Data Preprocessing

import pandas as pd
import numpy as np
from sklearn.impute import SimpleImputer

# Create sample data with missing values
data = {
    'A': [1, 2, np.nan, 4, 5],
    'B': [1.1, np.nan, 3.3, 4.4, 5.5],
    'C': ['a', 'b', 'c', np.nan, 'e']
}
df = pd.DataFrame(data)

# Check for missing values
print(df.isnull().sum())

# Fill missing values
df_filled = df.fillna(df.mean())  # For numerical columns
df_filled = df.fillna(df.mode().iloc[0])  # For categorical columns

# Using SimpleImputer
imputer = SimpleImputer(strategy='mean')
df_imputed = pd.DataFrame(imputer.fit_transform(df), columns=df.columns)

from sklearn.preprocessing import StandardScaler, MinMaxScaler
from sklearn.model_selection import train_test_split

# Sample data
X = np.random.randn(100, 3)
y = np.random.randint(0, 2, 100)

# Split data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Standardization (Z-score normalization)
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Min-Max scaling
minmax_scaler = MinMaxScaler()
X_train_minmax = minmax_scaler.fit_transform(X_train)
X_test_minmax = minmax_scaler.transform(X_test)