Merge pull request #157 from e2thenegpii/master

Added webscraper for Thrift Savings Plan

Author: davidastephens

docs/source/remote_data.rst

@@ -30,6 +30,7 @@ Currently the following sources are supported:
     - :ref:`World Bank<remote_data.wb>`
     - :ref:`OECD<remote_data.oecd>`
     - :ref:`Eurostat<remote_data.eurostat>`
+    - :ref:`Thrift Savings Plan<remote_data.tsp>`
 
 It should be noted, that various sources support different kinds of data, so not all sources implement the same methods and the data elements returned might also differ.
 
@@ -422,3 +423,16 @@ reconnect after waiting a few minutes.
     import pandas_datareader.data as web
     ed = web.DataReader('daily', 'edgar-index', '1998-05-18', '1998-05-18')
     ed[:5]
+
+.. _remote_data.tsp:
+
+TSP Fund Data
+
+Download mutual fund index prices for the TSP.
+
+.. ipython:: python
+
+    import pandas_datareader.tsp as tsp
+    tspreader = tsp.TSPReader(start='2015-10-1', end='2015-12-31')
+    tspreader.read()
+

docs/source/whatsnew.rst

@@ -18,6 +18,7 @@ What's New
 
 These are new features and improvements of note in each release.
 
+.. include:: whatsnew/v0.2.3.txt
 .. include:: whatsnew/v0.2.2.txt
 .. include:: whatsnew/v0.2.1.txt
 .. include:: whatsnew/v0.2.0.txt

docs/source/whatsnew/v0.2.3.txt

@@ -0,0 +1,31 @@
+.. _whatsnew_023:
+
+v0.2.3 (XXX)
+----------------------------
+
+This is a minor release from 0.2.2 and includes new features.
+
+
+Highlights include:
+
+
+.. contents:: What's new in v0.2.3
+    :local:
+    :backlinks: none
+
+.. _whatsnew_023.enhancements:
+
+New features
+~~~~~~~~~~~~
+
+- ``DataReader`` now supports pulling data for the TSP.
+
+.. _whatsnew_023.api_breaking:
+
+Backwards incompatible API changes
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. _whatsnew_023.bug_fixes:
+
+Bug Fixes
+~~~~~~~~~

pandas_datareader/base.py

@@ -91,14 +91,22 @@ def _read_url_as_StringIO(self, url, params=None):
         Open url (and retry)
         """
         response = self._get_response(url, params=params)
+        text = self._sanitize_response(response)
         out = StringIO()
-        if isinstance(response.content, compat.binary_type):
-            out.write(bytes_to_str(response.content))
+        if isinstance(text, compat.binary_type):
+            out.write(bytes_to_str(text))
         else:
-            out.write(response.content)
+            out.write(text)
         out.seek(0)
         return out
 
+    @staticmethod
+    def _sanitize_response(response):
+        """
+        Hook to allow subclasses to clean up response data
+        """
+        return response.content
+
     def _get_response(self, url, params=None):
         """ send raw HTTP request to get requests.Response from the specified url
         Parameters

pandas_datareader/tests/test_base.py

@@ -0,0 +1,32 @@
+import nose
+import pandas.util.testing as tm
+import pandas_datareader.base as base
+
+
+class TestBaseReader(tm.TestCase):
+    def test_valid_retry_count(self):
+        with tm.assertRaises(ValueError):
+            base._BaseReader([], retry_count='stuff')
+        with tm.assertRaises(ValueError):
+            base._BaseReader([], retry_count=-1)
+
+    def test_invalid_url(self):
+        with tm.assertRaises(NotImplementedError):
+            base._BaseReader([]).url
+
+    def test_invalid_format(self):
+        with tm.assertRaises(NotImplementedError):
+            b = base._BaseReader([])
+            b._format = 'IM_NOT_AN_IMPLEMENTED_TYPE'
+            b._read_one_data('a', None)
+
+
+class TestDailyBaseReader(tm.TestCase):
+    def test_get_params(self):
+        with tm.assertRaises(NotImplementedError):
+            b = base._DailyBaseReader()
+            b._get_params()
+
+if __name__ == '__main__':
+    nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],
+                   exit=False)

