Python numpy.genfromtxt函数代码示例

def compare(mooseCsv, nrnCsv):
    mooseData = None
    nrnData = None
    with open(mooseCsv, "r") as f:
        mooseTxt = f.read().split("\n")
        mooseHeader, mooseData = mooseTxt[0].split(","), np.genfromtxt(mooseTxt[1:],
                delimiter=',').T
    with open(nrnCsv, "r") as f:
        nrnTxt = f.read().split("\n")
        nrnHeader, nrnData = nrnTxt[0].split(','), 1e-3*np.genfromtxt(nrnTxt[1:],
                delimiter=',').T

    nrnTimeVec, nrnData = nrnData[0], nrnData[1:]
    mooseTimeVec, mooseData = mooseData[0], mooseData[1:]
    for i, comptName in enumerate(nrnHeader[1:]):
        if i == 1:
            break 
        nrnComptName = comptName.replace("table_", "")
        mooseComptId, mooseComptName = get_index(nrnComptName, mooseHeader[1:])
        print("%s %s- moose equivalent %s %s" % (i, nrnComptName, mooseComptId,
            mooseComptName))
        pylab.plot(mooseTimeVec, mooseData[ mooseComptId ], label = "Neuron: " + nrnComptName)
        pylab.plot(nrnTimeVec, nrnData[i], label = "MOOSE: " + mooseComptName)
    pylab.legend(loc='best', framealpha=0.4)
    pylab.show()

    def setUp(self):
        """
        """
        # Read initial dataset
        filename = os.path.join(self.BASE_DATA_PATH,
                                'completeness_test_cat.csv')
        test_data = np.genfromtxt(filename, delimiter=',', skip_header=1)
        # Create the catalogue A
        self.catalogueA = Catalogue.make_from_dict(
            {'year': test_data[:,3], 'magnitude': test_data[:,17]})

        # Read initial dataset
        filename = os.path.join(self.BASE_DATA_PATH,
                                'recurrence_test_cat_B.csv')
        test_data = np.genfromtxt(filename, delimiter=',', skip_header=1)
        # Create the catalogue A
        self.catalogueB = Catalogue.make_from_dict(
            {'year': test_data[:,3], 'magnitude': test_data[:,17]})

        # Read the verification table A
        filename = os.path.join(self.BASE_DATA_PATH,
                                'recurrence_table_test_A.csv')
        self.true_tableA = np.genfromtxt(filename, delimiter = ',')

        # Read the verification table A
        filename = os.path.join(self.BASE_DATA_PATH,
                                'recurrence_table_test_B.csv')
        self.true_tableB = np.genfromtxt(filename, delimiter = ',')

def learn(tuned_parameters,model):

	# produceFeature(trainfile)
	dataset = genfromtxt(open('Data/'+trainfile,'r'), delimiter=',',dtype='f8')[0:]
	target = [x[0] for x in dataset]
	train = [x[1:] for x in dataset]
	# print train[1:10]
	# print target
	# print len(train)

	# produceFeature(testfile)
	test = genfromtxt(open('Data/'+testfile,'r'),delimiter=',',dtype='f8')[0:]
	test_target = [x[1:] for x in test]


	# X, y = digits.data, digits.target
	trainnp = np.asarray(train)
	targetnp = np.asarray(target)


	# turn the data in a (samples, feature) matrix:
	X, y = trainnp, targetnp
	# X = digits.images.reshape((n_samples, -1))
	# y = digits.target

