Master LLMs with our FREE course in collaboration with Activeloop & Intel Disruptor Initiative. Join now!


How to Detect the Trend in the Time Series Data and Detrend in Python
Artificial Intelligence   Data Science   Latest   Machine Learning

How to Detect the Trend in the Time Series Data and Detrend in Python

Last Updated on February 1, 2024 by Editorial Team

Author(s): Rashida Nasrin Sucky

Originally published on Towards AI.

Photo by Polly Alexandra on Unsplash

Before choosing any time series forecasting model, it is very important to detect the trend, seasonality, or cycle in the data. Half the job is to understand the data properly. This tutorial will show you how to capture trends in the data and get rid of them as well.

The trend is a long-term increase or decrease in the data. It does not have to be linear all the time. The change of direction in the data for a sustained period can be called a trend.

It will be clearer with the examples below. To demonstrate the trend, we will use Pollution US 2000 to 2016 data from Kaggle. Please feel free to download the dataset from this link:

U.S. Pollution Data (

Here, we are using pd.read_csv() method to read the data into a pandas DataFrame:

import pandas as pdimport statsmodelsdf = pd.read_csv('/content/uspollution_pollution_us_2000_2016.csv')

This dataset is pritty big. We do not need all the columns. I will take the ‘Date Local’ and ‘CO Mean’ columns. Also, let’s change the column names to something.

df_co = df[['Date Local', 'CO Mean']]df_co = df_co.rename(columns={'Date Local': 'Date', 'CO Mean': 'CO'})df_co

As you can see from the ‘Date’ column above, there are data available from 2000 to… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI

Feedback ↓