def snd_url():
'''
拼接租房二级页面地址
:return:
'''
# details = detail()
index_list = regx_select(detail(url))
finall_list = []
inputname = raw_input('press in name:')
try:
for links in index_list:
for sec in link2nd_tool.linkstr(detail(links)):
print
links + sec + '>>>>>> is found'
finall_list.append(links + sec)
print
finall_list
print
"\r\n" * 10 + "-" * 30
IOutils.rtfile_input(str(finall_list), (inputname + '.txt'))
time.sleep(numpy.random.randint(1, 4))
except:
print("官方个别分站内容未填充，已跳过。。。")
finally:
return finall_list
def file_rt(page_list):
'''
结果保存
:param page_list:
:return:
'''
IOutils.rtfile_time(str(page_list), "txt")
print "列表完成"
def preprocess_all_mk2(mode='train',
disp=True):
"""Preprocesses all the data.
Mean cancellation by subtracting SENSOR_MEAN and scaling with SENSOR_STD"""
csvlist = io.get_file_list(mode=mode, fullpath=True)
pif = lambda msg: printflush(msg) if disp else None
pif('MK2 preprocessing for ' + mode + ' data\n')
for fullpath in csvlist:
t0 = time()
fpath, fname = os.path.split(fullpath)
data = pd.read_csv(fullpath).values[:,1:]
pif('Processing ' + fname + ' -- ' + str(data.shape[0]) + ' samples...')
# Removes the mean of each sensor
data -= utils.SENSOR_MEAN
# Scale the data with the standard deviation from the training data
data /= utils.SENSOR_STD
final_fname = fullpath[:-4] + '_mk2'
np.save(final_fname, data)
pif("%.3f"%(time()-t0) + " s\n")
def preprocess_all_mk1(norm_wind=None,
div_factor=300,
mode='train',
disp=True):
"""Preprocesses all the data.
Simply scales the data with div_factor, then applies running zeromean"""
csvlist = io.get_file_list(mode=mode, fullpath=True)
pif = lambda msg: printflush(msg) if disp else None
pif('MK1 preprocessing')
for fullpath in csvlist:
t0 = time()
fpath, fname = os.path.split(fullpath)
data = pd.read_csv(fullpath).values[:,1:]
pif('Processing ' + fname + ' -- ' + str(data.shape[0]) + ' samples...')
# Scale the data
data /= float(div_factor)
# Execute the running mean
if norm_wind is not None:
wind = norm_wind
else:
wind = data.shape[0]
final_data = utils.running_zeromean(data, wind, axis=0)
pif("\b" + "%.3f"%(time()-t0) + " s\n")
str_wind = 'FULL' if wind==data.shape[0] else str(wind)
final_fname = fullpath[:-4] + '_mk1_norm' + str_wind
np.save(final_fname, final_data)
def train_mean_std(disp=True):
"""Outputs the mean and standard deviation of each sensor, for the training data ONLY"""
csvlist = io.get_file_list(mode='train', fullpath=True)
pif = lambda msg: printflush(msg) if disp else None
# Sum all the means and STD together
mean = np.zeros(32, dtype=DTYPE)
var = np.zeros(32, dtype=DTYPE)
for fullpath in csvlist:
t0 = time()
fpath, fname = os.path.split(fullpath)
data = pd.read_csv(fullpath).values[:,1:]
pif('Processing ' + fname + ' -- ' + str(data.shape[0]) + ' samples...')
mean += np.mean(data, axis=0, dtype=DTYPE)
var += np.var(data, axis=0, dtype=DTYPE)
pif("\b" + "%.3f"%(time()-t0) + " s\n")
# Divide by # of datasets
dataset_count = len(csvlist)
mean /= dataset_count
var /= dataset_count
# Sqrt the variance
std = np.sqrt(var)
# print representation
print(repr(mean))
print(repr(std))
def preprocess_all_mk0(norm_wind=None,
nperseg=256,
mode='train',
max_freq_count=10,
disp=True):
"""Preprocesses all the data.
Append the 10 highest frequency components of each previous nperseg window"""
csvlist = io.get_file_list(mode=mode, fullpath=True)
pif = lambda msg: printflush(msg) if disp else None
pif('MK0 preprocessing')
for fullpath in csvlist:
t0 = time()
fpath, fname = os.path.split(fullpath)
data = pd.read_csv(fullpath).values[:,1:]
pif('Processing ' + fname + ' -- ' + str(data.shape[0]) + ' samples...')