	# Split the dataset in two equal parts
	X_train, X_test, y_train, y_test = train_test_split(
	    X, y, test_size=0.5, random_state=0)



	scores = ['precision', 'recall']

	for score in scores:
	    print("# Tuning hyper-parameters for %s" % score)
	    print()

	    clf = GridSearchCV(model, tuned_parameters, cv=5,
	                       scoring='%s_weighted' % score)
	    clf.fit(X_train, y_train)

	    print("Best parameters set found on development set:")
	    print()
	    print(clf.best_params_)
	    print()
	    print("Grid scores on development set:")
	    print()
	    for params, mean_score, scores in clf.grid_scores_:
	        print("%0.3f (+/-%0.03f) for %r"
	              % (mean_score, scores.std() * 2, params))
	    print()

	    print("Detailed classification report:")
	    print()
	    print("The model is trained on the full development set.")
	    print("The scores are computed on the full evaluation set.")
	    print()
	    y_true, y_pred = y_test, clf.predict(X_test)
	    print(classification_report(y_true, y_pred))
	    print()

def make_dtopo():
    '''
    Make geoclaw dtopo file
    '''
    from numpy import genfromtxt,zeros
    
    #Run params
    f='/Users/dmelgarm/Research/Slip_Inv/tohoku_tsunami/'
    stafile='tohoku.sta'
    dlon=0.033333
    dlat=0.033333
    dt=5
    stat_or_dyn='s'
    
    #Get station list
    
    sta=genfromtxt(f+'data/station_info/'+stafile,usecols=0,dtype='S4')
    s=genfromtxt(f+'data/station_info/'+stafile,usecols=[1,2])
    lon=s[:,0]
    lat=s[:,1]
    if stat_or_dyn.lower()=='s':
        n=zeros(len(sta))
        e=n.copy()
        u=n.copy()
        for ksta in range(len(sta)):
            print ksta
            neu=genfromtxt(f+'output/forward_models/'+str(sta[ksta])+'.static.neu')
            n[ksta]=neu[0]
            e[ksta]=neu[1]
            u[ksta]=neu[2]
            print neu[2]

def wide_dataset_large():
  print("Reading in Arcene training data for binomial modeling.")
  trainDataResponse = np.genfromtxt(pyunit_utils.locate("smalldata/arcene/arcene_train_labels.labels"), delimiter=' ')
  trainDataResponse = np.where(trainDataResponse == -1, 0, 1)
  trainDataFeatures = np.genfromtxt(pyunit_utils.locate("smalldata/arcene/arcene_train.data"), delimiter=' ')
  xtrain = np.transpose(trainDataFeatures).tolist()
  ytrain = trainDataResponse.tolist()
  trainData = h2o.H2OFrame.fromPython([ytrain]+xtrain)

  trainData[0] = trainData[0].asfactor()

  print("Run model on 3250 columns of Arcene with strong rules off.")
  model = H2OGeneralizedLinearEstimator(family="binomial", lambda_search=False, alpha=1)
  model.train(x=range(1,3250), y=0, training_frame=trainData)

  print("Test model on validation set.")
  validDataResponse = np.genfromtxt(pyunit_utils.locate("smalldata/arcene/arcene_valid_labels.labels"), delimiter=' ')
  validDataResponse = np.where(validDataResponse == -1, 0, 1)
  validDataFeatures = np.genfromtxt(pyunit_utils.locate("smalldata/arcene/arcene_valid.data"), delimiter=' ')
  xvalid = np.transpose(validDataFeatures).tolist()
  yvalid = validDataResponse.tolist()
  validData = h2o.H2OFrame.fromPython([yvalid]+xvalid)
  prediction = model.predict(validData)

  print("Check performance of predictions.")
  performance = model.model_performance(validData)

  print("Check that prediction AUC better than guessing (0.5).")
  assert performance.auc() > 0.5, "predictions should be better then pure chance"

def read(input_file="POSITIONS.OUT"):
  """ Reads a geometry """
  m = np.genfromtxt(input_file).transpose()
  g = geometry() # cretae geometry
  g.dimensionality = 0
  g.x = m[0]
  g.y = m[1]
  g.x = g.x - sum(g.x)/len(g.x) # normalize
  g.y = g.y - sum(g.y)/len(g.y) # normalize
  g.z = m[2]
  g.xyz2r() # create r coordinates
  try:   lat = np.genfromtxt("LATTICE.OUT")   # read lattice
  except: lat = None
  try: # two dimensional
    g.a1 = np.array([lat[0,0],lat[0,1],0.0])
    g.a2 = np.array([lat[1,0],lat[1,1],0.0])
    g.dimensionality=2
    return g
  except: pass
  try:
    g.celldis = lat
    g.dimensionality = 1
    return g
  except: pass
  g.dimensionality = 0
  return g

