Pushing the docs to dev/ for branch: master, commit 2c55551d0b487705e7c4fd17205ad746df1b25d6

Author: sklearn-ci

dev/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: caf8e3d0c856aa5dc00a8104a7bc5ddf
+config: 6c4edf2daed9c19d41ebfbca7ee68990
 tags: 645f666f9bcd5a90fca523b33c5a78b7

dev/_downloads/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\n# Author: Gael Varoquaux [email protected]\n# License: BSD 3 clause\n\nimport datetime\n\nimport numpy as np\nimport matplotlib.pyplot as plt\ntry:\n     from matplotlib.finance import quotes_historical_yahoo_ochl\nexcept ImportError:\n     # quotes_historical_yahoo_ochl was named quotes_historical_yahoo before matplotlib 1.4\n     from matplotlib.finance import quotes_historical_yahoo as quotes_historical_yahoo_ochl\nfrom matplotlib.collections import LineCollection\nfrom sklearn import cluster, covariance, manifold"
+        "print(__doc__)\n\n# Author: Gael Varoquaux [email protected]\n# License: BSD 3 clause\n\nfrom datetime import datetime\n\nimport numpy as np\nfrom matplotlib import pyplot as plt\nfrom matplotlib.collections import LineCollection\nfrom six.moves.urllib.request import urlopen\nfrom six.moves.urllib.parse import urlencode\nfrom sklearn import cluster, covariance, manifold"
       ]
     },
     {
@@ -44,7 +44,7 @@
       },
       "outputs": [],
       "source": [
-        "# Choose a time period reasonably calm (not too long ago so that we get\n# high-tech firms, and before the 2008 crash)\nd1 = datetime.datetime(2003, 1, 1)\nd2 = datetime.datetime(2008, 1, 1)\n\n# kraft symbol has now changed from KFT to MDLZ in yahoo\nsymbol_dict = {\n    'TOT': 'Total',\n    'XOM': 'Exxon',\n    'CVX': 'Chevron',\n    'COP': 'ConocoPhillips',\n    'VLO': 'Valero Energy',\n    'MSFT': 'Microsoft',\n    'IBM': 'IBM',\n    'TWX': 'Time Warner',\n    'CMCSA': 'Comcast',\n    'CVC': 'Cablevision',\n    'YHOO': 'Yahoo',\n    'DELL': 'Dell',\n    'HPQ': 'HP',\n    'AMZN': 'Amazon',\n    'TM': 'Toyota',\n    'CAJ': 'Canon',\n    'MTU': 'Mitsubishi',\n    'SNE': 'Sony',\n    'F': 'Ford',\n    'HMC': 'Honda',\n    'NAV': 'Navistar',\n    'NOC': 'Northrop Grumman',\n    'BA': 'Boeing',\n    'KO': 'Coca Cola',\n    'MMM': '3M',\n    'MCD': 'Mc Donalds',\n    'PEP': 'Pepsi',\n    'MDLZ': 'Kraft Foods',\n    'K': 'Kellogg',\n    'UN': 'Unilever',\n    'MAR': 'Marriott',\n    'PG': 'Procter Gamble',\n    'CL': 'Colgate-Palmolive',\n    'GE': 'General Electrics',\n    'WFC': 'Wells Fargo',\n    'JPM': 'JPMorgan Chase',\n    'AIG': 'AIG',\n    'AXP': 'American express',\n    'BAC': 'Bank of America',\n    'GS': 'Goldman Sachs',\n    'AAPL': 'Apple',\n    'SAP': 'SAP',\n    'CSCO': 'Cisco',\n    'TXN': 'Texas instruments',\n    'XRX': 'Xerox',\n    'LMT': 'Lookheed Martin',\n    'WMT': 'Wal-Mart',\n    'WBA': 'Walgreen',\n    'HD': 'Home Depot',\n    'GSK': 'GlaxoSmithKline',\n    'PFE': 'Pfizer',\n    'SNY': 'Sanofi-Aventis',\n    'NVS': 'Novartis',\n    'KMB': 'Kimberly-Clark',\n    'R': 'Ryder',\n    'GD': 'General Dynamics',\n    'RTN': 'Raytheon',\n    'CVS': 'CVS',\n    'CAT': 'Caterpillar',\n    'DD': 'DuPont de Nemours'}\n\nsymbols, names = np.array(list(symbol_dict.items())).T\n\nquotes = [quotes_historical_yahoo_ochl(symbol, d1, d2, asobject=True)\n          for symbol in symbols]\n\nopen = np.array([q.open for q in quotes]).astype(np.float)\nclose = np.array([q.close for q in quotes]).astype(np.float)\n\n# The daily variations of the quotes are what carry most information\nvariation = close - open"
