Scribd
Upload
11 views1 page

The Code I Provided Earlier Involves Several Steps To Forecast Weather Temperatures Using The SARIMA Model

Uploaded by

snehachowbanerjee
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
11 views1 page

The Code I Provided Earlier Involves Several Steps To Forecast Weather Temperatures Using The SARIMA Model

Uploaded by

snehachowbanerjee
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

The code I provided earlier involves several steps to forecast weather temperatures using the SARIMA

model. Here's a detailed explanation of each step:

Step 1: Import necessary libraries and load the dataset

 We import the necessary libraries:


o pandas for data manipulation and analysis
o numpy for numerical operations
o matplotlib.pyplot for plotting
o statsmodels.tsa.statespace.sarimax for the SARIMA model
o sklearn.model_selection for splitting data into training and testing sets
o sklearn.metrics for evaluating the model
 We load the dataset from an Excel file named weather_data.xls into a pandas DataFrame df.

Step 2: Prepare the data

 We assume the dataset has columns for each month (January to December) and create a new column
Temperature by taking the mean of these columns.
 We create a new column Year from the year column.
 We drop the original month columns.
 We set the Year column as the index of the DataFrame.

Step 3: Split the data into training and testing sets

 We split the data into training and testing sets using a 90% - 10% split.
 We create two DataFrames: train_data and test_data.

Step 4: Build and train the SARIMA model

 We build a SARIMA model with the following parameters:


o order=(1,1,1): This represents the number of autoregressive terms, differences, and moving average terms.
o seasonal_order=(1,1,1,12): This represents the number of seasonal autoregressive terms, differences, and
moving average terms, as well as the seasonality period (12 months).
 We train the model using the fit() method.

Step 5: Make predictions and evaluate the model

 We make predictions on the testing set using the predict() method.


 We evaluate the model using the Mean Squared Error (MSE) metric.

Step 6: Plot the results

 We plot the original data and predictions using matplotlib.

These steps help us build and evaluate a SARIMA model for weather temperature forecasting.

You might also like