I'm using the wrapped version of smith-waterman from skbio (0.5.4), but i have an unspected error:
_, score, _ = local_pairwise_align_ssw(protein_list[idx1], protein_list[idx2], substitution_matrix = blosum62)
File "/anaconda3/lib/python3.6/site-packages/skbio/alignment/_pairwise.py", line 732, in local_pairwise_align_ssw
validate=False)
File "/anaconda3/lib/python3.6/site-packages/skbio/alignment /_tabular_msa.py", line 785, in __init__
reset_index=minter is None and index is None)
File "/anaconda3/lib/python3.6/site-packages/skbio/alignment /_tabular_msa.py", line 1956, in extend
self._assert_valid_sequences(sequences)
File "/anaconda3/lib/python3.6/site-packages/skbio/alignment /_tabular_msa.py", line 2035, in _assert_valid_sequences
% (length, expected_length))
ValueError: Each sequence's length must match the number of positions in the MSA: 232 != 231
The weird thing is that sometimes the error appears with protein pair 0-10, and others with 0-116. So, i don't believe it's an error from protein fromat.
I have a similar problem. However, I was able to limit the error to the optimized SSW version. So no error in the sequence formatting.
import warnings
from skbio.sequence import Protein
with warnings.catch_warnings():
warnings.filterwarnings("ignore", message="...")
from Bio.Align import substitution_matrices
from skbio.alignment import local_pairwise_align_ssw
from skbio.alignment import local_pairwise_align
peptide1 = Protein("CGAGDNQAGTALIF")
peptide2 = Protein("CAGEEGGGADGLTF")
gap_open_penalty = 10
gap_extend_penalty = 10
substitution_matrix = substitution_matrices.load("BLOSUM45")
## works correct
rv = local_pairwise_align_ssw(
sequence1 = peptide1
, sequence2 = peptide2
, gap_open_penalty=1
, gap_extend_penalty=1
, substitution_matrix=substitution_matrix
)
print(rv)
## but if I swap peptide1 and peptide 2 the ValueError occur
rv = local_pairwise_align_ssw(
sequence1 = peptide2
, sequence2 = peptide1
, gap_open_penalty=1
, gap_extend_penalty=1
, substitution_matrix=substitution_matrix
)
print(rv)
## if I do the same with local_pairwise_align it works!
rv = local_pairwise_align(
seq1=peptide2
, seq2=peptide1
, gap_open_penalty=1
, gap_extend_penalty=1
, substitution_matrix=substitution_matrix
)
print(rv)
Related
Doing things on Google Colab.
transformers: 4.10.2
pytorch-lightning: 1.2.7
import torch
from torch.utils.data import DataLoader
from transformers import BertJapaneseTokenizer, BertForSequenceClassification
import pytorch_lightning as pl
dataset_for_loader = [
{'data':torch.tensor([0,1]), 'labels':torch.tensor(0)},
{'data':torch.tensor([2,3]), 'labels':torch.tensor(1)},
{'data':torch.tensor([4,5]), 'labels':torch.tensor(2)},
{'data':torch.tensor([6,7]), 'labels':torch.tensor(3)},
]
loader = DataLoader(dataset_for_loader, batch_size=2)
for idx, batch in enumerate(loader):
print(f'# batch {idx}')
print(batch)
category_list = [
'dokujo-tsushin',
'it-life-hack',
'kaden-channel',
'livedoor-homme',
'movie-enter',
'peachy',
'smax',
'sports-watch',
'topic-news'
]
tokenizer = BertJapaneseTokenizer.from_pretrained(MODEL_NAME)
max_length = 128
dataset_for_loader = []
for label, category in enumerate(tqdm(category_list)):
# file ./text has lots of articles, categorized by category
# and they are just plain texts, whose content begins from forth line
for file in glob.glob(f'./text/{category}/{category}*'):
lines = open(file).read().splitlines()
text = '\n'.join(lines[3:])
encoding = tokenizer(
text,
max_length=max_length,
padding='max_length',
truncation=True
)
encoding['labels'] = label
encoding = { k: torch.tensor(v) for k, v in encoding.items() }
dataset_for_loader.append(encoding)
