Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/dronabopche/100-ML-AI-Project/llms.txt

Use this file to discover all available pages before exploring further.

Consistency is a first-class concern in this repository. Every one of the 100+ projects uses the same top-level directory layout, the same naming conventions for source files, and the same separation between raw data, trained artifacts, and application logic. Once you understand the structure of one project, you can immediately navigate any other project in the repo and know exactly where to find the dataset, the trained model, the preprocessing code, and the entry point for the API.

​
Standard directory layout

Every project follows this exact structure: 
Project_Name/
│
├── Dataset/
├── Models/
├── Resources/
├── SRC/
│   ├── Processing/
│   ├── Output/
│   └── App.py
│
├── Project_Notebook.ipynb
├── requirements.txt
└── README.md

​
Directory and file reference

Directory / FileDescriptionContents
Dataset/Stores raw data for training and evaluationCSV files, image datasets, structured tabular data
Models/Contains trained and serialized models.pkl, .joblib, .h5, saved pipelines
Resources/Supporting assets for the projectDiagrams, visualization images, documentation files
SRC/Core application logicComplete ML pipeline implementation
SRC/App.pyEntry point of the applicationHandles input, preprocessing, model loading, inference, and prediction output
SRC/Processing/Data preprocessing moduleMissing value handling, encoding, feature engineering, scaling, transformations
SRC/Output/Output handling modulePrediction results, probability scores, confidence levels, timestamps
Project_Notebook.ipynbJupyter notebook for experimentationEDA, model training, evaluation, and result visualization
requirements.txtPython dependency listAll packages needed to run the project
README.mdProject documentationObjectives, dataset details, model summary, deployment notes

​
Real example: House Price Prediction (Project 01)

The House Price Prediction project illustrates how the standard structure maps to a working ML system. This project trains three regression models (Linear, Ridge, Lasso) on a Kaggle housing dataset and exposes predictions through a Flask API backed by Gemini for natural-language input parsing. 
House-Price-Prediction/
│
├── House_Price_Prediction.ipynb
├── README.md
├── requirements.txt
│
├── dataset/
│   └── HousePricePrediction.csv
│
├── model/
│   ├── lasso_model.pkl
│   ├── lr_model.pkl
│   └── ridge_model.pkl
│
├── output/
│   └── predictor.py
│
└── src/
    ├── app.py
    ├── environment.py
    │
    └── preprocessing/
        └── preprocessing.py
The src/app.py file is the Flask entry point. It receives a natural-language prompt from the client, passes it to the preprocessing pipeline (which calls the Gemini API to extract structured feature values), and then runs inference across all three models before averaging the predictions into a final price: 
@app.route("/predict", methods=["POST"])
def predict():
    body = request.get_json()
    prompt = body["prompt"]
    features_np = preprocess_prompt(prompt, GEMINI_API_KEY)
    predicted_price = int(predict_price(features_np))
    return jsonify({"predicted_sale_price": predicted_price})

​
ML pipeline

The diagram below shows the standard learning workflow that each project notebook documents, from raw data through to the trained model stored in Models/.

Build docs developers (and LLMs) love

Get started for freeTalk to us