Update README.md

README.md

@@ -22,8 +22,7 @@ EDA was performed in the Colab notebook to understand distributions and relation
 - `Smoking_Prevalence` is roughly centered around ~27–28 with moderate spread.
 - Many features such as `Peer_Influence`, `Media_Influence`, `Mental_Health` are on a 1–10 scale.
 - No strong class imbalance issues were found once the target was binarized (see classification section).
-
-> (Place your distribution plots here, e.g.)  
+ 
 > ![1 - Smoking Prevalence Distribution](1_Smoking_Prevalence_Distribution.png) 
 
 ### Relationships:
@@ -61,11 +60,11 @@ Key exploratory plots included:
 
 The goal of the regression model is to predict Smoking_Prevalence based on demographic, behavioral, and social factors
 
-גרף Actual vs Predicted
+> ![Actual_vs_Predicted](Actual_vs_Predicted.png)
 
 Conclusion of the feature importance:
 
-גרף feature importance
+> ![Linear_Regression_Coefficients](Linear_Regression_Coefficients.png)
 
 The baseline linear regression model performed poorly, indicating that smoking behavior is not well captured through a simple linear relationship with the selected features. This highlights the need for more advanced modeling techniques and potential feature engineering.
 
@@ -89,7 +88,7 @@ To improve model performance, several engineered features were created:
 
 These engineered features were re-used both for regression and classification tasks.
 
-גרף קלסטרז
+> ![clusters](clusters.png)
 
 ---