Home
Model
User space
Structure preprocessing
Data preprocessing
Modelling pipeline
Manual
Help
Contact
User Space
My Data
My Model
My Report
Structure Preprocessing
File check
Validation of molecules
Standardization of molecules
Custom Preprocessing
Data Preprocessing
Imputation of missing values
Removing low variance features
Removing high correlation features
Univariate feature selection
Tree-based feature selection
RFE feature selection
Modelling Process
Start Pipeline
Feature Calculation
Model Selection
Model Building
Prediction
Model interpretation
Feature importance
Tree visualization
Other tools
Statistical Analysis
Random training set split
Diverse training set split
| Step 1: Upload your file
Choose your file:
Example
| Step 2: Set parameters
Set the n_estimators value
The number of trees in the forest.
Set the max_features value
The number of features to consider when looking for the best split:
If int, then consider max_features features at each split.
If float, then max_features is a percentage and int(max_features * n_features) features are considered at each split.
If “auto”, then max_features=sqrt(n_features).
If “sqrt”, then max_features=sqrt(n_features).
If “log2”, then max_features=log2(n_features).
If None, then max_features=n_features.
Set the threshold value
The threshold value to use for feature selection. Features whose importance is greater or equal are kept while the others are discarded.(e.g., “1.25*mean”, "median", "1e-5", '0.001')
E-mail: biomed@csu.edu.cn
