Interpolation for missing numerics in Data Analysis Python

Introduction

Interpolation helps fill in missing numbers in data by guessing values based on nearby points. This keeps data complete and useful for analysis.

You have a time series with some missing temperature readings.

You want to fill gaps in sensor data collected every minute.

You need to estimate missing sales numbers in a monthly report.

You want to prepare data for a graph without breaks.

You want to avoid dropping rows with missing numeric values.

Syntax

Data Analysis Python

dataframe['column_name'].interpolate(method='linear', inplace=False)

method='linear' is the most common and fills missing values by connecting points with straight lines.

inplace=False means it returns a new series with filled values; set to True to change the original data.

Examples

Fill missing values in the 'temperature' column using linear interpolation.

Data Analysis Python

df['temperature'].interpolate()

Use quadratic interpolation for smoother filling of missing 'sales' data.

Data Analysis Python

df['sales'].interpolate(method='quadratic')

Fill missing 'sensor' values directly in the original dataframe.

Data Analysis Python

df['sensor'].interpolate(method='linear', inplace=True)

Sample Program

This code creates a small table with missing temperature values. It then fills those missing spots by guessing values between known points using linear interpolation.

Data Analysis Python

import pandas as pd
import numpy as np

# Create example data with missing values
data = {'time': [1, 2, 3, 4, 5],
        'temperature': [22.0, np.nan, np.nan, 25.0, 26.5]}
df = pd.DataFrame(data)

print('Original data:')
print(df)

# Fill missing temperature values by linear interpolation
df['temperature'] = df['temperature'].interpolate()

print('\nData after interpolation:')
print(df)

Important Notes

Interpolation only works well if missing values are surrounded by real numbers.

For missing values at the start or end, interpolation may not fill them unless you specify a method like 'pad' or 'nearest'.

Always check your data after interpolation to make sure the filled values make sense.

Summary

Interpolation fills missing numeric data by estimating values between known points.

Linear interpolation connects points with straight lines to guess missing values.

Use interpolation to keep your data complete and ready for analysis or visualization.