SEED=lambda:0.0
# random.shuffle(dataset_for_loader) # ランダムにシャッフル
random.shuffle(dataset_for_loader,SEED)
n = len(dataset_for_loader)
n_train = int(0.6*n)
n_val = int(0.2*n)
dataset_train = dataset_for_loader[:n_train]
dataset_val = dataset_for_loader[n_train:n_train+n_val]
dataset_test = dataset_for_loader[n_train+n_val:]
dataloader_train = DataLoader(
dataset_train, batch_size=32, shuffle=True
)
dataloader_val = DataLoader(dataset_val, batch_size=256)
dataloader_test = DataLoader(dataset_test, batch_size=256)
class BertForSequenceClassification_pl(pl.LightningModule):
def __init__(self, model_name, num_labels, lr):
super().__init__()
self.save_hyperparameters()
self.bert_sc = BertForSequenceClassification.from_pretrained(
model_name,
num_labels=num_labels
)
def training_step(self, batch, batch_idx):
output = self.bert_sc(**batch)
loss = output.loss
self.log('train_loss', loss)
return loss
def validation_step(self, batch, batch_idx):
output = self.bert_sc(**batch)
val_loss = output.loss
self.log('val_loss', val_loss)
def test_step(self, batch, batch_idx):
labels = batch.pop('labels')
output = self.bert_sc(**batch)
labels_predicted = output.logits.argmax(-1)
num_correct = ( labels_predicted == labels ).sum().item()
accuracy = num_correct/labels.size(0)
self.log('accuracy', accuracy)
def configure_optimizers(self):
return torch.optim.Adam(self.parameters(), lr=self.hparams.lr)
checkpoint = pl.callbacks.ModelCheckpoint(
monitor='val_loss',
mode='min',
save_top_k=1,
save_weights_only=True,
dirpath='model/',
)
trainer = pl.Trainer(
gpus=1,
max_epochs=10,
callbacks = [checkpoint]
)
model = BertForSequenceClassification_pl(
MODEL_NAME, num_labels=9, lr=1e-5
)
### (a) ###
# I think this is where I am doing fine-tuning
trainer.fit(model, dataloader_train, dataloader_val)
# this is to score after fine-tuning
test = trainer.test(test_dataloaders=dataloader_test)
print(f'Accuracy: {test[0]["accuracy"]:.2f}')
But I am not really sure how to do a test before fine-tuning, in order to compare two models before and after fine-tuning, in order to show how effective fine-tuning is.
Inserting the following two lines to ### (a) ###:
test = trainer.test(test_dataloaders=dataloader_test)
print(f'Accuracy: {test[0]["accuracy"]:.2f}')
I got this result:
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-13-c8b2c67f2d5c> in <module>()
9
10 # 6-19
---> 11 test = trainer.test(test_dataloaders=dataloader_test)
12 print(f'Accuracy: {test[0]["accuracy"]:.2f}')
13
/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py in test(self, model, test_dataloaders, ckpt_path, verbose, datamodule)
896 self.verbose_test = verbose
897
--> 898 self._set_running_stage(RunningStage.TESTING, model or self.lightning_module)
899
900 # If you supply a datamodule you can't supply train_dataloader or val_dataloaders
/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py in _set_running_stage(self, stage, model_ref)
563 the trainer and the model
564 """
--> 565 model_ref.running_stage = stage
566 self._running_stage = stage
567
AttributeError: 'NoneType' object has no attribute 'running_stage'
I noticed that Trainer.fit() can take None as arguments other than model, so I tried this:
trainer.fit(model)
test=trainer.test(test_dataloaders=dataloader_test)
print(f'Accuracy: {test[0]["accuracy"]:.2f}')
The result:
MisconfigurationException: No `train_dataloader()` method defined. Lightning `Trainer` expects as minimum a `training_step()`, `train_dataloader()` and `configure_optimizers()` to be defined.
Thanks.
The Trainer needs to call its .fit() in order to set up a lot of things and then only you can do .test() or other methods.
