前文中股票高相关k线筛选问题的延伸。基于github上的代码迁移应用到股票高相关预测上。
这里给出一个相关完整的代码实现案例。
1、数据准备
假设你已经有了一些历史股票的k线数据。如果数据能打标哪些股票趋势是上涨的、下跌的会更好。假设这是你目前正在研究的股票k线图:
其他支股票的k-线图如下:
plt.figure(figsize=(11,7))
colors = ['#D62728','#2C9F2C','#FD7F23','#1F77B4','#9467BD',
'#8C564A','#7F7F7F','#1FBECF','#E377C2','#BCBD27']
for i, r in enumerate([0,27,65,100,145,172]):
plt.subplot(3,2,i+1)
plt.plot(x_train[r][:100], label=labels[y_train[r]], color=colors[i], linewidth=2)
plt.xlabel('time sequece')
plt.legend(loc='upper left')
plt.tight_layout()
接下来要使用基于dtw距离计算的knn近邻算法来找出与目标股票ta高相关的Top10支股票,并将他们的k-线图与ta股票的k-线图进行可视化对比呈现。
2、训练KnnDtw算法模型
import sys
import collections
import itertools
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import mode
from scipy.spatial.distance import squareform
plt.style.use('bmh')
%matplotlib inline
try:
from IPython.display import clear_output
have_ipython = True
except ImportError:
have_ipython = False
class KnnDtw(object):
"""K-nearest neighbor classifier using dynamic time warping
as the distance measure between pairs of time series arrays
Arguments
---------
n_neighbors : int, optional (default = 5)
Number of neighbors to use by default for KNN
max_warping_window : int, optional (default = infinity)
Maximum warping window allowed by the DTW dynamic
programming function
subsample_step : int, optional (default = 1)
Step size for the timeseries array. By setting subsample_step = 2,
the timeseries length will be reduced by 50% because every second
item is skipped. Implemented by x[:, ::subsample_step]
"""
def __init__(self, n_neighbors=5, max_warping_window=10000, subsample_step=1):
self.n_neighbors = n_neighbors
self.max_warping_window = max_warping_window
self.subsample_step = subsample_step
def fit(self, x, l):
"""Fit the model using x as training data and l as class labels
Arguments
---------
x : array of shape [n_samples, n_timepoints]
Training data set for input into KNN classifer
l : array of shape [n_samples]
Training labels for input into KNN classifier
"""
self.x = x
self.l = l
def _dtw_distance(self, ts_a, ts_b, d = lambda x,y: abs(x-y)):
"""Returns the DTW similarity distance between two 2-D
timeseries numpy arrays.
Arguments
---------
ts_a, ts_b : array of shape [n_samples, n_timepoints]
Two arrays containing n_samples of timeseries data
whose DTW distance between each sample of A and B
will be compared
d : DistanceMetric object (default = abs(x-y))
the distance measure used for A_i - B_j in the
DTW dynamic programming function
Returns
-------
DTW distance between A and B
"""
# Create cost matrix via broadcasting with large int
ts_a, ts_b = np.array(ts_a), np.array(ts_b)
M, N = len(ts_a), len(ts_b)
cost = sys.maxsize * np.ones((M, N))
# Initialize the first row and column
cost[0, 0] = d(ts_a[0], ts_b[0])
for i in np.arange(1, M):
cost[i, 0] = cost[i-1, 0] + d(ts_a[i], ts_b[0])
for j in np.arange(1, N):
cost[0, j] = cost[0, j-1] + d(ts_a[0], ts_b[j])
# Populate rest of cost matrix within window
for i in np.arange(1, M):
for j in np.arange(max(1, i - self.max_warping_window),
min(N, i + self.max_warping_window)):
choices = cost[i - 1, j - 1], cost[i, j-1], cost[i-1, j]
cost[i, j] = min(choices) + d(ts_a[i], ts_b[j])
# Return DTW distance given window
return cost[-1, -1]
def _dist_matrix(self, x, y):
"""Computes the M x N distance matrix between the training
dataset and testing dataset (y) using the DTW distance measure
Arguments
---------
x : array of shape [n_samples, n_timepoints]
y : array of shape [n_samples, n_timepoints]
Returns
-------
Distance matrix between each item of x and y with
shape [training_n_samples, testing_n_samples]
"""
# Compute the distance matrix
dm_count = 0
# Compute condensed distance matrix (upper triangle) of pairwise dtw distances
# when x and y are the same array
if(np.array_equal(x, y)):
x_s = np.shape(x)
dm = np.zeros((x_s[0] * (x_s[0] - 1)) // 2, dtype=np.double)
p = ProgressBar(shape(dm)[0])
for i in np.arange(0, x_s[0] - 1):
for j in np.arange(i + 1, x_s[0]):
dm[dm_count] = self._dtw_distance(x[i, ::self.subsample_step],
y[j, ::self.subsample_step])
dm_count += 1
p.animate(dm_count)