# Get the spectrograph
f,t,sxx = utils.spectrogram(data, window='boxcar', nperseg=nperseg)
#spectro_fname = fullpath[:-4] + '_spectro'
#np.save(spectro_fname, sxx)
# N Principal frequencies (a normalized index)
max_freqs = principal_frequencies(sxx, max_freq_count)
# BLow up the max frequencies to match the data array
repeated_max_freqs = np.zeros((data.shape[0], max_freq_count), dtype=max_freqs.dtype)
tmp = np.zeros((1, max_freqs.shape[1]))
max_freqs = np.insert(max_freqs, 0, tmp, axis=0)
for k in range(0,max_freqs.shape[0]-1):
repeated_max_freqs[k*nperseg:(k+1)*nperseg,:] = np.tile(max_freqs[k,:], (nperseg,1))
final_index = k
# Execute the running mean
if norm_wind is not None:
wind = norm_wind
else:
wind = data.shape[0]
norm_data = utils.running_zeromean(data, wind, axis=0)
pif("\b" + "%.3f"%(time()-t0) + " s\n")
# Concatenate
#del data
final_data = np.append(norm_data, repeated_max_freqs, axis=1)
#del norm_data
str_wind = 'FULL' if wind==data.shape[0] else wind
final_fname = fullpath[:-4] + '_mk0' + '_W' + str(nperseg) + '_norm' + str(str_wind)
np.save(final_fname, final_data)
def load_csv_data(subid, serid, mode='train', dir_name=None):
"""Loads the data from the appropriate folder, unless dir_name is specified"""
if dir_name is None:
file_name = io.get_datadir(mode=mode)
else:
file_name = dir_name
file_name += '/subj'+str(subid)+'_series'+str(serid)
data = pd.read_csv(file_name+'_data.csv')
events = pd.read_csv(file_name+'_events.csv')
return data.values[:,1:], events.values[:,1:]
def preprocess_all_mk3(mode='train',
wind=3,
butter_order=4,
disp=True):
"""Preprocesses all the data.
Mean cancellation by subtracting SENSOR_MEAN and scaling with SENSOR_STD
an MA filter is used to reduce the impact of high frequency noise
"""
csvlist = io.get_file_list(mode=mode, fullpath=True)
pif = lambda msg: printflush(msg) if disp else None
pif('MK3 preprocessing for ' + mode + ' data\n')
for fullpath in csvlist:
t0 = time()
fpath, fname = os.path.split(fullpath)
data = pd.read_csv(fullpath).values[:,1:]
pif('Processing ' + fname + ' -- ' + str(data.shape[0]) + ' samples...')
# Removes the mean of each sensor
data -= utils.SENSOR_MEAN
# Scale the data with the standard deviation from the training data
data /= utils.SENSOR_STD
# Moving average, to remove outliers
data = utils.mov_avg(data, wind, axis=0)
# TODO
# Filter the data
brain_list = []
freq_mask = 0
for flo, fhi in utils.FREQUENCY_BANDS.itervalues():
brain_list.append(utils.butter_apply(data, low=flo, high=fhi))
freq_mask = int(round(flo+fhi*10))
del data #Free some memory!
final_data = np.concatenate(brain_list, axis=1)
# Save preprocessed data and print stuff to console
str_wind = 'FULL' if wind==final_data.shape[0] else str(wind)
final_fname = fullpath[:-4] + '_mk3_wind' + str_wind + '_fmask' + str(freq_mask)
np.save(final_fname, final_data)
del brain_list, final_data # Free some memory for the next datafile
pif("%.3f"%(time()-t0) + " s\n")
def __init__(self, subjects=SUBJECTS, series=SERIES): training_ds = IOutils.data_streamer(patients_list=subjects, series_list=series) all_data = list(training_ds) X,Y = zip(*all_data) self.data = X[0] self.events = Y[0] self.mean = self.data.mean(axis=0) self.std = self.data.std(axis=0) self.normalize()
import matplotlib.pylab as plt
from collections import Counter
import sys
if not len(sys.argv)>1:
print """arguments:
SUBJECT_ID: Id of the subject you want to train
"""
raise Exception('NEED MORE ARGUMENTS')
# NUM_ZERO_METRIC = sys.argv[3]
# obtain the first 7 datas for the 2nd subject
subject_id = int(sys.argv[1])
training_ds = IOutils.data_streamer2(keeplist=[ (subject_id, i) for i in range(1,7) ])
#nn = BasicNN(input_shape=(None,42), output_num_units=12, max_epochs=int(sys.argv[5]), hidden_num_units=int(sys.argv[4]))
vt = IOutils.VectorTransformer()
