User spectre

6 votes

Further Training a pre-trained LLM

answered Jun 12 at 12:32

4 votes

Modeling uncertainty from known physics

answered May 25 at 10:57

4 votes

Accepted

Does One-Hot encoding increase the dimensionality and sparsity of dataset?

answered Oct 5, 2021 at 10:38

4 votes

Best platform to work with when having millions of rows in dataframe

answered Oct 11, 2021 at 14:38

4 votes

How to determine if my data split is appropriate for my data size?

answered Dec 5, 2021 at 13:01

3 votes

Creating & handling large matrices in python?

answered Sep 22, 2021 at 9:54

3 votes

Accepted

Some simple questions about confusion matrix and metrics in general

answered May 27 at 4:11

3 votes

Accepted

Beginning my data science journey

answered Dec 21, 2021 at 7:26

3 votes

Accepted

Categorical to One hot encoding - Big data

answered Dec 31, 2021 at 8:10

2 votes

Accepted

Would time series input work in multiple polynomial regression model?

answered May 11 at 16:03

2 votes

Accepted

Can I run falcon-7b on a free google colab?

answered Jul 13 at 4:52

2 votes

calibrated classifier ValueError: could not convert string to float

answered Sep 23, 2021 at 6:04

2 votes

Which algorithm works well for forecasting sales prediction and the reason to choose particular algorithm?

answered Sep 25, 2021 at 7:42

2 votes

Accepted

Which major should I choose to become a Data Analyst?

answered Sep 12, 2021 at 14:31

2 votes

Where can I find study materials?

answered Sep 30, 2021 at 11:50

2 votes

Can data leakage be sometimes acceptable?

answered Jul 19, 2021 at 11:50

2 votes

Test / Train split - is it always necessary (supervised learning)?

answered Dec 15, 2021 at 13:07

2 votes

Dealing with unbalanced training set compared with real world data

answered Oct 8, 2021 at 11:59

2 votes

Accepted

Drop or impute the missing values?

answered Nov 27, 2021 at 15:13

2 votes

Accepted

Do I have to remove features with pairwise correlation even if I am doing a regularized logistic regression?

answered Oct 21, 2021 at 8:51

2 votes

Removing illogical observations, can I do it?

answered Oct 6, 2021 at 11:53

1 vote

How to predict the winner of a future sports match?

answered Oct 6, 2021 at 16:14

1 vote

Creating quality data with sklearn.datasets.make_classification

answered Sep 11, 2021 at 15:55

1 vote

How to use sklean pipeline to deal with data that read in line by line

answered Oct 8, 2021 at 11:22

1 vote

Accepted

Advantages to combining similarly-named columns for supervised ML?

answered Oct 14, 2021 at 9:19

1 vote

Consequences of using XGBoost regressor for small dataset(< 500 rows)

answered Nov 28, 2021 at 14:31

1 vote

Feature selection for regression

answered Oct 29, 2021 at 7:21

1 vote

Accepted

Activation and Loss Function not chosen correctly when use Neural Network

answered Dec 8, 2021 at 17:19

1 vote

What would be a good n_estimators matrix and thus param_grid for this problem?

answered Jul 19, 2021 at 12:05

1 vote

Can I run this job quicker for GridSearchCV?

answered Jul 19, 2021 at 12:20

Stack Exchange Network

137 Answers

Further Training a pre-trained LLM

Modeling uncertainty from known physics

Does One-Hot encoding increase the dimensionality and sparsity of dataset?

Best platform to work with when having millions of rows in dataframe

How to determine if my data split is appropriate for my data size?

Creating & handling large matrices in python?

Some simple questions about confusion matrix and metrics in general

Beginning my data science journey

Categorical to One hot encoding - Big data

Would time series input work in multiple polynomial regression model?

Can I run falcon-7b on a free google colab?

calibrated classifier ValueError: could not convert string to float

Which algorithm works well for forecasting sales prediction and the reason to choose particular algorithm?

Which major should I choose to become a Data Analyst?

Where can I find study materials?

Can data leakage be sometimes acceptable?

Test / Train split - is it always necessary (supervised learning)?

Dealing with unbalanced training set compared with real world data

Drop or impute the missing values?

Do I have to remove features with pairwise correlation even if I am doing a regularized logistic regression?

Removing illogical observations, can I do it?

How to predict the winner of a future sports match?

Creating quality data with sklearn.datasets.make_classification

How to use sklean pipeline to deal with data that read in line by line

Advantages to combining similarly-named columns for supervised ML?

Consequences of using XGBoost regressor for small dataset(< 500 rows)

Feature selection for regression

Activation and Loss Function not chosen correctly when use Neural Network

What would be a good n_estimators matrix and thus param_grid for this problem?

Can I run this job quicker for GridSearchCV?