len(window_data) == window:
# words[t] = ','.join([str(i) for i in window_data])
t += shift
words[t] = str(window_data)
if slider.reached_end_of_list(): break
return words
def generate_average_amplitude(array, window, shift, bands, resolution):
bucket_size = window
overlap_count = window - shift
slider = Slider(bucket_size, overlap_count)
slider.fit(array)
#change refactor
map = {}
symbolic = {}
t = 0
while True:
window_data = slider.slide()
if len(window_data) == window:
window_average = calcualate_average(window_data)
map[t] = window_average
symbolic[t] = get_quantized_number(window_average, bands,
resolution)
t += shift
if slider.reached_end_of_list(): break
return map, symbolic
import pyedflib
import numpy as np
from window_slider import Slider
overlap_ratio = 0.5
window_data_array = []
fname = "C:/Users/user/Desktop/Motor_Imagery_using_EEG/files/S001/S001R"
for j in range(1, 14):
f = pyedflib.EdfReader(fname + f"{j}.edf")
n = f.signals_in_file
signal_labels = f.getSignalLabels()
sigbufs = np.zeros((14, n, f.getNSamples()[0]))
for i in np.arange(n):
sigbufs[j, i, :] = f.readSignal(i)
list = sigbufs[j]
bucket_size = 5000 # length of sliding window
overlap_count = bucket_size * overlap_ratio # overlap
slider = Slider(bucket_size, overlap_count)
slider.fit(list)
while True:
window_data = slider.slide()
print(window_data[j])
if slider.reached_end_of_list():
window_data_array.append(window_data)
break
def finding_motifs(start_pos, end_pos, gen_id, per_bin, gen_file, motif):
#Reading the genome sequence file.
complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A', 'R': 'Y', 'Y': 'R'}
genome = open(gen_file, 'r')
R = ['A', 'G']
Y = ['C', 'T']
N = ['A', 'T', 'G', 'C']
List = []
reverse_List = []
#Using regular expression to check for the presence a character and replacing it with allowed nucleotides in its place and making a list of it
if re.search('N', motif):
for a in N:
motif_replaced = motif.replace('N', a)
List.append(motif_replaced)
elif re.search('R', motif):
for a in R:
motif_replaced = motif.replace('R', a)
List.append(motif_replaced)
elif re.search('Y', motif):
for a in Y:
motif_replaced = motif.replace('Y', a)
List.append(motif_replaced)
else:
List.append(motif)
for x in List:
motif_rev = "".join(complement.get(base, base) for base in reversed(x))
reverse_List.append(motif_rev)
reverse = "".join(complement.get(base, base) for base in reversed(motif))
size = len(motif)
overlap = size - 1
total_temp = 0
total_non_temp = 0
#Defining arrays
windows = []
strings = []
PAM_count = []
PAM_rev_count = []
total_count = []
average_count = []
#Iterating through our genome file with the start position and end position for each gene and using bin size of that particular gene as the iterator value
for start, end, bin_size, gene in zip(start_pos, end_pos, per_bin, gen_id):
ct = 1
x = start
#for x in range(start, end, bin_size):
while x <= end:
if ct == 1:
genome.seek(x)
frame = genome.read(bin_size + 2)
else:
x = x - 2
genome.seek(x)
frame = genome.read(bin_size + 2)
res = list(frame)
res_arr = np.array(res)
#Creating window slider of required size and overlap.
slider = Slider(size, overlap)
slider.fit(res_arr)
i = 0
# template=0
# non_template=0
while True:
data = slider.slide()
Window = str(x + i) + "-" + str(x + i + (size - 1))
windows.append(Window)
string = ''.join(data)
strings.append(string)
#Finding PAM motif and printing frequency.