linear = LogisticRegression(class_weight = 'auto')
# n_repeat_sampling = int(sys.argv[2])
dataset_count = 0
for X,Y in training_ds:
dataset_count += 1
# transform the Ys
Y = vt.transform(Y)
# print('total size before sampling:', len(Y))
X = X.astype(np.float)
# normalization for regression
X[np.isnan(X)] = 0
def step2():
'''
得到数据
:return:
'''
# 读取上一阶段保存的列表
fd = open('chuzu_list.txt', 'r')
all_text = fd.read()
fd.close()
# 列表处理
L = all_text.replace('[', '')
L = L.replace(']', '')
L = L.replace('\'', '')
chuzu_list = L.split(",")
# 出租房页面列表
chuzu_list = list(set(chuzu_list))
# 已有数据列表
done_list = list_check.done_lis()
print(done_list)
# 出错列表
error_list = []
# 详情页处理
item_pages = []
random.shuffle(chuzu_list)
for i in chuzu_list:
# 显示当前页面地址
print i
it_urls = get_itempage_url.get_url(i)
time.sleep(numpy.random.randint(3, 6))
# 详情获取和保存
for url in it_urls:
if url not in done_list:
if 'e.58.com' in url:
print('无效地址。。下一个')
elif 'jxjump' in url:
print('无效地址。。下一个')
else:
if 'short.58.com' in url:
url = url.replace('&end=end', '')
print(
'############################当前地址不在已完成列表中############################'
)
try:
# 得到页面数据
city, district, title, rental_type, phone_num, contacts, url_now, rent, lease, area, heading, community, address, detail, facility, advantage, pic = haoitem.get_items(
url)
# 得到处理后城市名
c_name = haoitem.get_cname()
# 所在地区和省份
region, province = get_city_info.get_areas(c_name)
# 保存到json的内容
detel = {
"region": region,
"province": province,
"city": city,
"district": district,
"title": title,
"rental_type": rental_type,
"url_now": url_now,
"rent": rent,
"lease": lease,
"area": area.replace(' ', ''),
"heading": heading,
"community": community,
'address': address,
"contacts": contacts,
"phone": phone_num,
"detail": detail,
"facility": facility,
"advantage": advantage,
"pics": pic
}
jStr = json.dumps(detel, ensure_ascii=False, indent=1)
IOutils.rtfile_time_with_path(jStr, 'json')
write_db.data_in(detel)
time.sleep(numpy.random.randint(3, 6))
except:
print(
'########################看来有的页面有问题，触发反爬了,休息片刻########################'
)
print('#' * 20 + url + '\t' + '#' * 20)
error_list.append(url)
time.sleep(15)
else:
print(
'############################页面已经搞过了，下一个############################'
)
time.sleep(numpy.random.randint(3, 5))
# finally:
# return item_pages
if it_urls != None:
it_pages = item_pages.append(it_urls)
print it_pages
# 详情页列表保存
file_zf = open('zf_item_list.txt', 'w')
file_zf.write(repr(it_pages))
file_zf.close()
file_zf = open('error_list.txt', 'w')
file_zf.write(repr(error_list))
file_zf.close()
return error_list
#parser.add_argument("--combineStages" , help= "e.g. <superMat_name1>:<Name1>,<Name2>;<sumperMat_name2>:<Name3>")
parser.add_argument(
"--fo",
help=
"name output figure. Extension indiciates figure type. Data files saved with same name but different extension"
)
#parser.add_argument("--stagesPlot")
parser.add_argument("--vmin", type=float)
parser.add_argument("--vmax", type=float)
parser.add_argument("--linkage_regTargets", default="complete")
parser.add_argument("--linkage_TFs", default="complete")
args = parser.parse_args()
###########################################################################################################################
## LOAD DATA
corrDF = IOutils.loadDF(args.geneCorr)
genes = list(
set().union(*[IOutils.readListFromFile(x) for x in args.genes.split(",")]))
genes_missing = [x for x in genes if not (x in corrDF.index)]
if len(genes_missing) > 0:
print("WARNING the following genes are not in correlation data {}".format(
genes_missing))
genes = [x for x in genes if x in corrDF.index]
TFs = list(
set().union(*[IOutils.readListFromFile(x) for x in args.TFs.split(",")]))
TFs_missing = [x for x in TFs if not (x in corrDF.index)]
if len(TFs_missing) > 0:
print("WARNING the following TFs are not in correlation data {}".format(
