Python 安排我的集群显示

我在三维数组的数据上运行k-means聚类算法，看起来是这样的（从1910年到2000年，每年都有51x200维的数组，这51维是我们的状态），这是1916年的例子，只针对前三行，即3x200）

我每年都会对50X200的阵列单独执行算法

我的问题是

问题1：一年一个地做是一件痛苦的事情，我是否可以在所有的年份里做一次算法，并将其绘制成3D图？ 我想成为第三维度是年份，并为所有数据的集群绘制一个3D图

问题2：每年读取一次所有数据，然后每年单独获取一次结果，因为目前我每年都要拆分数据文本文件，这是一件痛苦的事情

我的代码：

from __future__ import division
from sklearn.cluster import KMeans
from sklearn.metrics import pairwise_distances_argmin_min
import numpy
from numpy.random import *
import numpy as np
import random
from functools import partial
from sklearn.metrics import pairwise_distances_argmin_min
from scipy.spatial.distance import pdist,squareform
import pandas as pd
from functools import partial
from matplotlib import pyplot

def read_from_file(filename):
    with open(filename) as f:
        data = []
        for line in f:
            data.append([float(x) for x in line.split()[1:]])
        return data #returned the data we read.

def main():
    data = read_from_file("Data_Fcopy.txt") # This data is in scope for the initialize function now. :)


    km = KMeans(n_clusters=9,init= 'random').fit(data)
    print km
    centers = km.cluster_centers_
    labels = km.labels_
    n = km.fit_transform(data)
    #print n
    print labels

    numpy.set_printoptions(threshold=numpy.nan)
    #print centers
    numpy.set_printoptions(threshold=numpy.nan)



    paired_data = []
    for x in data:
         closest, ignored = pairwise_distances_argmin_min(x, centers)

         paired_data.append(closest) 
         new_list = [x+1 for x in paired_data] 

    #print paired_data

    S = pd.DataFrame(new_list, columns=['x' 'center'])

    print (S.to_string())

if __name__ == "__main__":



    main() # This is the general (awkward) pattern for main functions in python.

from __future__ import division
from sklearn.cluster import KMeans
from sklearn.metrics import pairwise_distances_argmin_min
import numpy
from numpy.random import *
import numpy as np
import random
from functools import partial
from sklearn.metrics import pairwise_distances_argmin_min
from scipy.spatial.distance import pdist,squareform
import pandas as pd
from functools import partial
from matplotlib import pyplot

def read_from_file(filename):
    with open(filename) as f:
        data = []
        for line in f:
            data.append([float(x) for x in line.split()[1:]])
        return data #returned the data we read.

def main():
    data = read_from_file("Data_Fcopy.txt") # This data is in scope for the initialize function now. :)


    km = KMeans(n_clusters=9,init= 'random').fit(data)
    print km
    centers = km.cluster_centers_
    labels = km.labels_
    n = km.fit_transform(data)
    #print n
    print labels

    numpy.set_printoptions(threshold=numpy.nan)
    #print centers
    numpy.set_printoptions(threshold=numpy.nan)



    paired_data = []
    for x in data:
         closest, ignored = pairwise_distances_argmin_min(x, centers)

         paired_data.append(closest) 
         new_list = [x+1 for x in paired_data] 

    #print paired_data

    S = pd.DataFrame(new_list, columns=['x' 'center'])

    print (S.to_string())

if __name__ == "__main__":



    main() # This is the general (awkward) pattern for main functions in python.