0 
    #!/usr/bin/python 

    """ 
        Skeleton code for k-means clustering mini-project.
    """




    import pickle
    import numpy
    import matplotlib.pyplot as plt
    import sys
    sys.path.append("../tools/")
    from feature_format import featureFormat, targetFeatureSplit




    def Draw(pred, features, poi, mark_poi=False, name="image.png", f1_name="feature 1", f2_name="feature 2"):
        """ some plotting code designed to help you visualize your clusters """

        ### plot each cluster with a different color--add more colors for
        ### drawing more than five clusters
        colors = ["b", "c", "k", "m", "g"]
        for ii, pp in enumerate(pred):
            plt.scatter(features[ii][0], features[ii][1], color = colors[pred[ii]])

        ### if you like, place red stars over points that are POIs (just for funsies)
        if mark_poi:
            for ii, pp in enumerate(pred):
                if poi[ii]:
                    plt.scatter(features[ii][0], features[ii][1], color="r", marker="*")
        plt.xlabel(f1_name)
        plt.ylabel(f2_name)
        plt.savefig(name)
        plt.show()



    ### load in the dict of dicts containing all the data on each person in the dataset
    data_dict = pickle.load( open("../final_project/final_project_dataset.pkl", "r") )
    ### there's an outlier--remove it! 
    data_dict.pop("TOTAL", 0)


    ### the input features we want to use 
    ### can be any key in the person-level dictionary (salary, director_fees, etc.) 
    feature_1 = "salary"
    feature_2 = "exercised_stock_options"
    poi  = "poi"
    features_list = [poi, feature_1, feature_2]
    data = featureFormat(data_dict, features_list )
    poi, finance_features = targetFeatureSplit( data )


    ### in the "clustering with 3 features" part of the mini-project,
    ### you'll want to change this line to 
    ### for f1, f2, _ in finance_features:
    ### (as it's currently written, the line below assumes 2 features)
    for f1, f2 in finance_features:
        plt.scatter( f1, f2 )
    plt.show()

    ### cluster here; create predictions of the cluster labels
    ### for the data and store them to a list called pred




    ### rename the "name" parameter when you change the number of features
    ### so that the figure gets saved to a different file
    try:
        Draw(pred, finance_features, poi, mark_poi=False, name="clusters.pdf", f1_name=feature_1, f2_name=feature_2)
    except NameError:
        print "no predictions object named pred found, no clusters to plot"

我收到此错误 EOF 因为它适用于其他人.. 但对我显示一些错误.. 请帮我解决这些问题.. 提前谢谢 我收到此错误 EOF 因为它适用于其他人.. 但对我显示一些错误..请帮我解决这些问题..提前谢谢 我收到此错误EOF 因为它适用于其他人..但对我显示一些错误..请帮我解决这些问题..提前谢谢 我收到此错误EOF 因为它适用于其他人..但对我显示了一些错误..请帮我解决这些问题..提前谢谢

ERROR :
Traceback (most recent call last):
File “C:\Users\LENOVO\Desktop\machine learning udacity\Mini-project 1\Email\k_means\k_means_cluster.py”, line 42, in 
data_dict = pickle.load( open("…/final_project/final_project_dataset.pkl", “r”) )
File “C:\Python27\lib\pickle.py”, line 1384, in load
return Unpickler(file).load()
File “C:\Python27\lib\pickle.py”, line 864, in load
dispatchkey
File “C:\Python27\lib\pickle.py”, line 886, in load_eof
raise EOFError
EOFError
4

1 回答 1

0

很可能您的泡菜文件已损坏。

例如，不完整（截断）。

于 2018-02-02T20:45:18.953 回答