Predicting and plotting the actual vs predicted stalk
- Python: Version 3.8 or higher
- pip: Latest version recommended
- Git: For cloning the repository
- Jupyter Notebook: To run
.ipynbfiles
Optional but recommended:
- Virtual environment (e.g.,
venvorconda) to isolate dependencies.
git clone https://github.com/shivansh31414/ML-PROJECT-.git
cd ML-PROJECT-Using venv:
python3 -m venv venv
source venv/bin/activate # On Linux/Mac
venv\Scripts\activate # On WindowsUsing conda:
conda create -n mlproject python=3.9
conda activate mlprojectSince the repo doesn’t list dependencies yet, here’s a starter set based on typical ML workflows:
pip install numpy pandas matplotlib scikit-learn jupyter👉 If you add a requirements.txt later, users can install everything with:
pip install -r requirements.txtLaunch Jupyter Notebook:
jupyter notebookOpen Untitled13.ipynb and run the cells to:
- Train the model
- Predict stalk values
- Plot actual vs predicted results
- Ensure plots are generated without errors.
- Confirm predictions align with expected outputs.
the code in the jupyter notebook helps to import various dataset for stock market train model and make predictions on it
this project as of now is in the devolopment stages we are focusing on to make a stock comparing and analysis tool that lets you pick stocks and analyse them
the dataset is used using python librarie yfinance why yfinance and how it contributes to the dataset ? yfinance uses an accronym for different companies this in turn what it does is that it takes that accronym for the company and then gives you stock data for the start and end date as requested by the user
ideally the project must take the user input company and display its stock report from start date to end date as requested and then also helps plot the data from start date to end date depending upon the users querie