동선생

[Kaggle Extra Study] 11. Polars

Polars?Pandas library is widely used for data analysis and processing because it is flexible and convenient to use.However, Pandas has limitations in handling large-scale data due to processing speed and memory usage constraints when dealing with big data.To address this issues, Polars has emerged as a new data processing tool. Polars is implemented in Rust that offers great performance for proc..

Briefly About TabNetTabNet is a deep learning architecture developed by Google in 2019 for analyzing tabular data.In many competitions, including Kaggle, tree-based ensemble models like XGBoost and LightGBM usually dominate the leaderboards when it comes to tabular data analysis.While deep learning leads in analyzing unstructured data like images, text, and audio, tree-based methods have been wi..

From the previous post which was about overfitting and underfitting, we mentioned that one of the most popular methods to get rid of overfitting is to restrict the weights, which is called Regularization.  [Kaggle Study] 4. Overfitting, Underfitting, Variance and BiasOverfitting and UnderfittingOverfitting refers to cases where a model performs well on the training set but shows poor performance..

Overfitting and UnderfittingOverfitting refers to cases where a model performs well on the training set but shows poor performance on the validation set.Underfitting occurs when there isn't big difference between training and validation set performance, but both show poor performance.Learning CurvesLearning curve: Graph showing the model's learning progressLearning curve at left is a typical gra..

What is Learning Rate?Learning rate is a crucial hyperparameter in machine learning that controls the degree of updates on the model's weights.Generally, a loss function represents a hyperplane(초평면) in multi-dimensional space characterized by complex curvatures.If the weight updates are too large and overshoot the global minimum(the point where the loss function could be minimized), it becomes i..

During data preprocessing step of data analysis, it is necessary to check the scale of the features. What do you mean by "scale of feature"?It simply means the range of values that a particular feature possesses.For example, when A feature has 1 ~ 10 range of numerical values and B feature has 500 ~ 1000 range of numerical values, we can say that these 2 features has a large difference in scale...

Before we begin with the plots, you can find detailed information about data imputation from previous post: [Kaggle Extra Study] 7. Data ImputationWhile training machine learning models, it is necessary to preprocess missing values because it might greatly affect the performance of the model. Accordingly, there are various methods to deal with those missing values. Types of Missing Values:Missin..

We have to take different approach when dealing with time-series data. The fillna() method is used for imputing missing values in such problem.Basic Imputation Techniques:'ffill' or 'pad': Replace NaN values with last observed value'bfill' or 'backfill': Replace NaN values with next observed valueLinear Interpolation method1. Imputing using 'ffill' or 'pad'Code Example:city_day.fillna(method='ff..

#1 Detecting missing values# credit: https://www.kaggle.com/willkoehrsen/start-here-a-gentle-introduction. def missing_values_table(df): # Total missing values mis_val = df.isnull().sum() # Percentage of missing values mis_val_percent = 100 * df.isnull().sum() / len(df) # Make a table with the results mis_val_table = pd.concat([mis_val, m..

While training machine learning models, it is necessary to preprocess missing values because it might greatly affect the performance of the model. Accordingly, there are various methods to deal with those missing values. Types of Missing Values:Missing completely at random (MCAR)Case when missing values occur independently of other variables, completely random in other words.No correlation with ..

First competition following Yuhan Lee's kaggle curriculum. Binary classification competition using tabular data.  First KernelEDA(Exploratory Data Analysis) written on Titanic competition by Yuhan himself.visualization tool used: matplotlib, seaborn, plotlydata analysis tool used: pandas, numpymachine learning tool: sklearncode: https://github.com/LDYWINNER/TIML/blob/main/kaggle-roadmap/binary-c..

My goal is to be a ranker in Kaggle community and I want to be somekind of running mate with readers of my blog. So I am planning to write some posts like this that records how I am studying.  As of 2024.10.25, I have some background knowledge about data science because I took some undergraduate courses and studied for about 1 or 2 month before. So, I just started to compete in kaggle instead of..

Loss FunctionMachine learning algorithms find the patterns of the given dataset by themselves. For example, let's think about a situation that we should predict whether it will rain tomorrow or not from humidity data. 1.5 * x + 0.1 = y (raining if y > 1) If we can simply express the relationship between the probability of rain and the humidity like this, "pattern" of this data is 1.5(weight) and..

What is Ensemble method?In real-world problems, it is obvious that we can end up in better conclusions if we ask for others' opinion and get advice. It works the same with making machine learning models: if we take a look at the results of various solutions and pick the best among them or deciding by majority, we can make better conclusion. Models trained for drawing conlcusions are called "ense..

Overfitting and UnderfittingBefore we talk about what cross validation method is, we should first think about overfitting and underfitting in terms of machine learning. In general ml problems, we utilize explanatory variables from train data to predict the target variable in the test data. However, test data would not have target variable which makes difficult for us to validate the performance ..