TFs_missing))
TFs = [x for x in TFs if x in corrDF.index]
import IOutils # from sklearn.naive_bayes import GaussianNB from sklearn.linear_model import LogisticRegression from sklearn.ensemble import RandomForestClassifier # from sklearn import svm import random import sys from sklearn.metrics import confusion_matrix from sklearn.metrics import precision_score from sklearn.metrics import recall_score from sklearn.metrics import f1_score ds = IOutils.data_streamer2() vt = IOutils.VectorTransformer() X_valid, Y_valid = ds.next() # use as follows: Y_valid = vt.transform(Y_valid) Y_valid [Y_valid != 0] = 1 # Y_valid [Y_valid == 0] = 0 # NaivB = GaussianNB() # linear = LogisticRegression(class_weight = 'auto') #accounts for class imbalance # support = svm.SVC(kernel='rbf',C=10)
import sys
sys.path.append("src")
import Argument
import IOutils
import ImageProcessing
userCommand = Argument.CommandParser()
userCommand.parseArguments()
inputVideo = userCommand.getInputVideoInfo()
outputVideo = userCommand.getOutputVideoInfo()
outputText = userCommand.getOutputTextInfo()
port = IOutils.IOport(inputVideo, outputVideo, outputText)
port.createFileInstancesUponRequirement()
preprocessor = ImageProcessing.VideoPreprocessor(inputVideo)
preprocessor.findSideToCrop()
preprocessor.findCropPoints()
scaleRatio = preprocessor.getDisplayTargetRatio()
algo = ImageProcessing.Algorithm()
arrowMaker = ImageProcessing.VideoArtist(scaleRatio)
arrowMaker.findBestFrameMapping((8, 8))
monitor = IOutils.Display()
frame = port.getInputVideoFrame()
croppedFrame = preprocessor.cropFrameIntoSquare(frame)
previousFrame = preprocessor.convertFrameIntoSpecifiedFormat(croppedFrame)
# In[1]:
import numpy as np
import matplotlib.pylab as plt
from collections import Counter
import IOutils
import random
from neuralnetworks.templates import BasicNN2
from sklearn.metrics import confusion_matrix, classification_report
from itertools import product
# In[2]:
training_ds = IOutils.data_streamer2(keeplist=[ (i, 0) for i in range(1,12) ]) # obtain data for first 11 patients
nn = BasicNN2(input_shape=(None,42), output_num_units=11, max_epochs=100, hidden=[200,120,30])
vt = IOutils.VectorTransformer()
# In[3]:
n_repeat_sampling = 1
dataset_count = 0
for X,Y in training_ds:
dataset_count += 1
# transform the Ys
Y = vt.transform(Y)
# print('total size before sampling:', len(Y))
# -*- coding:utf-8 -*-
'''
批量获取所有页面地址
需要配合反爬
'''
import IOutils
import get_pages
import numpy
import time
import re
index_list = IOutils.readfile()
# 列表字符处理
L = index_list.replace('[', '')
L = L.replace(']', '')
L = L.replace('\'', '')
list_u = L.split(",")
list_u = list(set(list_u))
print list_u
for url in list_u:
'''
再次处理url列表
'''
key = str(url)
regx = r'http\:\/\/[a-z]+\.58\.com\/(chuzu|ershoufang|pinpaigongyu)\/'
pattern1 = re.compile(regx)
def save_dicts():
dic = map_dict()
dicts = repr(dic)
IOutils.rtfile(dicts)
]
# In[4]:
nn = NeuralNet(layers_list,
max_epochs=30,
update=nesterov_momentum,
update_learning_rate=0.02,
verbose=1000,
**LF.kwargs)
# In[5]:
training_ds = IOutils.data_streamer(patients_list=[2], series_list=range(1,7))
# nn = BasicCNN(input_shape=(None,42), output_num_units=12, max_epochs=50, hidden=[256, 120], add_drops=[1,1])
vt = IOutils.VectorTransformer()
# In[ ]:
n_repeat_sampling = 1
dataset_count = 0
for X,Y in training_ds:
X = X.astype(np.float)
X[np.isnan(X)] = 0
X = X/X.max()
wg = window_generator_ND(X, window_size=WINDOW_SIZE)
dataset_count += 1
# transform the Ys
# coding: utf-8
# In[1]:
import numpy as np
import matplotlib.pylab as plt
from collections import Counter
import IOutils
import random
from neuralnetworks.templates import BasicNN2
from sklearn.metrics import confusion_matrix, classification_report
