Simple prediction of stock ups and downs using SVM and logistic regression

import numpy as np
import pandas as pd
from sklearn import svm
from sklearn import cross_validation

import tushare as ts
from sklearn.linear_model import LogisticRegression

data=ts.get_k_data('600000',start='2015-01-01',end='2018-04-12')#通过tushare的接口获取浦发银行的历史数据

data.head(10)

	date	open	close	high	low	volume	code
0	2015-01-05	10.178	10.300	10.415	9.973	5135687.0	600000
1	2015-01-06	10.255	10.338	10.691	10.140	5116845.0	600000
2	2015-01-07	10.191	10.133	10.364	9.954	3857168.0	600000
3	2015-01-08	10.172	9.774	10.178	9.742	3306271.0	600000
4	2015-01-09	9.742	9.890	10.415	9.685	4919999.0	600000
5	2015-01-12	9.935	9.755	10.069	9.582	3677872.0	600000
6	2015-01-13	9.697	9.730	9.877	9.678	1784049.0	600000
7	2015-01-14	9.813	9.928	10.120	9.813	3090188.0	600000
8	2015-01-15	9.928	10.332	10.351	9.864	3298268.0	600000
9	2015-01-16	10.409	10.556	10.736	10.358	4802458.0	600000

data_open=data['open']
data_close=data['close']
y=[]
num_x=len(data)

for i in range(num_x):   #准备数据y
    if data_open[i]>=data_close[i]:
        y.append(1)
    else:
        y.append(0)

x_data=data.as_matrix()

x=x_data[:,1:6]     #到这里x和y都已经准备好了

data_shape=x.shape
data_rows=data_shape[0]
data_cols=data_shape[1]

data_col_max=x.max(axis=0)
data_col_min=x.min(axis=0)
print(data_col_max,data_col_min)

(array([13.67, 13.76, 14.02, 13.53, 8379504.0], dtype=object), array([8.412, 8.311, 8.774, 7.989, 79967.0], dtype=object))

for i in xrange(0, data_rows, 1):#将输入数组归一化
    for j in xrange(0, data_cols, 1):
        x[i][j] = \
            (x[i][j] - data_col_min[j]) / \
            (data_col_max[j] - data_col_min[j])
print(x[0:2])

[[0.33586915176873344 0.3650211047898699 0.31280975981700343
  0.35805811225410594 0.6091568722448011]
 [0.35051350323316854 0.3719948614424664 0.36542127335112495
  0.388197076340011 0.6068866251213773]]

clf1 = svm.SVC(kernel='rbf')
clf2 = LogisticRegression()
result1 = []
result2 = []
for i in range(5):
    # x和y的验证集和测试集，切分80-20%的测试集
    x_train, x_test, y_train, y_test = \
        cross_validation.train_test_split(x, y, test_size=0.2)
    # 训练数据进行训练
    clf1.fit(x_train, y_train)
    # 将预测数据和测试集的验证数据比对
    result1.append(np.mean(y_test == clf1.predict(x_test)))
    clf2.fit(x_train, y_train)
    result2.append(np.mean(y_test == clf2.predict(x_test)))
print("svm classifier accuacy:")
print(result1)
print("LogisticRegression classifier accuacy:")
print(result2)

svm classifier accuacy:
[0.49673202614379086, 0.5490196078431373, 0.49673202614379086, 0.42483660130718953, 0.49673202614379086]
LogisticRegression classifier accuacy:
[0.67320261437908502, 0.62091503267973858, 0.69281045751633985, 0.84313725490196079, 0.72549019607843135]