+        "def quotes_historical_google(symbol, date1, date2):\n    \"\"\"Get the historical data from Google finance.\n\n    Parameters\n    ----------\n    symbol : str\n        Ticker symbol to query for, for example ``\"DELL\"``.\n    date1 : datetime.datetime\n        Start date.\n    date2 : datetime.datetime\n        End date.\n\n    Returns\n    -------\n    X : array\n        The columns are ``date`` -- datetime, ``open``, ``high``,\n        ``low``, ``close`` and ``volume`` of type float.\n    \"\"\"\n    params = urlencode({\n        'q': symbol,\n        'startdate': date1.strftime('%b %d, %Y'),\n        'enddate': date2.strftime('%b %d, %Y'),\n        'output': 'csv'\n    })\n    url = 'http://www.google.com/finance/historical?' + params\n    with urlopen(url) as response:\n        dtype = {\n            'names': ['date', 'open', 'high', 'low', 'close', 'volume'],\n            'formats': ['object', 'f4', 'f4', 'f4', 'f4', 'f4']\n        }\n        converters = {0: lambda s: datetime.strptime(s.decode(), '%d-%b-%y')}\n        return np.genfromtxt(response, delimiter=',', skip_header=1,\n                             dtype=dtype, converters=converters,\n                             missing_values='-', filling_values=-1)\n\n\n# Choose a time period reasonably calm (not too long ago so that we get\n# high-tech firms, and before the 2008 crash)\nd1 = datetime(2003, 1, 1)\nd2 = datetime(2008, 1, 1)\n\nsymbol_dict = {\n    'TOT': 'Total',\n    'XOM': 'Exxon',\n    'CVX': 'Chevron',\n    'COP': 'ConocoPhillips',\n    'VLO': 'Valero Energy',\n    'MSFT': 'Microsoft',\n    'IBM': 'IBM',\n    'TWX': 'Time Warner',\n    'CMCSA': 'Comcast',\n    'CVC': 'Cablevision',\n    'YHOO': 'Yahoo',\n    'DELL': 'Dell',\n    'HPQ': 'HP',\n    'AMZN': 'Amazon',\n    'TM': 'Toyota',\n    'CAJ': 'Canon',\n    'SNE': 'Sony',\n    'F': 'Ford',\n    'HMC': 'Honda',\n    'NAV': 'Navistar',\n    'NOC': 'Northrop Grumman',\n    'BA': 'Boeing',\n    'KO': 'Coca Cola',\n    'MMM': '3M',\n    'MCD': 'McDonald\\'s',\n    'PEP': 'Pepsi',\n    'K': 'Kellogg',\n    'UN': 'Unilever',\n    'MAR': 'Marriott',\n    'PG': 'Procter Gamble',\n    'CL': 'Colgate-Palmolive',\n    'GE': 'General Electrics',\n    'WFC': 'Wells Fargo',\n    'JPM': 'JPMorgan Chase',\n    'AIG': 'AIG',\n    'AXP': 'American express',\n    'BAC': 'Bank of America',\n    'GS': 'Goldman Sachs',\n    'AAPL': 'Apple',\n    'SAP': 'SAP',\n    'CSCO': 'Cisco',\n    'TXN': 'Texas Instruments',\n    'XRX': 'Xerox',\n    'WMT': 'Wal-Mart',\n    'HD': 'Home Depot',\n    'GSK': 'GlaxoSmithKline',\n    'PFE': 'Pfizer',\n    'SNY': 'Sanofi-Aventis',\n    'NVS': 'Novartis',\n    'KMB': 'Kimberly-Clark',\n    'R': 'Ryder',\n    'GD': 'General Dynamics',\n    'RTN': 'Raytheon',\n    'CVS': 'CVS',\n    'CAT': 'Caterpillar',\n    'DD': 'DuPont de Nemours'}\n\nsymbols, names = np.array(list(symbol_dict.items())).T\n\nquotes = [\n    quotes_historical_google(symbol, d1, d2) for symbol in symbols\n]\n\nclose_prices = np.stack([q['close'] for q in quotes])\nopen_prices = np.stack([q['open'] for q in quotes])\n\n# The daily variations of the quotes are what carry most information\nvariation = close_prices - open_prices"
       ]
     },
     {

dev/_downloads/auto_examples_python.zip

@@ -64,27 +64,59 @@
 # Author: Gael Varoquaux [email protected]
 # License: BSD 3 clause
 
