Copilot Instructions

Overview

This project involves analyzing flight data, building predictive models, and creating APIs to serve predictions. Below are the key instructions and guidelines for working with this project.

Key Components

Data Exploration and Cleaning:
- Analyze the dataset to identify missing or inconsistent values.
- Remove outliers using quantiles for
```
DepDelay
```
  and
```
ArrDelay
```
  columns.
- Ensure all columns have the correct data types and no missing values.
Model Building:
- Use
```
RandomForestClassifier
```
  to predict the likelihood of a flight being delayed (
```
DepDel15
```
  ).
- Features used for training:
  - ```
  DayOfWeek
```
- ```
DestAirportID
```
- Target variable:
```
DepDel15
```
  .
- Split the data into training and testing sets.
- Train the model and evaluate its performance.
- Save the trained model as
```
random_forest_model.pkl
```
  .
API Development:
- Create a Flask API with the following endpoints:
  - ```
  /predict
```
  : Accepts
```
  day_of_week
```
  and
```
  airport_id
```
  as query parameters and returns the delay probability and confidence.
- ```
/airports
```
    : Returns a list of airport names and IDs, sorted alphabetically.
Frontend Integration:
- Use the API to display predictions and airport data in a user-friendly interface.

Instructions for Notebooks

Ensure all notebooks are structured with clear markdown explanations and code cells.
Use quantiles to handle outliers in the data.
Save the cleaned data and models for reuse.

File Structure

```
data/
```
: Contains the raw and processed datasets.
```
server/
```
: Contains the Flask API code and model files.
```
possible-solution/
```
: Contains example notebooks and solutions.
```
client/
```
: Contains the frontend code.

Running the Project

Install dependencies:

pip install -r server/requirements.txt

Start the Flask server:

python server/app.py

Run the frontend application (if applicable).

Notes

Ensure all data is returned in JSON format for API responses.
Follow best practices for coding and documentation.

Copilot Instructions

Overview

This project involves analyzing flight data, building predictive models, and creating APIs to serve predictions. Below are the key instructions and guidelines for working with this project.

Key Components

Data Exploration and Cleaning:
- Analyze the dataset to identify missing or inconsistent values.
- Remove outliers using quantiles for
```
DepDelay
```
  and
```
ArrDelay
```
  columns.
- Ensure all columns have the correct data types and no missing values.
Model Building:
- Use
```
RandomForestClassifier
```
  to predict the likelihood of a flight being delayed (
```
DepDel15
```
  ).
- Features used for training:
  - ```
  DayOfWeek
```
- ```
DestAirportID
```
- Target variable:
```
DepDel15
```
  .
- Split the data into training and testing sets.
- Train the model and evaluate its performance.
- Save the trained model as
```
random_forest_model.pkl
```
  .
API Development:
- Create a Flask API with the following endpoints:
  - ```
  /predict
```
  : Accepts
```
  day_of_week
```
  and
```
  airport_id
```
  as query parameters and returns the delay probability and confidence.
- ```
/airports
```
    : Returns a list of airport names and IDs, sorted alphabetically.
Frontend Integration:
- Use the API to display predictions and airport data in a user-friendly interface.

Instructions for Notebooks

Ensure all notebooks are structured with clear markdown explanations and code cells.
Use quantiles to handle outliers in the data.
Save the cleaned data and models for reuse.

File Structure

```
data/
```
: Contains the raw and processed datasets.
```
server/
```
: Contains the Flask API code and model files.
```
possible-solution/
```
: Contains example notebooks and solutions.
```
client/
```
: Contains the frontend code.

Running the Project

Install dependencies:

pip install -r server/requirements.txt

Start the Flask server:

python server/app.py

Run the frontend application (if applicable).

Notes

Ensure all data is returned in JSON format for API responses.
Follow best practices for coding and documentation.

Copilot Instructions

Copilot Instructions

Overview

Key Components

Instructions for Notebooks

File Structure

Running the Project

Notes

Related Skills

Markdown Converter

Nano Banana Pro

1password

Copilot Instructions

Overview

Key Components

Instructions for Notebooks

File Structure

Running the Project

Notes