1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
|
"""Rolling submenu of quantitative models for rolling statistics."""
from typing import List
import pandas as pd
from openbb_core.app.model.example import APIEx, PythonEx
from openbb_core.app.model.obbject import OBBject
from openbb_core.app.router import Router
from openbb_core.app.utils import (
basemodel_to_df,
df_to_basemodel,
get_target_column,
)
from openbb_core.provider.abstract.data import Data
from openbb_quantitative.statistics import (
kurtosis_,
mean_,
skew_,
std_dev_,
var_,
)
from pydantic import NonNegativeFloat
router = Router(prefix="/stats")
@router.command(
methods=["POST"],
examples=[
PythonEx(
description="Get Skewness.",
code=[
'stock_data = obb.equity.price.historical(symbol="TSLA", start_date="2023-01-01", provider="fmp").to_df()', # noqa: E501
'returns = stock_data["close"].pct_change().dropna()',
'obb.quantitative.stats.skew(data=returns, target="close")',
],
),
APIEx(
parameters={
"target": "close",
"data": APIEx.mock_data(
"timeseries",
sample={"date": "2023-01-01", "close": 0.05},
),
}
),
],
)
def skew(
data: List[Data],
target: str,
) -> OBBject[List[Data]]:
"""Get the skew of the data set.
Skew is a statistical measure that reveals the degree of asymmetry of a distribution around its mean.
Positive skewness indicates a distribution with an extended tail to the right, while negative skewness shows a tail
that stretches left. Understanding skewness can provide insights into potential biases in data and help anticipate
the nature of future data points. It's particularly useful for identifying the likelihood of extreme outcomes in
financial returns, enabling more informed decision-making based on the distribution's shape over a specified period.
Parameters
----------
data : List[Data]
Time series data.
target : str
Target column name.
Returns
-------
OBBject[List[Data]]
Rolling skew.
"""
df = basemodel_to_df(data)
series_target = get_target_column(df, target)
results = pd.DataFrame([skew_(series_target)], columns=["skew"])
results = df_to_basemodel(results)
return OBBject(results=results)
@router.command(
methods=["POST"],
examples=[
PythonEx(
description="Get Variance.",
code=[
'stock_data = obb.equity.price.historical(symbol="TSLA", start_date="2023-01-01", provider="fmp").to_df()', # noqa: E501
'returns = stock_data["close"].pct_change().dropna()',
'obb.quantitative.stats.variance(data=returns, target="close")',
],
),
APIEx(
parameters={
"target": "close",
"data": APIEx.mock_data(
"timeseries",
sample={"date": "2023-01-01", "close": 0.05},
),
}
),
],
)
def variance(data: List[Data], target: str) -> OBBject[List[Data]]:
"""
Calculate the variance of a target column.
Variance measures the dispersion of a set of data points around their mean. It is a key metric for
assessing the volatility and stability of financial returns or other time series data.
Parameters
----------
data: List[Data]
The time series data as a list of data points.
target: str
The name of the column for which to calculate variance.
Returns
-------
OBBject[List[Data]]
An object containing the rolling variance values.
"""
df = basemodel_to_df(data)
series_target = get_target_column(df, target)
results = pd.DataFrame([var_(series_target)], columns=["variance"])
results = df_to_basemodel(results)
return OBBject(results=results)
@router.command(
methods=["POST"],
examples=[
PythonEx(
description="Get Standard Deviation.",
code=[
'stock_data = obb.equity.price.historical(symbol="TSLA", start_date="2023-01-01", provider="fmp").to_df()', # noqa: E501
'returns = stock_data["close"].pct_change().dropna()',
'obb.quantitative.stats.stdev(data=returns, target="close")',
],
),
APIEx(
parameters={
"target": "close",
"data": APIEx.mock_data(
"timeseries",
sample={"date": "2023-01-01", "close": 0.05},
),
}
),
],
)
def stdev(data: List[Data], target: str) -> OBBject[List[Data]]:
"""
Calculate the rolling standard deviation of a target column.
Standard deviation is a measure of the amount of variation or dispersion of a set of values.
It is widely used to assess the risk and volatility of financial returns or other time series data
It is the square root of the variance.
Parameters
----------
data: List[Data]
The time series data as a list of data points.
target: str
The name of the column for which to calculate standard deviation.
Returns
-------
OBBject[List[Data]]
An object containing the rolling standard deviation values.
