def parser(data):
AFMDict = defaultdict(lambda: defaultdict(dict))
for entry in data["entries"]:
newdict = {}
for stat in data["entries"][entry]['nestedStats']["entries"]:
newdict[stat] = data["entries"][entry]['nestedStats']["entries"][stat]
AFMDict[entry]['vectorName'] = newdict['vectorName']['description']
newdict.pop('vectorName')['description']
for key in newdict:
AFMDict[entry][key.strip('common.')] = newdict[key]['value']
return AFMDict
def __init__(self,repeatMaskerFile):
self.repeat = defaultdict(lambda: defaultdict(list))
with open(repeatMaskerFile,'r') as IN_REP:
IN_REP.readline()
IN_REP.readline()
IN_REP.readline()
for line in IN_REP:
line = line.strip()
score,pdiv,pdel,pins,chrom,beg,end,left,cplus,match,rep_class,rbeg,rend,rleft,id = line.split()
repeat[chrom]['start'].append(beg)
repeat[chrom]['end'].append(end)
def __init__(self, repeatMaskerFile):
self.repeat = defaultdict(lambda: defaultdict(list))
with open(repeatMaskerFile, 'r') as IN_REP:
IN_REP.readline()
IN_REP.readline()
IN_REP.readline()
for line in IN_REP:
line = line.strip()
score, pdiv, pdel, pins, chrom, beg, end, left, cplus, match, rep_class, rbeg, rend, rleft, id = line.split(
)
repeat[chrom]['start'].append(beg)
repeat[chrom]['end'].append(end)
def numSubmatrixSumTarget(self, m, target: int) -> int:
def pref(x):
asum = 0
p = [0] * len(x)
for i in range(len(x)):
asum += x[i]
p[i] = asum
return p
for i, r in enumerate(m):
m[i] = pref(r)
res = 0
for i in range(0, len(m[0])):
for j in range(i, len(m[0])):
h = defaultdict(lambda: 0)
h[0] = 1
asum = 0
for k in range(len(m)):
asum += (m[k][j] - m[k][i])
other = asum - target
if other in h:
res += h[other]
h[asum] += 1
return res
def append_inverted(url, token_list, result):
tf_raw = defaultdict(int)
count = len(token_list)
for token in token_list:
tf_raw[token] += 1
for token, c in tf_raw.items():
result[token].append({'url':url,'tf': c/count,'idf': None,'tf-idf':None})
def freqQuery(queries):
ans = []
counts = defaultdict(int)
freq = defaultdict(int)
for a, b in queries:
if a == 1:
freq[counts[b]] -= 1
counts[b] += 1
freq[counts[b]] += 1
elif a == 2 and counts[b] > 0:
freq[counts[b]] -= 1
counts[b] -= 1
freq[counts[b]] += 1
elif a == 3:
ans.append(1) if (freq[b] > 0) else ans.append(0)
return ans
def __init__(self, genome):
self.arg = arg
nodes = list(genome.node_genes.keys())
edges = defaultdict(list)
for conn in genome.conn_genes:
edges[conn.in_node_id].append(conn.out_node_id)
edges[conn.out_node_id].append(conn.in_node_id)
def countsort(values,mini, maxi):
count=defaultdict(int)
for i in array:
count[i]+=1
result=[]
for j in xrange(mini,maxi+1):
result+=[j]*count[j]
return result
def non_duplicate(string):
frequency = defaultdict(int)
for i in string:
frequency[i] += 1
for i in string:
if frequency[i] == 1:
return i
return -1
def get_amounts_by_canidate_and_category(file, fields, candidate_id_field):
data = {}
with open(os.path.join(FILE_DIR, file)) as fh:
for row in csv.DictReader(fh, fields, dialect='open_secrets'):
cid = row[candidate_id_field]
if cid not in data:
data[cid] = defaultdict(float)
realcode = row['RealCode']
data[cid][realcode] += float(row["Amount"])
return data
# >>> SafeFormatter().format('{one} {one:x} {one:10f} {two!r} {two[0]}', one=215, two=['James', 'Bond'])
# "215 d7 215.000000 ['James', 'Bond'] James"
# >>> SafeFormatter().format('{one} {one:x} {one:10f} {two!r} {two[0]}', one=215)
# '215 d7 215.000000 {two!r} {two[0]}'
# >>> SafeFormatter().format('{one} {one:x} {one:10f} {two!r} {two[0]}')
# '{one} {one:x} {one:10f} {two!r} {two[0]}'
# >>> SafeFormatter().format('{one} {one:x} {one:10f} {two!r} {two[0]}', two=['James', 'Bond'])
# "{one} {one:x} {one:10f} ['James', 'Bond'] James"
>>> from collections import defaultdict
>>> kwargs = {"name": "mark"}
>>> template = "My name is {0[name]} and I'm really {0[adjective]}."
