Python numpy.column_stack函数代码示例

def center_galaxy(image, original_image, centroid=None):
    if centroid is None:
        # apply median filter to find the galaxy centroid
        centroid = median_filter(image, size=10).argmax()
        centroid = np.unravel_index(centroid, image.shape)
    # recenter image
    roffset = centroid[0] - image.shape[0] / 2
    if roffset < 0:
        # add more white space to top of image
        extra_rows = image.shape[0] - 2 * centroid[0]
        image = np.vstack((np.zeros((extra_rows, image.shape[1])), image))
    elif roffset > 0:
        # add more white space to bottom of image
        extra_rows = 2 * centroid[0] - image.shape[0]
        image = np.vstack((image, np.zeros((extra_rows, image.shape[1]))))
    coffset = centroid[1] - image.shape[1] / 2
    if coffset > 0:
        # add more white space to right of image
        extra_columns = 2 * centroid[1] - image.shape[1]
        image = np.column_stack((image, np.zeros((image.shape[0], extra_columns))))
    elif coffset < 0:
        # add more white space to left of image
        extra_columns = image.shape[1] - 2 * centroid[1]
        image = np.column_stack((np.zeros((image.shape[0], extra_columns)), image))

    return image, centroid

    def expected(self, window_length, k, closes):
        """Compute the expected data (without adjustments) for the given
        window, k, and closes array.

        This uses talib.BBANDS to generate the expected data.
        """
        lower_cols = []
        middle_cols = []
        upper_cols = []
        for n in range(self.nassets):
            close_col = closes[:, n]
            if np.isnan(close_col).all():
                # ta-lib doesn't deal well with all nans.
                upper, middle, lower = [np.full(self.ndays, np.nan)] * 3
            else:
                upper, middle, lower = talib.BBANDS(
                    close_col,
                    window_length,
                    k,
                    k,
                )

            upper_cols.append(upper)
            middle_cols.append(middle)
            lower_cols.append(lower)

        # Stack all of our uppers, middles, lowers into three 2d arrays
        # whose columns are the sids. After that, slice off only the
        # rows we care about.
        where = np.s_[window_length - 1:]
        uppers = np.column_stack(upper_cols)[where]
        middles = np.column_stack(middle_cols)[where]
        lowers = np.column_stack(lower_cols)[where]
        return uppers, middles, lowers

 def writeOut(self, outname='',include_state=False):
     """
     Function writes out to file... only doing primitive variables for now.
     rho, u, p, maybe tack on e and h ....
     
     This needs to be nice, but for debugging purposes, only doing to 
     write out to ascii for now... just ot be quick and easy to focus on
     coding rather than fancy outputting.....
     """
     x   = self.grid.center()
     rho = self.getPrimitive('Density')
     u   = self.getPrimitive('Velocity')
     P   = self.getPrimitive('Pressure')
     
     if include_state:
         data = np.column_stack((x,rho,u,P,self.q[0],self.q[1],self.q[2]))
         header = '# x Density Velocity Pressure q0 q1 q2'
         
     else:
         data = np.column_stack((x,rho,u,P))
         header = '# x Density Velocity Pressure'
 
     
    # np.savetxt(outname + '_simstate_%3.3f_.txt'%(self.t), data,
     np.savetxt(outname + '_simstate.txt', data, header=header, fmt='%1.4e')

def combineTechnicalIndicators(ticker):
    dates, prices = getDateAndPrice(ticker)
    np_dates = np.chararray(len(dates), itemsize=len(dates[0]))
    for day in range(len(dates)):
        np_dates[day] = dates[day]

    percentChange = calcDailyPercentChange(prices)
    vol = calc30DayVol(percentChange)
    RSI = calcRSI(prices)


    if ticker == PREDICTED:
        np_prices = np.array(prices)
        label = np.zeros_like(np_prices)

