Mike's ML Forge
B. Feature Importance (for tree models) Use models like RandomForest or XGBoost to get importance scores. from sklearn.ensemble import RandomForestRegressor model = RandomForestRegressor() model.fit(X, y) importances = model.feature_importances_ # Show…
C. Statistical Tests
Depending on the type of data:
Numerical vs numerical? → correlation
Categorical vs numerical? → ANOVA / t-test
Categorical vs categorical? → Chi-Squared test
Depending on the type of data:
Numerical vs numerical? → correlation
Categorical vs numerical? → ANOVA / t-test
Categorical vs categorical? → Chi-Squared test
How to Improve a Predictive Model?
1. Evaluate Performance
Compare with a baseline model (simple predictor).
Check key metrics (accuracy, RMSE, etc.).
2. Improve Data
Collect more data if possible.
Clean, preprocess, and engineer better features.
3. Choose a Better Model
Try different algorithms (e.g., Decision Trees, SVM, Neural Networks) we'll see them in future
4. Tune Hyperparameters
Adjust settings like learning rate, tree depth, or batch size.
•Use GridSearchCV or •RandomizedSearchCV for optimization.
5. Prevent Overfitting & Underfitting
•Overfitting? Regularization, dropout, or pruning.
•Underfitting? More features, deeper models.
Optimize these steps, and your model will improve!
1. Evaluate Performance
Compare with a baseline model (simple predictor).
Check key metrics (accuracy, RMSE, etc.).
2. Improve Data
Collect more data if possible.
Clean, preprocess, and engineer better features.
3. Choose a Better Model
Try different algorithms (e.g., Decision Trees, SVM, Neural Networks) we'll see them in future
4. Tune Hyperparameters
Adjust settings like learning rate, tree depth, or batch size.
•Use GridSearchCV or •RandomizedSearchCV for optimization.
5. Prevent Overfitting & Underfitting
•Overfitting? Regularization, dropout, or pruning.
•Underfitting? More features, deeper models.
Optimize these steps, and your model will improve!
❤1
Hyperparameters are settings on a model you can adjust to improve its ability to find patterns
Parameters are patterns that the model finds in the data
Parameters are patterns that the model finds in the data
👍3
Forwarded from ᴏᴇᴜᴠʀᴇ 𐌓ₑ ᴋɪᴅᴜꜱ (ቅ𝔡𝔲ስ)
The Illusion of Being Put Together
Everyone looks like they’ve figured it all out...
Spoiler: they haven’t. It’s just good angles and practiced captions. Meanwhile, authenticity is quietly dying in everyone’s drafts.
#random_k
@oeuvre_de_kidus
🔥2
Forwarded from Journey Log⚡️
"I’m a university lecturer.
I was the top scorer in the Grade 12 national exam in my stream—possibly the highest of all time. I graduated with a perfect 4.00 GPA, the only one to do so at my university to date. I completed my master's degree at Addis Ababa University with very great distinction. I was considered the best of my generation. But truthfully, every university lecturer was once the best of their generation.
I've been teaching for seven years now. My net salary is 10,700 Birr. I pay 7,000 in rent and survive on the remaining 3,700. It feels less like a profession and more like a punishment for excelling in school.
Now, I’m expected to inspire my students—standing in front of them in worn-out shirts and uneven shoes, trying to convince them that hard work pays off. I was supposed to be a symbol of excellence, someone they could look up to. Instead, I’m a cautionary tale.
Meanwhile, cheaters, corrupt officials, and unqualified party loyalists reap the rewards of a broken system. This country doesn’t belong to them—it belongs to those who built it with knowledge, sweat, and service. It’s time to reclaim it from the parasites and restore dignity to those who earned it."
I was the top scorer in the Grade 12 national exam in my stream—possibly the highest of all time. I graduated with a perfect 4.00 GPA, the only one to do so at my university to date. I completed my master's degree at Addis Ababa University with very great distinction. I was considered the best of my generation. But truthfully, every university lecturer was once the best of their generation.
I've been teaching for seven years now. My net salary is 10,700 Birr. I pay 7,000 in rent and survive on the remaining 3,700. It feels less like a profession and more like a punishment for excelling in school.
Now, I’m expected to inspire my students—standing in front of them in worn-out shirts and uneven shoes, trying to convince them that hard work pays off. I was supposed to be a symbol of excellence, someone they could look up to. Instead, I’m a cautionary tale.
Meanwhile, cheaters, corrupt officials, and unqualified party loyalists reap the rewards of a broken system. This country doesn’t belong to them—it belongs to those who built it with knowledge, sweat, and service. It’s time to reclaim it from the parasites and restore dignity to those who earned it."
❤3🤣3😢1
I didn’t realize how much I missed lifting until I stepped away from it
🕊3❤1😢1
I don’t even know how to explain what I feel today. It’s not just about the ceremony. It’s looking back and seeing how God walked with me through chaos, through pain, through moments I didn’t think I’d survive. It’s not the grades or the accomplishments that move me it’s the quiet ways He held me together when I was falling apart.
3❤7
How do you thank a God like that? I can’t. no tears, no words are enough. His love didn’t just carry me it completely overwhelmed me. Broke me. Remade me. And I wouldn’t have it any other way. I love Him more than I know how to say.
❤5
"አቤቱ አምላኬ ሆይ፥ በልቤ ሁሉ አመሰግንሃለሁ፥ ለዘላለምም ስምህን አከብራለሁ"
መዝሙረ ዳዊት 86:12
መዝሙረ ዳዊት 86:12
🥰7❤🔥2
Forwarded from Hacker News
www.codelink.io
AI system development: LLM → RAG → AI Workflow → AI Agent | CodeLink
Confused by LLMs, RAG, & AI Agents? We break down the spectrum of AI system design with a familiar resume-screening example to show the leap in capabilities (and complexity) at each level.