Quick trial run for something

anomalies.py

from pathlib import Path
from re import sub
from sys import exit, stderr

import pandas as pd
import matplotlib.pyplot as plt
from colorama import Fore
from requests import get

URL = r"https://www.cpc.ncep.noaa.gov/data/indices/sstoi.indices"
DATA_FILE = Path(__file__).parent / "data.csv"


if __name__ == "__main__":
    # If the data file does not exist, download it
    if not DATA_FILE.exists():
        print(f"{Fore.CYAN}Downloading data from source!{Fore.RESET}")
        html = get(URL)
        # Safety checks
        if html.status_code != 200:
            print(f"{Fore.RED}Error:{Fore.RESET} Failed to download page!", file=stderr)
            exit(1)

        # Write the file
        with open(DATA_FILE, "w") as file:
            cleaned = (
                sub(r"\s+", r",", str(html.content))
                .replace(r"\n", "\n")
                .lstrip(r"b'")
                .rstrip("'")
            )  # Clean formatting
            file.write(cleaned)

    # Read the data
    print(f"{Fore.CYAN}Parsing data!{Fore.RESET}")
    df = pd.read_csv(DATA_FILE)

    # Print the whole table with pandas
    # with pd.option_context(
    #    "display.max_rows", None, "display.max_columns", None, "display.precision", 3
    # ):
    #    print(df)

    # Print pandas table from range
    _range = df[(df["YR"] >= 2015) & (df["YR"] <= 2022)]
    print(_range.to_string())

    _range.to_csv(Path(__file__).parent / "range.csv", encoding='utf-8', index=False)

    df = pd.read_csv('range.csv')

    # Configure Matplotlib
    print(f"{Fore.CYAN}Plotting data...{Fore.RESET}")
    plt.rcParams["figure.figsize"] = (7.50, 3.50)
    plt.rcParams["figure.autolayout"] = True
    headers = ['MON', 'ANOM', 'ANOM.1', 'ANOM.2', 'ANOM.3']

    ## Plot the actual data
    #data = [
    #    df['ANOM'],
    #    df['ANOM.1'],
    #    df['ANOM.2'],
    #    df['ANOM.3'],
    #]

    ##for column in data:
    ##    ax = plt.plot(column, lw=2, marker='.', markersize=10)
    #plt.plot(data)
    #plt.xticks(df['MON'])

    # Test 2
    years = df.groupby(['YR']).mean()

    # Print average of each value per year
    for column in years[['ANOM', 'ANOM.1', 'ANOM.2', 'ANOM.3']]:
        plt.plot(years['MON'], years[column], lw=1, marker='.', markersize=10)

    # show
    plt.title("Average of each value")
    plt.grid()
    plt.tight_layout()
    plt.xticks(years['MON'])
    plt.yticks([2.5, 2.0, 1.5, 1.0, 0.5, 0.0, -0.5, -1.0, -1.5, -2.0, -2.5, -3.0])
    plt.show()

    ## Test 1
    #year_shit = df.loc[(df['YR'] == 2020)]
    #year_shit = year_shit[['MON', 'ANOM', 'ANOM.1', 'ANOM.2', 'ANOM.3']]
    #print(year_shit)
    ##data = [
    ##    year_shit['ANOM'],
    ##    year_shit['ANOM.1'],
    ##    year_shit['ANOM.2'],
    ##    year_shit['ANOM.3'],
    ##]

    #for column in year_shit[['ANOM', 'ANOM.1', 'ANOM.2', 'ANOM.3']]:
    #    plt.plot(year_shit['MON'], year_shit[column], lw=1, marker='.', markersize=10)

    ## X, Y ticks
    #plt.title("2020 Anomalies")
    #plt.grid()
    #plt.tight_layout()
    #plt.xticks(year_shit['MON'])
    #plt.yticks([2.5, 2.0, 1.5, 1.0, 0.5, 0.0, -0.5, -1.0, -1.5, -2.0, -2.5, -3.0])

    ### Display it 
    #plt.show()