使用sklearn svm中的预测函数的内存错误

Question

我正在训练一个SVM，其中包含一个包含93个要素和61878个训练样例的大数据集。

由于我不想绘制如此大的数据集，我正在提取40个随机样本来训练另一个SVM以使其可视化。 但是我在轮廓绘图函数中的MEMORY ERROR函数中得到clf.predict()。

我的代码：

import numpy as np
from numpy import random
from matplotlib import cm
from sklearn.svm import SVC
import matplotlib.pyplot as plt
import matplotlib.axes as ax
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

#Making the meshgrid
def make_meshgrid(x, y, h=.02):
    x_min, x_max = x.min() - 1, x.max() + 1
    y_min, y_max = y.min() - 1, y.max() + 1
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                         np.arange(y_min, y_max, h),copy=False)
    return xx, yy

#plotting the decision contour
def plot_contours(ax, clf, xx, yy, **params):
    Z = clf.predict(np.c_[xx.ravel(),yy.ravel()])
    Z = Z.reshape(xx.shape)
    out = ax.contourf(xx, yy, Z, **params)
    return out

#extracting data from csv file
f1 = open('train.csv', 'r')
train_data = pd.read_csv(f1)
train_arr = np.array(train_data)
X = np.array(train_arr[:, :-1]) 
y = np.array(train_arr[:, 94])
X_train, X_cv, y_train, y_cv = train_test_split(X, y, test_size=0.3);
print('Printing cross validation data.....')
print(X_cv)
print(y_cv)

clf = SVC(C=1, kernel='poly', gamma='auto')
clf.fit(X_train, y_train)
print('Cross validation score:', clf.score(X_cv, y_cv))
print('Cross validation prediction:')

res = clf.predict(X_cv)
print(res)
print('Cross validation accuracy score:', accuracy_score(y_cv, res, normalize=True))

f2 = open('test.csv', 'r')
test_data = pd.read_csv(f2)
test_arr = np.array(test_data)
print('Test data prediction:')
y_res = clf.predict(test_arr)
print(y_res)

#plotting part of the data by taking random 40 rows to reduce the data set
plot_arr=[]
for i in range(0,39):
    j = random.randint(0,61878)
    plot_arr.append(train_arr[j,:])
parr = np.asarray(plot_arr)
X_plot = parr[:,:-1]
y_plot = parr[:,94]
clf1 = SVC(C=1, kernel='poly', gamma='auto')
clf1.fit(X_plot, y_plot)
X0, X1 = X_plot[:, :], X_plot[:, :]
xx, yy = make_meshgrid(X0,X1)
plot_contours(plt, clf1, xx, yy,cmap=plt.cm.coolwarm, alpha=0.8)
plt.scatter(X0, X1, cmap=plt.cm.coolwarm, s=20, edgecolors='k')
plt.show()
f1.close()
f2.close()  

我得到的错误如下：

Traceback (most recent call last):
File "C:\Program Files\JetBrains\PyCharm Community Edition 2017.2.3\helpers\pydev\pydevd.py", line 1599, in <module>
    globals = debugger.run(setup['file'], None, None, is_module)
File "C:\Program Files\JetBrains\PyCharm Community Edition 2017.2.3\helpers\pydev\pydevd.py", line 1026, in run
    pydev_imports.execfile(file, globals, locals)  # execute the script
File "C:\Program Files\JetBrains\PyCharm Community Edition 2017.2.3\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "C:/Users/Chinnu/PycharmProject/ml/different", line 59, in <module>
    plot_contours(plt, clf, xx, yy,cmap=plt.cm.coolwarm, alpha=0.8)
File "C:/Users/Chinnu/PycharmProject/ml/different", line 38, in plot_contours
    Z = clf.predict(np.c_[xx.ravel(),yy.ravel()])
MemoryError

有谁能告诉我如何纠正这个错误？