General improvements

catalyst/data/bundles/poloniex.py

@@ -115,12 +115,13 @@ def poloniex_cryptoassets(symbols, start=None, end=None):
                     day_data.volume.sum(),   # sum of all volumes
                 )
 
-            # scale to allow trading 100-ths of a coin
-            daily_bars.loc[:, 'open'] /= 100.0
-            daily_bars.loc[:, 'high'] /= 100.0
-            daily_bars.loc[:, 'low'] /= 100.0
-            daily_bars.loc[:, 'close'] /= 100.0
-            daily_bars.loc[:, 'volume'] *= 100.0
+            # scale to allow trading 10-ths of a coin
+            scale = 10.0
+            daily_bars.loc[:, 'open'] /= scale
+            daily_bars.loc[:, 'high'] /= scale
+            daily_bars.loc[:, 'low'] /= scale
+            daily_bars.loc[:, 'close'] /= scale
+            daily_bars.loc[:, 'volume'] *= scale
             
             return daily_bars
 
@@ -171,8 +172,10 @@ def poloniex_cryptoassets(symbols, start=None, end=None):
                     yield sid, daily_bars
                     sid += 1
 
-
-        daily_bar_writer.write(_pricing_iter())
+        daily_bar_writer.write(
+            _pricing_iter(),
+            assets=metadata.symbol.index,
+        )
 
         symbol_map = pd.Series(metadata.symbol.index, metadata.symbol)
 

catalyst/data/bundles/quandl.py

@@ -5,6 +5,7 @@ from io import BytesIO
 from itertools import count
 import tarfile
 from time import time, sleep
+from datetime import datetime
 
 from click import progressbar
 from logbook import Logger
@@ -36,10 +37,17 @@ def _fetch_raw_metadata(api_key, cache, retries, environ):
                 try:
                     raw = pd.read_csv(
                         format_metadata_url(api_key, page_number),
+                        date_parser=pd.tseries.tools.to_datetime,
                         parse_dates=[
                             'oldest_available_date',
                             'newest_available_date',
                         ],
+                        dtypes={
+                            'dataset_code': 'int',
+                            'name': 'str',
+                            'oldest_available_date': 'str',
+                            'newest_available_date': 'str',
+                        },
                         usecols=[
                             'dataset_code',
                             'name',
@@ -126,6 +134,10 @@ def fetch_symbol_metadata_frame(api_key,
     # we need to escape the paren because it is actually splitting on a regex
     data.asset_name = data.asset_name.str.split(r' \(', 1).str.get(0)
     data['exchange'] = 'QUANDL'
+
+    data['start_date'] = data['start_date'].astype(datetime)
+    data['end_date'] = data['end_date'].astype(datetime)
+
     data['auto_close_date'] = data['end_date'] + pd.Timedelta(days=1)
     return data
 
@@ -313,6 +325,7 @@ def quandl_bundle(environ,
             dividends,
             environ.get('QUANDL_DOWNLOAD_ATTEMPTS', 5),
         ),
+        assets=metadata.index,
         show_progress=show_progress,
     )
     adjustment_writer.write(

catalyst/data/loader.py

@@ -300,12 +300,13 @@ def ensure_crypto_benchmark_data(symbol, first_date, last_date, now,
                 day_data.volume.sum(),   # sum of all volumes
             )
 
-        # scale to allow trading 100-ths of a coin
-        daily_bars.loc[:, 'open'] /= 100.0
-        daily_bars.loc[:, 'high'] /= 100.0
-        daily_bars.loc[:, 'low'] /= 100.0
-        daily_bars.loc[:, 'close'] /= 100.0
-        daily_bars.loc[:, 'volume'] *= 100.0
+        # scale to allow trading 10-ths of a coin
+        scale = 10.0
+        daily_bars.loc[:, 'open'] /= scale
+        daily_bars.loc[:, 'high'] /= scale
+        daily_bars.loc[:, 'low'] /= scale
+        daily_bars.loc[:, 'close'] /= scale
+        daily_bars.loc[:, 'volume'] *= scale
         
         return daily_bars