>>> template.format(defaultdict(str, kwargs))
"My name is mark and I'm really ."
from functools import partial
s = partial("{foo} {bar}".format, foo="FOO")
print s(bar="BAR")
# FOO BAR
import string
try:
# Python 3
from _string import formatter_field_name_split
len(samples)
outputs[0]
[x.split('|', 2) for x in outputs][0]
[x.strip().split('|', 2) for x in outputs][0]
outputs = [x.strip().split('|', 2) for x in outputs]
outputs[0]
outputs[0]
[[x[0], map(int, x[1].split()), x[2] for x in outputs][0]
]
[[x[0], map(int, x[1].split()), x[2]] for x in outputs][0]
[[x[0], map(int, x[1].split()) + x[2]] for x in outputs][0]
[[x[0], map(int, x[1].split()) + [x[2]]] for x in outputs][0]
outputs = [[x[0], map(int, x[1].split()) + [x[2]]] for x in outputs]
get_ipython().magic(u'save read.py 0-23')
from collection import default_dict
from collections import default_dict
from collection import defaultdict
from collections import defaultdict
genes = defaultdict(list)
outputs[0]
for output in outputs:
defaultdict[output[0]].append(output[1])
outputs[0]
outputs[2]
for output in outputs:
genes[output[0]].append(output[1])
genes
get_ipython().magic(u'save read.py 0-35')
def not_game(state):
responses = defaultdict(lambda:state)
responses['Restart'],responses['Exit'] = 'Init','Exit'
return responses[action]
def __init__(self,name):
self.name= name
def __repr__(self):
return 'Item({!r})'.format(self.name)
q = PriorityQueue()
# 1.6 字典中的键映射多个值
from collection import defaultdict
d = default(list)
d['a'].append(1)
d['a'].append(2)
d['b'].append(4)
d = defaultdict(set)
d['a'].add(1)
d['a'].add(2)
d['b'].add(4)
# 1.7 字典排序
from collections import OrderdDict
def orderd_dict():
d = OrderDict()
d['foo'] = 1
d['fbar'] = 2
d['spa'] = 3
import json
json.dumps(d)
def __init__(self):
self.checkpoints = []
self.checkpoint_names = []
self.time_accumulator = defaultdict(float)
self.accumulator_starts = defaultdict(float)
def __init__(self):
self.edges = defaultdict(list)
def __init__(self,filename):
self.fileName=filename
self.conditions=defaultdict(list)
self.indentList=defaultdict(list)
self.file=open(filename,"r")
self.controlFlowModifiers=["while","for","if","elif","else:"]
def Q(state,id_team,id_player):
dicoaction = {"conserver":conserver,"dribbler":dribbler,"tirer":
tirer,finition":finition"}
S = discretisation(state,id_team,id_player)
senario{S : dicoation}
return senario
Q = dict()
Q[s]=defaultdict(float)
Q[s][a]
def Monte_carlo(Q= None, scenario = [(state,action)...,(state,action)]):
R = recompense(senario[-1][0])
if Q is None:
Q = dict()
for (s,a) in senario[-2::-1]:
if s not in Q:
Q[s] = defaultdict(float)
Q[s][a] = Q[s][a] + alpha*(R-Q[s][a])
R = gamma * R +recompense(s)
from collection import defaultdict
n = int(input())
A = list(int(x) for x in input().split())
B = list(int(x) for x in input().split())
C = set(int(x) for x in input().split())
A_dict = defaultdict(set)
B_dict = defaultdict(set)
for i, x in enumerate(A):
A_dict[x].add(i)
for i, x in enumerate(B):
if i in C:
B_dict[x].add(i)
from collection import defaultdict
RESULTS_DIR = "./output/"
MODEL_KEY = 'alg_name'
FOLD_KEY = 'fold_num'
DB_NAME_KEY = 'dataset_name'
dbs_results = defaultdict(lambda: defaultdict(lambda: defaultdict(dict)))
for file_path in os.listdir(RESULTS_DIR):
if file_path.endswith(".csv"):
df = pd.read_csv(os.path.join(RESULTS_DIR, file_path))
for row in df.to_dict(orient='records'):
model = row[MODEL_KEY]
fold_num = row[FOLD_KEY]
db_name = row[DB_NAME_KEY]
row.pop(MODEL_KEY)
row.pop(FOLD_KEY)
row.pop(DB_NAME_KEY)
dbs_results[db_name][model][fold_num] = row
print(dbs_results)
write_all_results(dbs_results)
def download_dir(remoteDir, localDir, sftp):
filterKeys = ('bam','sam','bai','junction','htm')
dirItems =sftp.listdir_attr(remoteDir)
os.path.exists(localDir) or os.path.makedirs(loaclDir)
for item in dirItems:
remotePath = remoteDir + '/' + item.filname
if '_' not in item.filename:
fmtFilName=item.filename
else:
fmtFilName='_'.join(item.filename.split('_')[0:2]+\
'.'+'.'.join(item.filename.split('.')[-2:])
localpath = os.path.join(loaclDir , fmtFilName)
try:
sftp.listdir_arrt(remotePath)
download_dir(remoteDir, localDir, sftp)
except:
if remotePath.endwith(filterKeys): continue
sftp.get(remotePath,localpath)