 def test_dtype_with_object(self):
     "Test using an explicit dtype with an object"
     from datetime import date
     import time
     data = """
     1; 2001-01-01
     2; 2002-01-31
     """
     ndtype = [('idx', int), ('code', np.object)]
     func = lambda s: strptime(s.strip(), "%Y-%m-%d")
     converters = {1: func}
     test = np.genfromtxt(StringIO.StringIO(data), delimiter=";", dtype=ndtype,
                          converters=converters)
     control = np.array([(1, datetime(2001,1,1)), (2, datetime(2002,1,31))],
                        dtype=ndtype)
     assert_equal(test, control)
     #
     ndtype = [('nest', [('idx', int), ('code', np.object)])]
     try:
         test = np.genfromtxt(StringIO.StringIO(data), delimiter=";",
                              dtype=ndtype, converters=converters)
     except NotImplementedError:
         pass
     else:
         errmsg = "Nested dtype involving objects should be supported."
         raise AssertionError(errmsg)

def plotme(typeid,num,h):
	yMax           = '6'

	cuibmFolder    = '/scratch/src/cuIBM'
	caseFolder     = cuibmFolder + '/validation/error/cylinder/'+typeid+num
	validationData = cuibmFolder + '/validation-data/cylinderRe40-KL95.txt'

	print caseFolder+'/forces'
	my_data = genfromtxt(caseFolder+'/forces',dtype=float,delimiter='\t')
	time = [my_data[i][0] for i in xrange(1,len(my_data))]
	force = [my_data[i][1]*2 for i in xrange(1,len(my_data))]

	validation_data = genfromtxt(validationData, dtype=float, delimiter='\t')
	validation_time=[validation_data[i][0]*0.5 for i in xrange(1,len(validation_data))]
	validation_force=[validation_data[i][1] for i in xrange(1,len(validation_data))]

	plt.plot(validation_time,validation_force, 'o', color = 'red', markersize = 8, label = 'Koumoutsakos and Leonard, 1995')
	plt.plot(time,force, '-', color='blue', linewidth=2, label='Present Work')
	plt.title('Flow over an impulsively started cylinder at Reynolds number 40')
	plt.legend(loc='upper right', numpoints=1, fancybox=True)
	plt.xlabel('Non-dimensional time')
	plt.ylabel('Drag Coefficient')
	plt.xlim([0,3])
	plt.ylim([0,int(yMax)])
	plt.savefig('/scratch/src/cuIBM/validation/error/cylinder/'+typeid+h+'.pdf')
	plt.clf()

def co():
        import numpy as np
        import os
        home = os.path.expanduser('~')
        band = raw_input('Select the band:')
        if band == 'pacs':
                upper, lower = 200, 54
        if band == 'spire':
                upper, lower = 671, 200
        level = np.genfromtxt(home+'/data/co_level.txt', dtype='str')
        ref = np.genfromtxt(home+'/data/co_ref.txt','str')
        for i in range(0,len(level[0:])):
                for j in range(0, len(ref[0:])):
                        if ref[j,1] == level[i,0]:
                                ref[j,0] = level[i,2]
                                ref[j,1] = level[i,3]
                        if ref[j,2] == level[i,0]:
                                ref[j,2] = level[i,3]
        c = 2.998e8
        ref[:,4] = c/ref[:,4].astype(float)/1e9*1e6
        ref = ref[np.argsort(ref[:,4].astype(float))]
        ref_sort = ref
        dummy = np.copy(ref[:,0])
        ref_sort[:,0],ref_sort[:,1],ref_sort[:,2],ref_sort[:,3],ref_sort[:,4] = ref[:,1],ref[:,2],ref[:,4],ref[:,3],ref[:,5]
        ref_sort[:,5] = dummy
        ind = np.where((ref_sort[:,2].astype(float) >= lower) & (ref_sort[:,2].astype(float) <= upper))
        slt_trans = ref_sort[ind,:]
        print slt_trans
        print len(slt_trans[0,:,0])
        foo = open(home+'/data/co_ref_sort.txt','w')
        np.savetxt(foo,ref_sort, fmt='%s')
        foo.close()

