Fix floats for volume in data.history

catalyst/data/_equities.pyx

@@ -215,13 +215,11 @@ cpdef _read_bcolz_data(ctable_t table,
                 else:
                     continue
 
-        if column_name in ['open', 'high', 'low', 'close']:
+        if column_name in ['open', 'high', 'low', 'close', 'volume']:
             where_nan = (outbuf == 0)
             outbuf_as_float = outbuf.astype(float64) * .000000001
             outbuf_as_float[where_nan] = NAN
             results.append(outbuf_as_float)
-        elif column_name != 'volume':
-            results.append(outbuf.astype(uint32))
         else:
             results.append(outbuf)
     return results

catalyst/data/bundles/base.py

@@ -491,7 +491,7 @@ class BaseBundle(object):
                     data_frequency,
                 )
                 raw_data.index = pd.to_datetime(raw_data.index, utc=True)
-                raw_data.index = raw_data.index.tz_localize('UTC')
+                #raw_data.index = raw_data.index.tz_localize('UTC')
 
                 # Filter incoming data to fit start and end sessions.
                 raw_data = raw_data[

catalyst/data/dispatch_bar_reader.py

@@ -18,6 +18,7 @@ from numpy import (
     full,
     nan,
     int64,
+    float64,
     zeros
 )
 from six import iteritems, with_metaclass
@@ -70,7 +71,9 @@ class AssetDispatchBarReader(with_metaclass(ABCMeta)):
         return self._dt_window_size(start_dt, end_dt), num_sids
 
     def _make_raw_array_out(self, field, shape):
-        if field != 'volume' and field != 'sid':
+        if field == 'volume':
+            out = zeros(shape, dtype=float64)
+        elif field != 'sid':
             out = full(shape, nan)
         else:
             out = zeros(shape, dtype=int64)

catalyst/data/minute_bars.py

@@ -39,7 +39,7 @@ from catalyst.data._minute_bar_internal import (
 from catalyst.gens.sim_engine import NANOS_IN_MINUTE
 
 from catalyst.data.bar_reader import BarReader, NoDataOnDate
-from catalyst.data.us_equity_pricing import check_uint32_safe
+from catalyst.data.us_equity_pricing import check_uint64_safe
 from catalyst.utils.calendars import get_calendar
 from catalyst.utils.cli import maybe_show_progress
 from catalyst.utils.memoize import lazyval
@@ -52,7 +52,7 @@ FUTURES_MINUTES_PER_DAY = 1440
 
 DEFAULT_EXPECTEDLEN = US_EQUITIES_MINUTES_PER_DAY * 252 * 15
 
-OHLC_RATIO = 1000
+OHLC_RATIO = 100000000
 
 
 class BcolzMinuteOverlappingData(Exception):
@@ -114,15 +114,15 @@ def _sid_subdir_path(sid):
 
 
 def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
-    """Adapt OHLCV columns into uint32 columns.
+    """Adapt OHLCV columns into uint64 columns.
 
     Parameters
     ----------
     cols : dict
         A dict mapping each column name (open, high, low, close, volume)
-        to a float column to convert to uint32.
+        to a float column to convert to uint64.
     scale_factor : int
-        Factor to use to scale float values before converting to uint32.
+        Factor to use to scale float values before converting to uint64.
     sid : int
         Sid of the relevant asset, for logging.
     invalid_data_behavior : str
@@ -135,6 +135,7 @@ def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
     scaled_highs = np.nan_to_num(cols['high']) * scale_factor
     scaled_lows = np.nan_to_num(cols['low']) * scale_factor
     scaled_closes = np.nan_to_num(cols['close']) * scale_factor
+    scaled_volumes = np.nan_to_num(cols['volume']) * scale_factor
 
     exclude_mask = np.zeros_like(scaled_opens, dtype=bool)
 
@@ -143,11 +144,12 @@ def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
         ('high', scaled_highs),
         ('low', scaled_lows),
         ('close', scaled_closes),
+        ('volume', scaled_volumes),
     ]:
         max_val = scaled_col.max()
 
         try:
-            check_uint32_safe(max_val, col_name)
+            check_uint64_safe(max_val, col_name)
         except ValueError:
             if invalid_data_behavior == 'raise':
                 raise
@@ -155,20 +157,20 @@ def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
             if invalid_data_behavior == 'warn':
                 logger.warn(
                     'Values for sid={}, col={} contain some too large for '
-                    'uint32 (max={}), filtering them out',
+                    'uint64 (max={}), filtering them out',
                     sid, col_name, max_val,
                 )
 
