def rolling_corr_pairwise(df, window, min_periods=None):
"""
Computes pairwise rolling correlation matrices as Panel whose items are
dates
Parameters
----------
df : DataFrame
window : int
min_periods : int, default None
Returns
-------
correls : Panel
"""
from pandas import Panel
from collections import defaultdict
all_results = defaultdict(dict)
for i, k1 in enumerate(df.columns):
for k2 in df.columns[i:]:
corr = rolling_corr(df[k1], df[k2], window,
min_periods=min_periods)
all_results[k1][k2] = corr
all_results[k2][k1] = corr
return Panel.from_dict(all_results).swapaxes('items', 'major')
def rolling_corr_pairwise(df, window, min_periods=None):
"""
Computes pairwise rolling correlation matrices as Panel whose items are
dates
Parameters
----------
df : DataFrame
window : int
min_periods : int, default None
Returns
-------
correls : Panel
"""
from pandas import Panel
from collections import defaultdict
all_results = defaultdict(dict)
for i, k1 in enumerate(df.columns):
for k2 in df.columns[i:]:
corr = rolling_corr(df[k1], df[k2], window,
min_periods=min_periods)
all_results[k1][k2] = corr
all_results[k2][k1] = corr
return Panel.from_dict(all_results).swapaxes('items', 'major')
def rolling_corr_pairwise(df, window, min_periods=None):
"""
Computes pairwise rolling correlation matrices as Panel whose items are
dates.
Parameters
----------
df : DataFrame
window : int
Size of the moving window. This is the number of observations used for
calculating the statistic.
min_periods : int, default None
Minimum number of observations in window required to have a value
(otherwise result is NA).
Returns
-------
correls : Panel
"""
from pandas import Panel
from collections import defaultdict
all_results = defaultdict(dict)
for i, k1 in enumerate(df.columns):
for k2 in df.columns[i:]:
corr = rolling_corr(df[k1],
df[k2],
window,
min_periods=min_periods)
all_results[k1][k2] = corr
all_results[k2][k1] = corr
return Panel.from_dict(all_results).swapaxes('items', 'major')
def rolling_corr_pairwise(df, window, min_periods=None):
"""
Computes pairwise rolling correlation matrices as Panel whose items are
dates.
Parameters
----------
df : DataFrame
window : int
Size of the moving window. This is the number of observations used for
calculating the statistic.
min_periods : int, default None
Minimum number of observations in window required to have a value
(otherwise result is NA).
Returns
-------
correls : Panel
"""
from pandas import Panel
from collections import defaultdict
all_results = defaultdict(dict)
for i, k1 in enumerate(df.columns):
for k2 in df.columns[i:]:
corr = rolling_corr(df[k1], df[k2], window,
min_periods=min_periods)
all_results[k1][k2] = corr
all_results[k2][k1] = corr
return Panel.from_dict(all_results).swapaxes('items', 'major')
def _flex_binary_moment(arg1, arg2, f, pairwise=False):
if not (isinstance(arg1, (np.ndarray, Series, DataFrame)) and isinstance(arg2, (np.ndarray, Series, DataFrame))):
raise TypeError("arguments to moment function must be of type " "np.ndarray/Series/DataFrame")
if isinstance(arg1, (np.ndarray, Series)) and isinstance(arg2, (np.ndarray, Series)):
X, Y = _prep_binary(arg1, arg2)
return f(X, Y)
elif isinstance(arg1, DataFrame):
def dataframe_from_int_dict(data, frame_template):
result = DataFrame(data, index=frame_template.index)
result.columns = frame_template.columns[result.columns]
return result
results = {}
if isinstance(arg2, DataFrame):
if pairwise is False:
if arg1 is arg2:
# special case in order to handle duplicate column names
for i, col in enumerate(arg1.columns):
results[i] = f(arg1.iloc[:, i], arg2.iloc[:, i])
return dataframe_from_int_dict(results, arg1)
else:
if not arg1.columns.is_unique:
raise ValueError("'arg1' columns are not unique")
if not arg2.columns.is_unique:
raise ValueError("'arg2' columns are not unique")
X, Y = arg1.align(arg2, join="outer")
X = X + 0 * Y
Y = Y + 0 * X
res_columns = arg1.columns.union(arg2.columns)
for col in res_columns:
if col in X and col in Y:
results[col] = f(X[col], Y[col])
return DataFrame(results, index=X.index, columns=res_columns)
elif pairwise is True:
results = defaultdict(dict)
for i, k1 in enumerate(arg1.columns):
for j, k2 in enumerate(arg2.columns):
if j < i and arg2 is arg1:
# Symmetric case
results[i][j] = results[j][i]
else:
results[i][j] = f(*_prep_binary(arg1.iloc[:, i], arg2.iloc[:, j]))
p = Panel.from_dict(results).swapaxes("items", "major")
p.major_axis = arg1.columns[p.major_axis]
p.minor_axis = arg2.columns[p.minor_axis]
return p
else:
raise ValueError("'pairwise' is not True/False")
else:
results = {}
for i, col in enumerate(arg1.columns):
results[i] = f(*_prep_binary(arg1.iloc[:, i], arg2))
return dataframe_from_int_dict(results, arg1)
