Для расстояния вам нужно изменить формулу на
def getDistance(x, y, x_i, y_i):
return sqrt((x_i -x)^2 + (y_i - y)^2)
с (x, y) как точкой данных, а (x_i, y_i) с точкой.
Попробуйте использовать NumPy для векторизации. Явное циклическое прохождение точек данных, скорее всего, будет менее эффективным, однако, в зависимости от вашего варианта использования, оно может быть достаточно быстрым. (Если вам нужно запустить его на регулярной основе, я думаю, что векторизация легко превзойдет явный путь). Это может выглядеть примерно так:
import numpy as np # Universal abbreviation for the module
datapoints = np.random.rand(3,2) # Returns a vector with randomized entries of size 3x2 (Imagine it as 3 sets of x- and y-values
contour1 = np.random.rand(1000, 2) # Other than the size (which is 1000x2) no different than datapoints
contour2 = np.random.rand(1000, 2)
contour3 = np.random.rand(1000, 2)
def squareDistanceUnvectorized(datapoint, contour):
retVal = 0.
print("Using datapoint with values x:{}, y:{}".format(datapoint[0], datapoint[1]))
lengthOfContour = np.size(contour, 0) # This gets you the number of lines in the vector
for pointID in range(lengthOfContour):
squaredXDiff = np.square(contour[pointID,0] - datapoint[0])
squaredYDiff = np.square(contour[pointID,1] - datapoint[1])
retVal += np.sqrt(squaredXDiff + squaredYDiff)
retVal = retVal / lengthOfContour # As we want the average, we are dividing the sum by the element count
return retVal
if __name__ == "__main__":
noOfDatapoints = np.size(datapoints,0)
contID = 0
for currentDPID in range(noOfDatapoints):
dist1 = squareDistanceUnvectorized(datapoints[currentDPID,:], contour1)
dist2 = squareDistanceUnvectorized(datapoints[currentDPID,:], contour2)
dist3 = squareDistanceUnvectorized(datapoints[currentDPID,:], contour3)
if dist1 > dist2 and dist1 > dist3:
contID = 1
elif dist2 > dist1 and dist2 > dist3:
contID = 2
elif dist3 > dist1 and dist3 > dist2:
contID = 3
else:
contID = 0
if contID == 0:
print("Datapoint {} is inbetween two contours".format(currentDPID))
else:
print("Datapoint {} is closest to contour {}".format(currentDPID, contID))
Хорошо, теперь переходим к земле векторов.
Я позволил себе приспособить эту часть к тому, что я считаю вашим набором данных. Попробуйте и дайте мне знать, если это работает.
import numpy as np
import pandas as pd
# Generate 1000 points (2-dim Vector) with random values between 0 and 1. Make them strings afterwards.
# This is the first contour
random2Ddata1 = np.random.rand(1000,2)
listOfX1 = [str(x) for x in random2Ddata1[:,0]]
listOfY1 = [str(y) for y in random2Ddata1[:,1]]
# Do the same for a second contour, except that we de-center this 255 units into the first dimension
random2Ddata2 = np.random.rand(1000,2)+[255,0]
listOfX2 = [str(x) for x in random2Ddata2[:,0]]
listOfY2 = [str(y) for y in random2Ddata2[:,1]]
# After this step, our 'contours' are basically two blobs of datapoints whose centers are approx. 255 units apart.
# Generate a set of 4 datapoints and make them a Pandas-DataFrame
datapoints = {'X': ['0.5', '0', '255.5', '0'], 'Y': ['0.5', '0', '0.5', '-254.5']}
datapoints = pd.DataFrame(datapoints, columns=['X', 'Y'])
# Do the same for the two contours
contour1 = {'Xf': listOfX1, 'Yf': listOfY1}
contour1 = pd.DataFrame(contour1, columns=['Xf', 'Yf'])
contour2 = {'Xf': listOfX2, 'Yf': listOfY2}
contour2 = pd.DataFrame(contour2, columns=['Xf', 'Yf'])
# We do now have 4 datapoints.
# - The first datapoint is basically where we expect the mean of the first contour to be.
# Contour 1 consists of 1000 points with x, y- values between 0 and 1
# - The second datapoint is at the origin. Its distances should be similar to the once of the first datapoint
# - The third datapoint would be the result of shifting the first datapoint 255 units into the positive first dimension
# - The fourth datapoint would be the result of shifting the first datapoint 255 units into the negative second dimension
# Transformation into numpy array
# First the x and y values of the data points
dpArray = ((datapoints.values).T).astype(np.float)
c1Array = ((contour1.values).T).astype(np.float)
c2Array = ((contour2.values).T).astype(np.float)
# This did the following:
# - Transform the datapoints and contours into numpy arrays
# - Transpose them afterwards so that if we want all x values, we can write var[0,:] instead of var[:,0].
# A personal preference, maybe
# - Convert all the values into floats.
# Now, we iterate through the contours. If you have a lot of them, putting them into a list beforehand would do the job
for contourid, contour in enumerate([c1Array, c2Array]):
# Now for the datapoints
for _index, _value in enumerate(dpArray[0,:]):
# The next two lines do vectorization magic.
# First, we square the difference between one dpArray entry and the contour x values.
# You might notice that contour[0,:] returns an 1x1000 vector while dpArray[0,_index] is an 1x1 float value.
# This works because dpArray[0,_index] is broadcasted to fit the size of contour[0,:].
dx = np.square(dpArray[0,_index] - contour[0,:])
# The same happens for dpArray[1,_index] and contour[1,:]
dy = np.square(dpArray[1,_index] - contour[1,:])
# Now, we take (for one datapoint and one contour) the mean value and print it.
# You could write it into an array or do basically anything with it that you can imagine
distance = np.mean(np.sqrt(dx+dy))
print("Mean distance between contour {} and datapoint {}: {}".format(contourid+1, _index+1, distance))
# But you want to be able to call this... so here we go, generating a function out of it!
def getDistanceFromDatapointsToListOfContoursFindBetterName(datapoints, listOfContourDataFrames):
""" Takes a DataFrame with points and a list of different contours to return the average distance for each combination"""
dpArray = ((datapoints.values).T).astype(np.float)
listOfContours = []
for item in listOfContourDataFrames:
listOfContours.append(((item.values).T).astype(np.float))
retVal = np.zeros((np.size(dpArray,1), len(listOfContours)))
for contourid, contour in enumerate(listOfContours):
for _index, _value in enumerate(dpArray[0,:]):
dx = np.square(dpArray[0,_index] - contour[0,:])
dy = np.square(dpArray[1,_index] - contour[1,:])
distance = np.mean(np.sqrt(dx+dy))
print("Mean distance between contour {} and datapoint {}: {}".format(contourid+1, _index+1, distance))
retVal[_index, contourid] = distance
return retVal
# And just to see that it is, indeed, returning the same results, run it once
getDistanceFromDatapointsToListOfContoursFindBetterName(datapoints, [contour1, contour2])