             # We want to exclude all rows that have an unsafe value in
             # this column.
-            exclude_mask &= (scaled_col >= np.iinfo(np.uint32).max)
+            exclude_mask &= (scaled_col >= np.iinfo(np.uint64).max)
 
     # Convert all cols to uint32.
-    opens = scaled_opens.astype(np.uint32)
+    opens = scaled_opens.astype(np.uint64)
-    highs = scaled_highs.astype(np.uint32)
+    highs = scaled_highs.astype(np.uint64)
-    lows = scaled_lows.astype(np.uint32)
+    lows = scaled_lows.astype(np.uint64)
-    closes = scaled_closes.astype(np.uint32)
+    closes = scaled_closes.astype(np.uint64)
-    volumes = cols['volume'].astype(np.uint32)
+    volumes = scaled_volumes.astype(np.uint64)
 
     # Exclude rows with unsafe values by setting to zero.
     opens[exclude_mask] = 0
@@ -288,7 +290,7 @@ class BcolzMinuteBarMetadata(object):
         ohlc_ratio : int
             The default ratio by which to multiply the pricing data to
             convert the floats from floats to an integer to fit within
-            the np.uint32. If ohlc_ratios_per_sid is None or does not
+            the np.uint64. If ohlc_ratios_per_sid is None or does not
             contain a mapping for a given sid, this ratio is used.
         ohlc_ratios_per_sid : dict
              A dict mapping each sid in the output to the factor by
@@ -372,13 +374,13 @@ class BcolzMinuteBarWriter(object):
         The last trading session in the data set.
     default_ohlc_ratio : int, optional
         The default ratio by which to multiply the pricing data to
-        convert from floats to integers that fit within np.uint32. If
+        convert from floats to integers that fit within np.uint64. If
         ohlc_ratios_per_sid is None or does not contain a mapping for a
-        given sid, this ratio is used. Default is OHLC_RATIO (1000).
+        given sid, this ratio is used. Default is OHLC_RATIO (10^8).
     ohlc_ratios_per_sid : dict, optional
         A dict mapping each sid in the output to the ratio by which to
         multiply the pricing data to convert the floats from floats to
-        an integer to fit within the np.uint32.
+        an integer to fit within the np.uint64.
     expectedlen : int, optional
         The expected length of the dataset, used when creating the initial
         bcolz ctable.
@@ -401,11 +403,9 @@ class BcolzMinuteBarWriter(object):
     Each individual asset's data is stored as a bcolz table with a column for
     each pricing field: (open, high, low, close, volume)
 
-    The open, high, low, and close columns are integers which are 1000 times
+    The open, high, low, close and volume columns are integers which are 10^8 times
     the quoted price, so that the data can represented and stored as an
-    np.uint32, supporting market prices quoted up to the thousands place.
+    np.uint64, supporting market prices quoted up to the 1/10^8-th place.
-
-    volume is a np.uint32 with no mutation of the tens place.
 
     The 'index' for each individual asset are a repeating period of minutes of
     length `minutes_per_day` starting from each market open.
@@ -573,7 +573,7 @@ class BcolzMinuteBarWriter(object):
         if not os.path.exists(sid_containing_dirname):
             # Other sids may have already created the containing directory.
             os.makedirs(sid_containing_dirname)
-        initial_array = np.empty(0, np.uint32)
+        initial_array = np.empty(0, np.uint64)
         table = ctable(
             rootdir=path,
             columns=[
@@ -610,7 +610,7 @@ class BcolzMinuteBarWriter(object):
         minute_offset = len(table) % self._minutes_per_day
         num_to_prepend = numdays * self._minutes_per_day - minute_offset
 