count = List.count(string)
PAM_count.append(count)
non_template = non_template + count
count_rev = reverse_List.count(string)
PAM_rev_count.append(count_rev)
# template=template+count_rev
i = i + 1
if slider.reached_end_of_list():
dict1 = {
'Windows': windows,
'PAM': strings,
motif: PAM_count,
reverse: PAM_rev_count
}
df = pd.DataFrame.from_dict(dict1)
df = df.transpose()
print(df)
str1 = str(gene) + "_bin" + str(ct)
ct = ct + 1
df.to_csv(str1)
windows = []
strings = []
PAM_count = []
PAM_rev_count = []
dict1.clear()
x = x + bin_size + 2
break
# total_temp=total_temp+template
# total_non_temp=total_non_temp+non_template
count_list = [total_temp, total_non_temp]
return (count_list)
})
data.head()
#sliding window - 1 bucket_size with 0 overlap count
from window_slider import Slider
bucket_size = 1
overlap_count = 0
slider1 = Slider(bucket_size, overlap_count)
slider2 = Slider(bucket_size, overlap_count)
slider3 = Slider(bucket_size, overlap_count)
slider1.fit(data['x'].values)
slider2.fit(data['y'].values)
slider3.fit(data['z'].values)
i = 1
while True:
acc1 = slider1.slide()
acc2 = slider2.slide()
acc3 = slider3.slide()
arr = np.array([acc1, acc2, acc3])
mag = norm(arr)
# write to csv-file.
with open('Tot_BodyMag_Freq_51.14.csv', 'a', newline='' ) as f:
writer = csv.writer( f )
if (i==1):
writer.writerow(["blank","AccMag"])
i = 2
writer.writerow(["%f\r\n" % (i),(mag)])
if slider2.reached_end_of_list(): break
def finding_motifs(gene_positions, gen_file, motif):
#Reading the genome sequence file.
complement = {'A' : 'T', 'C' : 'G', 'G' : 'C', 'T' : 'A', 'R':'Y', 'Y':'R'}
genome=open(gen_file, 'r')
R=['A','G']
Y=['C','T']
N=['A','T','G','C']
List=[]
reverse_List=[]
#Using regular expression to check for the presence a character and replacing it with allowed nucleotides in its place and making a list of it
if re.search('N',motif):
for a in N:
motif_replaced=motif.replace('N', a)
List.append(motif_replaced)
elif re.search('R', motif):
for a in R:
motif_replaced=motif.replace('R', a)
List.append(motif_replaced)
elif re.search('Y', motif):
for a in Y:
motif_replaced=motif.replace('Y', a)
List.append(motif_replaced)
else:
List.append(motif)
print(List)
for x in List:
motif_rev="".join(complement.get(base, base) for base in reversed(x))
reverse_List.append(motif_rev)
print(reverse_List)
reverse="".join(complement.get(base, base) for base in reversed(motif))
size=len(motif)
overlap=size-1
total_temp=0
total_non_temp=0
#Defining arrays
windows=[]
strings=[]
PAM_count=[]
PAM_rev_count=[]
total_count=[]
average_count=[]
#Finding the start positions, creating 1000 bp frame, and storing it as an array.
final=0
for pos in gene_positions:
genome.seek(pos-1)
frame=genome.read(1000)
res=list(frame)
res_arr=np.array(res)
#Creating window slider of required size and overlap.
slider=Slider(size, overlap)
slider.fit(res_arr)
i=0
template=0
non_template=0
dict={}
while True:
data=slider.slide()
Window=str(pos+i)+"-"+str(pos+i+(size-1))
windows.append(Window)
string=''.join(data)
strings.append(string)
#Finding PAM motif and printing frequency.
count=List.count(string)
PAM_count.append(count)
non_template=non_template+count
count_rev=reverse_List.count(string)
PAM_rev_count.append(count_rev)
template=template+count_rev
i=i+1
if slider.reached_end_of_list():
dict1= {'Windows':windows,'PAM':strings, motif : PAM_count, reverse : PAM_rev_count}
df=pd.DataFrame.from_dict(dict1)
df=df.transpose()
print(df)
str1="gene"+str(pos)
df.to_csv(str1)
windows=[]
strings=[]
PAM_count=[]
PAM_rev_count=[]
dict1.clear()
break
dict1.clear()
total_temp=total_temp+template
total_non_temp=total_non_temp+non_template
count_list=[total_temp, total_non_temp]
return(count_list)