"""
df = basemodel_to_df(data)
series_target = get_target_column(df, target)
results = pd.DataFrame([std_dev_(series_target)], columns=["stdev"])
results = df_to_basemodel(results)
return OBBject(results=results)
@router.command(
methods=["POST"],
examples=[
PythonEx(
description="Get Kurtosis.",
code=[
'stock_data = obb.equity.price.historical(symbol="TSLA", start_date="2023-01-01", provider="fmp").to_df()', # noqa: E501
'returns = stock_data["close"].pct_change().dropna()',
'obb.quantitative.stats.kurtosis(data=returns, target="close")',
],
),
APIEx(
parameters={
"target": "close",
"data": APIEx.mock_data(
"timeseries",
sample={"date": "2023-01-01", "close": 0.05},
),
}
),
],
)
def kurtosis(data: List[Data], target: str) -> OBBject[List[Data]]:
"""
Calculate the rolling kurtosis of a target column.
Kurtosis measures the "tailedness" of the probability distribution of a real-valued random variable.
High kurtosis indicates a distribution with heavy tails (outliers), suggesting a higher risk of extreme outcomes.
Low kurtosis indicates a distribution with lighter tails (less outliers), suggesting less risk of extreme outcomes.
This function helps in assessing the risk of outliers in financial returns or other time series data.
Parameters
----------
data: List[Data]
The time series data as a list of data points.
target: str
The name of the column for which to calculate kurtosis.
Returns
-------
OBBject[List[Data]]
An object containing the kurtosis value
"""
df = basemodel_to_df(data)
series_target = get_target_column(df, target)
results = pd.DataFrame([kurtosis_(series_target)], columns=["kurtosis"])
results = df_to_basemodel(results)
return OBBject(results=results)
@router.command(
methods=["POST"],
examples=[
PythonEx(
description="Get Quantile.",
code=[
'stock_data = obb.equity.price.historical(symbol="TSLA", start_date="2023-01-01", provider="fmp").to_df()', # noqa: E501
'returns = stock_data["close"].pct_change().dropna()',
'obb.quantitative.stats.quantile(data=returns, target="close", quantile_pct=0.75)',
],
),
APIEx(
parameters={
"target": "close",
"data": APIEx.mock_data(
"timeseries",
sample={"date": "2023-01-01", "close": 0.05},
),
}
),
],
)
def quantile(
data: List[Data],
target: str,
quantile_pct: NonNegativeFloat = 0.5,
) -> OBBject[List[Data]]:
"""
Calculate the quantile of a target column at a specified quantile percentage.
Quantiles are points dividing the range of a probability distribution into intervals with equal probabilities,
or dividing the sample in the same way.
Parameters
----------
data: List[Data]
The time series data as a list of data points.
target: str
The name of the column for which to calculate the quantile.
quantile_pct: NonNegativeFloat, optional
The quantile percentage to calculate (e.g., 0.5 for median), default is 0.5.
Returns
-------
OBBject[List[Data]]
An object containing the rolling quantile values with the median.
"""
df = basemodel_to_df(
data,
)
series_target = get_target_column(df, target)
results = pd.DataFrame(
[series_target.quantile(quantile_pct)], columns=[f"{quantile_pct}_quantile"]
)
results = df_to_basemodel(results)
return OBBject(results=results)
@router.command(
methods=["POST"],
examples=[
PythonEx(
description="Get Mean.",
code=[
'stock_data = obb.equity.price.historical(symbol="TSLA", start_date="2023-01-01", provider="fmp").to_df()', # noqa: E501
'returns = stock_data["close"].pct_change().dropna()',
'obb.quantitative.stats.mean(data=returns, target="close")',
],
),
APIEx(
parameters={
"target": "close",
"data": APIEx.mock_data(
"timeseries",
sample={"date": "2023-01-01", "close": 0.05},
),
}
),
],
)
def mean(
data: List[Data],
target: str,
) -> OBBject[List[Data]]:
"""
Calculate the mean (average) of a target column.
The rolling mean is a simple moving average that calculates the average of a target variable.
This function is widely used in financial analysis to smooth short-term fluctuations and highlight longer-term trends
or cycles in time series data.
Parameters
----------
data: List[Data]
The time series data as a list of data points.
target: str
The name of the column for which to calculate the mean.
Returns
-------
OBBject[List[Data]]
An object containing the mean value.
"""
df = basemodel_to_df(data)
|
