Handling class imbalance using random oversampling in Pandas

Last update on December 21 2024 07:41:25 (UTC/GMT +8 hours)

Pandas: Machine Learning Integration Exercise-13 with Solution

Write a Pandas program to handling class imbalance using random oversampling.

This exercise show how to handle class imbalance using random oversampling with the RandomOverSampler from Imbalanced-learn.

Sample Solution :

Code :

import pandas as pd
from imblearn.over_sampling import RandomOverSampler

# Load the dataset
df = pd.read_csv('data.csv')

# Split into features and target
X = df.drop('Target', axis=1)
y = df['Target']

# Initialize the RandomOverSampler
ros = RandomOverSampler(random_state=42)

# Apply random oversampling to balance the target classes
X_resampled, y_resampled = ros.fit_resample(X, y)

# Output the resampled dataset
print(pd.concat([X_resampled, y_resampled], axis=1))

Output:

   ID      Name   Age  Gender   Salary  Target
0   1      Sara  25.0  Female  50000.0       0
1   2    Ophrah  30.0    Male  60000.0       1
2   3    Torben  22.0    Male  70000.0       0
3   4  Masaharu  35.0    Male  80000.0       1
4   5      Kaya   NaN  Female  55000.0       0
5   6   Abaddon  29.0    Male      NaN       1

Explanation:

• Loaded the dataset using Pandas.
• Split the data into features (X) and target (y).
• Initialized RandomOverSampler from Imbalanced-learn to balance the dataset by oversampling the minority class.
• Applied oversampling and displayed the resampled dataset.

Python-Pandas Code Editor:

Have another way to solve this solution? Contribute your code (and comments) through Disqus.