Scikit-Learn ბიბლიოთეკა
Scikit-Learn ბიბლიოთეკა
Embedded Files
გამოიყენება მანქანური სწავლებისთვის.
Purpose: Splits a dataset into training and testing subsets.
Purpose: Evaluates a model's performance using cross-validation.
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
Purpose: Converts categorical data into a binary (one-hot encoded) format.
Purpose: Encodes target labels with values between 0 and n_classes-1.
Purpose: Converts categorical data into numeric values, preserving a meaningful order between categories.
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OrdinalEncoder
Purpose: An under-sampling technique to balance the dataset by reducing the majority class.
Purpose: A hybrid sampling technique that combines SMOTE (over-sampling) and Tomek Links (under-sampling) to balance the dataset.
Purpose: A simple over-sampling technique to balance the dataset by duplicating samples from the minority class.
from imblearn.under_sampling import NearMiss
from imblearn.combine import SMOTETomek
from imblearn.over_sampling import
RandomOverSampler
Purpose: A statistical test for assessing the relationship between categorical features and a target variable.
Purpose: Incrementally selects or removes features to find the best subset for a model.
Purpose: Evaluates all possible combinations of features to find the best subset.
Purpose: Measures the average squared difference between actual and predicted values in regression tasks.
Purpose: Selects features based on their importance weights from a fitted model.
from sklearn.feature_selection import chi2
from mlxtend.feature_selection import
SequentialFeatureSelector
from mlxtend.feature_selection import
ExhaustiveFeatureSelector
from sklearn.metrics import mean_squared_error
from sklearn.feature_selection import SelectFromModel
Purpose: Scales and translates each feature to a given range (default is [0, 1]).
Purpose: Scales features to have zero mean and unit variance (standard normal distribution).
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import StandardScaler
Purpose:
Automates the process of hyperparameter tuning by exhaustively searching over a specified parameter grid.
Finds the best combination of hyperparameters for a machine learning model using cross-validation
from sklearn.model_selection import GridSearchCV
Purpose:
Automates the process of hyperparameter tuning by exhaustively searching over a specified parameter grid.
Finds the best combination of hyperparameters for a machine learning model using cross-validation
from sklearn.model_selection import GridSearchCV
Purpose:
Combines multiple weak learners (usually decision stumps, i.e., shallow decision trees) to create a strong classifier.
Focuses on correcting errors made by previous weak learners.
Purpose:
Builds an ensemble of decision trees, where each tree corrects the errors of the combined predictions of all previous trees.
Uses a gradient descent approach to minimize the loss function (e.g., log loss for classification).
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import GradientBoostingClassifier
Purpose:
Combines multiple weak learners (usually decision stumps, i.e., shallow decision trees) to create a strong classifier.
Focuses on correcting errors made by previous weak learners.
Purpose:
Builds an ensemble of decision trees, where each tree corrects the errors of the combined predictions of all previous trees.
Uses a gradient descent approach to minimize the loss function (e.g., log loss for classification).
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import GradientBoostingClassifier
Purpose: A regression algorithm for predicting a continuous target variable.
Purpose: A classification algorithm for binary or multi-class problems.
Purpose: A classification algorithm that uses a tree-like structure to make decisions.
Purpose: A non-parametric classification algorithm based on proximity to training samples.
Purpose: A classification algorithm that separates data using hyperplanes.
Purpose: A probabilistic classification algorithm based on Bayes' theorem.
Purpose: An ensemble classification algorithm that builds multiple decision trees.
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClasifier
from sklearn.neighbors import KneighborsClassisier
from sklearn.SVM import SVC
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier
Purpose: Combines the predictions of different estimators to make a final prediction. (1.Hard 2.Soft)
from sklearn.ensemble import VotingClassifier
Purpose: Combines the predictions of different estimators to make a final prediction. (1.Hard 2.Soft)
from sklearn.ensemble import VotingClassifier
Purpose: Measures the proportion of correct predictions made by a model.
Purpose: Provides a matrix of actual vs. predicted classifications, giving a deeper view of a model's performance.
Purpose: Provides a detailed report with multiple evaluation metrics such as precision, recall, F1 score, and support for each class.
from sklearn.metrics import
accuracy_score ,
confusion_matrix ,
classification_report
Page updated
Google Sites
Report abuse