    #create label for price of SPY
        for x in range(len(np_prices[:-lagTime])):
            print x
            if np_prices[x] < np_prices[x + lagTime]:
                label[x] = 1
            else:
                label[x] = 0
        features = np.column_stack((np_dates,  percentChange, vol, RSI, label))
        headers = ['date', 'return_'+ ticker, 'vol_'+ ticker, 'RSI_'+ ticker, 'label']
    else:
        features = np.column_stack((np_dates, percentChange, vol, RSI))
        headers = ['date', 'return_'+ ticker, 'vol_'+ ticker, 'RSI_'+ ticker]

    df_features = pd.DataFrame(features, columns=headers)
    print df_features[25:35]
    return df_features

    def _recalc(self):
        self.clear()
        assert len(self.artists) == 0
        if self.layout is None:
            return

        # layout[0] is [x0, x0, x[parent0], nan, ...]
        # layout[1] is [y0, y[parent0], y[parent0], nan, ...]
        ids = 3 * np.arange(self.layer.data.size)

        try:
            if isinstance(self.layer, Subset):
                ids = ids[self.layer.to_mask()]

            x, y = self.layout
            blank = np.zeros(ids.size) * np.nan
            x = np.column_stack([x[ids], x[ids + 1],
                                 x[ids + 2], blank]).ravel()
            y = np.column_stack([y[ids], y[ids + 1],
                                 y[ids + 2], blank]).ravel()
        except IncompatibleAttribute as exc:
            self.disable_invalid_attributes(*exc.args)
            return False

        self.artists = self._axes.plot(x, y, '--')
        return True

def main():
    
    t0 = time.time() # start time

    # output files path
    TRAINX_OUTPUT = "../../New_Features/train_x_processed.csv"
    TEST_X_OUTPUT = "../../New_Features/test__x_processed.csv"
    # input files path
    TRAIN_FILE_X1 = "../../ML_final_project/sample_train_x.csv"
    TRAIN_FILE_X2 = "../../ML_final_project/log_train.csv"
    TEST__FILE_X1 = "../../ML_final_project/sample_test_x.csv"
    TEST__FILE_X2 = "../../ML_final_project/log_test.csv"
    # load files
    TRAIN_DATA_X1 = np.loadtxt(TRAIN_FILE_X1, delimiter=',', skiprows=1, usecols=(range(1, 18)))
    TEST__DATA_X1 = np.loadtxt(TEST__FILE_X1, delimiter=',', skiprows=1, usecols=(range(1, 18)))
    TRAIN_DATA_X2 = logFileTimeCount(np.loadtxt(TRAIN_FILE_X2, delimiter=',', skiprows=1, dtype=object))
    TEST__DATA_X2 = logFileTimeCount(np.loadtxt(TEST__FILE_X2, delimiter=',', skiprows=1, dtype=object))
    # combine files
    TRAIN_DATA_X0 = np.column_stack((TRAIN_DATA_X1, TRAIN_DATA_X2))
    TEST__DATA_X0 = np.column_stack((TEST__DATA_X1, TEST__DATA_X2))
    # data preprocessing
    scaler = StandardScaler()
    TRAIN_DATA_X = scaler.fit_transform(TRAIN_DATA_X0)
    TEST__DATA_X = scaler.transform(TEST__DATA_X0)
    # output processed files
    outputXFile(TRAINX_OUTPUT, TRAIN_DATA_X)
    outputXFile(TEST_X_OUTPUT, TEST__DATA_X)

    t1 = time.time() # end time
    print "...This task costs " + str(t1 - t0) + " second."

def wide_dataset_large():
    