-        prepend_array = np.zeros(num_to_prepend, np.uint32)
+        prepend_array = np.zeros(num_to_prepend, np.uint64)
         # Fill all OHLCV with zeros.
         table.append([prepend_array] * 5)
         table.flush()
@@ -815,11 +815,11 @@ class BcolzMinuteBarWriter(object):
 
         minutes_count = all_minutes_in_window.size
 
-        open_col = np.zeros(minutes_count, dtype=np.uint32)
+        open_col = np.zeros(minutes_count, dtype=np.uint64)
-        high_col = np.zeros(minutes_count, dtype=np.uint32)
+        high_col = np.zeros(minutes_count, dtype=np.uint64)
-        low_col = np.zeros(minutes_count, dtype=np.uint32)
+        low_col = np.zeros(minutes_count, dtype=np.uint64)
-        close_col = np.zeros(minutes_count, dtype=np.uint32)
+        close_col = np.zeros(minutes_count, dtype=np.uint64)
-        vol_col = np.zeros(minutes_count, dtype=np.uint32)
+        vol_col = np.zeros(minutes_count, dtype=np.uint64)
 
         dt_ixs = np.searchsorted(all_minutes_in_window.values,
                                  dts.astype('datetime64[ns]'))
@@ -1125,8 +1125,8 @@ class BcolzMinuteBarReader(MinuteBarReader):
             else:
                 return np.nan
 
-        if field != 'volume':
+        #if field != 'volume':
-            value *= self._ohlc_ratio_inverse_for_sid(sid)
+        value *= self._ohlc_ratio_inverse_for_sid(sid)
         return value
 
     def get_last_traded_dt(self, asset, dt):
@@ -1248,7 +1248,7 @@ class BcolzMinuteBarReader(MinuteBarReader):
             if field != 'volume':
                 out = np.full(shape, np.nan)
             else:
-                out = np.zeros(shape, dtype=np.uint32)
+                out = np.zeros(shape, dtype=np.float64)
 
             for i, sid in enumerate(sids):
                 carray = self._open_minute_file(field, sid)
@@ -1262,11 +1262,11 @@ class BcolzMinuteBarReader(MinuteBarReader):
                 where = values != 0
                 # first slice down to len(where) because we might not have
                 # written data for all the minutes requested
-                if field != 'volume':
+                #if field != 'volume':
-                    out[:len(where), i][where] = (
+                out[:len(where), i][where] = (
                         values[where] * self._ohlc_ratio_inverse_for_sid(sid))
-                else:
+                #else:
-                    out[:len(where), i][where] = values[where]
+                #    out[:len(where), i][where] = values[where]
 
             results.append(out)
         return results

catalyst/data/us_equity_pricing.py

@@ -441,7 +441,7 @@ class BcolzDailyBarWriter(object):
         dates = raw_data.index.values.astype('datetime64[s]')
         check_uint32_safe(dates.max().view(np.int64), 'day')
         processed['day'] = dates.astype('uint32')
-        processed['volume'] = raw_data.volume.astype('uint64')
+        processed['volume'] = (raw_data.volume * PRICE_ADJUSTMENT_FACTOR).astype('uint64')
         return ctable.fromdataframe(processed)
 
 
@@ -494,9 +494,8 @@ class BcolzDailyBarReader(SessionBarReader):
 
     The data in these columns is interpreted as follows:
 
-    - Price columns ('open', 'high', 'low', 'close') are interpreted as 1000 *
+    - Price columns ('open', 'high', 'low', 'close') and Volume are interpreted 
-      as-traded dollar value.
+      as 10^9 * as-traded dollar value.
-    - Volume is interpreted as as-traded volume.
     - Day is interpreted as seconds since midnight UTC, Jan 1, 1970.
     - Id is the asset id of the row.
 
@@ -762,13 +761,10 @@ class BcolzDailyBarReader(SessionBarReader):
         """
         ix = self.sid_day_index(sid, dt)
         price = self._spot_col(field)[ix]
-        if field != 'volume':
+        if field != 'volume' and price == 0:
-            if price == 0:
+            return nan
-                return nan
-            else:
-                return price / PRICE_ADJUSTMENT_FACTOR
         else:
-            return price
+            return price / PRICE_ADJUSTMENT_FACTOR
 
 
 class PanelBarReader(SessionBarReader):

etc/requirements.txt

@@ -1,7 +1,7 @@
 # Incompatible with earlier PIP versions
 pip>=7.1.0
 # bcolz fails to install if this is not in the build_requires.
-setuptools>18.0
+setuptools>36.0
 
 # Logging
 Logbook==0.12.5