# In[ ]:
training_ds = IOutils.data_streamer2(keeplist=[ (1, i) for i in range(1,7) ]) # obtain the first 7 datas for the 1st subject
nn = BasicNN2(input_shape=(None,42), output_num_units=11, max_epochs=100, hidden=[200,120,30])
vt = IOutils.VectorTransformer()
# In[ ]:
n_repeat_sampling = 1
dataset_count = 0
for X,Y in training_ds:
dataset_count += 1
# transform the Ys
Y = vt.transform(Y)
# print('total size before sampling:', len(Y))
X = X.astype(np.float)
# normalization for regression
#IOutils.LABEL_NAMES has all the classes we wish to predict
#HI
# initialize logistic regressors
LRs = {}
LRsprocessed = {}
for label_name in IOutils.LABEL_NAMES:
# each label will have its own logistic regressor
LRs[label_name] = LogisticRegression()
LRsprocessed[label_name] = LogisticRegression()
print('Initialized logistic regressors')
# Load training data
# load 1 trial each from 3 patients
train_data = IOutils.data_streamer(mode='train', num_patients=1, num_series=8)
filters = ['alpha', 'beta']
# obtain a validation set
X_valid, Y_valid = train_data.next()
# X_valid = X_valid[]
selected_channels = range(X_valid.shape[1])
# selected_channels = [3,4]
X_valid = X_valid[:,selected_channels]
# print Y_valid
# X_valid = np.array(X_valid)
Y_valid = np.array(Y_valid)
def url_list():
list_u = IOutils.readfile()
return list_u
import numpy as np
import os
import pandas as pd
# Grab train data
data = []
label = []
n_sub = 1
n_series = 8
train_streamer = io.data_streamer2(mode='train')
for k in range(n_sub):
sub_data = []
sub_label = []
for series in range(n_series):
d, e = train_streamer.next()
sub_data.append(d)
sub_label.append(e)
data.append(sub_data)
label.append(sub_label)
np.save('eeg_train.npy', [data, label])
del data, label
this code runs LR and NN at the same time """ import numpy as np import IOutils # from sklearn.naive_bayes import GaussianNB from sklearn.linear_model import LogisticRegression from sklearn import svm import random import sys from sklearn.metrics import confusion_matrix, precision_score, recall_score, f1_score, classification_report from neuralnetworks.templates import BasicNN2 nn = BasicNN2(max_epochs=100, hidden=[200,50,30], input_shape=(None, 42), output_num_units=2) ds = IOutils.data_streamer2(keeplist=[ (i,0) for i in xrange(1,12) ]) vt = IOutils.VectorTransformer() # NaivB = GaussianNB() lr = LogisticRegression(class_weight="auto") #svc = svm.SVC(kernel='rbf',C=10,class_weight="auto") #======= # svc = svm.SVC(kernel='rbf',C=10,class_weight="auto") for X_next, Y_next in ds: X_next = X_next.astype(np.float)/X_next.max() X_next[np.isnan(X_next)]=0 zipped = zip(X_next,Y_next) random.shuffle(zipped) X,Y = zip(*zipped)
#exampleArgs="--fi_expr ../exprData/impute-t10_libNorm10K_cells.foreskin_genesGeq1Pct.all.kcyte.pkl \
#--fi_stageIDs ../clusterCells/kasp.ka10.k30_impute.t10_gene.geq5UMIgeq100Cell.all.csv \
#--cells ./cellNames.passFilter.tmp \
#--superstages progenitor:stage1,stage2,stage3;\
#progenitor.stage4:stage1,stage2,stage3,stage4;\
#differentiated:stage5,stage6,stage7;\
#differentiated.stage4:stage4,stage5,stage6,stage7;\
#all.noStage8:stage1,stage2,stage3,stage4,stage5,stage6,stage7 \
#--corrMethod logTpm \
#--fo corr_tmpA"
#args = parser.parse_args(exampleArgs.split())
if args.superstages is not None:
superstage_dict = IOutils.parseStrToDict(args.superstages,
valueType="str",
pairSep=";")
try:
superstage_dict = OrderedDict([(k, [int(x) for x in v.split(",")])
for k, v in superstage_dict.items()])
except:
superstage_dict = OrderedDict([
(k, [int(re.search(r'(\d+)$', x).group(1)) for x in v.split(",")])
for k, v in superstage_dict.items()
])
############################################################################################################
## Load data
cellData = IOutils.loadCellData(
OrderedDict([("expr", args.fi_expr), ("pcComps", args.fi_stageIDs)]))
cellData = pd.concat([
