def dataGettingEvent(sc):
print("Fetching data")
getData.main()
#re-setup scheduler
# todo set this way higher
datagettingScheduler.enter(180, 1, dataGettingEvent, (sc,))
def main():
getLogger()
logging.info("start ETL process")
if config.CREATE_DATABASE_OBJECTS_FLAG:
logging.info("create DB")
databaseUtils.main()
logging.info("download data")
getData.main()
logging.info("prepare data")
shipping_lines_data = prepareData.get_shipping_lines_data()
logging.info("load data")
databaseUtils.load_shipping_lines_table(shipping_lines_data)
logging.info("end ETL process")
def get_data():
try:
data = pd.read_csv("rb1901.csv", index_col=0)
data.index = pd.to_datetime(data.index)
except:
import getData
getData.main()
data = pd.read_csv("rb1901.csv", index_col=0)
data.index = pd.to_datetime(data.index)
days_number = np.load("days_number.npy")
da = [
data.iloc[days_number[i]:days_number[i + 1]]
for i in xrange(len(days_number) - 1)
]
def stat():
form = UserDate(request.form)
requsted_date_from = form.input_date_from._value()
requsted_date_to = form.input_date_to._value()
all_managers = getData.main(requsted_date_from, requsted_date_to)
visible_managers = {}
visible_dealingers = {}
for num in managers_num:
if all_managers.has_key(num):
visible_managers[num] = all_managers[num]
for num in dealingers_num:
if all_managers.has_key(num):
visible_dealingers[num] = all_managers[num]
return render_template("stat.html",
work_hours = work_hours,
all_hours = all_hours,
today = requsted_date_from,
title = 'Get Report',
form = form,
dealingers = visible_dealingers,
managers_names = managers_names,
visible_managers = visible_managers,
managers = all_managers)
def main():
messageSize = 32
mostFrequentWords = 9999
fullLog, wordFreq = getData.main()
#data, labels, nameDict = standardizePackets(fullLog, messageSize)
dictionary = convertFreqTable(wordFreq, mostFrequentWords)
data, labels = standardizePackets(fullLog, messageSize, dictionary)
#trainingData, trainingLabels, testingData, testingLabels = splitTrainTest(data, labels, .9)
printToFile(data, 'data.txt')
printToFile(labels, 'labels.txt')
return data, labels, (messageSize)
def main(careerData=None,seasonStats=None):
"""
This is the main module. This can be run without any inputs, in which case
the careerData and seasonStats variables will be creating using modules
in the getData.py file. Once all the features are created they are saved
as pickle files.
Inputs:
careerData - dictionary or pickle file, optional (default=None)
This is the dictionary containing all relevant career data.
If the data has not been collected previously, then it will be
collected with the default input. Either a dictionary or a saved
pickle file are acceptable inputs
seasonStats - dictionary of pickle file, optional (default=None)
This is the dictionary containing end of season stats for all
relevant years. If the data has not been collected previously,
then it will be collected with the default input. Either a
dictionary or a saved pickle file are acceptable inputs
Outputs:
nonRookieData - dictionary
This is the dictionary containing all relevant feature data for
Non-Rookies. The keys are the seasons and the values are
the features
rookieData - dictionary
This is the dictionary containing all relevant feature data for
Rookies. The keys are the seasons and the values are
the features
careerData - dictionary
If a new player is found during feature extraction that was not
previously in the saved careerData variable, it will be updated.
