Victor Barros
FOR ACADEMIC USE ONLY!!!
This project aims to create a value forecasting model based on historical data using time series techniques.
Here are the technologies used in this project:
- Python with the following libraries:
os
for system commandspathlib
for file system path manipulationtextwrap
(useful for text formatting in command-line interfaces)numpy
for mathematical operations (e.g., sqrt, abs, ...)pandas
for CSV data manipulationgoogle.generativeai
for utilizing Geminihashlib
for secure hash calculation and message digestsuser_data
from Google Colab to retrieve theGOOGLE_API_KEY
display
andMarkdown
from IPython for displaying formatted contentLinearRegression
fromsklearn
for linear regressiondata_table
from Google Colab for table formatting
- Google Colab Notebook
Open Google Colab Notebooks: https://colab.research.google.com/drive/1ZqX9SHqcRmn2RPC2bVPPQwBufXyWZuiQ?authuser=0#scrollTo=Io4_kLs-URlW
Despite the small size of the time series dataset, both predictions were approximately correct. Our conclusion is that the provided data demonstrates the use of Google Gemini, but the low sample quantity may impact the classifier's accuracy.
-
Utilize the following libraries:
tensorflow
for neural networkskeras
for neural networks
-
Stream data acquisition
-
Repository: https://github.com/vicssb/lab_asset_forecast
- In case of sensitive bugs like security vulnerabilities, please contact YOUR EMAIL directly instead of using issue tracker. We value your effort to improve the security and privacy of this project!
1.0.0.0
- Victor Barros:
- @vicssb (https://github.com/vicssb)
- [email protected]
Please follow github and join us! Thanks for visiting and happy coding!