Scikit-learn Preprocessing

StandardScaler
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

MinMaxScaler
from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler()
X_scaled = scaler.fit_transform(X)

RobustScaler
from sklearn.preprocessing import RobustScaler
scaler = RobustScaler()
X_scaled = scaler.fit_transform(X)

LabelEncoder
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
y_encoded = le.fit_transform(y)

OneHotEncoder
from sklearn.preprocessing import OneHotEncoder
encoder = OneHotEncoder()
X_encoded = encoder.fit_transform(X)

Pandas get_dummies
df_encoded = pd.get_dummies(df, columns=[category])

Basic split
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(
  X, y, test_size=0.2, random_state=42
)

Stratified split
X_train, X_test, y_train, y_test = train_test_split(
  X, y, test_size=0.2, stratify=y
)

SelectKBest
from sklearn.feature_selection import SelectKBest, f_classif
selector = SelectKBest(f_classif, k=10)
X_new = selector.fit_transform(X, y)

RFE (Recursive Feature Elimination)
from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression
rfe = RFE(LogisticRegression(), n_features_to_select=5)
X_new = rfe.fit_transform(X, y)

SMOTE (Synthetic Minority Oversampling)
from imblearn.over_sampling import SMOTE
smote = SMOTE()
X_resampled, y_resampled = smote.fit_resample(X, y)

RandomUnderSampler
from imblearn.under_sampling import RandomUnderSampler
rus = RandomUnderSampler()
X_resampled, y_resampled = rus.fit_resample(X, y)

Create pipeline
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

pipeline = Pipeline([
  (scaler, StandardScaler()),
  (classifier, LogisticRegression())
])

pipeline.fit(X_train, y_train)
predictions = pipeline.predict(X_test)