https://github.com/ag-ds-bubble/tseuler
A library for Time-Series exploration, analysis & modelling.
https://github.com/ag-ds-bubble/tseuler
analysis dashboard exploratory-data-analysis forecasting jupyter-notebook mathematical-modelling modelling python3 statistical-models statistics time-series
Last synced: 4 months ago
JSON representation
A library for Time-Series exploration, analysis & modelling.
- Host: GitHub
- URL: https://github.com/ag-ds-bubble/tseuler
- Owner: ag-ds-bubble
- License: bsd-3-clause
- Created: 2020-12-05T10:30:40.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2020-12-10T15:55:49.000Z (over 5 years ago)
- Last Synced: 2025-09-01T14:15:36.307Z (10 months ago)
- Topics: analysis, dashboard, exploratory-data-analysis, forecasting, jupyter-notebook, mathematical-modelling, modelling, python3, statistical-models, statistics, time-series
- Language: Python
- Homepage:
- Size: 28 MB
- Stars: 17
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# tseuler
A library for Time Series exploration, analysis & modelling. This includes -
As of now, this libray is in pre-alpha phase, i.e there is a lot of work still left before its first stable release.
### TSMAD - Time Series Mini Analysis DashBoard.
Functionalities Include
- A mini Dashboard for Time Series Analysis, with multiple variations to each kind of analysis
- Inbuilt Freqency Variation analysis
- Intervention Analysis (In Future)
### TSSTATS - Time Series Statistical & Modelling Functions
Functionalities Include:
- Rolling Origin Framework (Currently Supports - statsmodels, sklearn, sklearn) for both multi-variate and uni-variate
- Residual Diagnostics
- Statistical Tests
- Entropy Calculations
- Intervention Analysis (In Future)
## Example
****
## Installation
****
Installation
```py
pip install tseuler
```
## Usage
****
- ### Instantiating a DashBoard
```py
import pandas as pd
import tseuler as tse
# Read the Time Series DataFrame
dataDF = pd.read_csv('Raw Data/stocks_data.csv', index_col=0)
tsmadObj = tse.TSMAD(tsdata = dataDF, data_desc = 'Stocks Data',
target_columns = ['close'], categorical_columns = ['Name'],
dt_format = '%Y-%m-%d', dt_freq = 'B',
how_aggregate = {'open':'first', 'high':'max', 'low':'min', 'close':'last'},
force_interactive = True)
tsmadObj.get_board()
```
`tseuler` has been built upon:-
****
- pandas
- numpy
- panel
- altair
- matplotlib
- statsmodels
## History
****
v0.0.4dev0 : Development Package
- Added TSMAD
- Added TSSTATS