pandas_datareader/tests/test_tsp.py

@@ -0,0 +1,29 @@
+import nose
+import pandas.util.testing as tm
+import datetime as dt
+
+import pandas_datareader.tsp as tsp
+
+
+class TestTSPFunds(tm.TestCase):
+    def test_get_allfunds(self):
+        tspdata = tsp.TSPReader(start='2015-11-2', end='2015-11-2').read()
+
+        assert len(tspdata == 1)
+
+        assert round(tspdata['I Fund'][dt.date(2015, 11, 2)], 5) == 25.0058
+
+    def test_sanitize_response(self):
+        class response(object):
+            pass
+        r = response()
+        r.text = ' , '
+        ret = tsp.TSPReader._sanitize_response(r)
+        assert ret == ''
+        r.text = ' a,b '
+        ret = tsp.TSPReader._sanitize_response(r)
+        assert ret == 'a,b'
+
+if __name__ == '__main__':
+    nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],
+                   exit=False)

pandas_datareader/tsp.py

@@ -0,0 +1,64 @@
+from pandas_datareader.base import _BaseReader
+
+
+class TSPReader(_BaseReader):
+
+    """
+    Returns DataFrame of historical TSP fund prices from symbols, over date
+    range, start to end.
+
+    Parameters
+    ----------
+    symbols : string, array-like object (list, tuple, Series), or DataFrame
+        Single stock symbol (ticker), array-like object of symbols or
+        DataFrame with index containing stock symbols.
+    start : string, (defaults to '1/1/2010')
+        Starting date, timestamp. Parses many different kind of date
+        representations (e.g., 'JAN-01-2010', '1/1/10', 'Jan, 1, 1980')
+    end : string, (defaults to today)
+        Ending date, timestamp. Same format as starting date.
+    retry_count : int, default 3
+        Number of times to retry query request.
+    pause : int, default 0
+        Time, in seconds, to pause between consecutive queries of chunks. If
+        single value given for symbol, represents the pause between retries.
+    session : Session, default None
+        requests.sessions.Session instance to be used
+    """
+
+    def __init__(self,
+                 symbols=['Linc', 'L2020', 'L2030', 'L2040', 'L2050', 'G', 'F', 'C', 'S', 'I'],
+                 start=None, end=None, retry_count=3, pause=0.001,
+                 session=None):
+        super(TSPReader, self).__init__(symbols=symbols,
+                                        start=start, end=end,
+                                        retry_count=retry_count,
+                                        pause=pause, session=session)
+        self._format = 'string'
+
+    @property
+    def url(self):
+        return 'https://www.tsp.gov/InvestmentFunds/FundPerformance/index.html'
+
+    def read(self):
+        """ read one data from specified URL """
+        df = super(TSPReader, self).read()
+        df.columns = map(lambda x: x.strip(), df.columns)
+        return df
+
+    @property
+    def params(self):
+        return {'startdate': self.start.strftime('%m/%d/%Y'),
+                'enddate': self.end.strftime('%m/%d/%Y'),
+                'fundgroup': self.symbols,
+                'whichButton': 'CSV'}
+
+    @staticmethod
+    def _sanitize_response(response):
+        """
+        Clean up the response string
+        """
+        text = response.text.strip()
+        if text[-1] == ',':
+            return text[0:-1]
+        return text

setup.py

@@ -24,7 +24,7 @@ def readme():
         return f.read()
 
 INSTALL_REQUIRES = (
-    ['pandas', 'requests', 'requests-file', 'requests-ftp']
+    ['pandas', 'requests>=2.3.0', 'requests-file', 'requests-ftp']
 )
 
 setup(