Most popular
@KDnuggets tweets for Apr 24 - 30 were:
Most Favorited, Viewed & Clicked:
Another 10 Free Must-Read Books for Machine Learning and Data Science
https://t.co/K63ttnc1xV https://t.co/pl8gaWlfFg
Most Retweeted:
Top #DataScience & #MachineLearning Methods Used in 2018/19:
1. Regression
2. Decision Trees /Rules
3. Clustering
4. Visualization
5. Random Forests
6. Statistics - Descriptive
7. K-Nearest Neighbors
8. Time Series
9. Ensemble Methods
10. Text Mining
https://t.co/w57JAZYRKZ https://t.co/TPPRanID24
Top 10 most engaging Tweets
- Another 10 Free Must-Read Books for Machine Learning and Data Science https://t.co/K63ttnc1xV https://t.co/pl8gaWlfFg
- Top #DataScience & #MachineLearning Methods Used in 2018/19:
1. Regression
2. Decision Trees /Rules
3. Clustering
4. Visualization
5. Random Forests
6. Statistics - Descriptive
7. K-Nearest Neighbors
8. Time Series
9. Ensemble Methods
10. Text Mining
https://t.co/w57JAZYRKZ https://t.co/TPPRanID24
- Data Visualization in Python: Matplotlib vs Seaborn https://t.co/2WabKaxEV2 https://t.co/5dVX9XvH3i
- Data Science Project Flow for Startups https://t.co/YU93ktiAFz https://t.co/VggSonyGrr
- Pandas DataFrame Indexing by @_brohrer_
"The goal of this post is identify a single strategy for pulling data from a DataFrame using the Pandas Python library that is straightforward to interpret and produces reliable results."
https://t.co/LdqxrhVf06 https://t.co/4VMYeKaRFV
- Best Data Visualization Techniques for small and large data
https://t.co/QxGKXgQUhl https://t.co/6XIjhv9GM0
- Data Visualization in Python: Matplotlib vs Seaborn https://t.co/2WabKaxEV2 https://t.co/EIIZMnUCK5
- How to avoid pitfalls when using #MachineLearning for time series forecasting:
“Defining the model to predict the difference in values between time steps rather than the value itself, is a much stronger test of the models predictive powers.” https://t.co/VHtcrM3EjO https://t.co/iWsXPan2U4
- The most desired skill in #DataScience https://t.co/Xb1hR6ZSyH https://t.co/dcZQYMWyp9
- Google Experiment Destroyed Assumptions of Representation Learning - it showed that unsupervised learning of disentangled representations is impossible without inductive biases both on the learning approaches and the data sets #MachineLearning
https://t.co/JaiWNJXO3T https://t.co/WpBRFBqh2p