def compressFunc(self):
path = self.name.get()
global h
h = HuffmanCoding(path)
global output_path
output_path = h.compress()
print("Compressed file path: " + output_path)
def main():
""" In this function we read the folder healthy_cow where are store the csv files that contains the matrix of pixels of the images and we selected an specific file.
At first, we applied a compression with FFT and it returns a csv file, which will be compress again using the huffman method and will return a binary file.
Followed by this, we decompress the binary file with the huffman method and it returns a csv file that will be decompress with FFT.
Finally, using the library PIL, we show the original imagen and the decompress image.
:raises: file not found
:rtype: Image in PNG format
"""
directory_sick_cow = "/Users/isabella/Documents/Segundo Semestre/Estructura de Datos /Proyecto/ganado_enfermo_csv"
directory_healthy_cow = "/Users/isabella/Documents/Segundo Semestre/Estructura de Datos /Proyecto/Entrega 3/Codigo/huffman-coding-master/Vacas_Enferma"
directory = directory_healthy_cow
cont = os.listdir(directory)
matriz_csv_var = load_img(directory+'/'+cont[0])
fft_compression(matriz_csv_var, 0.05)
h = HuffmanCoding("compressFFT.csv")
output_path = h.compress()
print("Compressed file path: " + output_path)
decom_path = h.decompress(output_path)
print("Decompressed file path: " + decom_path)
img_fft_descompress = fft_descompression(decom_path)
show_img(matriz_csv_var)
show_img(img_fft_descompress)
savetxt('dataff.csv', matriz_csv_var, delimiter=',')
def main():
from huffman import HuffmanCoding
import sys
inputFilePath = "sample.txt"
handle = HuffmanCoding(inputFilePath)
output_path = handle.compress()
print("Compressed file path: " + output_path)
decom_path = h.decompress(output_path)
print("Decompressed file path: " + decom_path)
def algorithm(path):
h = HuffmanCoding(path)
first1 = time.time()
output_path = h.compress()
second1 = time.time()
delta_time1 = second1 - first1
first2 = time.time()
decom_path = h.decompress(output_path)
second3 = time.time()
delta_time2 = second3 - first2
return output_path, delta_time1, delta_time2, decom_path
def main(argv):
filepath = argv[1]
read_bit_size = 8
if len(argv) > 2:
read_bit_size = argv[2]
print(read_bit_size)
h = HuffmanCoding(filepath, read_bit_size)
output_path = h.compress()
print("Compressed file path: " + output_path)
decom_path = h.decompress(output_path)
print("Decompressed file path: " + decom_path)
def mask_compression(mask):
prev = 1
rl = 0
cnt = 0
result = []
for e in mask:
if e == prev:
rl += 1
else:
result += [rl]
rl = 0
prev = e
if rl > 0:
result += [rl]
huffman = HuffmanCoding()
size = len(huffman.compress(result)) * 4
return size
def use_huffman(filename, wordlength=14):
h = HuffmanCoding(filename, wordlength)
output_path = h.compress()
#h.decompress(output_path)
return output_path
# # cv2.imshow("deltaback", img)
# print "Redecoded entropy: "
# print shannon_entropy(img)
filenames = glob.glob("images/*.png")
images = [cv2.imread(img) for img in filenames]
sum_ratio = 0
for img in images:
img = img[:, :, 0]
img = delta_encode(img)
h = HuffmanCoding(img, os.getcwd() + "/test")
h.compress()
img = h.decompress(os.getcwd() + "/test.bin")
img = delta_decode(img)
rawsize = os.stat('raw.bin')
testsize = os.stat('test.bin')
ratio = float(float(testsize.st_size) / float(rawsize.st_size))
sum_ratio += ratio
print "Redecoded entropy: "
print shannon_entropy(img)
print "Compression ratio: "
print ratio
from huffman import HuffmanCoding
import sys
from pathlib import Path
import time
import cv2
path = "tiger.bmp"
image = cv2.imread(path, 0)
cv2.imwrite("tiger_gray.bmp", image)
h = HuffmanCoding(path)
output_path, image_shape = h.compress()
print("Compressed file path: " + output_path)
