fPCA_data_preparation.py

import pandas as pd
import numpy as np

# Import the CSV file with only useful columns
# source: https://www.data.gouv.fr/fr/datasets/temperature-quotidienne-departementale-depuis-janvier-2018/
df = pd.read_csv("temperature-quotidienne-departementale.csv", sep=";", usecols=[0,1,4])

# Rename columns to simplify syntax
df = df.rename(columns={"Code INSEE département": "Region", "TMax (°C)": "Temp"})

# Select 2019 records only
df = df[(df["Date"]>="2019-01-01") & (df["Date"]<="2019-12-31")]

# Pivot table to get "Date" as index and regions as columns 
df = df.pivot(index='Date', columns='Region', values='Temp')

# Select a set of regions across France
df = df[["06","25","59","62","83","85","75"]]

display(df)

# Convert the Pandas dataframe to a Numpy array with time-series only
f = df.to_numpy().astype(float)

# Create a float vector between 0 and 1 for time index
time = np.linspace(0,1,len(f))