"""
# Computing autocorrelation
Correlation against itself at different lags to quantify how past values
effect the future.

Partial correlation has more control by comparing at shorter lags
"""
import os
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
import pandas as pd
import matplotlib.pyplot as plt

# Chart config
plt.rcParams['figure.figsize'] = (12, 6)

# Ensure assets directory
os.makedirs("assets", exist_ok=True)

# Load solar data
data = pd.read_csv(
    "../assets/datasets/time_series_solar.csv",
    parse_dates=["Datetime"],
    index_col="Datetime",
)
series = data["Incoming Solar"]

# Resample to daily
series_daily = series.resample("D").sum()

# Compute autocorrelation, acf = Auto Correlation Function
# Compares against lags up to a year away
# acf_scores = acf(x=series_daily, nlags=365)

# Compute partial autocorrelation
# pacf_scores = pacf(x=series_daily, nlags=365)

# Convience functions to do math and plot
plot_acf(series_daily, lags=365)
plt.savefig("assets/autocorrelation.png")
plot_pacf(series_daily, lags=365)
plt.savefig("assets/partion_autocorrelation.png")