    

    print("Reading in Arcene training data for binomial modeling.")
    trainDataResponse = np.genfromtxt(tests.locate("smalldata/arcene/arcene_train_labels.labels"), delimiter=' ')
    trainDataResponse = np.where(trainDataResponse == -1, 0, 1)
    trainDataFeatures = np.genfromtxt(tests.locate("smalldata/arcene/arcene_train.data"), delimiter=' ')
    trainData = h2o.H2OFrame(np.column_stack((trainDataResponse, trainDataFeatures)).tolist())

    print("Run model on 3250 columns of Arcene with strong rules off.")
    model = h2o.glm(x=trainData[1:3250], y=trainData[0].asfactor(), family="binomial", lambda_search=False, alpha=[1])

    print("Test model on validation set.")
    validDataResponse = np.genfromtxt(tests.locate("smalldata/arcene/arcene_valid_labels.labels"), delimiter=' ')
    validDataResponse = np.where(validDataResponse == -1, 0, 1)
    validDataFeatures = np.genfromtxt(tests.locate("smalldata/arcene/arcene_valid.data"), delimiter=' ')
    validData = h2o.H2OFrame(np.column_stack((validDataResponse, validDataFeatures)).tolist())
    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 get_peaks(data,threshold,gap_threshold):
	# apply threshold, result is a boolean array
	abovethr = np.where( data >= threshold )[0]
	belowthr = np.where( data <  threshold )[0]
	
	#### extract peaks
	# first, find gaps in "above"/"below" labels (differences bigger than 1)
	b1 = np.where( np.diff(abovethr)>1 )[0]
	b2 = np.where( np.diff(belowthr)>1 )[0]
	
	#~ pdb.set_trace()
	
	# second, concatenate peak start and stop indices
	# note the +1 which fixes the diff-offset
	if belowthr[b2][0] > abovethr[b1][0]:
		b1 = b1[1:]
	if len(belowthr[b2]) == len(abovethr[b1]):
		indices = np.column_stack(( belowthr[b2],abovethr[b1])) + 1
	else:
		indices = np.column_stack(( belowthr[b2], 
					np.concatenate((abovethr[b1],[abovethr[-1]])) )) + 1
	
	# third, merge peaks if they are very close to eachother
	indices_gaps = indices.flatten()[1:-1].reshape((-1,2))
	gaps_to_preserve = np.where(np.diff(indices_gaps).flatten() > gap_threshold )[0]

	indices_filtered = np.concatenate(( [indices[0,0]], 
											indices_gaps[gaps_to_preserve].flatten(), 
											[indices[-1,1]] )).reshape((-1,2))
											
	return indices_filtered

	def write_parameters_outputvalues(self, P):		


		Mstar, SFR_opt, _ = model.stellar_info_array(self.chain.flatchain_sorted, self.data, self.out['realizations2int'])
		column_names = np.transpose(np.array(["P025","P16","P50","P84","P975"], dtype='|S3'))
		chain_pars = np.column_stack((self.chain.flatchain_sorted, Mstar, SFR_opt))		
											# np.mean(chain_pars, axis[0]),
											# np.std(chain_pars, axis[0]),
		if self.out['calc_intlum']:			


			SFR_IR = model.sfr_IR(self.int_lums[0]) #check that ['intlum_names'][0] is always L_IR(8-100)
			
			chain_others =np.column_stack((self.int_lums.T, SFR_IR))
			outputvalues = np.column_stack((np.transpose(map(lambda v: (v[0],v[1],v[2],v[3],v[4]), zip(*np.percentile(chain_pars, [2.5,16, 50, 84,97.5], axis=0)))),
											np.transpose(map(lambda v: (v[0],v[1],v[2],v[3],v[4]), zip(*np.percentile(chain_others, [2.5,16, 50, 84,97.5], axis=0))))											)) 


	
			outputvalues_header= ' '.join([ i for i in np.hstack((P.names, 'Mstar', 'SFR_opt', self.out['intlum_names'], 'SFR_IR',))] )

		else:
			outputvalues = np.column_stack((map(lambda v: (v[1], v[2]-v[1], v[1]-v[0]), zip(*np.percentile(chain_pars, [16, 50, 84],  axis=0))))) 
			outputvalues_header=' '.join( [ i for i in P.names] )
		return outputvalues, outputvalues_header

    def residuals(self, src, dst):
        """Compute the Sampson distance.

