def stock_month_plot():
    '''
    Show how to make date plots in matplotlib using date tick locators and formatters.
    '''
    date1 = datetime.date(2002, 1, 5)
    date2 = datetime.date(2003, 12, 1)

    # every monday
    mondays = WeekdayLocator(MONDAY)
    # every 3rd month
    months = MonthLocator(range(1, 13), bymonthday=1, interval=3)
    monthsFmt = DateFormatter("%b '%y")

    quotes = quotes_historical_yahoo_ochl('INTC', date1, date2)
    if len(quotes) == 0:
        print('Found no quotes')
        raise SystemExit
    dates = [q[0] for q in quotes]
    opens = [q[1] for q in quotes]

    fig, ax = plt.subplots()
    ax.plot_date(dates, opens, '-')
    ax.xaxis.set_major_locator(months)
    ax.xaxis.set_major_formatter(monthsFmt)
    ax.xaxis.set_minor_locator(mondays)
    ax.autoscale_view()
    #ax.xaxis.grid(False, 'major')
    #ax.xaxis.grid(True, 'minor')
    ax.grid(True)

    fig.autofmt_xdate()
    plt.show()

def stock_year_plot():
    '''
    Show how to make date plots in matplotlib using date tick locators and formatters.
    '''
    date1 = datetime.date(1995, 1, 1)
    date2 = datetime.date(2004, 4, 12)

    years = YearLocator()   # every year
    months = MonthLocator()  # every month
    yearsFmt = DateFormatter('%Y')

    quotes = quotes_historical_yahoo_ochl('INTC', date1, date2)
    if len(quotes) == 0:
        print('Found no quotes')
        raise SystemExit
    dates = [q[0] for q in quotes]
    opens = [q[1] for q in quotes]

    fig, ax = plt.subplots()
    ax.plot_date(dates, opens, '-')
    # format the ticks
    ax.xaxis.set_major_locator(years)
    ax.xaxis.set_major_formatter(yearsFmt)
    ax.xaxis.set_minor_locator(months)
    ax.autoscale_view()
    # format the coords message box
    def price(x):
        return '$%1.2f' % x
    ax.fmt_xdata = DateFormatter('%Y-%m-%d')
    ax.fmt_ydata = price
    ax.grid(True)

    fig.autofmt_xdate()
    plt.show()

def symbolsToPriceDict(symbols,startDate,endDate):
    """
    From a list of stock symbols and a range of dates, returns a prices by symbols numpy array
    listing the opening prices for the stocks in the given date range.
    """
    #add check to account for missing values in data
    quotes = [list(finance.quotes_historical_yahoo_ochl(symbol, startDate, endDate,asobject = True).open) for symbol in symbols]
    return dict(zip(symbols,quotes))

def symbolsToPrices(symbols,startDate,endDate):
    """
    From a list of stock symbols and a range of dates, returns a prices by symbols numpy array
    listing the opening prices for the stocks in the given date range.
    """
    #add check to account for missing values in data
    quotes = [finance.quotes_historical_yahoo_ochl(symbol, startDate, endDate,asobject = True).open for symbol in symbols]
    print "prices shape:"
    print np.array(quotes).T.shape
    return np.array(quotes).T

def main(symbols, percent, days, verbose):
    if verbose:
        print "Symbols: %s" % symbols
        print "Percent: %s" % percent
        print "Days: %d" % days
        print "Verbose: %s" % verbose

    print

    if days > 0:
        days = -days

    print "Checking for a %s%% decline over the past " \
          "%d days" % (percent, abs(days))
    print

    for ticker in symbols:
        ticker = ticker.upper()
        print "Stock: %s" % ticker

        start_date = datetime.datetime.now() + datetime.timedelta(days)
        end_date = datetime.datetime.now()

        quotes_objects = quotes_historical_yahoo_ochl(ticker,
                                                      start_date,
                                                      end_date,
                                                      asobject=True)

        max_value = round(float(max(quotes_objects.close)), 5)
        print "- max value over %d days: %s" % (abs(days), max_value)

        most_recent_close = round(float(quotes_objects.close[-1]), 5)
        print "- most recent close: %s" % most_recent_close