	def load(self):
		# load data
		values = []
		if verbose: print()
		if verbose: print("visualization: loading chains ...")
		f = "prob-chain0.dump"
		if not os.path.exists(f):
			raise Exception("visualization: chains not available yet.")
		try:
			# I think the first column is the probabilities, the second is without prior
			probabilities = numpy.genfromtxt(f, skip_footer=1, dtype='f')[:,0]
		except Exception as e:
			raise Exception("visualization: chains couldn't be loaded; perhaps no data yet: " + str(e))
		for p in self.params:
			f = "%s-chain-0.prob.dump" % p['name']
			if verbose: print("	loading chain %s" % f)
			if not os.path.exists(f):
				raise Exception("visualization: chains not available yet.")
			try:
				v = numpy.genfromtxt(f, skip_footer=1, dtype='f')
			except Exception as e:
				raise Exception("visualization: chains couldn't be loaded; perhaps no data yet: " + str(e))
			values.append(v)
		nvalues = min(map(len, values))
		if verbose: print("visualization: loading chains finished; %d values" % nvalues)
		self.values = [v[:nvalues][-self.nlast::nevery] for v in values]
		self.probabilities = probabilities[:nvalues][-self.nlast::nevery]

def read_gf_from_txt(block_txtfiles, block_name):
    """
    Read a GfReFreq from text files with the format (w, Re(G), Im(G)) for a single block.
    
    Notes
    -----
    A BlockGf must be constructed from multiple GfReFreq objects if desired.
    The mesh must be the same for all files read in.
    Non-uniform meshes are not supported.

    Parameters
    ----------
    block_txtfiles: Rank 2 square np.array(str) or list[list[str]]
        The text files containing the GF data that need to read for the block.
        e.g. [['up_eg1.dat']] for a one-dimensional block and
             [['up_eg1_1.dat','up_eg2_1.dat'],
              ['up_eg1_2.dat','up_eg2_2.dat']] for a 2x2 block.
    block_name: str
        Name of the block.

    Returns
    -------
    g: GfReFreq
        The real frequency Green's function read in.
    """
    block_txtfiles = np.array(block_txtfiles) # Must be an array to use certain functions
    N1,N2 = block_txtfiles.shape
    mesh = np.genfromtxt(block_txtfiles[0,0],usecols=[0]) # Mesh needs to be the same for all blocks
    g = GfReFreq(indices=range(N1),window=(np.min(mesh),np.max(mesh)),n_points=len(mesh),name=block_name)
    for i,j in product(range(N1),range(N2)):
        data = np.genfromtxt(block_txtfiles[i,j],usecols=[1,2])
        g.data[:,i,j] = data[:,0] + 1j*data[:,1]
    return g

def load_hop(s, hop=hop_script_path): 
    """
    Loads the hop catalog for the given RAMSES snapshot. If the
    catalog doesn't exist, it tries to run hop to create one via the
    'script_hop.sh' script found in the RAMSES distribution. The hop
    output should be in a 'hop' directory in the base directory of the
    simulation.

    **Input**:
    
    *s* : loaded RAMSES snapshot

    **Optional Keywords**:

    *hop* : path to `script_hop.sh`

    """

    if s.filename[-1] == '/' : 
        name = s.filename[-6:-1] 
        filename = s.filename[:-13]+'hop/grp%s.pos'%name
    else: 
        name = s.filename[-5:]
        filename = s.filename[:-12]+'hop/grp%s.pos'%name
    
    try : 
        data = np.genfromtxt(filename,unpack=True)
    except IOError : 
        import os
        dir = s.filename[:-12] if len(s.filename[:-12]) else './'
        
        os.system('cd %s;/home/itp/roskar/ramses/galaxy_formation/script_hop.sh %d;cd ..'%(dir,int(name)))
        data = np.genfromtxt(filename,unpack=True)