You are right about putting a .fit() just before .test() but the fit call needs to a valid one. You have to feed a dataloader/datamodule to it. But since you don't want to do a training/validation in this fit call, just pass limit_[train/val]_batches=0 while Trainer construction.
trainer = Trainer(gpus=..., ..., limit_train_batches=0, limit_val_batches=0)
trainer.fit(model, dataloader_train, dataloader_val)
trainer.test(model, dataloader_test) # without fine-tuning
The fit call here will just set things up for you and skip training/validation. And then the testing follows. Next time run the same code but without the limit_[train/val]_batches, this will do the pretraining for you
trainer = Trainer(gpus=..., ...)
trainer.fit(model, dataloader_train, dataloader_val)
trainer.test(model, dataloader_test) # with fine-tuning
Clarifying a bit about .fit() taking None for all but model: Its not quite true - you must provide either a DataLoader or a DataModule.
#i have scraped data below is my code, now i want to add a column of symbols to the respective company data, plz guide me how the symbol can be added to the respective firm data
#code below
from time import sleep
import pandas as pd
import os
import numpy as np
from bs4 import BeautifulSoup
from selenium import webdriver
from webdriver_manager.chrome import ChromeDriverManager
browser = webdriver.Chrome(ChromeDriverManager().install())
symbols =['FATIMA',
'SSGC',
'FCCL',
'ISL',
'KEL',
'NCL',
'DGKC',
'SNGP',
'NML',
'ENGRO',
'HUMNL',
'CHCC',
'ATRL',
'HUBC',
'ASTL',
'PIBTL',
'OGDC',
'EFERT',
'FFC',
'NCPL',
'KTML',
'PSO',
'LUCK',
'SEARL',
'KOHC',
'ABOT',
'AICL',
'HASCOL',
'PTC',
'KAPCO',
'PIOC',
'POL',
'SHEL',
'GHGL',
'HCAR',
'DCR',
'BWCL',
'MTL',
'GLAXO',
'PKGS',
'SHFA','MARI',
'ICI',
'ACPL',
'PSMC',
'SPWL',
'THALL',
'BNWM',
'EFUG',
'GADT',
'AABS']
company = 1
for ThisSymbol in symbols :
# Get first symbol from the above python list
company = 2
# In the URL, make symbol as variable
url = 'http://www.scstrade.com/stockscreening/SS_CompanySnapShotYF.aspx?symbol=' + ThisSymbol
browser.get(url)
sleep(2)
# The below command will get all the contents from the url
html = browser.execute_script("return document.documentElement.outerHTML")
# So we will supply the contents to beautiful soup and we tell to consider this text as a html, with the following command
soup = BeautifulSoup (html, "html.parser")
for rn in range(0,9) :
plist = []
r = soup.find_all('tr')[rn]
# Condition: if first row, then th, otherwise td
if (rn==0) :
celltag = 'th'
else :
celltag = 'td'
# Now use the celltag instead of using fixed td or th
col = r.find_all(celltag)
print()
if col[i] == 0:
print ("")
else:
for i in range(0,4) :
cell = col[i].text
clean = cell.replace('\xa0 ', '')
clean = clean.replace (' ', '')
plist.append(clean)
# If first row, create df, otherwise add to it
if (rn == 0) :
df = pd.DataFrame(plist)
else :
df2 = pd.DataFrame(plist)
colname = 'y' + str(2019-rn)
df[colname] = df2
if (company == 1):
dft = df.T
# Get header Column
head = dft.iloc[0]
# Exclude first row from the data
dft = dft[1:]
dft.columns = head
dft = dft.reset_index()
# Assign Headers
dft = dft.drop(['index'], axis = 'columns')
else:
dft2 = df.T
# Get header Column
head = dft2.iloc[0]
# Exclude first row from the data
dft2 = dft2[1:]
dft2.columns = head
dft2 = dft2.reset_index()
# Assign Headers
dft2 = dft2.drop(['index'], axis = 'columns')
dft['Symbol'] = ThisSymbol
dft = dft.append(dft2, sort=['Year','Symbol'])
company = company +1
dft
my output looks this, i want to have a symbol column to each respective firm data
Symbol,i have added
dft['Symbol'] = ThisSymbol
but it add just first company from the list to all companies data
enter image description here
I have problem with the syntax in the last part of steg program. I tried to convert python 2 version (of the working code) to python 3, and this is the last part of it:
flag = base64.b64decode("".join(chars)) <- error
print(flag)
The program 1. encrypts the message in the Last Significiant Bits of the image as saves it as a new image. Then 2.decrypts the message, which is stored in "flag", and prints it.