a = Path("tiger_gray.bmp").stat().st_size
b = Path(output_path).stat().st_size
print("Calculating size")
for i in range(10):
print(".", end='')
time.sleep(1)
decom_path = h.decompress(output_path, image_shape)
print("compression percent", 100 * (a - b) / a)
print("Decompressed file path: " + decom_path)
def encode_block(self, block):
symbols = diagonalOrder(block)
h = HuffmanCoding(symbols)
encoded = h.compress()
return (encoded, h.reverse_mapping)
clientSocket = socket.socket()
host = socket.gethostname()
port = 9001
clientSocket.connect((host, port))
filePath = input("Enter the path of the file: ")
fileName = os.path.basename(filePath)
start = datetime.now()
clientSocket.send(bytes(fileName, "utf-8"))
huffman = HuffmanCoding(filePath)
compressedFilePath = huffman.compress()
sleep(1)
clientSocket.send(pickle.dumps(huffman))
with open(compressedFilePath, "rb") as fp:
data = fp.read(1024)
while data:
clientSocket.send(data)
data = fp.read(1024)
end = datetime.now()
duration = end - start
compressionRatio = os.path.getsize(filePath) / os.path.getsize(
compressedFilePath)
def compress(fromdir):
h = HuffmanCoding(fromdir)
output_path = h.compress()
return output_path
total_cmp = 0
total_len = 0
h = HuffmanCoding(2)
for filename in os.listdir("contracts"):
with open("contracts/" + filename, 'r') as file:
text = file.read().rstrip()
total_len += len(text)
h.make_frequency_dict(text)
# compressing all contracts
for filename in os.listdir("contracts"):
with open("contracts/" + filename,
'r') as input, open("compressed_contracts/" + filename,
'w') as output:
compressed = h.compress(input.read())
total_cmp += len(compressed)
output.write(compressed)
saved = total_len - total_cmp
print("Total chars saved: " + str(saved))
print("Compression rate: " + str(saved * 100 / total_len) + "%")
# decompressing all contracts
for filename in os.listdir("compressed_contracts"):
with open("compressed_contracts/" + filename,
"r") as input, open("decompressed_contracts/" + filename,
'w') as output:
text = input.read()
decompressed = h.decompress(text)
# Etape 6 huffman and RLE
# blocs_stringY = ''.join([str(elem) for elem in bloc[0]])
# blocs_stringCb = ''.join([str(elem) for elem in bloc[1]])
# blocs_stringCr = ''.join([str(elem) for elem in bloc[2]])
# str_bloc = np.asarray(bloc).flatten().astype('str')
# str_bloc = ''.join(str_bloc)
# #print(blocs_stringCr)
# rleBlock = RLE.compress(str_bloc)
# rleBlock = str(int(rleBlock, 2))
# huffmanBlock = HuffmanCoding.compress(rleBlock)
# jpegImage.append(huffmanBlock)
rle_compress = RLE.compress(zigzag_string)
rle_ascii =''
for i in range(len(rle_compress)):
rle_ascii += chr((int(rle_compress[i], 2)))
huffman_compress, dictionnaire = HuffmanCoding.compress(rle_ascii)
print(len(huffman_compress))
#Decompress
#cv2.imshow("Normal", image)
#cv2.imshow("YCC", YCCimage)
cv2.waitKey()
def huffman_encoding(filename):
print("Huffman Encoding...")
h = HuffmanCoding(filename)
output_path = h.compress()
#print(output_path)
h.decompress(output_path)
from huffman import HuffmanCoding
#input file path of your pc where the files are stored
path = "C:/Users/Panchal/Desktop/huffman/sample.txt"
h = HuffmanCoding(path)
h.compress() # calling compress function
h.decompress("C:/Users/Panchal/Desktop/huffman/sample.bin"
) # calling decompresse fuction
def main():
h = HuffmanCoding(sample_data)
output_path = h.compress()
h.decompress(output_path)
print("Invalid Switch/Usage " + sys.argv[1])
print("Usage :\n")
print("To compress : \npython " + sys.argv[0] +
" -c filename.txt [dictfile.dict]\n")
print("To decompress : \npython " + sys.argv[0] +
" -x filename.bin [dictfile.dict]")
print(
"filename.dict is optional, to be used if the dictionary was saved under a different name."
