def test_series_setitem(self):
s = self.ymd['A']
s[2000, 3] = np.nan
self.assert_(isnull(s[42:65]).all())
self.assert_(notnull(s[:42]).all())
self.assert_(notnull(s[65:]).all())
s[2000, 3, 10] = np.nan
self.assert_(isnull(s[49]))
def test_merge_int(self):
left = Series({'a': 1., 'b': 2., 'c': 3., 'd': 4})
right = Series({1: 11, 2: 22, 3: 33})
self.assert_(left.dtype == np.float_)
self.assert_(issubclass(right.dtype.type, np.integer))
merged = left.merge(right)
self.assert_(merged.dtype == np.float_)
self.assert_(isnull(merged['d']))
self.assert_(not isnull(merged['c']))
def test_merge_int(self):
left = Series({'a' : 1., 'b' : 2., 'c' : 3., 'd' : 4})
right = Series({1 : 11, 2 : 22, 3 : 33})
self.assert_(left.dtype == np.float_)
self.assert_(issubclass(right.dtype.type, np.integer))
merged = left.merge(right)
self.assert_(merged.dtype == np.float_)
self.assert_(isnull(merged['d']))
self.assert_(not isnull(merged['c']))
def _bucketpanel_by(series, xby, yby, xbins, ybins):
xby = xby.reindex(series.index)
yby = yby.reindex(series.index)
n = len(series)
# indices = np.arange(n)
xlabels = _bucket_labels(xby.reindex(series.index), xbins)
ylabels = _bucket_labels(yby.reindex(series.index), ybins)
labels = _uniquify(xlabels, ylabels, xbins, ybins)
mask = isnull(labels)
labels[mask] = -1
unique_labels = np.unique(labels)
bucketed = bucketcat(series, labels)
_ulist = list(labels)
index_map = dict((x, _ulist.index(x)) for x in unique_labels)
def relabel(key):
pos = index_map[key]
xlab = xlabels[pos]
ylab = ylabels[pos]
return '%sx%s' % (int(xlab) if notnull(xlab) else 'NULL',
int(ylab) if notnull(ylab) else 'NULL')
return bucketed.rename(columns=relabel)
def _bucketpanel_by(series, xby, yby, xbins, ybins):
xby = xby.reindex(series.index)
yby = yby.reindex(series.index)
n = len(series)
# indices = np.arange(n)
xlabels = _bucket_labels(xby.reindex(series.index), xbins)
ylabels = _bucket_labels(yby.reindex(series.index), ybins)
labels = _uniquify(xlabels, ylabels, xbins, ybins)
mask = isnull(labels)
labels[mask] = -1
unique_labels = np.unique(labels)
bucketed = bucketcat(series, labels)
_ulist = list(labels)
index_map = dict((x, _ulist.index(x)) for x in unique_labels)
def relabel(key):
pos = index_map[key]
xlab = xlabels[pos]
ylab = ylabels[pos]
return '%sx%s' % (int(xlab) if notnull(xlab) else 'NULL',
int(ylab) if notnull(ylab) else 'NULL')
return bucketed.rename(columns=relabel)
def predict(self,
beta=None,
x=None,
fill_value=None,
fill_method=None,
axis=0):
"""
Parameters
----------
beta : Series
x : Series or DataFrame
fill_value : scalar or dict, default None
fill_method : {'backfill', 'bfill', 'pad', 'ffill', None}, default None
axis : {0, 1}, default 0
See DataFrame.fillna for more details
Notes
-----
1. If both fill_value and fill_method are None then NaNs are dropped
(this is the default behavior)
2. An intercept will be automatically added to the new_y_values if
the model was fitted using an intercept
Returns
-------
Series of predicted values
"""
if beta is None and x is None:
return self.y_predict
if beta is None:
beta = self.beta
else:
beta = beta.reindex(self.beta.index)
if isnull(beta).any():
raise ValueError('Must supply betas for same variables')
if x is None:
x = self._x
orig_x = x
else:
orig_x = x
if fill_value is None and fill_method is None:
x = x.dropna(how='any')
else:
x = x.fillna(value=fill_value, method=fill_method, axis=axis)
if isinstance(x, Series):
x = DataFrame({'x': x})
if self._intercept:
x['intercept'] = 1.
x = x.reindex(columns=self._x.columns)
rs = np.dot(x.values, beta.values)
return Series(rs, x.index).reindex(orig_x.index)
def test_reindex_bool(self):
frame = DataMatrix(np.ones((10, 2), dtype=bool),
index=np.arange(0, 20, 2),
columns=[0, 2])
reindexed = frame.reindex(np.arange(10))
self.assert_(reindexed.values.dtype == np.float_)
self.assert_(np.isnan(reindexed[0][1]))
reindexed = frame.reindex(columns=range(3))
self.assert_(reindexed.values.dtype == np.float_)
self.assert_(isnull(reindexed[1]).all())
def format_query(sql, *args):
"""
"""
processed_args = []
for arg in args:
if isinstance(arg, float) and isnull(arg):
arg = None
formatter = _formatters[type(arg)]
processed_args.append(formatter(arg))
return sql % tuple(processed_args)
def format_query(sql, *args):
"""
"""
processed_args = []
for arg in args:
if isinstance(arg, float) and isnull(arg):
arg = None
formatter = _formatters[type(arg)]
processed_args.append(formatter(arg))
return sql % tuple(processed_args)
def predict(self, beta=None, x=None, fill_value=None,
fill_method=None, axis=0):
"""
Parameters
----------
beta : Series
x : Series or DataFrame
fill_value : scalar or dict, default None
fill_method : {'backfill', 'bfill', 'pad', 'ffill', None}, default None
axis : {0, 1}, default 0
See DataFrame.fillna for more details
Notes
-----
1. If both fill_value and fill_method are None then NaNs are dropped
(this is the default behavior)
2. An intercept will be automatically added to the new_y_values if
the model was fitted using an intercept
Returns
-------
Series of predicted values
"""
if beta is None and x is None:
return self.y_predict
if beta is None:
beta = self.beta
else:
beta = beta.reindex(self.beta.index)
if isnull(beta).any():
raise ValueError('Must supply betas for same variables')
if x is None:
x = self._x
orig_x = x
else:
orig_x = x
if fill_value is None and fill_method is None:
x = x.dropna(how='any')
else:
x = x.fillna(value=fill_value, method=fill_method, axis=axis)
if isinstance(x, Series):
x = DataFrame({'x': x})
if self._intercept:
x['intercept'] = 1.
x = x.reindex(columns=self._x.columns)
rs = np.dot(x.values, beta.values)
return Series(rs, x.index).reindex(orig_x.index)
def test_reindex_bool_pad(self):
# fail
ts = self.ts[5:]
bool_ts = Series(np.zeros(len(ts), dtype=bool), index=ts.index)
filled_bool = bool_ts.reindex(self.ts.index, fillMethod='pad')
self.assert_(isnull(filled_bool[:5]).all())
def wrapper(x):
if isnull(x).any():
return np.nan
return np.median(x)
def test_reindex_bool_pad(self):
# fail
ts = self.ts[5:]
bool_ts = Series(np.zeros(len(ts), dtype=bool), index=ts.index)
filled_bool = bool_ts.reindex(self.ts.index, fillMethod='pad')
self.assert_(isnull(filled_bool[:5]).all())