        percent_change = round(float(
                               rate_of_return(max_value, most_recent_close)
                               ), 2)
        print "- percent change: %s%%" % percent_change

        target_price = max_value - (max_value * (percent / 100.0))

        print "- target price: %s (%s%% below %s)" % (target_price, percent,
                                                      max_value)

        if percent_change < -percent:
            print
            print "ALERT! %s has dropped %s%% " \
                  "over the last %s days" % (ticker,
                                             percent_change,
                                             abs(days))

        print

def symbols(stock_symbol):
    today = date.today()
    start = (today.year , today.month, today.day - 1)   # Here we have a bug. If report running on weekend, you will get error because we only minus one day which possible is NOT value market date.
    quotes = quotes_historical_yahoo_ochl(stock_symbol, start, today)
    df = pd.DataFrame(quotes)
    df.columns = [u'Date', u'Open',u'Close',u'High',u'Low',u'Volume']
    #####
    #df.to_csv('stock_%s.csv' %stock_symbol)
    #test = pd.read_csv('stock_FTNT.csv')
    #print "TEST \n "
    #print test
    ##### 
    sum = 0
    
    for i in xrange(df.shape[0]):
        #print "%.2f + %.2f = %.2f" %(sum,df['Close'][i],sum+df['Close'][i])
        sum += df['Close'][i]
    
    return (sum/df.shape[0])

def PlotData(code, start, end, list):
    start_date = _wxdate2pydate(start)
    end_date = _wxdate2pydate(end)
    print code
    print start_date
    print end_date
    quotes = quotes_historical_yahoo_ochl(code, start_date, end_date)
    fields = ['date', 'open', 'close', 'high', 'low', 'volume']
    list1 = []
    for i in range(0, len(quotes)):
        x = date.fromordinal(int(quotes[i][0]))
        y = datetime.strftime(x, '%Y-%m-%d')
        list1.append(y)
    print list1

    quotesdf = pd.DataFrame(quotes, index=list1, columns=fields)
    quotesdf = quotesdf.drop(['date'], axis=1)
    quotesdftemp = pd.DataFrame()
    print quotesdftemp

    for i in range(0, len(list)):
        quotesdftemp[list[i]] = quotesdf[list[i]]
    print "ready to plot"
    quotesdftemp.plot(marker='o')

"""
数据的简单处理与筛选

"""
from matplotlib.finance import quotes_historical_yahoo_ochl  # 注matplotlib包里已经没有了quotes_historical_yahoo方法了，改为quotes_historical_yahoo_ochl
from datetime import date
from datetime import datetime
import pandas as pd 
import numpy as np 
import time


today = date.today()
start = (today.year - 5, today.month, today.day)
quotes = quotes_historical_yahoo_ochl('AXP', start, today) #美国运通公司最近一年股票代码
fields = ['date', 'open', 'close', 'high', 'low', 'volume']
list1 = []
for i in range(0,len(quotes)):
	x = date.fromordinal(int(quotes[i][0]))
	y = datetime.strftime(x, "%Y-%m-%d")
	list1.append(y)

qutoesdf = pd.DataFrame(quotes, index=list1, columns=fields) # 利用index属性可以将索引改变。　日期为格里高利时间，用函数改变
qutoesdf = qutoesdf.drop(['date'], axis = 1)
# print qutoesdf

#求平均值
print qutoesdf.mean(columns='close')
#求开盘价大于80的成交量

import datetime
import numpy as np
import pylab as pl
from matplotlib.finance import quotes_historical_yahoo_ochl
from matplotlib.dates import YearLocator, MonthLocator, DateFormatter
from hmmlearn.hmm import GaussianHMM


print(__doc__)

###############################################################################
# Downloading the data
date1 = datetime.date(1995, 1, 1)  # start date
date2 = datetime.date(2012, 1, 6)  # end date
# get quotes from yahoo finance
quotes = quotes_historical_yahoo_ochl("INTC", date1, date2)
if len(quotes) == 0:
    raise SystemExit

# unpack quotes
dates = np.array([q[0] for q in quotes], dtype=int)
close_v = np.array([q[2] for q in quotes])
volume = np.array([q[5] for q in quotes])[1:]

