How To Convert Sklearn Dataset To Pandas Dataframe In Python

In this article, we look at how to convert sklearn dataset to a pandas dataframe in Python.

Sklearn and pandas are python libraries that are used widely for data science and machine learning operations. Pandas is majorly focused on data processing, manipulation, cleaning, and visualization whereas sklearn library provides a vast list of tools and functions to train machine learning models.

Example 1: Convert Sklearn Dataset(iris) To Pandas Dataframe

Here we imported the iris dataset from the sklearn library. We then load this data by calling the load_iris() method and saving it in the iris_data named variable. This variable has the type sklearn.utils._bunch.Bunch. The iris_data has different attributes, namely, data, target, frame, target_names, DESCR, feature_names, filename, data_module. We will make use of the data and feature_names attribute. The data attribute returns the complete data matrix for the iris dataset. The feature_names attribute returns a list of column names to consider for the data.

Python3

# IMPORT THE PANDAS LIBRARY
# TO USE THE DATAFRAME TOOL
import pandas as pd

# IMPORT THE IRIS DATA FROM THE
# SKLEARN MODULE
from sklearn.datasets import load_iris

# LOAD THE IRIS DATASET BY CALLING
# THE FUNCTION
iris_data = load_iris()

# PLACE THE IRIS DATA IN A PANDAS
# DATAFRAME
df = pd.DataFrame(data=iris_data.data,
                  columns=iris_data.feature_names)

# DISPLAY FIRST 5 RECORDS OF THE
# DATAFRAME
df.head()

Output:

   sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)
0                5.1               3.5                1.4               0.2
1                4.9               3.0                1.4               0.2
2                4.7               3.2                1.3               0.2
3                4.6               3.1                1.5               0.2
4                5.0               3.6                1.4               0.2

Example 2: Convert Sklearn Dataset(diabetes) To Pandas Dataframe

In this example, we will create a function named convert_to_dataframe that will help us to convert the sklearn datasets to pandas dataframe. This function will require one parameter i.e. sk_data which is the sklearn dataset and return a pandas dataframe format of this data. We are using sklearn’s diabetes dataset in this example.

Python3

# IMPORT THE PANDAS LIBRARY
# TO USE THE DATAFRAME TOOL
import pandas as pd

# IMPORT THE DIABETES DATA FROM THE
# SKLEARN MODULE
from sklearn.datasets import load_diabetes

# CREATE THE `convert_to_dataframe()
# FUNCTION
from sklearn.utils._bunch import Bunch


def convert_to_dataframe(sk_data: Bunch):
    if not isinstance(sk_data, Bunch):
        raise Exception("Not a sklearn dataset")
    return pd.DataFrame(data=sk_data.data,
                        columns=sk_data.feature_names)


# LOAD THE DIABETES DATA USING
# THE `convert_to_dataframe()` FUNCTION
diabetes_data = convert_to_dataframe(sk_data=load_diabetes())

# DISPLAY FIRST 5 RECORDS OF THE DATAFRAME
diabetes_data.head()

Output:

        age       sex       bmi        bp        s1        s2        s3  \

0  0.038076  0.050680  0.061696  0.021872 -0.044223 -0.034821 -0.043401   

1 -0.001882 -0.044642 -0.051474 -0.026328 -0.008449 -0.019163  0.074412   

2  0.085299  0.050680  0.044451 -0.005670 -0.045599 -0.034194 -0.032356   

3 -0.089063 -0.044642 -0.011595 -0.036656  0.012191  0.024991 -0.036038   

4  0.005383 -0.044642 -0.036385  0.021872  0.003935  0.015596  0.008142   

         s4        s5        s6  

0 -0.002592  0.019907 -0.017646  

1 -0.039493 -0.068332 -0.092204  

2 -0.002592  0.002861 -0.025930  

3  0.034309  0.022688 -0.009362  

4 -0.002592 -0.031988 -0.046641