In this article, we will learn how to normalize a column in Pandas. Let’s discuss some concepts first :
- Pandas: Pandas is an open-source library that’s built on top of the NumPy library. It is a Python package that provides various data structures and operations for manipulating numerical data and statistics. It’s mainly popular for importing and analyzing data much easier. Pandas is fast and it’s high-performance & productive for users.
- Data Normalization: Data Normalization could also be a typical practice in machine learning which consists of transforming numeric columns to a standard scale. In machine learning, some feature values differ from others multiple times. The features with higher values will dominate the learning process.
Steps Needed
Here, we will apply some techniques to normalize the column values and discuss these with the help of examples. For this, let’s understand the steps needed for normalization with Pandas.
- Import Library (Pandas)
- Import / Load / Create data.
- Use the technique to normalize the column.
Examples:
Here, we create data by some random values and apply some normalization techniques on a column.
Python3
# importing packagesimport pandas as pd # create datadf = pd.DataFrame({'Column 1':[200,-4,90,13.9,5, -90,20,300.7,30,-200,400], 'Column 2':[20,30,23,45,19,38, 25,45,34,37,12]}) # view datadisplay(df) |
Output:
Dataset consists of two columns where Column 1 is not normalized but Column 2 is normalized. So we apply normalization techniques in Column 1.
Python3
df['Column 1'].plot(kind = 'bar') |
Output:
Using The maximum absolute scaling:
The maximum absolute scaling rescales each feature between -1 and 1 by dividing every observation by its maximum absolute value. We can apply the maximum absolute scaling in Pandas using the .max() and .abs() methods, as shown below.
Python3
# copy the datadf_max_scaled = df.copy() # apply normalization techniques on Column 1column = 'Column 1'df_max_scaled[column] = df_max_scaled[column] /df_max_scaled[column].abs().max() # view normalized datadisplay(df_max_scaled) |
Output:
Using The min-max feature scaling:
The min-max approach (often called normalization) rescales the feature to a hard and fast range of [0,1] by subtracting the minimum value of the feature then dividing by the range. We can apply the min-max scaling in Pandas using the .min() and .max() methods.
Python3
# copy the datadf_min_max_scaled = df.copy() # apply normalization techniques by Column 1column = 'Column 1'df_min_max_scaled[column] = (df_min_max_scaled[column] - df_min_max_scaled[column].min()) / (df_min_max_scaled[column].max() - df_min_max_scaled[column].min()) # view normalized datadisplay(df_min_max_scaled) |
Output :
Let’s check with this plot.
Python3
df_min_max_scaled['Column 1'].plot(kind = 'bar') |
Using The z-score method:
The z-score method (often called standardization) transforms the info into distribution with a mean of 0 and a typical deviation of 1. Each standardized value is computed by subtracting the mean of the corresponding feature then dividing by the quality deviation.
Python3
# copy the datadf_z_scaled = df.copy() # apply normalization technique to Column 1column = 'Column 1'df_z_scaled[column] = (df_z_scaled[column] - df_z_scaled[column].mean()) / df_z_scaled[column].std() # view normalized data display(df_z_scaled) |
Output :
Let’s check with this plot.
Python3
df_z_scaled['Column 1'].plot(kind = 'bar') |
Using sklearn:
Transform features by scaling each feature to a given range. This estimator scales and translates each feature individually such that it is in the given range on the training set, e.g. between zero and one. Here, we will use minmax scaler.
Python3
from sklearn.preprocessing import MinMaxScalerimport numpy as np # copy the datadf_sklearn = df.copy() # apply normalization techniquescolumn = 'Column 1'df_sklearn[column] = MinMaxScaler().fit_transform(np.array(df_sklearn[column]).reshape(-1,1)) # view normalized data display(df_sklearn) |
Output :
Let’s check with this plot:
Python3
df_sklearn['Column 1'].plot(kind = 'bar') |
