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 fetch_yahoo(*args: str,
period: str = 'max',
multi_index: bool = False,
**kwargs: str):
df = None
if len(args) == 1:
df = __download_yahoo_data(args[0], period)
else:
# convert args to kwargs
if len(args) > 0:
kwargs = merge_kwargs({arg: arg for arg in args}, kwargs)
for k, v in kwargs.items():
px = f'{k}_'
df_ = __download_yahoo_data(v, period)
if multi_index:
df_.columns = pd.MultiIndex.from_product([[k], df_.columns])
if df is None:
df = df_
else:
df = inner_join(df, df_)
else:
if df is None:
df = df_.add_prefix(px)
else:
df = inner_join(df, df_, prefix=px)
# print some statistics
if df is None:
logging.warning("nothing downloaded")
else:
logging.info(
f'number of rows for joined dataframe = {len(df)}, from {df.index[0]} to {df.index[-1]}'
)
return df
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