# take diff of close value
# this makes len(diff) = len(close_t) - 1
# therefore, others quantity also need to be shifted
diff = close_v[1:] - close_v[:-1]
dates = dates[1:]
close_v = close_v[1:]

symbols_all, names_all = stock_list.Symbol.values, stock_list.Name.values


print symbols_all

print(type(symbols_all))
# print 'this are the symbols'
# print symbols

# print 'this are the names'
# print names
ticker_index = 1
for symbol in symbols_all:
    # print 'starting...', ticker_index
    quotes = [finance.quotes_historical_yahoo_ochl(symbol, d1, d2, asobject=True)]
    # print 'working...', ticker_index
    # ticker_index = ticker_index + 1

# quotes = [finance.quotes_historical_yahoo_ochl(symbol, d1, d2, asobject = True) for symbol in symbols_all]

# print quotes

open = np.array([q.open for q in quotes]).astype(np.float)
# print open

close = np.array([q.close for q in quotes]).astype(np.float)
# print close

variation = close - open
# print variation

import time
from matplotlib.finance import quotes_historical_yahoo_ochl
from datetime import date
from datetime import datetime
import pandas as pd
import matplotlib.pyplot as plt
import pylab as pl
import numpy as np

start = datetime(2014, 1, 1)
end = datetime(2014, 12, 31)
quotesMS14 = quotes_historical_yahoo_ochl("MSFT", start, end)
fields = ["date", "open", "close", "high", "low", "volume"]
list1 = []
for i in range(0, len(quotesMS14)):
    x = date.fromordinal(int(quotesMS14[i][0]))
    y = datetime.strftime(x, "%Y-%m-%d")
    list1.append(y)
# print list1
quotesdfMS14 = pd.DataFrame(quotesMS14, index=list1, columns=fields)
# print quotesMS14
listtemp1 = []
for i in range(0, len(quotesdfMS14)):
    temp = time.strptime(quotesdfMS14.index[i], "%Y-%m-%d")
    listtemp1.append(temp.tm_mon)
# print listtemp1
quotesdfMS14["month"] = listtemp1
# print quotesdfMS14
# closemaxINTC = quotesdfMS14.groupby('month').max().close
openMS = quotesdfMS14.groupby("month").mean().open
listopen = []

from matplotlib.finance import quotes_historical_yahoo_ochl

# retrieve symbol lists
markets = ['amex','nasdaq','nyse','otcbb']
symbols = []
for m in markets:
    fname = 'symbols-' + m + '-unique.txt'
    with open(fname, 'r') as f:
        symbols += f.read().splitlines()

print len(symbols), 'symbols listed'

exit
# set date range
date1 = date(1984, 1, 1)
date2 = date(2014, 12, 31)
# date2 = date.today()
# date1 = date2 - timedelta(days=14)

# retrieve all data
for symbol in symbols:
    try:
        data = quotes_historical_yahoo_ochl(symbol, date1, date2)
        if None != data and len(data) > 0:
            print symbol, len(data)
            with open('csv/' + symbol + '.csv', 'w') as f:
                writer = csv.writer(f)
                writer.writerows(data)
    except:
        True

from matplotlib.dates import MonthLocator
from matplotlib.finance import quotes_historical_yahoo_ochl
from matplotlib.finance import candlestick_ochl
import sys
from datetime import date

today = date.today()
start = (today.year - 1, today.month, today.day)

alldays = DayLocator()
months = MonthLocator()
month_formatter = DateFormatter("%b %Y")

# 从财经频道下载股价数据
symbol = 'BIDU' # 百度的股票代码
quotes = quotes_historical_yahoo_ochl(symbol, start, today)

# 创建figure对象，这是绘图组件的顶层容器
fig = plt.figure()
# 增加一个子图
ax = fig.add_subplot(111)
# x轴上的主定位器设置为月定位器，该定位器负责x轴上较粗的刻度
ax.xaxis.set_major_locator(months)
# x轴上的次定位器设置为日定位器，该定位器负责x轴上较细的刻度
ax.xaxis.set_minor_locator(alldays)
# x轴上的主格式化器设置为月格式化器，该格式化器负责x轴上较粗刻度的标签
ax.xaxis.set_major_formatter(month_formatter)