        The Sampson distance is the first approximation to the geometric error.

        Parameters
        ----------
        src : (N, 2) array
            Source coordinates.
        dst : (N, 2) array
            Destination coordinates.

        Returns
        -------
        residuals : (N, ) array
            Sampson distance.

        """
        src_homogeneous = np.column_stack([src, np.ones(src.shape[0])])
        dst_homogeneous = np.column_stack([dst, np.ones(dst.shape[0])])

        F_src = self.params @ src_homogeneous.T
        Ft_dst = self.params.T @ dst_homogeneous.T

        dst_F_src = np.sum(dst_homogeneous * F_src.T, axis=1)

        return np.abs(dst_F_src) / np.sqrt(F_src[0] ** 2 + F_src[1] ** 2
                                           + Ft_dst[0] ** 2 + Ft_dst[1] ** 2)

def process_recarray(data, endog_idx=0, exog_idx=None, stack=True, dtype=None):
    names = list(data.dtype.names)

    if isinstance(endog_idx, (int, long)):
        endog = array(data[names[endog_idx]], dtype=dtype)
        endog_name = names[endog_idx]
        endog_idx = [endog_idx]
    else:
        endog_name = [names[i] for i in endog_idx]

        if stack:
            endog = np.column_stack(data[field] for field in endog_name)
        else:
            endog = data[endog_name]

    if exog_idx is None:
        exog_name = [names[i] for i in range(len(names))
                     if i not in endog_idx]
    else:
        exog_name = [names[i] for i in exog_idx]

    if stack:
        exog = np.column_stack(data[field] for field in exog_name)
    else:
        exog = recarray_select(data, exog_name)

    if dtype:
        endog = endog.astype(dtype)
        exog = exog.astype(dtype)

    dataset = Dataset(data=data, names=names, endog=endog, exog=exog,
                      endog_name=endog_name, exog_name=exog_name)

    return dataset

def create_colored_3d_points_from_matrices(matrices, index_list):
    points3d_l = []
    colors_ll = []
    mat_l = []
    X_MULTIPLIER = 1/15.

    for i, mat in enumerate(matrices):
        X, Y = np.meshgrid(range(mat.shape[0]), range(mat.shape[1]))
        x_size = mat.shape[0] * X_MULTIPLIER
        X = np.matrix(X * X_MULTIPLIER) + x_size * i + (i * x_size / 3.)
        #Y = (np.matrix(np.ones((mat.shape[0], 1))) * times_m).T
        Y = (np.matrix(np.ones((mat.shape[0], 1))) * index_list[i]).T
        Z = np.matrix(np.zeros(mat.shape)).T

        points = np.row_stack((X.reshape(1, X.shape[0] * X.shape[1]),
                               Y.reshape(1, Y.shape[0] * Y.shape[1]),
                               Z.reshape(1, Z.shape[0] * Z.shape[1])))
        colors = np.matrix(np.zeros((4, mat.shape[0]*mat.shape[1])))
        mat_l.append(mat.T.reshape((1,mat.shape[1] * mat.shape[0])))
        points3d_l.append(points)
        colors_ll.append(colors)

    all_mats = np.column_stack(mat_l)
    all_points = np.column_stack(points3d_l)
    all_colors = np.column_stack(colors_ll)
    return all_mats, all_points, all_colors

