Merge pull request #5492 from TomAugspurger/fred_multi_series

ENH: accept mutliple series for FRED DataReader

Author: jreback

doc/source/release.rst

@@ -220,6 +220,7 @@ Improvements to existing features
     option it is no longer possible to round trip Excel files with merged
     MultiIndex and Hierarchical Rows. Set the ``merge_cells`` to ``False`` to
     restore the previous behaviour.  (:issue:`5254`)
+  - The FRED DataReader now accepts multiple series (:issue`3413`)
 
 API Changes
 ~~~~~~~~~~~

doc/source/remote_data.rst

@@ -81,7 +81,9 @@ FRED
     gdp=web.DataReader("GDP", "fred", start, end)
     gdp.ix['2013-01-01']
 
-
+    # Multiple series:
+    inflation = web.DataReader(["CPIAUCSL", "CPILFESL"], "fred", start, end)
+    inflation.head()
 .. _remote_data.ff:
 
 Fama/French

pandas/io/data.py

@@ -17,7 +17,7 @@
 )
 import pandas.compat as compat
 from pandas import Panel, DataFrame, Series, read_csv, concat
-from pandas.core.common import PandasError
+from pandas.core.common import is_list_like, PandasError
 from pandas.io.parsers import TextParser
 from pandas.io.common import urlopen, ZipFile, urlencode
 from pandas.util.testing import _network_error_classes
@@ -41,8 +41,9 @@ def DataReader(name, data_source=None, start=None, end=None,
 
     Parameters
     ----------
-    name : str
-        the name of the dataset
+    name : str or list of strs
+        the name of the dataset. Some data sources (yahoo, google, fred) will
+        accept a list of names.
     data_source: str
         the data source ("yahoo", "google", "fred", or "ff")
     start : {datetime, None}
@@ -436,24 +437,37 @@ def get_data_fred(name, start=dt.datetime(2010, 1, 1),
     Date format is datetime
 
     Returns a DataFrame.
+
+    If multiple names are passed for "series" then the index of the
+    DataFrame is the outer join of the indicies of each series.
     """
     start, end = _sanitize_dates(start, end)
 
     fred_URL = "http://research.stlouisfed.org/fred2/series/"
 
-    url = fred_URL + '%s' % name + '/downloaddata/%s' % name + '.csv'
-    with urlopen(url) as resp:
-        data = read_csv(resp, index_col=0, parse_dates=True,
-                        header=None, skiprows=1, names=["DATE", name],
-                        na_values='.')
-    try:
-        return data.truncate(start, end)
-    except KeyError:
-        if data.ix[3].name[7:12] == 'Error':
-            raise IOError("Failed to get the data. Check that {0!r} is "
-                          "a valid FRED series.".format(name))
-        raise
+    if not is_list_like(name):
+        names = [name]
+    else:
+        names = name
 
+    urls = [fred_URL + '%s' % n + '/downloaddata/%s' % n + '.csv' for
+            n in names]
+
+    def fetch_data(url, name):
+        with urlopen(url) as resp:
+            data = read_csv(resp, index_col=0, parse_dates=True,
+                            header=None, skiprows=1, names=["DATE", name],
+                            na_values='.')
+        try:
+            return data.truncate(start, end)
+        except KeyError:
+            if data.ix[3].name[7:12] == 'Error':
+                raise IOError("Failed to get the data. Check that {0!r} is "
+                              "a valid FRED series.".format(name))
+            raise
+    df = concat([fetch_data(url, n) for url, n in zip(urls, names)],
+                axis=1, join='outer')
+    return df
 
 def get_data_famafrench(name):
     # path of zip files

pandas/io/tests/test_data.py

@@ -16,6 +16,10 @@
 import pandas.util.testing as tm
 from numpy.testing import assert_array_equal
 
+if compat.PY3:
+    from urllib.error import HTTPError
+else:
+    from urllib2 import HTTPError
 
 def _skip_if_no_lxml():
     try:
@@ -422,6 +426,24 @@ def test_invalid_series(self):
         name = "NOT A REAL SERIES"
         self.assertRaises(Exception, web.get_data_fred, name)
 
+    @network
+    def test_fred_multi(self):
+        names = ['CPIAUCSL', 'CPALTT01USQ661S', 'CPILFESL']
+        start = datetime(2010, 1, 1)
+        end = datetime(2013, 1, 27)
+
+        received = web.DataReader(names, "fred", start, end).head(1)
+        expected = DataFrame([[217.478, 0.99701529, 220.544]], columns=names,
+                             index=[pd.tslib.Timestamp('2010-01-01 00:00:00')])
+        expected.index.rename('DATE', inplace=True)
+        assert_frame_equal(received, expected, check_less_precise=True)
+
+    @network
+    def test_fred_multi_bad_series(self):
+
+        names = ['NOTAREALSERIES', 'CPIAUCSL', "ALSO FAKE"]
+        with tm.assertRaises(HTTPError):
+            DataReader(names, data_source="fred")
 
 if __name__ == '__main__':
     nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],