# 使用matplotlib.finance包的candlestick函数绘制k线图
candlestick_ochl(ax, quotes)
# 将x轴上的标签格式化为日期

"""
get google's stock exchange data using matplotlib
"""
from matplotlib.finance import quotes_historical_yahoo_ochl
from datetime import date, datetime, timedelta
import pandas as pd

today = date.today()
start = today - timedelta(days=365)
quotes = quotes_historical_yahoo_ochl("GOOG", start, today)
fields = ["date", "open", "close", "high", "low", "volume"]
# convert date format
dates = []
for i in range(0, len(quotes)):
    x = date.fromordinal(int(quotes[i][0]))
    y = datetime.strftime(x, "%Y-%m-%d")
    dates.append(y)
# set dates to index
quotesdf = pd.DataFrame(quotes, index=dates, columns=fields)
quotesdf = quotesdf.drop(["date"], axis=1)
# print
# print quotesdf
# print quotesdf[u'2014-12-02' : u'2014-12-09']
# print quotesdf.loc[1:5, ] # [row, col]
# print quotesdf.loc[:, ['low', 'volume']]
print quotesdf[(quotesdf.index >= u"2015-01-30") & (quotesdf.close > 600)]
# group (example)
# g = tempdf.groupby('month')
# gvolume = g['volume']
# print gvolume.sum()

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import time
from matplotlib.finance import quotes_historical_yahoo_ochl
from datetime import date
from datetime import datetime
import pandas as pd
import matplotlib.pyplot as plt
__author__ = 'wangjj'
__mtime__ = '20161022下午 11:39'
today = date.today()
start = (today.year - 1, today.month, today.day)
quotes = quotes_historical_yahoo_ochl('KO', start, today)
fields = ['date', 'open', 'close', 'high', 'low', 'volume']
list1 = []
for i in range(0, len(quotes)):
    x = date.fromordinal(int(quotes[i][0]))
    y = datetime.strftime(x, '%Y-%m-%d')
    list1.append(y)
# print(list1)
quoteskodf = pd.DataFrame(quotes, index=list1, columns=fields)
quoteskodf = quoteskodf.drop(['date'], axis=1)
# print(quotesdf)
listtemp = []
for i in range(0, len(quoteskodf)):
    temp = time.strptime(quoteskodf.index[i], "%Y-%m-%d")
    listtemp.append(temp.tm_mon)
print(listtemp)  # “print listtemp” in Python 2.x
tempkodf = quoteskodf.copy()
tempkodf['month'] = listtemp
closeMeansKO = tempkodf.groupby('month').mean().close

  'AMZN': 'Amazon',
  'KO':   'Coca Cola',
  'PEP':  'Pepsi',
  'MCD':  'Mc Donalds',
  'YUM':  'Taco Bell',
  'CMG':  'Chipotle Mexican Grill',
  'WMT':  'Wal-Mart',
  'HD':   'Home Depot',
  'CVS':  'CVS'
}

symbols, names = np.array(list(symbol_dict.items())).T
print('_'*140 + "\n>>> quotes:")
for symbol in symbols:
  try:
    quote = finance.quotes_historical_yahoo_ochl(symbol, d1, d2, asobject=True)
    print("\n%s %s:\n%s" % (symbol, symbol_dict[symbol], quote))
  except Exception as e:
    # this is usually a 404 error, coz of the date range (ie a stock may not have existed),
    # so we could enter a zeroed entry ???
print('_'*140 + "\n")

cls1 = datetime.datetime(2009, 1, 1)
cls2 = datetime.datetime(2015, 1, 1)
symbol = 'YUM' # Taco Bell
# symbol = 'CMG' # Chipotle Mexican Grill
quote = finance.quotes_historical_yahoo_ochl(symbol, cls1, cls2, asobject=True)
print("\n%s %s\ntype(quote)=%s=\nquote:\n%s" % (symbol, symbol_dict[symbol], type(quote), quote))


