Top Tweets for #CodeForChange
Day 47 of #111DaysOfLearningForChange
Added gradient clipping to training loop. Prevents exploding gradients. Logs grad norm to MLflow.
@CodeForChangeNp #CodeForChange #Day47LearningForChange
Day 46 of #111DaysOfLearningForChange
Added learning rate scheduler to training. Auto-reduces LR on plateau. Logs each change to MLflow.
@CodeForChangeNp #CodeForChange #Day46LearningForChange
Day 45 of #111DaysOfLearningForChange
Added early stopping callback to training. Stops if validation loss doesn't improve for 10 epochs. Saves time, prevents overfitting.
@CodeForChangeNp #CodeForChange #Day45LearningForChange
Day 44 of #111DaysOfLearningForChange
Added cross-validation to training pipeline. Logs mean ± std of 5 folds to MLflow. More robust metrics.
@CodeForChangeNp #CodeForChange #Day44LearningForChange
Day 43 of #111DaysOfLearningForChange
Integrated Optuna with MLflow. Auto hyperparameter tuning → logs best params and metrics to MLflow. 50 trials, best accuracy saved.
@CodeForChangeNp #CodeForChange #Day43LearningForChange
Day 42 of #111DaysOfLearningForChange
Added automatic model card generation on every registered model. Markdown file with run_id, params, metrics, and training timestamp saved as MLflow artifact.
@CodeForChangeNp #CodeForChange #Day42LearningForChange
Day 41 of #111DaysOfLearningForChange
Added pre-commit hooks to my repo: black, isort, and flake8. Every commit auto-formats Python code. No more style fights.
@CodeForChangeNp #CodeForChange #Day41LearningForChange
Day 40 of #111DaysOfLearningForChange
Added GitHub Actions workflow to deploy MLflow server using Terraform. Plan on PR, apply on merge to main.
@CodeForChangeNp #CodeForChange #Day40LearningForChange
Day 39of #111DaysOfLearningForChange
Wrote a Terraform script to provision MLflow server on EC2. Infrastructure as code for reproducible MLOps stack.
@CodeForChangeNp #CodeForChange #Day39LearningForChange
Day 38 of #111DaysOfLearningForChange
Added S3 backup for MLflow artifacts. Every new run automatically syncs models and metrics to cloud storage. Disaster recovery ready.
@CodeForChangeNp #CodeForChange #Day38LearningForChange
🚀 Day 42 of #111DaysOfLearningForChange!
Worked on IQR-based outlier detection using the placement dataset. Used the 1.5 * IQR rule for trimming and capping extreme values.
@CodeForChangeNp
#42Days #CodeForChange
🚀 Day 41 of #111DaysOfLearningForChange!
Worked on outlier detection and treatment using the placement dataset. Explored trimming, Z-score filtering, and capping to handle extreme values better.
@CodeForChangeNp
#41Days #CodeForChange
Day 37 of #111DaysOfLearningForChange
Added Prometheus alerts for high latency (>100ms p95) and error rate (>5%). Alertmanager sends to Discord webhook.
@CodeForChangeNp #CodeForChange #Day37LearningForChange
Day 36 of #111DaysOfLearningForChange
Added a Grafana dashboard connected to Prometheus metrics from my model API. Real-time latency, error rate, and prediction volume graphs.
@CodeForChangeNp #CodeForChange #Day36LearningForChange
Day 35 of #111DaysOfLearningForChange
Added prediction explanation caching. SHAP values for frequent inputs served from Redis. 10x faster explainability.
@CodeForChangeNp #CodeForChange #Day35LearningForChange
Day 39
Learn about vector database today .
#111DaysOfLearningForChange
#CodeForChange #Day3LearningForChange
@CodeForChangeNp
Day 34 of #111DaysOfLearningForChange
Added model explainability endpoint to FastAPI. Returns SHAP values as JSON for any input. Debug predictions in real time.
@CodeForChangeNp #CodeForChange #Day34LearningForChange
Day 38
Batch Gradient Descent vs SGD
This is about how AI updates its knowledge while learning.
A way to convert text, images, or other data into numbers (vectors) while preserving meaning
#111DaysOfLearningForChange
#CodeForChange #Day3LearningForChange
@CodeForChangeNp
Day 37
this is about embedding
#111DaysOfLearningForChange
#CodeForChange #Day3LearningForChange
@CodeForChangeNp
🚀 Day 38 of #111DaysOfLearningForChange!
Exploring advanced missing value handling in Pandas and Scikit-learn. Learned random sample imputation, missing indicators, and how to tune imputer settings inside a pipeline.
@CodeForChangeNp
#CodeForChange #38DaysOfLearning
Last Seen Hashtags on Sotwe
XG_1stWORLDTOUR
bop
Seen from United States
m2f
Seen from Colombia
rapekink #roughsex
Seen from France
รีทวิตส่งคลิปเต็มไม่เบลอ
Seen from Thailand
lefkoşagay
Seen from Turkey
หลุดทวิต
Seen from Thailand
desahancewek #moancewek
Seen from Indonesia
latexAsriel
Seen from Argentina
teenage #nolimit() +filter:native_video
Seen from United States
Trends for you
Most Popular Users
Elon Musk 
@elonmusk
240.1M followers
Barack Obama
@barackobama
119.3M followers
Donald J. Trump
@realdonaldtrump
111.6M followers
Cristiano Ronaldo
@cristiano
108.8M followers
Narendra Modi
@narendramodi
106.9M followers
Rihanna
@rihanna
97.2M followers
NASA
@nasa
92.1M followers
Justin Bieber
@justinbieber
90.5M followers
KATY PERRY
@katyperry
86.7M followers
Taylor Swift
@taylorswift13
80.5M followers
Lady Gaga
@ladygaga
72.1M followers
Kim Kardashian
@kimkardashian
69.3M followers
YouTube
@youtube
68.6M followers
Virat Kohli
@imvkohli
68.4M followers
Bill Gates
@billgates
63.4M followers
The Ellen Show
@theellenshow
62.5M followers
CNN
@cnn
61.9M followers
Neymar Jr
@neymarjr
61M followers
X
@x
60.9M followers
CNN Breaking News
@cnnbrk
59.9M followers