Visit KDnuggets.

com for more

cheatsheets and additional Standardization Unsupervised Learning Model lr.score(X_test, y_test)
learning resources.
from sklearn.preprocessing import StandardScaler from sklearn.metrics import accuracy_score
scaler = StandardScaler() accuracy_score(y_test, y_pred)
scaled_X_train = scaler.fit_transform(X_train) Principal Component Analysis

Scikit-learn CheatSheet scaled_X_test = scaler.transform(X_test)

from sklearn.decomposition import PCA
Classification Report

Normalization pca = PCA(n_components=2) from sklearn.metrics import classification_report

print(classification_report(y_test, y_pred))
from sklearn.preprocessing import Normalizer K Means
norm = Normalizer() Mean Squared Error
norm_X_train = norm.fit_transform(X_train) from sklearn.cluster import KMeans
norm_X_test = norm.transform(X_test) kmeans = KMeans(n_clusters=5, random_state=0) from sklearn.metrics import mean_squared_error
mean_squared_error(y_test, y_pred)
Binarization
R2 Score
from sklearn.preprocessing import Binarizer
Scikit-learn is an open-source Python library for all kinds binary = Binarizer(threshold=0.0) Model Fitting from sklearn.metrics import r2_score
of predictive data analysis. You can perform binary_X = binary.fit_transform(X) r2_score(y_test, y_pred)
classification, regression, clustering, dimensionality
reduction, model tuning, and data preprocessing tasks. Encoding Categorical Features Adjusted Rand Index
Supervised Learning
from sklearn.preprocessing import LabelEncoder from sklearn.metrics import adjusted_rand_score
lab_enc = LabelEncoder() lr.fit(X_train, y_train) adjusted_rand_score(y_test, y_pred)
y = lab_enc.fit_transform(y) svm_svc.fit(X_train, y_train)
Loading the Data
Imputer Unsupervised Learning
Cross-Validation
from sklearn.impute import SimpleImputer model = pca.fit_transform(X_train)
Classification imp_mean = SimpleImputer(missing_values=0, kmeans.fit(X_train)
strategy='mean')
from sklearn import datasets imp_mean.fit_transform(X_train)
X, y = datasets.load_wine(return_X_y=True) from sklearn.model_selection import cross_val_score
cross_val_score( lr, X, y, cv=5, scoring='f1_macro')
Regression Prediction
diabetes = datasets.load_diabetes()
Supervised Learning Model
X, y = diabetes.data, diabetes.target
Supervised Learning Model Tuning
Linear Regression y_pred = lr.predict_proba(X_test)
y_pred = svm_svc.predict(X_test)

Training And Test Data from sklearn.linear_model import LinearRegression

Unsupervised Learning
from sklearn.model_selection import GridSearchCV
lr = LinearRegression() parameters = {'kernel':('linear', 'rbf'), 'C':[1, 10]}
model = GridSearchCV(svm_svc, parameters)
Support Vector Machines y_pred = kmeans.predict(X_test) model.fit(X_train, y_train)
print(model.best_score_)
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC print(model.best_estimator_)
X_train, X_test, y_train, y_test = train_test_split(
svm_svc = SVC(kernel='linear')
X, y, random_state=0
) Evaluation
Naive Bayes
Subscribe to KDnuggets News
from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()
Accuracy Score
Preprocessing the Data

Abid Ali Awan | 2022