# Convert to squareform
dm = squareform(dm)
return dm
# Compute full distance matrix of dtw distnces between x and y
else:
x_s = np.shape(x)
y_s = np.shape(y)
dm = np.zeros((x_s[0], y_s[0]))
dm_size = x_s[0]*y_s[0]
p = ProgressBar(dm_size)
for i in np.arange(0, x_s[0]):
for j in np.arange(0, y_s[0]):
dm[i, j] = self._dtw_distance(x[i, ::self.subsample_step],
y[j, ::self.subsample_step])
# Update progress bar
dm_count += 1
p.animate(dm_count)
return dm
def predict(self, x):
"""Predict the class labels or probability estimates for
the provided data
Arguments
---------
x : array of shape [n_samples, n_timepoints]
Array containing the testing data set to be classified
Returns
-------
2 arrays representing:
(1) the predicted class labels
(2) the knn label count probability
"""
dm = self._dist_matrix(x, self.x)
# Identify the k nearest neighbors
knn_idx = dm.argsort()[:, :self.n_neighbors]
# Identify k nearest labels
knn_labels = self.l[knn_idx]
# Model Label
mode_data = mode(knn_labels, axis=1)
mode_label = mode_data[0]
mode_proba = mode_data[1]/self.n_neighbors
return mode_label.ravel(), mode_proba.ravel()
class ProgressBar:
"""This progress bar was taken from PYMC
"""
def __init__(self, iterations):
self.iterations = iterations
self.prog_bar = '[]'
self.fill_char = '*'
self.width = 40
self.__update_amount(0)
if have_ipython:
self.animate = self.animate_ipython
else:
self.animate = self.animate_noipython
def animate_ipython(self, iter):
# print('\r', self,)
# sys.stdout.flush()
self.update_iteration(iter + 1)
def update_iteration(self, elapsed_iter):
self.__update_amount((elapsed_iter / float(self.iterations)) * 100.0)
self.prog_bar += ' %d of %s complete' % (elapsed_iter, self.iterations)
def __update_amount(self, new_amount):
percent_done = int(round((new_amount / 100.0) * 100.0))
all_full = self.width - 2
num_hashes = int(round((percent_done / 100.0) * all_full))
self.prog_bar = '[' + self.fill_char * num_hashes + ' ' * (all_full - num_hashes) + ']'
pct_place = (len(self.prog_bar) // 2) - len(str(percent_done))
pct_string = '%d%%' % percent_done
self.prog_bar = self.prog_bar[0:pct_place] + \
(pct_string + self.prog_bar[pct_place + len(pct_string):])
def __str__(self):
return str(self.prog_bar)
模型训练、预测
m = KnnDtw(n_neighbors=1, max_warping_window=10)
m.fit(x_train[::10], y_train[::10]) # 做数据采样,每10个元素采样
label, proba = m.predict(x_test[::10])
模型评估
from sklearn.metrics import classification_report, confusion_matrix
print(classification_report(label, y_test[::10],
target_names=[l for l in labels.values()]))
conf_mat = confusion_matrix(label, y_test[::10])
fig = plt.figure(figsize=(6,6))
width = np.shape(conf_mat)[1]
height = np.shape(conf_mat)[0]
res = plt.imshow(np.array(conf_mat), cmap=plt.cm.summer, interpolation='nearest')
for i, row in enumerate(conf_mat):
for j, c in enumerate(row):
if c>0:
plt.text(j-.2, i+.1, c, fontsize=16)
cb = fig.colorbar(res)
plt.title('Confusion Matrix')
_ = plt.xticks(range(6), [l for l in labels.values()], rotation=90)
_ = plt.yticks(range(6), [l for l in labels.values()])
3、为目标股票ta筛选Top10高相似的股票
3.1 计算股票的dtw距离,并筛选出Top10高相关股票
m._dtw_distance(x_train[1], x_train[1112])
x_similaritys = {}
# 选定一支目标股票
ta = x_test[0]
# 分别计算其他200支股票与目标股票的相关性系数
for stock_id, stock_data in enumerate(x_test[1:200]):
dtw_dist = m._dtw_distance(ta, stock_data)
if stock_id not in x_similaritys.keys() and stock_id!=0:
x_similaritys[stock_id] = dtw_dist
#选出与目标股票Top10相似的股票k线
res = sorted(x_similaritys.items(), key=lambda x: x[1])
print("与目标股票Ta高相关的10支股票为:")
for stock_id,dtw_dist in res[:10]:
print("股票id:",stock_id," , DTW距离: ",dtw_dist)
3.2 可视化Top10高相似股票曲线
# 绘制TopN股票趋势曲线
plt.figure(figsize=(11, 11))
for i, (stock_id,dtw_dist) in enumerate(res[:10]):
# print(i, stock_id,dtw_dist)
plt.subplot(5,2,i+1)
plt.plot(x_test[0][:100], label="stock-0", color=colors[0], linewidth=2)
plt.plot(x_test[stock_id][:100], label="stock-%d"%stock_id, color=(0.2/(i+1),0.1/(i+1),0.7-0.2/(i+1)-0.1/(i+1)), linewidth=2)
plt.xlabel('time')
plt.legend(loc='upper left')
plt.tight_layout()
红色的是目标股票Ta的k-线图,与之高相似的10支股票的k-线图为蓝色曲线,分别呈现在10个子图中,做为对比可视化,能更直观的对两支股票的走势作出差异对比。方便交付给投资者对比查看股票走势。
Done