"""
if careerData:
try: careerData = pickle.load(careerData)
except: pass
if seasonStats:
try: seasonStats = pickle.load(seasonStats)
except: pass
if not (careerData and seasonStats):
careerData,seasonStats=getData.main()
nonRookieData,rookieData,careerData=getTrainData(careerData,seasonStats)
pickle.dump(nonRookieData,open('nonRookieData.p','wb'))
pickle.dump(rookieData,open('rookieData.p','wb'))
pickle.dump(careerData,open('careerData.p','wb'))
return(nonRookieData,rookieData,careerData)
def testMethods(nonRookieData=None,rookieData=None,careerData=None):
"""
The test suite for deciding the best model
"""
if not careerData:
seasonStats,careerData,lookUp = getData.main()
if not (nonRookieData and rookieData):
nonRookieData,rookieData,careerData=getFeatures.main(careerData)
resultsNonRookies,predsNonRookies = getCrossVal(nonRookieData,careerData)
resultsRookies,predsRookies = getRookieCrossVal(rookieData,careerData)
resultsNonRookies = writeResToPandas(resultsNonRookies,'nonRookies')
resultsRookies = writeResToPandas(resultsRookies,'rookies')
return(resultsNonRookies,resultsRookies,predsNonRookies,predsRookies)
def predictNextSeason(year=2015,nonRookieData='nonRookieData.p',rookieData='rookieData.p',careerData='careerData.p',seasonStats='seasonStats.p'):
"""This module uses previously selected algorithms:
-Veterans: Random Forest; n_estimators=500, min_samples_split=125
-Novices: SVM; C=.15, gamma = .015, epsilon= .05
It then trains the models and generates predictions in csv format
Inputs:
year - string, optional (default=2015)
nonRookieData,rookieData,careerData,seasonStats - dictionary, optional (default = None)
If None, then the variable is generated using the getFeatures.py file
Outputs:
predictionNonRookies,predicitonRookies - Pandas Dataframe
The dataframes containing the predictions for both groups
"""
t0=time.time()
last2digits=str(year)[-2:]
season = str((datetime.datetime(year,1,1)-datetime.timedelta(days=365)).year)+'-'+last2digits
if not (careerData and seasonStats):
seasonStats,careerData,lookUp = getData.main()
if not (nonRookieData and rookieData):
nonRookieData,rookieData,careerData=getFeatures.main(careerData)
nonRookieData,rookieData,careerData,seasonStats=tryPickle(nonRookieData,rookieData,careerData,seasonStats)
print('All past data found! Now fitting models ',time.time()-t0)
nonRookiesModel,nonRookiesTrain,nonRookiesScaler = getModel(nonRookieData,'nonRookies')
rookiesModel,rookiesTrain,rookiesScaler = getModel(rookieData,'rookies')
print('Models fitted! Now getting all current players features ',time.time()-t0)
nonRookies,rookies = findPlayerFeatures(year,seasonStats[year],careerData,
nonRookiesTrain,rookiesTrain,nonRookiesScaler,rookiesScaler)
print('Features found! Now making predictions ',time.time()-t0)
predictionsNonRookies = getPredictions(nonRookies,nonRookiesModel,'nonRookies')
print('Non-Rookie Predictions made! Now predicting Rookies ',time.time()-t0)
## predictionsNonRookies.to_csv(season+'_Veteran_Predictions.csv',index=False)
predictionsRookies = getPredictions(rookies,rookiesModel,'rookies')
## predictionsRookies.to_csv(season+'_Novice_Predictions.csv',index=False)
predictionsNonRookies.append(predictionsRookies).to_csv(season+'_Predictions.csv',index=False)
print('Total Runtime is ',time.time()-t0,'s')
return(predictionsNonRookies,predictionsRookies)
def test_production_analysis_with_energies():
args = default_args()
args['energies'] = 'Yes'
getData.main(args)
def test_production_analysis():
getData.main(default_args())
def main(runPams):
timeStam = str(int(time.time()))
#saveExcelPath = "C:\\Users\\pdang\\Desktop\\" + timeStam + ".xlsx"
saveExcelPath = "/N/project/zhangclab/pengtao/myProjectsDataRes/20200113Predicte/results/l1NormCRNumCNN_small/block1/excelRes/" + timeStam + ".xlsx"
#st = time.time()
# get samples, featureMap, optFeatureMap
olabel, samples, featureMap, optFeatureMap = getData.main(runPams)
'''