* can the error be caused by the wrong type of input?:
message = input("Your message: ")
BELOW: UNHIDING PROGRAM
#coding: utf-8
import base64
from PIL import Image
image = Image.open("after.png")
extracted = ''
pixels = image.load()
#Iterating in 1st row
for x in range(0,image.width):
r,g,b = pixels[x,0]
# Storing LSB of each color
extracted += bin(r)[-1]
extracted += bin(g)[-1]
extracted += bin(b)[-1]
chars = []
for i in range(len(extracted)/8):
byte = extracted[i*8:(i+1)*8]
chars.append(chr(int(''.join([str(bit) for bit in byte]), 2)))
flag = base64.b64decode(''.join(chars))
print flag
BELOW: HIDING PROGRAM:
import bitarray
import base64
from PIL import Image
with Image.open('before.png') as im:
pixels=im.load()
message = input("Your message: ")
encoded_message = base64.b64encode(message.encode('utf-8'))
#Convert the message into an array of bits
ba = bitarray.bitarray()
ba.frombytes(encoded_message)
bit_array = [int(i) for i in ba]
#Duplicate the original picture
im = Image.open("before.png")
im.save("after.png")
im = Image.open("after.png")
width, height = im.size
pixels = im.load()
#Hide message in the first row
i = 0
for x in range(0,width):
r,g,b = pixels[x,0]
#print("[+] Pixel : [%d,%d]"%(x,0))
#print("[+] \tBefore : (%d,%d,%d)"%(r,g,b))
#Default values in case no bit has to be modified
new_bit_red_pixel = 255
new_bit_green_pixel = 255
new_bit_blue_pixel = 255
if i<len(bit_array):
#Red pixel
r_bit = bin(r)
r_last_bit = int(r_bit[-1])
r_new_last_bit = r_last_bit & bit_array[i]
new_bit_red_pixel = int(r_bit[:-1]+str(r_new_last_bit),2)
i += 1
if i<len(bit_array):
#Green pixel
g_bit = bin(g)
g_last_bit = int(g_bit[-1])
g_new_last_bit = g_last_bit & bit_array[i]
new_bit_green_pixel = int(g_bit[:-1]+str(g_new_last_bit),2)
i += 1
if i<len(bit_array):
#Blue pixel
b_bit = bin(b)
b_last_bit = int(b_bit[-1])
b_new_last_bit = b_last_bit & bit_array[i]
new_bit_blue_pixel = int(b_bit[:-1]+str(b_new_last_bit),2)
i += 1
pixels[x,0] = (new_bit_red_pixel,new_bit_green_pixel,new_bit_blue_pixel)
#print("[+] \tAfter: (%d,%d,%d)"%(new_bit_red_pixel,new_bit_green_pixel,new_bit_blue_pixel))
im.save('after.png')
error
ValueError: string argument should contain only ASCII characters
help for base64.b64decode says:
b64decode(s, altchars=None, validate=False)
Decode the Base64 encoded bytes-like object or ASCII string s.
...
Considering that in Python 2 there were "normal" strs and unicode-strs (u-prefixed), I suggest taking closer look at what produce "".join(chars). Does it contain solely ASCII characters?
I suggest adding:
print("Codes:",[ord(c) for c in chars])
directly before:
flag = base64.b64decode("".join(chars))
If there will be number >127 inside codes, that mean it might not work as it is fit only for pure ASCII strs.
I have been trying to build an empirical codon substitution matrix given a multiple sequence alignment in fasta format using Biopython.
