def test_add_multi_index(self):
df = pd.DataFrame({}, index=[1, 2, 3, 4])
df1 = add_multi_index(df, "A", axis=0)
df2 = add_multi_index(df1, "B", axis=0, level=1)
df3 = add_multi_index(df1, "B", axis=0, level=2)
# print(df3)
self.assertListEqual(df1.index.to_list(), [("A", 1), ("A", 2),
("A", 3), ("A", 4)])
self.assertListEqual(df2.index.to_list(),
[("A", "B", 1), ("A", "B", 2), ("A", "B", 3),
("A", "B", 4)])
self.assertListEqual(df3.index.to_list(),
[(1, "A", "B"), (2, "A", "B"), (3, "A", "B"),
(4, "A", "B")])
def fetch_timeseries(providers: Dict[Callable[[Any], pd.DataFrame], List[str]],
start_date: str = None,
force_lower_case: bool = False,
multi_index: bool = None,
ffill: bool = False,
**kwargs):
symbol_type = (List, Tuple, Set)
expected_frames = sum(
len(s) if isinstance(s, symbol_type) else 1
for s in providers.values())
df = None
if multi_index is None and expected_frames > 1:
multi_index = True
for provider, symbols in providers.items():
# make sure provider is an actual provider -> a callable
if not callable(provider):
provider = PROVIDER_MAP[provider]
# make sure the symbols are iterable -> wrap single symbols into a list
if not isinstance(symbols, symbol_type):
symbols = [symbols]
# fetch all symbols of all providers (later we could do this in parallel)
for symbol in symbols:
_df = call_callable_dynamic_args(provider,
symbol,
multi_index=multi_index,
**kwargs)
if _df is None:
continue
if multi_index:
if not isinstance(_df.columns, pd.MultiIndex):
_df = add_multi_index(_df, symbol, True)
if force_lower_case:
_df.columns = pd.MultiIndex.from_tuples([
(h.lower(), c.lower())
for h, c in _df.columns.to_list()
])
else:
if isinstance(_df.columns, pd.MultiIndex):
_df.columns = [t[-1] for t in _df.columns.to_list()]
if force_lower_case:
_df.columns = [c.lower() for c in _df.columns.to_list()]
if df is None:
df = _df
else:
df = inner_join(df,
_df,
force_multi_index=multi_index,
ffill=ffill)
return df if start_date is None else df[start_date:]
def ta_multi_ma(df: _t.PatchedDataFrame, average_function='sma', period=12, factors=_np.linspace(1 - 0.2, 1 + 0.2, 5)) -> _t.PatchedDataFrame:
ma = {'sma': ta_sma, 'ema': ta_ema, 'wilder': ta_wilders}
res = _pd.DataFrame({}, index=df.index)
if df.ndim > 1:
res = None
for col in df.columns.to_list():
_df = ta_multi_ma(df[col], average_function, period, factors)
_df = add_multi_index(_df, col)
res = inner_join(res, _df, force_multi_index=True)
return res
for x in factors:
res[f"{df.name}_{average_function}({period})({x:.3f})"] = ma[average_function](df, period) * x
return res
def fetch_fred(symbols, multi_index=False):
if "FRED_API_KEY" not in os.environ:
raise ValueError(
"you need to set the environment variable `FRED_API_KEY`. You can get a key as described here:"
"https://github.com/mortada/fredapi")
fred = Fred()
df = None
if not isinstance(symbols, (List, Tuple, Iterator)):
symbols = [symbols]
for symbol in symbols:
series = fred.get_series(symbol)
if not series.name:
series.name = symbol
if df is None:
df = series.to_frame()
else:
df = df.join(series)
return add_multi_index(df, "FRED", True) if multi_index else df
def as_joined_frame(self):
frame = pd.concat([add_multi_index(flatten_multi_column_index(f, as_string=True), i) for i, f in enumerate(self._frames)], axis=1, join='outer')
frame.columns = frame.columns.to_list()
return frame
np.nans = np_nans
setattr(PandasObject, "_", property(lambda self: MLCompatibleValues(self)))
setattr(PandasObject, "inner_join", inner_join)
setattr(
PandasObject, "has_multi_index_columns", lambda self: isinstance(
self, pd.DataFrame) and isinstance(self.columns, pd.MultiIndex))
setattr(PandasObject, "has_multi_index_rows",
lambda self: isinstance(self.index, pd.MultiIndex))
setattr(pd.DataFrame, "to_frame", lambda self: self)
setattr(pd.DataFrame, "flatten_columns", flatten_multi_column_index)
setattr(pd.DataFrame, "unique_level_columns", unique_level_columns)
setattr(pd.DataFrame, "has_indexed_columns",
lambda self: has_indexed_columns(self))
setattr(pd.DataFrame, "add_multi_index",
lambda self, *args, **kwargs: add_multi_index(self, *args, **kwargs))
setattr(pd.Series, "add_multi_index",
lambda self, *args, **kwargs: add_multi_index(self, *args, **kwargs))
setattr(pd.MultiIndex, "unique_level",
lambda self, *args: unique_level(self, *args))
class Typing(object):
PatchedDataFrame = pd.DataFrame
PatchedSeries = pd.Series
PatchedPandas = Union[PatchedDataFrame, PatchedSeries]
AnyPandasObject = PandasObject
DataFrame = pd.DataFrame
Series = pd.Series