-import datetime
+from datetime import datetime
 
 import numpy as np
-import matplotlib.pyplot as plt
-try:
-     from matplotlib.finance import quotes_historical_yahoo_ochl
-except ImportError:
-     # quotes_historical_yahoo_ochl was named quotes_historical_yahoo before matplotlib 1.4
-     from matplotlib.finance import quotes_historical_yahoo as quotes_historical_yahoo_ochl
+from matplotlib import pyplot as plt
 from matplotlib.collections import LineCollection
+from six.moves.urllib.request import urlopen
+from six.moves.urllib.parse import urlencode
 from sklearn import cluster, covariance, manifold
 
 ###############################################################################
 # Retrieve the data from Internet
 
+def quotes_historical_google(symbol, date1, date2):
+    """Get the historical data from Google finance.
+
+    Parameters
+    ----------
+    symbol : str
+        Ticker symbol to query for, for example ``"DELL"``.
+    date1 : datetime.datetime
+        Start date.
+    date2 : datetime.datetime
+        End date.
+
+    Returns
+    -------
+    X : array
+        The columns are ``date`` -- datetime, ``open``, ``high``,
+        ``low``, ``close`` and ``volume`` of type float.
+    """
+    params = urlencode({
+        'q': symbol,
+        'startdate': date1.strftime('%b %d, %Y'),
+        'enddate': date2.strftime('%b %d, %Y'),
+        'output': 'csv'
+    })
+    url = 'http://www.google.com/finance/historical?' + params
+    with urlopen(url) as response:
+        dtype = {
+            'names': ['date', 'open', 'high', 'low', 'close', 'volume'],
+            'formats': ['object', 'f4', 'f4', 'f4', 'f4', 'f4']
+        }
+        converters = {0: lambda s: datetime.strptime(s.decode(), '%d-%b-%y')}
+        return np.genfromtxt(response, delimiter=',', skip_header=1,
+                             dtype=dtype, converters=converters,
+                             missing_values='-', filling_values=-1)
+
+
 # Choose a time period reasonably 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)
+d1 = datetime(2003, 1, 1)
+d2 = datetime(2008, 1, 1)
 
-# kraft symbol has now changed from KFT to MDLZ in yahoo
 symbol_dict = {
     'TOT': 'Total',
     'XOM': 'Exxon',
@@ -102,7 +134,6 @@
     'AMZN': 'Amazon',
     'TM': 'Toyota',
     'CAJ': 'Canon',
-    'MTU': 'Mitsubishi',
     'SNE': 'Sony',
     'F': 'Ford',
     'HMC': 'Honda',
@@ -111,9 +142,8 @@
     'BA': 'Boeing',
     'KO': 'Coca Cola',
     'MMM': '3M',
-    'MCD': 'Mc Donalds',
+    'MCD': 'McDonald\'s',
     'PEP': 'Pepsi',
-    'MDLZ': 'Kraft Foods',
     'K': 'Kellogg',
     'UN': 'Unilever',
     'MAR': 'Marriott',
@@ -129,11 +159,9 @@
     'AAPL': 'Apple',
     'SAP': 'SAP',
     'CSCO': 'Cisco',
-    'TXN': 'Texas instruments',
+    'TXN': 'Texas Instruments',
     'XRX': 'Xerox',
-    'LMT': 'Lookheed Martin',
     'WMT': 'Wal-Mart',
-    'WBA': 'Walgreen',
     'HD': 'Home Depot',
     'GSK': 'GlaxoSmithKline',
     'PFE': 'Pfizer',
@@ -149,14 +177,16 @@
 
 symbols, names = np.array(list(symbol_dict.items())).T
 
-quotes = [quotes_historical_yahoo_ochl(symbol, d1, d2, asobject=True)
-          for symbol in symbols]
+quotes = [
+    quotes_historical_google(symbol, d1, d2) for symbol in symbols
+]
 
-open = np.array([q.open for q in quotes]).astype(np.float)
-close = np.array([q.close for q in quotes]).astype(np.float)
+close_prices = np.stack([q['close'] for q in quotes])
+open_prices = np.stack([q['open'] for q in quotes])
 
 # The daily variations of the quotes are what carry most information
-variation = close - open
+variation = close_prices - open_prices
+
 
 ###############################################################################
 # Learn a graphical structure from the correlations