Question

我正在尝试使用scikit-learn在Python中创建股票预测系统。这是我的代码：

import numpy as np
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score
import matplotlib.pyplot as plt
from sklearn import svm,preprocessing
from sklearn.metrics import precision_recall_fscore_support
import pandas as pd
import time
##import statistics


def my_kernel(X, Y):
    """
    We create a custom kernel:

                 (2  0)
    k(X, Y) = X  (    ) Y.T
                 (0  1)
    """
    M = np.array([[2, 0], [0, 1.0]])
    return np.dot(np.dot(X, M), Y.T)



FEATURES =  ['DE Ratio',
             'Trailing P/E',
             'Price/Sales',
             'Price/Book',
             'Profit Margin',
             'Operating Margin',
             'Return on Assets',
             'Return on Equity',
             'Revenue Per Share',
             'Market Cap',
             'Enterprise Value',
             'Forward P/E',
             'PEG Ratio',
             'Enterprise Value/Revenue',
             'Enterprise Value/EBITDA',
             'Revenue',
             'Gross Profit',
             'EBITDA',
             'Net Income Avl to Common ',
             'Diluted EPS',
             'Earnings Growth',
             'Revenue Growth',
             'Total Cash',
             'Total Cash Per Share',
             'Total Debt',
             'Current Ratio',
             'Book Value Per Share',
             'Cash Flow',
             'Beta',
             'Held by Insiders',
             'Held by Institutions',
             'Shares Short (as of',
             'Short Ratio',
             'Short % of Float',
             'Shares Short (prior ']

def Build_Data_Set():
    data_df = pd.DataFrame.from_csv("key_stats.csv")
    data_df = data_df.reindex(np.random.permutation(data_df.index))
    ##print data_df
    X = np.array(data_df[FEATURES].values)

    y = (data_df["Status"]
         .replace("underperform",0)
         .replace("outperform",1)
         .values.tolist())

    X = preprocessing.scale(X)
    X = StandardScaler().fit_transform(X)
    Z0 = np.array(data_df["stock_p_hancge"])
    Z1 = np.array(data_df["sp500_p_change"])
    return X,y,Z0,Z1


def mykernel(X, Y,gamma=None):

    X, Y = check_pairwise_arrays(X, Y)
    if gamma is None:
        gamma = 1.0 / X.shape[1]

    K = euclidean_distances(X, Y, squared=True)
    k *= -gamma
    np.exp(K, K)    # exponentiate K in-place
    return safe_sparse_dot(X, Y.T, dense_output=True) + k 

size = 2094
invest_amount = 10000
total_invests = 0
if_market = 0
if_strat = 0
X, y , Z0,Z1= Build_Data_Set()
print(len(X))
test_size = len(X) - size -1 

start = time.clock()
clf = svm.SVC(kernel="mykernel")
clf.fit(X[:size],y[:size])

y_pred = clf.predict(X[size+1:])
y_true = y[size+1:]
time_taken = time.clock()-start
print time_taken,"Seconds"

for x in range(1, test_size+1):
    if y_pred[-x] == 1:
        invest_return = invest_amount + (invest_amount * (Z0[-x]/100))
        market_return = invest_amount + (invest_amount * (Z1[-x]/100))
        total_invests += 1
        if_market += market_return
        if_strat += invest_return

print accuracy_score(y_true, y_pred)

print precision_recall_fscore_support(y_true, y_pred, average='macro')

print "Total Trades:", total_invests
print "Ending with Strategy:",if_strat
print "Ending with Market:",if_market

compared = ((if_strat - if_market) / if_market) * 100.0
do_nothing = total_invests * invest_amount

avg_market = ((if_market - do_nothing) / do_nothing) * 100.0
avg_strat = ((if_strat - do_nothing) / do_nothing) * 100.0


print "Compared to market, we earn",str(compared)+"% more" 
print "Average investment return:", str(avg_strat)+"%" 
print "Average market return:", str(avg_market)+"%"

预定义的内核正在运行，但对于我的自定义内核，我收到错误：

ValueError: 'mykernel' is not in list

根据官方文档，上面的代码似乎应该有效。

Answer 1

您需要将内核函数本身作为kernel=参数传递，而不仅仅是函数名称，即：

clf = svm.SVC(kernel=mykernel)

而不是

clf = svm.SVC(kernel="mykernel")

如何为sklearn.svm.SVC定义自定义内核函数？

1 个答案: