In [1]:
# Author: Gael Varoquaux gael.varoquaux@normalesup.org
# License: BSD 3 clause
%matplotlib inline
import datetime
import numpy as np
import matplotlib.pyplot as plt
try:
from matplotlib.finance import quotes_historical_yahoo
except ImportError:
from matplotlib.finance import quotes_historical_yahoo_ochl as quotes_historical_yahoo
from matplotlib.collections import LineCollection
from sklearn import cluster, covariance, manifold
In [3]:
# Retrieve the data from Internet
# Choose a time period reasonnably calm (not too long ago so that we get
# high-tech firms, and before the 2008 crash)
d1 = datetime.datetime(2003, 1, 1)
d2 = datetime.datetime(2008, 1, 1)
# kraft symbol has now changed from KFT to MDLZ in yahoo
symbol_dict = {
'TOT': 'Total',
'XOM': 'Exxon',
'CVX': 'Chevron',
'COP': 'ConocoPhillips',
'VLO': 'Valero Energy',
'MSFT': 'Microsoft',
'IBM': 'IBM',
'TWX': 'Time Warner',
'CMCSA': 'Comcast',
'CVC': 'Cablevision',
'YHOO': 'Yahoo',
'DELL': 'Dell',
'HPQ': 'HP',
'AMZN': 'Amazon',
'TM': 'Toyota',
'CAJ': 'Canon',
'MTU': 'Mitsubishi',
'SNE': 'Sony',
'F': 'Ford',
'HMC': 'Honda',
'NAV': 'Navistar',
'NOC': 'Northrop Grumman',
'BA': 'Boeing',
'KO': 'Coca Cola',
'MMM': '3M',
'MCD': 'Mc Donalds',
'PEP': 'Pepsi',
'MDLZ': 'Kraft Foods',
'K': 'Kellogg',
'UN': 'Unilever',
'MAR': 'Marriott',
'PG': 'Procter Gamble',
'CL': 'Colgate-Palmolive',
'GE': 'General Electrics',
'WFC': 'Wells Fargo',
'JPM': 'JPMorgan Chase',
'AIG': 'AIG',
'AXP': 'American express',
'BAC': 'Bank of America',
'GS': 'Goldman Sachs',
'AAPL': 'Apple',
'SAP': 'SAP',
'CSCO': 'Cisco',
'TXN': 'Texas instruments',
'XRX': 'Xerox',
'LMT': 'Lookheed Martin',
'WMT': 'Wal-Mart',
'WBA': 'Walgreen',
'HD': 'Home Depot',
'GSK': 'GlaxoSmithKline',
'PFE': 'Pfizer',
'SNY': 'Sanofi-Aventis',
'NVS': 'Novartis',
'KMB': 'Kimberly-Clark',
'R': 'Ryder',
'GD': 'General Dynamics',
'RTN': 'Raytheon',
'CVS': 'CVS',
'CAT': 'Caterpillar',
'DD': 'DuPont de Nemours'}
symbols, names = np.array(list(symbol_dict.items())).T
In [4]:
quotes = [quotes_historical_yahoo(symbol, d1, d2, asobject=True)
for symbol in symbols]
stock_open = np.array([q.open for q in quotes]).astype(np.float)
stock_close = np.array([q.close for q in quotes]).astype(np.float)
In [5]:
import pickle
output = open('/Users/chengjun/GitHub/cjc2016/data/stock_open.pkl', 'wb')
# Pickle dictionary using protocol 0.
pickle.dump(stock_open, output)
output.close()
output = open('/Users/chengjun/GitHub/cjc2016/data/stock_close.pkl', 'wb')
# Pickle dictionary using protocol 0.
pickle.dump(stock_close, output)
output.close()
In [5]:
import pickle
data = open('/Users/chengjun/GitHub/cjc2016/data/stock_open.pkl', 'r')
# Pickle dictionary using protocol 0.
stock_open = pickle.load(data)
data.close()
data = open('/Users/chengjun/GitHub/cjc2016/data/stock_close.pkl', 'r')
# Pickle dictionary using protocol 0.
stock_close = pickle.load(data)
data.close()
In [6]:
# The daily variations of the quotes are what carry most information
variation = stock_close - stock_open
In [7]:
variation
Out[7]:
In [14]:
# Learn a graphical structure from the correlations
edge_model = covariance.GraphLassoCV()
# standardize the time series: using correlations rather than covariance
# is more efficient for structure recovery
X = variation.copy().T
X /= X.std(axis=0)
edge_model.fit(X)
Out[14]:
In [9]:
_, 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])))
In [10]:
# Find a low-dimension embedding for visualization: find the best position of
# the nodes (the stocks) on a 2D plane
# We use a dense eigen_solver to achieve reproducibility (arpack is
# initiated with random vectors that we don't control). In addition, we
# use a large number of neighbors to capture the large-scale structure.
node_position_model = manifold.LocallyLinearEmbedding(
n_components=2, eigen_solver='dense', n_neighbors=6)
embedding = node_position_model.fit_transform(X.T).T
In [11]:
# Display a graph of the partial correlations
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)
In [12]:
# Plot the nodes using the coordinates of our embedding
plt.scatter(embedding[0], embedding[1], s=100 * d ** 2, c=labels,
cmap=plt.cm.spectral)
plt.show()
In [13]:
# Visualization
plt.figure(1, facecolor='w', figsize=(10, 8))
plt.clf()
ax = plt.axes([0., 0., 1., 1.])
plt.axis('off')
# Display a graph of the partial correlations
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)
# Plot the nodes using the coordinates of our embedding
plt.scatter(embedding[0], embedding[1], s=100 * d ** 2, c=labels,
cmap=plt.cm.spectral)
# Plot the edges
start_idx, end_idx = np.where(non_zero)
#a sequence of (*line0*, *line1*, *line2*), where::
# linen = (x0, y0), (x1, y1), ... (xm, ym)
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)
# Add a label to each node. The challenge here is that we want to
# position the labels to avoid overlap with other labels
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.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()
In [ ]: