# Author: Gael Varoquaux gael.varoquaux@normalesup.org
# License: BSD 3 clause

import datetime

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

#import matplotlib.collections.LineCollection

from sklearn import cluster, covariance, manifold

d1 = datetime.datetime(2013, 1, 1)
d2 = datetime.datetime(2014, 1, 1)

symbol_dict = {
    'TOT': 'Total',
    'XOM': 'Exxon',
    'CVX': 'Chevron',
    'COP': 'ConocoPhillips',
    'VLO': 'Valero Energy',
    'MSFT': 'Microsoft',
    'IBM': 'IBM',
    'TWX': 'Time Warner',
    'CVC': 'Cablevision',
    'YHOO': 'Yahoo',
    'HPQ': 'HP',
    'AMZN': 'Amazon',
    'COST': 'Costco',
    'ADBE': 'Adobe',
    'INTC': 'Intel',
    'SBUX': 'Starbucks',
    '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',
    'GOOG':'Google',
    'AAPL': 'Apple',
    'GOOG':'Google',
    '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
quotes = get_pricing(symbols, start_date=d1, end_date=d2, frequency='daily')
print len(symbols)

#print quotes.axes
#quotes.keys()
#print quotes
history = pd.DataFrame(quotes['close_price']-quotes['open_price']).dropna(axis=1)
history = history.T

#s_open = []
#s_close =[]

   
variation = np.array([history[stock] for stock in history]).astype(np.float)

print variation.shape

'''
Label Groups Based on Pipeline data rather than the symbol dict

'''

groups = []
numGroups = labels.max() + 1
for x in range(numGroups):  
    groups.append([])  
# filter the sids into the groups  
for i, grp_idx in enumerate(labels):
    ticker = str(history.T.columns[i])
    groups[grp_idx].append(ticker[ticker.find("[")+1:ticker.find("]")])  
# display stock sids that co-fluctuate:  
for g in range(numGroups):  
    print 'Cluster %i: %s' % (g + 1, ", ".join([str(s) for s in groups[g]])) 

###############################################################################
# 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

###############################################################################
# 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())