)
exit(0)
if [sys.argv[1]] == ['-c']:
print()
pathf = sys.argv[2]
dictf = ''
if len(sys.argv) > 3:
dictf = sys.argv[3]
h = HuffmanCoding(pathf)
out = h.compress()
h.save_codes(dictf)
h.get_code()
h.get_freq()
elif [sys.argv[1]] == ['-x']:
print()
pathf = sys.argv[2]
dictf = ''
if len(sys.argv) > 3:
dictf = sys.argv[3]
h = HuffmanCoding(pathf, dictf)
h.decompress()
def testing(text, test_number, path, test_name):
ratio = []
timing = []
print(f"test number: {test_number}")
output = open(path + f"/test_{test_number}.txt", 'w')
output.write(text)
original_size = os.path.getsize(path + f"/test_{test_number}.txt")
# Huffman
print("Compressing with Huffman...")
h = HuffmanCoding(output.name)
start = time.time()
compressed = h.compress()
timing.append((time.time() - start) * 1000)
h.decompress(compressed)
ratio.append(os.path.getsize(compressed) / original_size * 100)
print("Compressing with Huffman finished")
# RLE
print("Compressing with RLE...")
rle = RLE()
output = open(path + f"/test_{test_number}_rle.rle", 'w')
start = time.time()
output.write(rle.encode(text))
timing.append((time.time() - start) * 1000)
ratio.append(
os.path.getsize(path + f"/test_{test_number}_rle.rle") /
original_size * 100)
print("Compressing with RLE finished")
# LZW
print("Compressing with LZW...")
start = time.time()
lzw3Compressor.LZWCompressor().compress(
path + f"/test_{test_number}.txt",
path + f"/test_{test_number}_lzw.lzw")
timing.append((time.time() - start) * 1000)
# lzw3Decompressor.LZWDecompressor().decompress(path + f"/test_{test_number}_lzw.lzw", path + f"/test_{test_number}_lzw_decompressed.txt")
ratio.append(
os.path.getsize(path + f"/test_{test_number}_lzw.lzw") /
original_size * 100)
print("Compressing with LZW finished")
# LZ78
print("Compressing with LZ78...")
output = open(path + f"/test_{test_number}_lz78.lz78", 'w')
start = time.time()
output.write(lz78_compress(text))
timing.append((time.time() - start) * 1000)
ratio.append(
os.path.getsize(path + f"/test_{test_number}_lz78.lz78") /
original_size * 100)
print("Compressing with LZ78 finished")
# PPM
print("compression with PPM...")
start = time.time()
ppm_compression(path + f"/test_{test_number}.txt",
path + f"/test_{test_number}_ppm.ppm")
timing.append((time.time() - start) * 1000)
# ppm_decompression(path + f"/test_{test_number}_ppm.ppm", path + f"/test_{test_number}_ppm_decompresed.txt")
ratio.append(
os.path.getsize(path + f"/test_{test_number}_ppm.ppm") /
original_size * 100)
print("compressing with PPM finished")
save_bar_graph(
ratio, timing,
f"{test_name} N°{test_number}\nOriginal Size: {original_size} bytes",
f"graphs/{test_name} {test_number}.svg")
tick_label = ['Huffman', 'RLE', 'LZW', 'LZ78', 'PPM']
with open(os.getcwd() + f"/data.txt", 'a') as records:
records.write(f"\nOriginal Size: {original_size} bytes\n")
records.write(f"\t\t\tSize\t\tCompression Ratio\t\t\tTime\n")
for i in range(5):
spacing = [
"\t" if i != 0 else "", "\t" if int(ratio[i]) < 100 else "",
"\t" if int(ratio[i] / 100 * original_size) < 100000 else ""
]
records.write(
f"{tick_label[i]}:\t{spacing[0]}{int(ratio[i]/100*original_size)} bytes{spacing[2]}\t{ratio[i]}%\t\t{timing[i]} ms\n"
)
return ratio, timing
def upload_file():
f = request.files['file']
tag = request.form['tag']
data = bytes(f.read())
input_file_size = len(data)
filename, file_extension = os.path.splitext(f.filename)
if (tag == "huffman"):
h = HuffmanCoding(data)
huffman_file_size = h.compress(f.filename)
return jsonify({
'success': True,
'fileSize': input_file_size,
'HuffmanEncoding': {
'compressionRatio': huffman_file_size / input_file_size,
'compressionFactor': input_file_size / huffman_file_size,
'savingPercentage':
(input_file_size - huffman_file_size) / input_file_size,
'fileSize': huffman_file_size
},
})
if (tag == "shannon"):
ShannonCompress(data, f.filename)
shf_file_size = os.path.getsize(filename + ".shf")
os.remove(filename + ".shf")
return jsonify({