    return data

def main():
    print "Solve small matrix..."
    R = array([0, 0, 1, 1, 1, 2, 2])
    C = array([0, 1, 0, 1, 2, 1, 2])
    V = array([4.0, -1.0, -1.0,  4.0, -1.0, -1.0, 4.0])
    b = array([3.0, 2.0, 3.0])
    A = coo_matrix((V, (R, C)), shape=(3, 3))
    # convert to csr format for efficiency
    x = spsolve(A.tocsr(), b)
    print "x = ", x

    print "Solve psd matrix..."
    # skip the first row (n, nnz)
    A = numpy.genfromtxt('../data/psd.txt', skiprows=1)
    b = numpy.genfromtxt('../data/b.txt')
    coo = coo_matrix((A[:, 2], (A[:, 0], A[:, 1])))
    x = spsolve(coo.tocsr(), b)
    print 'x = ', x

    print "Solve big matrix..."
    A = numpy.genfromtxt('../data/mat_helmholtz.txt', skiprows=1)
    coo = coo_matrix((A[:, 2], (A[:, 0], A[:, 1])))
    n = coo.shape[0]
    b = numpy.ones(n)
    x = spsolve(coo.tocsr(), b)
    print 'x = ', x

def main(options):

    freq_range=range(options["from"], options["to"]+1)
    
    gt_file=gzip.open(options["gt_file"], "r")
    pos_file=gzip.open(options["pos_file"], "r")
    out_haps=gzip.open(options["out_root"]+"/haps.gz", "w")
    out_haps_fn=[gzip.open(options["out_root"]+"/haps.f"+str(x)+".gz", "w") for x in freq_range]

    out_samples=open(options["out_root"]+"/samples.txt", "w")

    gt=np.genfromtxt(gt_file, delimiter=1)
    pos=np.genfromtxt(pos_file)
    pos=np.floor(pos*options["chr_len"]).astype(int)
    
    gt=gt.transpose().astype(int)
    # This is because on some platforms the np.genfromtxt tries to import the line endings...     
    gt=gt[range(len(pos)),]               
    
    (nsnp,nind)=gt.shape

    ACs=np.sum(gt, axis=1)
    MACs=np.minimum(ACs, nind-ACs)
    for i in range(nsnp):
        out_haps.write(("\t".join(["%d"]*(nind+1))+"\n")%((pos[i],)+tuple(gt[i,])))
        if MACs[i]>=options["from"] and MACs[i]<= options["to"]:
            idx=MACs[i]-options["from"]
            out_haps_fn[idx].write(("\t".join(["%d"]*(nind+1))+"\n")%((pos[i],)+tuple(gt[i,])))

    for i in range(int(nind/2)):
        out_samples.write("SIM%d\n"%(i+1,))
            
    for fil in [gt_file, pos_file, out_haps]+out_haps_fn:
        fil.close()

def main():

    trainset = np.genfromtxt(open('train.csv','r'), delimiter=',')[1:]
    X = np.array([x[1:8] for x in trainset])
    y = np.array([x[8] for x in trainset])
    #print X,y
    import math
    for i, x in enumerate(X):
        for j, xx in enumerate(x):
            if(math.isnan(xx)):
                X[i][j] = 26.6
   
    
    testset = np.genfromtxt(open('test.csv','r'), delimiter = ',')[1:]

    test = np.array([x[1:8] for x in testset])
    for i, x in enumerate(test):
        for j, xx in enumerate(x):
            if(math.isnan(xx)):
                test[i][j] = 26.6
   

    X, test = decomposition_pca(X, test)

    bdt = AdaBoostClassifier(base_estimator = KNeighborsClassifier(n_neighbors=20, algorithm = 'auto'), algorithm="SAMME", n_estimators = 200)
    bdt.fit(X, y)
    


    print 'PassengerId,Survived'
    for i, t in enumerate(test):
        print '%d,%d' % (i + 892, int(bdt.predict(t)[0]))