else:
return _flex_binary_moment(arg2, arg1, f)
def _flex_binary_moment(arg1, arg2, f, pairwise=False):
if not (isinstance(arg1, (np.ndarray, Series, DataFrame))
and isinstance(arg2, (np.ndarray, Series, DataFrame))):
raise TypeError("arguments to moment function must be of type "
"np.ndarray/Series/DataFrame")
if isinstance(arg1, (np.ndarray, Series)) and \
isinstance(arg2, (np.ndarray,Series)):
X, Y = _prep_binary(arg1, arg2)
return f(X, Y)
elif isinstance(arg1, DataFrame):
results = {}
if isinstance(arg2, DataFrame):
X, Y = arg1.align(arg2, join='outer')
if pairwise is False:
X = X + 0 * Y
Y = Y + 0 * X
res_columns = arg1.columns.union(arg2.columns)
for col in res_columns:
if col in X and col in Y:
results[col] = f(X[col], Y[col])
elif pairwise is True:
results = defaultdict(dict)
for i, k1 in enumerate(arg1.columns):
for j, k2 in enumerate(arg2.columns):
if j < i and arg2 is arg1:
# Symmetric case
results[k1][k2] = results[k2][k1]
else:
results[k1][k2] = f(
*_prep_binary(arg1[k1], arg2[k2]))
return Panel.from_dict(results).swapaxes('items', 'major')
else:
raise ValueError("'pairwise' is not True/False")
else:
res_columns = arg1.columns
X, Y = arg1.align(arg2, axis=0, join='outer')
results = {}
for col in res_columns:
results[col] = f(X[col], Y)
return DataFrame(results, index=X.index, columns=res_columns)
else:
return _flex_binary_moment(arg2, arg1, f)
def _flex_binary_moment(arg1, arg2, f, pairwise=False):
if not (isinstance(arg1,(np.ndarray, Series, DataFrame)) and
isinstance(arg2,(np.ndarray, Series, DataFrame))):
raise TypeError("arguments to moment function must be of type "
"np.ndarray/Series/DataFrame")
if isinstance(arg1, (np.ndarray, Series)) and \
isinstance(arg2, (np.ndarray,Series)):
X, Y = _prep_binary(arg1, arg2)
return f(X, Y)
elif isinstance(arg1, DataFrame):
results = {}
if isinstance(arg2, DataFrame):
X, Y = arg1.align(arg2, join='outer')
if pairwise is False:
X = X + 0 * Y
Y = Y + 0 * X
res_columns = arg1.columns.union(arg2.columns)
for col in res_columns:
if col in X and col in Y:
results[col] = f(X[col], Y[col])
elif pairwise is True:
results = defaultdict(dict)
for i, k1 in enumerate(arg1.columns):
for j, k2 in enumerate(arg2.columns):
if j<i and arg2 is arg1:
# Symmetric case
results[k1][k2] = results[k2][k1]
else:
results[k1][k2] = f(*_prep_binary(arg1[k1], arg2[k2]))
return Panel.from_dict(results).swapaxes('items', 'major')
else:
raise ValueError("'pairwise' is not True/False")
else:
res_columns = arg1.columns
X, Y = arg1.align(arg2, axis=0, join='outer')
results = {}
for col in res_columns:
results[col] = f(X[col], Y)
return DataFrame(results, index=X.index, columns=res_columns)
else:
return _flex_binary_moment(arg2, arg1, f)
def _flex_binary_moment(arg1, arg2, f, pairwise=False):
if not (isinstance(arg1, (np.ndarray, Series, DataFrame))
and isinstance(arg2, (np.ndarray, Series, DataFrame))):
raise TypeError("arguments to moment function must be of type "
"np.ndarray/Series/DataFrame")
if isinstance(arg1, (np.ndarray, Series)) and \
isinstance(arg2, (np.ndarray,Series)):
X, Y = _prep_binary(arg1, arg2)
return f(X, Y)
elif isinstance(arg1, DataFrame):
def dataframe_from_int_dict(data, frame_template):
result = DataFrame(data, index=frame_template.index)
result.columns = frame_template.columns[result.columns]
return result
results = {}
if isinstance(arg2, DataFrame):
if pairwise is False:
if arg1 is arg2:
# special case in order to handle duplicate column names
for i, col in enumerate(arg1.columns):
results[i] = f(arg1.iloc[:, i], arg2.iloc[:, i])
return dataframe_from_int_dict(results, arg1)
else:
if not arg1.columns.is_unique:
raise ValueError("'arg1' columns are not unique")
if not arg2.columns.is_unique:
raise ValueError("'arg2' columns are not unique")
X, Y = arg1.align(arg2, join='outer')
X = X + 0 * Y
Y = Y + 0 * X
res_columns = arg1.columns.union(arg2.columns)
for col in res_columns:
if col in X and col in Y:
results[col] = f(X[col], Y[col])
return DataFrame(results,
index=X.index,
columns=res_columns)
elif pairwise is True:
results = defaultdict(dict)
for i, k1 in enumerate(arg1.columns):
for j, k2 in enumerate(arg2.columns):
if j < i and arg2 is arg1:
# Symmetric case
results[i][j] = results[j][i]
else:
results[i][j] = f(
*_prep_binary(arg1.iloc[:, i], arg2.iloc[:,
j]))
p = Panel.from_dict(results).swapaxes('items', 'major')
p.major_axis = arg1.columns[p.major_axis]
p.minor_axis = arg2.columns[p.minor_axis]
return p
else:
raise ValueError("'pairwise' is not True/False")
else:
results = {}
for i, col in enumerate(arg1.columns):
results[i] = f(*_prep_binary(arg1.iloc[:, i], arg2))
return dataframe_from_int_dict(results, arg1)
else:
return _flex_binary_moment(arg2, arg1, f)