It appears to be relatively straigh-forward for single nucleotide substitution matrices using the AlignInfo module when the aligned sequences have the same length. Here is what I managed to do using python2.7:
#!/usr/bin/env python
import os
import argparse
from Bio import AlignIO
from Bio.Align import AlignInfo
from Bio import SubsMat
import sys
version = "0.0.1 (23.04.20)"
name = "Aln2SubMatrix.py"
parser=argparse.ArgumentParser(description="Outputs a codon substitution matrix given a multi-alignment in FastaFormat. Will raise error if alignments contain dots (\".\"), so replace those with dashes (\"-\") beforehand (e.g. using sed)")
parser.add_argument('-i','--input', action = "store", dest = "input", required = True, help = "(aligned) input fasta")
parser.add_argument('-o','--output', action = "store", dest = "output", help = "Output filename (default = <Input-file>.codonSubmatrix")
args=parser.parse_args()
if not args.output:
args.output = args.input + ".codonSubmatrix" #if no outputname was specified set outputname based on inputname
def main():
infile = open(args.input, "r")
outfile = open(args.output, "w")
align = AlignIO.read(infile, "fasta")
summary_align = AlignInfo.SummaryInfo(align)
replace_info = summary_align.replacement_dictionary()
mat = SubsMat.SeqMat(replace_info)
print >> outfile, mat
infile.close()
outfile.close()
sys.stderr.write("\nfinished\n")
main()
Using a multiple sequence alignment file in fasta format with sequences of same length (aln.fa), the output is a half-matrix corresponding to the number of nucleotide substitutions oberved in the alignment (Note that gaps (-) are allowed):
python Aln2SubMatrix.py -i aln.fa
- 0
a 860 232
c 596 75 129
g 571 186 75 173
t 892 58 146 59 141
- a c g t
What I am aiming to do is to compute similar empirical substitution matrix but for all nucleotide triplets (codons) present in a multiple sequence alignment.
I have tried to tweak the _pair_replacement function of the AlignInfo module in order to accept nucleotide triplets by changing:
line 305 to 308
for residue_num in range(len(seq1)):
residue1 = seq1[residue_num]
try:
residue2 = seq2[residue_num]
to
for residue_num in range(0, len(seq1), 3):
residue1 = seq1[residue_num:residue_num+3]
try:
residue2 = seq2[residue_num:residue_num+3]
At this stage it can retrieve the codons from the alignment but complains about the alphabet (the module only accepts single character alphabet?).
Note that
(i) I would like to get a substitution matrix that accounts for the three possible reading frames
Any help is highly appreciated.
I am trying to perform multiple sample comparison and Tukey HSD using the statsmodels module, but I keep getting this error message, "ValueError: v must be > 1 when p >= .9". I have tried looking this up on the internet for a possible solution, but no avail. Any chance anyone familiar with this module could help me out decipher what I am doing wrong to prompt this error. I use Python version 2.7x and spyder. Below is a sample of my data and the print statement. Thanks!
import numpy as np
from statsmodels.stats.multicomp import (pairwise_tukeyhsd,MultiComparison)
###--- Here are the data I am using:
data1 = np.array([ 1, 1, 1, 1, 976, 24, 1, 1, 15, 15780])
data2 = np.array(['lau15', 'gr17', 'fri26', 'bays29', 'dantzig4', 'KAT38','HARV50', 'HARV10', 'HARV20', 'HARV41'], dtype='|S8')
####--- Here's my print statement code:
print pairwise_tukeyhsd(data1, data2, alpha=0.05)
Seems you have to provide more data than a single observation per group, in order for the test to work.
Minimal example:
from statsmodels.stats.multicomp import pairwise_tukeyhsd,MultiComparison
data=[1,2,3]
groups=['a','b','c']
print("1st try:")
try:
print(pairwise_tukeyhsd(data,groups, alpha=0.05))
except ValueError as ve:
print("whoops!", ve)
data.append(2)
groups.append('a')
print("2nd try:")
try:
print( pairwise_tukeyhsd(data, groups, alpha=0.05))
except ValueError as ve:
print("whoops!", ve)
Output:
1st try:
/home/user/.local/lib/python3.7/site-packages/numpy/core/fromnumeric.py:3367: RuntimeWarning: Degrees of freedom <= 0 for slice
**kwargs)
/home/user/.local/lib/python3.7/site-packages/numpy/core/_methods.py:132: RuntimeWarning: invalid value encountered in double_scalars
ret = ret.dtype.type(ret / rcount)
whoops! v must be > 1 when p >= .9
2nd try:
Multiple Comparison of Means - Tukey HSD, FWER=0.05
====================================================
group1 group2 meandiff p-adj lower upper reject
----------------------------------------------------
a b 0.5 0.1 -16.045 17.045 False
a c 1.5 0.1 -15.045 18.045 False
b c 1.0 0.1 -18.1046 20.1046 False
----------------------------------------------------