[Sklearn] Modules

1. What is Scikit-Learn?

Scikit-learn(Sklearn) is the most useful and robust library for machine learning in Python. It provides a selection of efficient tools for machine learning and statistical modeling including classification, regression, clustering and dimensionality reduction via a consistence interface in Python. This library, which is largely written in Python, is build upon Numpy, Scipy and Matplotlib.

 

2. Most used modules in sklearn

# Preprocessing modules 
# Scalers 
from sklearn.preprocessing import MinMaxScaler, RobustScaler, StandardScaler 
# Encoders 
from sklearn.preprocessing import LabelEncoder, OneHotEncoder 

# Model selection 
# Train-Test split 
from sklearn.model_selection import KFold, StratifiedKFold, train_test_split 
# Hyperparameter tuning 
from sklearn.model_selection import GridSearchCV

# Model learning 
# Ensemble models 
from sklearn.ensemble import AdaBoostClassifier, GradientBoostingClassifier, RandomForestClassifier, RandomForestRegressor 
# Linear models 
from sklearn.linear_model import LogisticRegression, RidgeCalssifier 
# Neighbors 
from sklearn.neighbors import KNeighborsClassifier
# Support Vector Machines 
from sklearn.svm import SVC, SVR
# Tree models 
from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor, ExtraTreeClassifier, ExtraTreeRegressor 

# Model Evaluation 
# Metrics : Regression problems 
from sklearn.metrics import accuracy_score, mean_absolute_error, mean_squared_error, r2_score
# Metrics : Classification problems 
from sklearn.metrics import classification_report, confusion_matrix, f1_score, log_loss, roc_auc_score 
# We can evaluate model using built in methods in each model
# model.predict() and model.predict_proba() 

# Final Ensemble
from sklearn.ensemble import StackingClassifier, StackingRegressor, VotingClassifier, VotingRegressor

 

 

Source from :

• https://www.tutorialspoint.com/scikit_learn/scikit_learn_introduction.htm
• https://www.kaggle.com/datasets/agileteam/bigdatacertificationkr