Feature Scaling

Feature Scaling | CodeSignal Learn

Lesson Introduction

Hey there! Today, we're going to learn about feature scaling . You might be wondering, what is feature scaling, and why should we care? Simply put, feature scaling is like making sure all the ingredients in your recipe are measured in the same unit. Imagine trying to mix pounds of flour and teaspoons of salt without converting one to the other — it wouldn't make sense, right? Our goal is to understand why feature scaling is crucial in machine learning and to learn how to do it using Python and a library called SciKit Learn .

What is Feature Scaling?

\mu

Example of Feature Scaling with `StandardScaler`

Let's create a small sample dataset to see how feature scaling works. Python import pandas as pd from sklearn.preprocessing import StandardScaler, MinMaxScaler # Sample dataset data = {'Feature1': [1, 2, 3, 4], 'Feature2': [10, 20, 30, 40]} df = pd.DataFrame(data) print("Original DataFrame:") print(df) Output: Original DataFrame: Feature1 Feature2 0 1 10 1 2 20 2 3 30 3 4 40 Before scaling, Feature1 ranges from 1 to 4, and Feature2 ranges from 10 to 40. Let's scale this dataset using StandardScaler .

Join the 1M+ learners on CodeSignal

Be a part of our community of 1M+ users who develop and demonstrate their skills on CodeSignal

Feature scaling ensures that all your data features contribute equally when building a machine learning model. Without scaling, large values might dominate, leading to biased outcomes. For example, if predicting house prices, and one feature was in thousands (like square footage) and another in single digits (like the number of rooms), the model might overlook the smaller values just because they seem less relevant.

There are two common types:

Standardization: Transforms data to have a mean ( $\mu$ ) of 0 and a standard deviation ( $\sigma$ ) of 1.

Formula: $z = \frac{x - \mu}{\sigma}$ , where $x$ is the original feature value, $\mu$ is the mean of the feature, and $\sigma$ is the standard deviation of the feature.
Normalization: Rescales data to range between 0 and 1.

Formula: $x' = \frac{x - \min(x)}{\max(x) - \min(x)}$ , where $x$ is the original feature value, $\min(x)$ is the minimum value of the feature, and $\max(x)$ is the maximum value of the feature.

Today, we'll focus on both standardization using StandardScaler and normalization using MinMaxScaler from SciKit Learn.

Applying Feature Scaling with `StandardScaler`

We’ll use the StandardScaler to perform the scaling. The fit_transform method will calculate the mean and standard deviation for scaling, and then apply the scaling to the data. Python # Feature scaling with StandardScaler standard_scaler = StandardScaler() scaled_data_standard = standard_scaler.fit_transform(df) # Feature scaling with StandardScaler standard_scaler = StandardScaler() scaled_data_standard = standard_scaler.fit_transform(df) Continuing from where we left off, we need to convert this scaled data back to a DataFrame for better readability. Python # Convert the scaled data back to a DataFrame for better readability scaled_df_standard = pd.DataFrame(scaled_data_standard, columns=df.columns) print("Scaled DataFrame (StandardScaler):") print(scaled_df_standard) # Convert the scaled data back to a DataFrame for better readability scaled_df_standard = pd.DataFrame(scaled_data_standard, columns=df.columns) print("Scaled DataFrame (StandardScaler):") print(scaled_df_standard) Output: Scaled DataFrame (StandardScaler): Feature1 Feature2 0 -1.341641 -1.341641 1 -0.447214 -0.447214 2 0.447214 0.447214 3 1.341641 1.341641 Scaled DataFrame (StandardScaler): Feature1 Feature2 0 -1.341641 -1.341641 1 -0.447214 -0.447214 2 0.447214 0.447214 3 1.341641 1.341641

Scaling Double-check

Let's check if the data is scaled correctly. We will calculate mean and standard deviation for both features: Python print("Mean of each feature after scaling (should be close to 0):") print(scaled_df_standard.mean()) print("Standard deviation of each feature after scaling (should be close to 1):") print(scaled_df_standard.std()) print("Mean of each feature after scaling (should be close to 0):") print(scaled_df_standard.mean()) print("Standard deviation of each feature after scaling (should be close to 1):") print(scaled_df_standard.std()) Here is the output: Mean of each feature after scaling (should be close to 0): Feature1 0.0 Feature2 0.0 dtype: float64 Standard deviation of each feature after scaling (should be close to 1): Feature1 1.0 Feature2 1.0 dtype: float64 Mean of each feature after scaling (should be close to 0): Feature1 0.0 Feature2 0.0 dtype: float64 Standard deviation of each feature after scaling (should be close to 1): Feature1 1.0 Feature2 1.0 dtype: float64 The mean of each feature in the scaled DataFrame is 0, and the standard deviation is 1. This makes it easier for the machine learning model to treat all features equally.

Example of Feature Scaling with `MinMaxScaler`

Let's also apply feature scaling using the MinMaxScaler to see how normalization works. The good news is that using the MinMaxScaler is exactly the same as for the StandardScaler . You literally just change the scaler's name and everything works! Python # Feature scaling with MinMaxScaler minmax_scaler = MinMaxScaler() scaled_data_minmax = minmax_scaler.fit_transform(df) # Feature scaling with MinMaxScaler minmax_scaler = MinMaxScaler() scaled_data_minmax = minmax_scaler.fit_transform(df) Convert the normalized data back to a DataFrame for better readability and verify the range. Python # Convert the scaled data back to a DataFrame for better readability scaled_df_minmax = pd.DataFrame(scaled_data_minmax, columns=df.columns) print("Scaled DataFrame (MinMaxScaler):") print(scaled_df_minmax) # Convert the scaled data back to a DataFrame for better readability scaled_df_minmax = pd.DataFrame(scaled_data_minmax, columns=df.columns) print("Scaled DataFrame (MinMaxScaler):") print(scaled_df_minmax) Output: Scaled DataFrame (MinMaxScaler): Feature1 Feature2 0 0.0 0.0 1 0.3 0.3 2 0.6 0.6 3 1.0 1.0 Scaled DataFrame (MinMaxScaler): Feature1 Feature2 0 0.0 0.0 1 0.3 0.3 2 0.6 0.6 3 1.0 1.0

Scaling Double-Check

Let's validate the results: Python print("Minimum of each feature after scaling (should be 0):") print(scaled_df_minmax.min()) print("Maximum of each feature after scaling (should be 1):") print(scaled_df_minmax.max()) print("Minimum of each feature after scaling (should be 0):") print(scaled_df_minmax.min()) print("Maximum of each feature after scaling (should be 1):") print(scaled_df_minmax.max()) Output: Minimum of each feature after scaling (should be 0): Feature1 0.0 Feature2 0.0 dtype: float64 Maximum of each feature after scaling (should be 1): Feature1 1.0 Feature2 1.0 dtype: float64 Minimum of each feature after scaling (should be 0): Feature1 0.0 Feature2 0.0 dtype: float64 Maximum of each feature after scaling (should be 1): Feature1 1.0 Feature2 1.0 dtype: float64 The minimum of each feature in the scaled DataFrame is 0, and the maximum is 1, ensuring that all data points fall within this range.