Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,17 +11,17 @@ pinned: false
|
|
| 11 |
short_description: A futuristic take on carbon footprint + AI.
|
| 12 |
---
|
| 13 |
|
| 14 |
-
#
|
| 15 |
|
| 16 |
> A futuristic take on carbon footprint + AI.
|
| 17 |
|
| 18 |
-
##
|
| 19 |
|
| 20 |
**GreenPrint AI** is a user-friendly web app that predicts your **carbon footprint** based on daily activities and suggests actionable steps to reduce it. From energy consumption to travel and food habits, the app personalizes insights using machine learning.
|
| 21 |
|
| 22 |
---
|
| 23 |
|
| 24 |
-
##
|
| 25 |
|
| 26 |
To develop a carbon footprint detection system that:
|
| 27 |
- Takes input as user activities (e.g., electricity use, transport habits, meat consumption).
|
|
@@ -30,9 +30,9 @@ To develop a carbon footprint detection system that:
|
|
| 30 |
|
| 31 |
---
|
| 32 |
|
| 33 |
-
##
|
| 34 |
|
| 35 |
-
###
|
| 36 |
|
| 37 |
- A synthetic dataset named `synthetic_carbon_footprint.csv` was generated using realistic formulas for CO₂ emissions from:
|
| 38 |
- **Electricity consumption**
|
|
@@ -44,7 +44,7 @@ To develop a carbon footprint detection system that:
|
|
| 44 |
|
| 45 |
---
|
| 46 |
|
| 47 |
-
###
|
| 48 |
|
| 49 |
- Model Used: RandomForestRegressor from scikit-learn
|
| 50 |
- Training done using `Running_Model.ipynb`
|
|
@@ -57,7 +57,7 @@ To develop a carbon footprint detection system that:
|
|
| 57 |
- **Root Mean Squared Error (RMSE)** for prediction accuracy
|
| 58 |
- The trained model was saved as `carbon_model.pkl`
|
| 59 |
|
| 60 |
-
###
|
| 61 |
|
| 62 |
RandomForestRegressor was chosen because:
|
| 63 |
- It handles non-linear relationships and interactions between features better than linear models.
|
|
@@ -67,7 +67,7 @@ RandomForestRegressor was chosen because:
|
|
| 67 |
|
| 68 |
---
|
| 69 |
|
| 70 |
-
###
|
| 71 |
|
| 72 |
- A `model_columns.pkl` file was created to store the expected feature column order.
|
| 73 |
- This prevents column mismatch during inference in the Streamlit frontend.
|
|
|
|
| 11 |
short_description: A futuristic take on carbon footprint + AI.
|
| 12 |
---
|
| 13 |
|
| 14 |
+
# 🌿 GreenPrint AI
|
| 15 |
|
| 16 |
> A futuristic take on carbon footprint + AI.
|
| 17 |
|
| 18 |
+
## Overview
|
| 19 |
|
| 20 |
**GreenPrint AI** is a user-friendly web app that predicts your **carbon footprint** based on daily activities and suggests actionable steps to reduce it. From energy consumption to travel and food habits, the app personalizes insights using machine learning.
|
| 21 |
|
| 22 |
---
|
| 23 |
|
| 24 |
+
## Aim
|
| 25 |
|
| 26 |
To develop a carbon footprint detection system that:
|
| 27 |
- Takes input as user activities (e.g., electricity use, transport habits, meat consumption).
|
|
|
|
| 30 |
|
| 31 |
---
|
| 32 |
|
| 33 |
+
## Step-by-Step Project Workflow
|
| 34 |
|
| 35 |
+
### Step 1: Dataset Creation
|
| 36 |
|
| 37 |
- A synthetic dataset named `synthetic_carbon_footprint.csv` was generated using realistic formulas for CO₂ emissions from:
|
| 38 |
- **Electricity consumption**
|
|
|
|
| 44 |
|
| 45 |
---
|
| 46 |
|
| 47 |
+
### Step 2: Model Training
|
| 48 |
|
| 49 |
- Model Used: RandomForestRegressor from scikit-learn
|
| 50 |
- Training done using `Running_Model.ipynb`
|
|
|
|
| 57 |
- **Root Mean Squared Error (RMSE)** for prediction accuracy
|
| 58 |
- The trained model was saved as `carbon_model.pkl`
|
| 59 |
|
| 60 |
+
### Why Random Forest Regressor?
|
| 61 |
|
| 62 |
RandomForestRegressor was chosen because:
|
| 63 |
- It handles non-linear relationships and interactions between features better than linear models.
|
|
|
|
| 67 |
|
| 68 |
---
|
| 69 |
|
| 70 |
+
### Step 3: Feature Metadata Handling
|
| 71 |
|
| 72 |
- A `model_columns.pkl` file was created to store the expected feature column order.
|
| 73 |
- This prevents column mismatch during inference in the Streamlit frontend.
|