 def listener_func(msg):
     amat = vectorize_func(msg)
     t    = np.matrix([msg.header.stamp.to_time()])
     got_lock = False
     if self.channels[topic][0] == None:
         self.channels[topic] = [amat, t, threading.RLock()]
     else:
         lock = self.channels[topic][2]
         lock.acquire()
         got_lock = True
         #print 'l locked'
         new_record = [np.column_stack((self.channels[topic][0], amat)), 
                       np.column_stack((self.channels[topic][1], t)),
                       lock]
         #print 'got something', new_record[0].shape
         self.channels[topic] = new_record
         #print 'after appending', self.channels[topic][0].shape, self.channels[topic][1].shape
         #print 'time recorded is', t[0,0]
         #print 'shape', self.channels[topic][0].shape
         #lock.release()
         #print 'l released'
                                 
     lock = self.channels[topic][2]
     if not got_lock:
         lock.acquire()
     #lock.acquire()
     #select only messages n-seconds ago
     n_seconds_ago = t[0,0] - buffer_length_secs
     records_in_range = (np.where(self.channels[topic][1] >= n_seconds_ago)[1]).A1
     #print records_in_range, self.channels[topic][0].shape
     self.channels[topic][0] = self.channels[topic][0][:, records_in_range]
     self.channels[topic][1] = self.channels[topic][1][:, records_in_range]
     #print 'after shortening', self.channels[topic][0].shape, self.channels[topic][1].shape
     #print 'shape after selection...', self.channels[topic][0].shape
     lock.release()

def main(): #clustering and write output
    if len(pep_array)>1:
        matrix=[]
        for i in range(0,len(pep_array)):
            matrix.append(pep_array[i][4].replace('\"',"").split(','))

        dataMatrix=numpy.array(matrix,dtype=float)
        d = sch.distance.pdist(dataMatrix,metric)# vector of pairwise distances
        if metric=="correlation":
            D = numpy.clip(d,0,2) #when using correlation, all values in distance matrix should be in range[0,2]
        else:
            D=d
        try:
            cutoff=float(t)
        except ValueError:
            print "please provide a numeric value for --t"; sys.exit()
        L = sch.linkage(D, method,metric)
        ind = sch.fcluster(L,cutoff,'distance')#distance is dissmilarity(1-correlation)
        p=numpy.array(pep_array)
        p=numpy.column_stack([p,ind])
        formatoutput(p)
    else:
        p=numpy.array(pep_array)
        p=numpy.column_stack([p,[0]])
        formatoutput(p)

def main():
	LAMB = 10.0
	SPLIT = 40

	t0 = time.time()

	TRAIN19_FILE = 'hw4_train.dat'
	TRAIN19_DATA = np.loadtxt(TRAIN19_FILE, dtype=np.float)
	xTrain19 = np.column_stack((np.ones(TRAIN19_DATA.shape[0]), TRAIN19_DATA[:, 0:(TRAIN19_DATA.shape[1] - 1)]))
	yTrain19 = TRAIN19_DATA[:, (TRAIN19_DATA.shape[1] - 1)]

	TEST19_FILE = 'hw4_test.dat'
	TEST19_DATA = np.loadtxt(TEST19_FILE, dtype=np.float)
	xTest19 = np.column_stack((np.ones(TEST19_DATA.shape[0]), TEST19_DATA[:, 0:(TEST19_DATA.shape[1] - 1)]))
	yTest19 = TEST19_DATA[:, (TEST19_DATA.shape[1] - 1)]

	lambPowList = []
	eCvList     = []
	for lambPower in range(-10, 3):
		eCv = vFoldErr(xTrain19, yTrain19, math.pow(LAMB, lambPower), SPLIT)
		lambPowList.append(lambPower)
		eCvList.append(eCv)
	eCvList  = np.array(eCvList)
	minIndex = np.where(eCvList == eCvList.min())
	index    = minIndex[0].max()
	plotHist(lambPowList, eCvList, "log(lambda)", "Ecv", "Q19", 1, False)

	t1 = time.time()
	print '========================================================='
	print 'Question 19: log(lambda) is', lambPowList[index], 'Ecv is', eCvList[index]
	print '---------------------------------------------------------'
	print 'Q19 costs', t1 - t0, 'seconds'
	print '========================================================='