股票关联性分析-新手使用两个数据源

import baostock as bs
import pandas as pd

# 登陆系统
lg = bs.login()
# 显示登陆返回信息
print('login respond error_code:'+lg.error_code)
print('login respond  error_msg:'+lg.error_msg)

# 获取上证50成分股
rs = bs.query_sz50_stocks()
print('query_sz50 error_code:'+rs.error_code)
print('query_sz50  error_msg:'+rs.error_msg)

# 打印结果集
sz50_stocks = []
while (rs.error_code == '0') & rs.next():
    # 获取一条记录，将记录合并在一起
    sz50_stocks.append(rs.get_row_data())
result = pd.DataFrame(sz50_stocks, columns=rs.fields)
# 结果集输出到csv文件
#result.to_csv("~/sz50_stocks.csv", encoding="gbk", index=False)
import numpy as np
result['code']=result['code'].str.replace('sh.','')+'.sh'
stocks=dict(zip(result['code'],result['code_name']))
codes, names = np.array(sorted(stocks.items())).T
print(names)
import tushare as ts
token=''
pro=ts.pro_api(token)
def get_data(code,start='20191210',end='20201210'):
    df=ts.pro_bar(ts_code=code,adj='qfq', 
                  start_date=start, end_date=end)
   
    return df

codes, names = np.array(sorted(stocks.items())).T
data=pd.DataFrame({name:(get_data(code).close-get_data(code).open) 
                   for code,name in zip(codes,names)})
variation=data.dropna().values
data.head(5)
from matplotlib.collections import LineCollection
from sklearn import cluster, covariance, manifold
# 相关系数

edge_model = covariance.GraphicalLassoCV()
X = variation.copy()
X /= X.std(axis=0)
edge_model.fit(X)
_, labels = cluster.affinity_propagation(edge_model.covariance_)
n_labels = labels.max()

for i in range(n_labels + 1):
    print('Cluster %i: %s' % ((i + 1), ', '.join(names[labels == i])))
    import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
node_position_model = manifold.LocallyLinearEmbedding(
    n_components=2, eigen_solver='dense', n_neighbors=6)

embedding = node_position_model.fit_transform(X.T).T
# 可视化
plt.figure(1, facecolor='w', figsize=(10, 8))
plt.clf()
ax = plt.axes([0., 0., 1., 1.])
plt.axis('off')

# 计算偏相关系数
partial_correlations = edge_model.precision_.copy()
d = 1 / np.sqrt(np.diag(partial_correlations))
partial_correlations *= d
partial_correlations *= d[:, np.newaxis]
non_zero = (np.abs(np.triu(partial_correlations, k=1)) > 0.02)

# 使用嵌入的坐标绘制节点
plt.scatter(embedding[0], embedding[1], s=100 * d ** 2, c=labels,
            cmap=plt.cm.nipy_spectral)

# 画相互关联的边
start_idx, end_idx = np.where(non_zero)
segments = [[embedding[:, start], embedding[:, stop]]
            for start, stop in zip(start_idx, end_idx)]
values = np.abs(partial_correlations[non_zero])
lc = LineCollection(segments,
                    zorder=0, cmap=plt.cm.hot_r,
                    norm=plt.Normalize(0, .7 * values.max()))
lc.set_array(values)
lc.set_linewidths(15 * values)
ax.add_collection(lc)

#向每个节点添加一个标签，难点在于定位标签，以避免与其他标签重叠
for index, (name, label, (x, y)) in enumerate(
        zip(names, labels, embedding.T)):

    dx = x - embedding[0]
    dx[index] = 1
    dy = y - embedding[1]
    dy[index] = 1
    this_dx = dx[np.argmin(np.abs(dy))]
    this_dy = dy[np.argmin(np.abs(dx))]
    if this_dx > 0:
        horizontalalignment = 'left'
        x = x + .002
    else:
        horizontalalignment = 'right'
        x = x - .002
    if this_dy > 0:
        verticalalignment = 'bottom'
        y = y + .002
    else:
        verticalalignment = 'top'
        y = y - .002
    plt.text(x, y, name, size=10,
             horizontalalignment=horizontalalignment,
             verticalalignment=verticalalignment,
             bbox=dict(facecolor='w',
                       edgecolor=plt.cm.nipy_spectral(label / float(n_labels)),
                       alpha=.6))

plt.xlim(embedding[0].min() - .15 * embedding[0].ptp(),
         embedding[0].max() + .10 * embedding[0].ptp(),)
plt.ylim(embedding[1].min() - .03 * embedding[1].ptp(),
         embedding[1].max() + .03 * embedding[1].ptp())

plt.show()

通过小的例子去熟悉两个数据源接口，并能够有一定的金融知识积累，后面会梳理一些小算法在金融数据的展示，当然也会去获取更多的数据，然后做一个整个思考的想法吧