print>>sys.stdeer,'[INFO] Download {} success!'.format(fmtFilName)
return sftp
def downloadServer(barcodeDic,configInfo,ip,username,pwd,port=22):
localDir = configInfo['baseInfo']['inputdir']
remoteDir = configInfo['Server']['path']
transport = paramiko.Transport ((ip,port))
transport.connect(username=username,password=pwd)
sftp = paramiko.SFTPClient.from_transport(transport)
for name in barcodeDic:
barcodeLst = barcodeDic[name].split(',')
for barcode in barcodeLst:
remotePath = remoteDir + '/' + barcode
localpath =os.path.join(loaclDir,barcode)
1 if os.path.join.exists(localpath) else os.mkdir(localpath)
download_dir(remotePath,localpath,sftp)
transport,close()
print >>sys.stdeer,'[INFO] Download total tesults from PGM server success'
return 0
def createCustomResDir(barcodeDic,outdir):
for key in barcodeDic:
outPath = os.path.join(outdir , key)
1 if os.path.exists(outPath) else os.mkdir (outPath)
return 0
def writeFPKM(fpkmFil,geneDb,results):
resDict= collections.defaultdict()
with open(fpkmFil,'r') as fpRead :
header =fpRead.readline()
index1 =header.split('\t').index('FPKM')
index2 =header.split('\t').index('gene_short_name')
for line in fpRead:
if not in line: continue
lineFmt =line.strip().split('\t')
resDict[lineFmt[index2]]= line[index1]
[results[gene].append(resDict[gene]) if gene in resDict else results[gene].append(0) for gene in geneDb]
return results
def getFPKM(barcodeDic,customInfo,geneDb,timeSerie,suffix='genes.fpkm_tracking'):
inputDir = customInfos['baseInfo']['inputdir']
outputdir = customInfos['baseInfo']['outdir']
for name in barcodeDic:
outPath = os.path.join(outputdir,name)
results = collection.defaultdict(list)
import sys
import csv
import pysam
from Bio import SeqIO
from Bio.Seq import Seq
from Bio.Alphabet import generic_dna
from collection import defaultdict
#dicionario de f*g [Rd1/Rd2, +/-]
flag_dict = {'73':[1,1], '89':[1,1], '121':[1,-1], '153':[-1,-1], '185':[-1,-1], '137':[-1,1], '99':[1,1], '147':[-1,-1], '83':[1,-1], '163':[-1,1], '67':[1,1], '115':[1,-1], '179':[-1,-1], '81':[1,-1], "161":[-1,1], '97':[1,1], '145':[-1,-1], '65':[1,1], '129':[-1,1], '113':[1,-1], '177':[-1,-1] }
Genome = {}
non_can = set([])
can = set([])
dn_count = defaultdict(int)
def Genomictabulator(fasta):
print >> sys.stderr, "Cargando genoma en la memoria RAM ...",
f = open(fasta)
for chrfa in SeqIO.parse(f, "fasta"):
Genome[chrfa.id] = chrfa.seq
print >> sys.stderr, "OK"
f.close()
normal dict
for key in s:
if key in d:
d[key]+=1
else:
d[key]=1
import collections
d = collections.defaultdict(int)
from collection import defaultdict
dd=defaultdict(int)
for key in s:
dd[key]+=1
ordereddict
from collection import Ordereddict
dict1=Ordereddict()
from collection import namedtuple
point =namedtuple('point','x,y')
pt1=point(1,2)
def __init__(self):
self.graph = defaultdict(list)
def __init__(self):
self._observers = defaultdict(list)
from urllib import request
import csv
my_url = 'https://www.stats.govt.nz/assets/Uploads/Annual-enterprise-survey/Annual-enterprise-survey-2018-financial-year-provisional/Download-data/annual-enterprise-survey-2018-financial-year-provisional-size-bands-csv.csv'
def download_csv(csv_url):
response = request.urlopen(csv_url)
csv = response.read()
str_csv = str(csv)
lines = str_csv.split("\\n")
name_url = r'first.csv'
fs = open(name_url, 'w')
for line in lines:
fs.write(line + '\n')
fs.close()
download_csv(my_url)
from collection import defaultdict
my_result=defaultdict(list)
with open('first.csv', 'rb') as csvfile:
for row in csv.reader(csvfile, delimiter=','):
my_result[age].append(name)
print(zip(sorted((my_result.value(), my_result.key()))
'179': [-1, -1],
'81': [1, -1],
"161": [-1, 1],
'97': [1, 1],
'145': [-1, -1],
'65': [1, 1],
'129': [-1, 1],
'113': [1, -1],
'177': [-1, -1]
}
Genome = {}
non_can = set([])
can = set([])
dn_count = defaultdict(int)
def Genomictabulator(fasta):
print >> sys.stderr, "Cargando genoma en la memoria RAM ...",
f = open(fasta)
for chrfa in SeqIO.parse(f, "fasta"):
Genome[chrfa.id] = chrfa.seq
print >> sys.stderr, "OK"
f.close()
def not_game(): ''' 判断Win或游戏Gameover-->读取用户输入的动作(action) ''' response = defaultdict(lambda:state) # 默认当前状态，没有就当前状态的界面循环 response['Restart'],response['Exit'] = 'Init','Exit' return response[action]
