ENH: TrueFX tick datareader

pandas_datareader/data.py

@@ -18,6 +18,7 @@
 from pandas_datareader.famafrench import FamaFrenchReader
 from pandas_datareader.oecd import OECDReader
 from pandas_datareader.edgar import EdgarIndexReader
+from pandas_datareader.truefx import TrueFXReader
 
 
 def get_data_fred(*args, **kwargs):
@@ -141,6 +142,9 @@ def DataReader(name, data_source=None, start=None, end=None,
         return EdgarIndexReader(symbols=name, start=start, end=end,
                                 retry_count=retry_count, pause=pause,
                                 session=session).read()
+    elif data_source == "truefx":
+        return TrueFXReader(retry_count=retry_count, pause=pause,
+                                session=session).read(symbols=name, start=start, end=end)
     else:
         msg = "data_source=%r is not implemented" % data_source
         raise NotImplementedError(msg)

pandas_datareader/tests/test_truefx.py

@@ -0,0 +1,32 @@
+import os
+import pandas as pd
+import pandas.util.testing as tm
+import pandas_datareader.data as web
+from pandas_datareader.truefx import TrueFXReader
+
+class TestTrueFX(tm.TestCase):
+    def setUp(self):
+        if os.getenv('USE_REQUESTS_CACHE', '0') == '1':
+            import requests_cache
+            from datetime import timedelta
+            self.session = requests_cache.CachedSession(cache_name='cache', expire_after=timedelta(days=30))
+        else:
+            self.session = None
+        self.dr = TrueFXReader(retry_count=3, pause=0.001, session=self.session)
+
+    def test_url(self):
+        expected = 'http://www.truefx.com/dev/data/2014/JANUARY-2014/AUDUSD-2014-01.zip'
+        tm.assert_equal(self.dr.url('AUDUSD', 2014, 1), expected)
+
+    def test_filename_csv(self):
+        expected = 'AUDUSD-2014-01.csv'
+        tm.assert_equal(self.dr._filename_csv('AUDUSD', 2014, 1), expected)
+
+    def test_get_truefx_datareader(self):
+        df = web.DataReader('AUD/USD', 'truefx', '2014-01-01', '2014-02-28', session=self.session)
+        tm.assert_almost_equal(df.loc['2014-01-01 21:55:34.404', 'Ask'], 0.88922)
+        tm.assert_almost_equal(df.loc['2014-02-03 00:03:38.169', 'Ask'], 0.87524)
+
+if __name__ == '__main__':
+    import nose
+    nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'], exit=False)

pandas_datareader/truefx.py

@@ -0,0 +1,69 @@
+import logging
+logger = logging.getLogger(__name__)
+
+import datetime
+
+import pandas as pd
+import pandas.compat as compat
+from pandas.io.common import ZipFile
+
+from pandas_datareader.base import _BaseReader
+
+class TrueFXReader(_BaseReader):
+
+    """Get data from TrueFX"""
+
+    def __init__(self, retry_count=3, pause=0.001, session=None):
+        if not isinstance(retry_count, int) or retry_count < 0:
+            raise ValueError("'retry_count' must be integer larger than 0")
+        self.retry_count = retry_count
+        self.pause = pause
+        self.session = self._init_session(session, retry_count)
+
+    def url(self, symbol, year, month):
+        month_name = datetime.datetime(year=year, month=month, day=1).strftime('%B').upper()
+        return 'http://www.truefx.com/dev/data/{year:04d}/{month_name}-{year:04d}/{symbol}-{year:04d}-{month:02d}.zip'.format(year=year, month=month, symbol=symbol, month_name=month_name)
+
+    def _sanitize_symbol(self, symbol):
+        return symbol.replace("/", "").upper()
+
+    def _filename_csv(self, symbol, year, month):
+        return "{symbol}-{year:04d}-{month:02d}.csv".format(year=year, month=month, symbol=symbol)
+
+    def read(self, symbols, start, end):
+        """ read data """
+        start, end = self._sanitize_dates(start, end)
+        # If a single symbol, (e.g., 'GOOG')
+        if isinstance(symbols, (compat.string_types, int)):
+            df = self._read_several_months(symbols, start, end)
+        # Or multiple symbols, (e.g., ['GOOG', 'AAPL', 'MSFT'])
+        else:
+            raise NotImplementedError("Can't download several symbols")
+        return df
+
+    def _read_one_month(self, symbol, year, month):
+        url = self.url(symbol, year, month)
+        symbol = symbol.replace("/", "").upper()
+
+        logger.debug("querying '%s'" % url)
+        response = self.session.get(url)
+        zip_data = compat.BytesIO(response.content)
+
+        with ZipFile(zip_data, 'r') as zf:
+            zfile = zf.open(self._filename_csv(symbol, year, month))
+            df = pd.read_csv(zfile, names=['Symbol', 'Date', 'Bid', 'Ask'])
+
+        df['Date'] = pd.to_datetime(df['Date'], format='%Y%m%d %H:%M:%S.%f')
+        df = df.set_index('Date')
+
+        return df
+
+    def _read_several_months(self, symbol, start, end):
+        symbol = self._sanitize_symbol(symbol)
+        months = pd.date_range(start, end, freq='MS')
+        lst = []
+        for dt in months:
+            year, month = dt.year, dt.month
+            df = self._read_one_month(symbol, year, month)
+            lst.append(df)
+        return pd.concat(lst)