'success': True,
'fileSize': input_file_size,
'ShannonFano': {
'compressionRatio': shf_file_size / input_file_size,
'compressionFactor': input_file_size / shf_file_size,
'savingPercentage':
(input_file_size - shf_file_size) / input_file_size,
'fileSize': shf_file_size
},
})
if (tag == "lempel"):
LempelZivWelch(data, f.filename, 8)
lzw_file_size = os.path.getsize(filename + ".lzw")
os.remove(filename + ".lzw")
return jsonify({
'success': True,
'fileSize': input_file_size,
'LempelZivWelch': {
'compressionRatio': lzw_file_size / input_file_size,
'compressionFactor': input_file_size / lzw_file_size,
'savingPercentage':
(input_file_size - lzw_file_size) / input_file_size,
'fileSize': lzw_file_size
}
})
if (tag == "rle"):
RunLengthEncoding(data, f.filename)
rle_file_size = os.path.getsize(filename + ".rle")
os.remove(filename + ".rle")
return jsonify({
'success': True,
'fileSize': input_file_size,
'RunLengthEncoding': {
'compressionRatio': rle_file_size / input_file_size,
'compressionFactor': input_file_size / rle_file_size,
'savingPercentage':
(input_file_size - rle_file_size) / input_file_size,
'fileSize': rle_file_size
},
})
return jsonify({'success': False, "message": "Please pass a valid tag"})
from huffman import HuffmanCoding
import sys
path = "textfile.txt"
h = HuffmanCoding(path)
output_path = h.compress()
print("Compressed file path: " + output_path)
decom_path = h.decompress(output_path)
print("Decompressed file path: " + decom_path)
def forward(self, x, ss_map=None):
# sample from input
if self.use_subsampling:
x, thresh = x
self.sizes[0] += x.view(-1).size(0) * 8
# feature
feat_1 = self.ctx(x)
feat_1_ = self.unpool(feat_1)
else:
self.sizes[0] += x.view(-1).size(0) * 8
x = self.sample(x)
# after CNN
self.sizes[1] += x.view(-1).size(0) * 8
if ss_map is not None:
ss_map = self.unpool(ss_map) > 0.5
unpooled = self.unpool(self.pool(x))
x = torch.where(ss_map, unpooled, x)
# subsampling
# data to be sent: mask + actual data
B, C, H, W = x.size()
if self.use_subsampling:
th_1 = thresh
# sub-sample
ss_1 = self.unpool(self.pool1(x))
# conditions
cond_1 = feat_1_ < th_1
mask_1 = feat_1 < th_1
# subsampled data in different areas
data_1 = self.pool1(x)[mask_1]
cond_0 = torch.logical_not(cond_1)
data_0 = x[cond_0]
comp_data = torch.cat((data_0, data_1), 0)
# after RAF
self.sizes[2] += comp_data.size(0) * 8
# affected data in the original shape
if not self.training:
x = torch.where(cond_1, ss_1, x)
else:
x = torch.mul(x, feat_1_) + torch.mul(ss_1, 1 - feat_1_)
# quantization
xsize = list(x.size())
x = x.view(*(xsize + [1]))
quant_dist = torch.pow(x - self.centers, 2)
softout = torch.sum(self.centers *
nn.functional.softmax(-quant_dist, dim=-1),
dim=-1)
minval, index = torch.min(quant_dist, dim=-1, keepdim=True)
hardout = torch.sum(self.centers * (minval == quant_dist), dim=-1)
x = softout
# x = softout + (hardout - softout).detach()
if self.use_subsampling:
comp_data = comp_data.view(*(list(comp_data.size()) + [1]))
quant_dist = torch.pow(comp_data - self.centers, 2)
index2 = torch.min(quant_dist, dim=-1, keepdim=True)[1]
# after Q
self.sizes[3] += index2.view(-1).size(0) * 3
# running length coding on bitmap
huffman = HuffmanCoding()
real_size = len(huffman.compress(
index2.view(-1).cpu().numpy())) * 4 # bit
rle_len1 = mask_compression(mask_1.view(-1).cpu().numpy())
real_size += rle_len1
# after lossless
self.sizes[4] += real_size
filter_loss = torch.mean(feat_1)
real_cr = 1 / 16. * real_size / (H * W * C * B * 8)
softmax_dist = nn.functional.softmax(-quant_dist, dim=-1)
soft_prob = torch.mean(softmax_dist, dim=0)
entropy = -torch.sum(torch.mul(soft_prob, torch.log(soft_prob)))
return x, (filter_loss, real_cr, entropy)
else:
self.sizes[2] += index.view(-1).size(0) * 3
huffman = HuffmanCoding()
real_size = len(huffman.compress(index.view(-1).cpu().numpy())) * 4
self.sizes[3] += real_size
real_cr = 1 / 16. * real_size / (H * W * C * B * 8)
return x, real_cr
