# ClickML Studio

## Docs

- [Exploratory data analysis (EDA) component](https://docs.clickml.app/components/analytics/eda.md): Use the EDA component to profile, visualize, and summarize your dataset with charts and statistics before building a machine learning model.
- [CSV Reader component](https://docs.clickml.app/components/data/csv-reader.md): Load a CSV file into your ClickML Studio pipeline as a DataFrame, with options for delimiters, headers, and column type inference.
- [Excel Reader component](https://docs.clickml.app/components/data/excel-reader.md): Load Excel workbooks (.xlsx and .xls) into your ClickML Studio pipeline as a DataFrame, with sheet selection and header configuration options.
- [Model evaluation component](https://docs.clickml.app/components/evaluation/evaluation.md): Measure your trained model's performance with classification and regression metrics, confusion matrices, ROC curves, and residual plots.
- [Model inference component](https://docs.clickml.app/components/evaluation/inference.md): Apply a trained ClickML Studio model to your test set or new data to produce predictions and feed results into downstream evaluation steps.
- [Model Selector component](https://docs.clickml.app/components/evaluation/model-selector.md): Choose a specific saved version of a trained model from your ClickML Studio workspace to load into a pipeline for inference or evaluation.
- [Feature Extraction component](https://docs.clickml.app/components/feature-engineering/feature-extraction.md): Reduce dimensionality with techniques like PCA and ICA to extract a compact set of features that capture most of the variance in your dataset.
- [Feature Selection component](https://docs.clickml.app/components/feature-engineering/feature-selection.md): Keep only the most informative features in your dataset using statistical tests, model-based importance, and recursive feature elimination methods.
- [Feature Transformation component](https://docs.clickml.app/components/feature-engineering/feature-transformation.md): Create new features from existing columns through polynomial expansion, binning, log transforms, and other engineered transformations.
- [Decision Tree Classifier component](https://docs.clickml.app/components/models/classification/decision-tree.md): Train an interpretable decision tree classifier that splits data by feature thresholds to assign class labels, with tunable depth and split criteria.
- [Gradient Boosting Classifier component](https://docs.clickml.app/components/models/classification/gradient-boosting.md): Train a gradient boosting classifier that sequentially fits decision trees to correct prior errors, delivering strong accuracy on tabular data.
- [K-Nearest Neighbors Classifier component](https://docs.clickml.app/components/models/classification/knn.md): Classify examples using the majority vote of their K nearest neighbors, with configurable distance metrics and neighbor weighting strategies.
- [Logistic Regression Classifier component](https://docs.clickml.app/components/models/classification/logistic-regression.md): Train a linear logistic regression model for binary and multi-class classification, with L1 and L2 regularization and configurable solvers.
- [Random Forest Classifier component](https://docs.clickml.app/components/models/classification/random-forest.md): Train a random forest ensemble that aggregates many decision trees through bagging to deliver robust, accurate classification on tabular data.
- [Support Vector Classifier (SVC) component](https://docs.clickml.app/components/models/classification/svc.md): Train a support vector classifier that finds the maximum-margin hyperplane separating classes, with linear, polynomial, and RBF kernels.
- [Decision Tree Regressor component](https://docs.clickml.app/components/models/regression/decision-tree.md): Train an interpretable decision tree regressor that predicts continuous targets by partitioning feature space, with tunable depth and split criteria.
- [Gradient Boosting Regressor component](https://docs.clickml.app/components/models/regression/gradient-boosting.md): Train a gradient boosting regressor that sequentially fits decision trees to minimize prediction error, achieving strong accuracy on tabular targets.
- [K-Nearest Neighbors Regressor component](https://docs.clickml.app/components/models/regression/knn.md): Predict continuous values by averaging the targets of the K nearest neighbors, with configurable distance metrics and neighbor weighting strategies.
- [Lasso Regression component](https://docs.clickml.app/components/models/regression/lasso.md): Train a linear regression model with L1 regularization that shrinks unimportant coefficients to zero, performing automatic feature selection.
- [Linear Regression component](https://docs.clickml.app/components/models/regression/linear-regression.md): Fit an ordinary least squares linear regression model to predict continuous targets, with optional intercept fitting and coefficient inspection.
- [Random Forest Regressor component](https://docs.clickml.app/components/models/regression/random-forest.md): Train a random forest ensemble that aggregates many decision trees through bagging to predict continuous values with strong accuracy and stability.
- [Ridge Regression component](https://docs.clickml.app/components/models/regression/ridge.md): Train a linear regression model with L2 regularization that shrinks coefficients toward zero to reduce overfitting and handle multicollinearity.
- [Support Vector Regressor (SVR) component](https://docs.clickml.app/components/models/regression/svr.md): Train a support vector regressor that fits an epsilon-insensitive tube to predict continuous values, with linear, polynomial, and RBF kernels.
- [ClickML Studio components reference](https://docs.clickml.app/components/overview.md): Browse every drag-and-drop component available on the ClickML Studio canvas, including data readers, processors, models, and evaluation blocks.
- [Data Cleaning component](https://docs.clickml.app/components/processing/data-cleaning.md): Quickly handle missing values in your dataset by dropping rows and columns or filling gaps with mean, median, mode, or constant strategies.
- [Data Transformation component](https://docs.clickml.app/components/processing/data-transformation.md): Apply mathematical transformations like log, square root, Box-Cox, and Yeo-Johnson to numerical columns to reduce skew and stabilize variance.
- [Delete Columns and Rows component](https://docs.clickml.app/components/processing/delete-columns-rows.md): Remove unwanted columns and rows from your DataFrame by name, index, or condition to slim down a dataset before training your ML model.
- [Categorical Encoding component](https://docs.clickml.app/components/processing/encoding.md): Convert categorical columns into numerical values using label encoding, one-hot encoding, ordinal encoding, and target encoding strategies.
- [Missing Values imputation component](https://docs.clickml.app/components/processing/missing-values.md): Handle missing data with advanced imputation methods including interpolation, KNN imputation, and iterative model-based filling for numerical columns.
- [Feature Scaling component](https://docs.clickml.app/components/processing/scaling.md): Normalize numerical features with standard, min-max, robust, and max-abs scalers to bring columns to a common range before model training.
- [Train-Test Split component](https://docs.clickml.app/components/processing/train-test-split.md): Split your dataset into training and test sets with configurable ratios, random seeds, and stratification to evaluate model generalization.
- [Concatenate DataFrames component](https://docs.clickml.app/components/wrangling/concatenate.md): Stack two DataFrames vertically to add more rows or horizontally to add more columns, with control over index alignment and join behavior.
- [Merge and Join DataFrames component](https://docs.clickml.app/components/wrangling/merge-join.md): Join two DataFrames on a shared key column using inner, left, right, or outer joins to combine related datasets before model training.
- [Introduction to ClickML Studio](https://docs.clickml.app/introduction.md): ClickML Studio is a no-code visual platform for building, training, and evaluating machine learning pipelines through drag-and-drop components.
- [Quickstart guide to building ML pipelines](https://docs.clickml.app/quickstart.md): Build your first end-to-end machine learning pipeline in ClickML Studio in under five minutes by connecting data, model, and evaluation components.

## OpenAPI Specs

- [openapi](https://docs.clickml.app/api-reference/openapi.json)