import pandas as pd

from sklearn.preprocessing import StandardScaler

from sklearn.decomposition import PCA

# Read in forestfires.csv

fires $=$ pd$.$read$\_$csv$("$forestfires$.$csv$")$

# Create a new data frame with the columns

X $=$ fires$[[\text{'}$FFMC$\text{'},\text{'}$DMC$\text{'},\text{'}$DC$\text{'},$ 'ISI', 'temp', $\text{'}$RH$\text{'},$ 'wind', 'rain'$]]$

# Calculate the correlation matrix for the data in the data frame X

XCorr $=$ X$.$corr$()$

print$($XCorr$)$

# Scale the data

scaler $=$ StandardScaler$()$

firesScaled $=$ scaler.fit$\_$transform$($X$)$

# Perform four$-$component factor analysis on the scaled data

pca $=$ PCA$($n$\_$components$=4)$

pca.fit$($firesScaled$)$

# Print the factors and the explained variance.

print$("$Factors: $",$ pca.components$\_)$

print$("$Explained variance: $",$ pca.explained$\_$variance$\_$ratio$\_)$