[print(olabel[i], samples[i]) for i in range(len(samples))]
print("------------------------------------------------------")
[print(olabel[i], featureMap[i]) for i in range(len(featureMap))]
print("--------------------------------------------------")
[print(olabel[i], optFeatureMap[i]) for i in range(len(optFeatureMap))]
print("---------------------------------------------------------------")
print(olabel.size())
print(samples.size())
print(featureMap.size())
print(optFeatureMap.size())
sys.exit()
'''
# choose spu or gpu automatically
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# samples data
net, optimizer, lossFunc = getCNNPams(samples.size()[1],
samples.size()[2],
samples.size()[3], device,
runPams.lr)
sres, sytrue_ypred = Predicte.myUtils.myTrainTest.train_test(
olabel, samples, net, device, optimizer, lossFunc, runPams)
# featureMap data
net, optimizer, lossFunc = getCNNPams(featureMap.size()[1],
featureMap.size()[2],
featureMap.size()[3], device,
runPams.lr)
fres, fytrue_ypred = Predicte.myUtils.myTrainTest.train_test(
olabel, featureMap, net, device, optimizer, lossFunc, runPams)
# optFeatureMap data
net, optimizer, lossFunc = getCNNPams(optFeatureMap.size()[1],
optFeatureMap.size()[2],
optFeatureMap.size()[3], device,
runPams.lr)
ores, oytrue_ypred = Predicte.myUtils.myTrainTest.train_test(
olabel, optFeatureMap, net, device, optimizer, lossFunc, runPams)
# prepare results
res = list()
if runPams.minusMean == 1:
res.append("c*r-E")
else:
res.append("c*r")
res.append(runPams.xn)
res.append("N(0-" + str(runPams.stdBias / 10) + ")")
res.append("10*" + str(runPams.sampleNum))
res.append(runPams.numThreshold)
res.append("7*" + str(samples.size()[2]))
res.append(sres)
res.append("7*" + str(featureMap.size()[3]))
res.append(fres)
res.append("7*" + str(optFeatureMap.size()[3]))
res.append(ores)
# save data to excel
resDF = pd.DataFrame(res)
resDF.columns = ["res"]
sytrue_ypred = pd.DataFrame(sytrue_ypred)
sytrue_ypred.columns = ["true", "pred"]
cytrue_ypred = pd.DataFrame(fytrue_ypred)
cytrue_ypred.columns = ["true", "pred"]
oytrue_ypred = pd.DataFrame(oytrue_ypred)
oytrue_ypred.columns = ["true", "pred"]
writer = pd.ExcelWriter(saveExcelPath) # 写入Excel文件
resDF.to_excel(writer, index=False)
sytrue_ypred.to_excel(writer, startcol=2, index=False)
cytrue_ypred.to_excel(writer, startcol=5, index=False)
oytrue_ypred.to_excel(writer, startcol=8, index=False)
writer.save()
writer.close()
# output data
res = ','.join(str(i) for i in res)
print(res)
return ()
import statsmodels.api as sm
import statsmodels.formula.api as smf
import seaborn as sns
#import getData
__all__ = [
"data", "futurepng", "days_number", "get_vwap", "vwap", "last",
"rejectData", "getData", "get_vabp", "get_mabp"
]
try:
data = pd.read_csv("rb1901.csv", index_col=0)
data.index = pd.to_datetime(data.index)
except:
import getData
getData.main()
data = pd.read_csv("rb1901.csv", index_col=0)
data.index = pd.to_datetime(data.index)
days_number = np.load("days_number.npy")
da = [
data.iloc[days_number[i]:days_number[i + 1]]
for i in xrange(len(days_number) - 1)
]
def get_data():
try:
data = pd.read_csv("rb1901.csv", index_col=0)
data.index = pd.to_datetime(data.index)
except:
from pandas.plotting import scatter_matrix import matplotlib.pyplot as plt from sklearn import model_selection from sklearn.metrics import classification_report from sklearn.metrics import confusion_matrix from sklearn.metrics import accuracy_score from sklearn.linear_model import LogisticRegression from sklearn.tree import DecisionTreeClassifier from sklearn.neighbors import KNeighborsClassifier from sklearn.discriminant_analysis import LinearDiscriminantAnalysis from sklearn.naive_bayes import GaussianNB from sklearn.svm import SVC import getData dataset = getData.main() # box and whisker plots dataset.plot(kind='box', subplots=True, layout=(2,2), sharex=False, sharey=False) plt.show() # histograms dataset.hist() plt.show() # scatter plot matrix scatter_matrix(dataset)