# quotes = [finance.quotes_historical_yahoo(symbol, d1, d2, asobject=True) for symbol in symbols]

This example requires an active internet connection since it uses
yahoo finance to get the data for plotting
"""

import matplotlib.pyplot as plt
from matplotlib.finance import quotes_historical_yahoo_ochl
from matplotlib.dates import YearLocator, MonthLocator, DateFormatter
import datetime
date1 = datetime.date(1995, 1, 1)
date2 = datetime.date(2004, 4, 12)

years = YearLocator()   # every year
months = MonthLocator()  # every month
yearsFmt = DateFormatter('%Y')

quotes = quotes_historical_yahoo_ochl(
    'INTC', date1, date2)
if len(quotes) == 0:
    raise SystemExit

dates = [q[0] for q in quotes]
opens = [q[1] for q in quotes]

fig, ax = plt.subplots()
ax.plot_date(dates, opens, '-')

# format the ticks
ax.xaxis.set_major_locator(years)
ax.xaxis.set_major_formatter(yearsFmt)
ax.xaxis.set_minor_locator(months)
ax.autoscale_view()

    "601668": "中国建筑",
    "601688": "华泰证券",
    "601766": "中国中车",
    "601800": "中国交建",
    "601818": "光大银行",
    "601857": "中国石油",
    "601901": "方正证券",
    "601988": "中国银行",
    "601989": "中国重工",
    "601998": "中信银行"}

symbols, names = np.array(list(symbol_dict.items())).T

#quotes = [ts.get_hist_data(symbol,start=d1,end=d2) for symbol in symbols]
## 一次最多30个 然后需要等待了
quotes = [pd.DataFrame(quotes_historical_yahoo_ochl(symbol+".ss", d1, d2),columns=['date','open','high','low','close','volume'])
          for symbol in symbols]
              
for symbol in symbols:
    quotes.append(pd.DataFrame(quotes_historical_yahoo_ochl(symbol+".ss", d1, d2),columns=['date','open','high','low','close','volume']))              
              
open_price  = np.array([q.open.values for q in quotes])
close_price = np.array([q.close.values for q in quotes])

# 每日价格浮动包含了重要信息！
variation = close_price - open_price

###############################################################################
# Learn a graphical structure from the correlations
edge_model = covariance.GraphLassoCV()

    'MMM',
    'MRK',
    'MSFT',
    'NKE',
    'PFE',
    'PG',
    'T',
    'TRV',
    'UNH',
    'UTX',
    'V',
    'VZ',
    'WMT',
    'XOM']
quotes = [[0 for col in range(90)] for row in range(30)]
listTemp = [[0 for col in range(90)] for row in range(30)]
for i in range(30):
    quotes[i] = quotes_historical_yahoo_ochl(listDji[i], start, end)
    days = len(quotes[0])
for i in range(30):
    for j in range(days - 1):
        if (quotes[i][j][2] and quotes[i][j + 1][2]
                and (quotes[i][j + 1][2] >= quotes[i][j][2])):
            listTemp[i][j] = 1.0
        else:
            listTemp[i][j] = -1.0
data = vstack(listTemp)
centroids, _ = kmeans(data, 4)  # float or double is supported
result, _ = vq(data, centroids)
print(result)

import time
from matplotlib.finance import quotes_historical_yahoo_ochl
from datetime import date
from datetime import datetime
import pandas as pd
import matplotlib.pyplot as plt
import pylab as pl
import numpy as np

start = datetime(2014, 1, 1)
end = datetime(2014, 12, 31)
quotesMSFT = quotes_historical_yahoo_ochl("MSFT", start, end)
quotesINTC = quotes_historical_yahoo_ochl("INTC", start, end)
fields = ["date", "open", "close", "high", "low", "volume"]
# quotesdf = pd.DataFrame(quotes, columns = fields)
# quotesdf = pd.DataFrame(quotes, index = range(1,len(quotes)+1),columns = fields)
list1 = []
for i in range(0, len(quotesMSFT)):
    x = date.fromordinal(int(quotesMSFT[i][0]))
    y = datetime.strftime(x, "%Y-%m-%d")
    list1.append(y)
# print list1
list2 = []
for i in range(0, len(quotesINTC)):
    x = date.fromordinal(int(quotesINTC[i][0]))
    y = datetime.strftime(x, "%Y-%m-%d")
    list2.append(y)
quotesmsftdf = pd.DataFrame(quotesMSFT, index=list1, columns=fields)
print "----------------", type(quotesmsftdf["open"])
quotesmsftdf = quotesmsftdf.drop(["date"], axis=1)