"""
Lab 3 - Percentiles and CDFs for PV inverter data
Reads the ORIGINAL sheet exported from Excel directly (no manual pre-cleaning),
using the same reading technique fixed for Labs 1 and 2.
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

FILE = "PV2013January.csv"


def load_pv_sheet(path):
    """
    Load one day's PV sheet exactly as Excel exports it:
      line 1: empty
      line 2: sensor names (TimeStamp / SENS0500... / WR11LV02...)
      line 3: the real column names (TimeStamp, ExlSolIrr, IntSolIrr, ...)
      line 4: units (hh:mm, W/m^2, W/m^2, ...)
      line 5+: data, with decimal numbers written as "11227,85" (comma
               instead of a dot, wrapped in quotes because a comma is
               otherwise the column separator).
    Returns a DataFrame with a proper TimeStamp column and every other
    column converted to a real number.
    """
    df = pd.read_csv(path, skiprows=2)             # ignore the 2 rows above the header
    df = df.drop(index=0).reset_index(drop=True)   # drop the units row
    df = df.rename(columns={df.columns[0]: "TimeStamp"})

    numeric_cols = df.columns.drop("TimeStamp")
    df[numeric_cols] = df[numeric_cols].apply(
        lambda col: pd.to_numeric(col.astype(str).str.replace(",", ".", regex=False), errors="coerce")
    )
    return df


df = load_pv_sheet(FILE)
print("Loaded", len(df), "rows,", len(df.columns), "columns")
print(df[["TimeStamp", "TmpMdul C", "Fac", "Pac"]].head())


def cdf_xy(data):
    """Return sorted values and their empirical CDF (percentile rank, 0-1)."""
    xs = np.sort(data.to_numpy())
    n = len(xs)
    ys = np.arange(1, n + 1) / n
    return xs, ys


def report_percentiles(name, data):
    p25, p50, p75 = np.percentile(data, [25, 50, 75])
    print(f"{name}: n={len(data)}  25th={p25:.3f}  50th (median)={p50:.3f}  75th={p75:.3f}")
    return p25, p50, p75


# =====================================================================
# Column F: TmpMdul C (module temperature)
# =====================================================================
tmod = df["TmpMdul C"]
print("\n--- F: TmpMdul C ---")
report_percentiles("TmpMdul C (raw)", tmod)
print("zeros in TmpMdul C:", int((tmod == 0).sum()))

fig, ax = plt.subplots(figsize=(6, 4.2))
xs, ys = cdf_xy(tmod)
ax.plot(xs, ys, color="#2F3C7E")
ax.set_xlabel("Module temperature, C")
ax.set_ylabel("CDF")
ax.set_title("F -- TmpMdul C: CDF (raw)")
fig.tight_layout()
fig.savefig("F_cdf_raw.png", dpi=150)
plt.close(fig)

# TmpMdul C has no physical zeros to filter (module temperature is never
# exactly 0 C in this dataset), but we check anyway, per the general
# "filter zeros if needed" instruction.
tmod_nz = tmod[tmod != 0]
if len(tmod_nz) != len(tmod):
    report_percentiles("TmpMdul C (zeros removed)", tmod_nz)
    fig, ax = plt.subplots(figsize=(6, 4.2))
    xs, ys = cdf_xy(tmod_nz)
    ax.plot(xs, ys, color="#2F3C7E")
    ax.set_xlabel("Module temperature, C")
    ax.set_ylabel("CDF")
    ax.set_title("F -- TmpMdul C: CDF (zeros removed)")
    fig.tight_layout()
    fig.savefig("F_cdf_filtered.png", dpi=150)
    plt.close(fig)
else:
    print("No zeros found in TmpMdul C -- filtered CDF is identical to the raw one.")

# =====================================================================
# Column I: Fac (AC / grid frequency) -- dominated by zeros (inverter idle)
# =====================================================================
fac = df["Fac"]
print("\n--- I: Fac ---")
report_percentiles("Fac (raw, incl. zeros)", fac)
fac_zeros = int((fac == 0).sum())
print("zeros in Fac:", fac_zeros, f"({fac_zeros/len(fac)*100:.1f}% of readings)")

fig, ax = plt.subplots(figsize=(6, 4.2))
xs, ys = cdf_xy(fac)
ax.plot(xs, ys, color="#F96167")
ax.set_xlabel("Fac, Hz")
ax.set_ylabel("CDF")
ax.set_title("I -- Fac: CDF (raw, incl. zeros)")
fig.tight_layout()
fig.savefig("I_cdf_raw.png", dpi=150)
plt.close(fig)

fac_nz = fac[fac > 0]
report_percentiles("Fac (zeros removed)", fac_nz)

fig, ax = plt.subplots(figsize=(6, 4.2))
xs, ys = cdf_xy(fac_nz)
ax.plot(xs, ys, color="#F96167")
ax.set_xlabel("Fac, Hz")
ax.set_ylabel("CDF")
ax.set_title("I -- Fac: CDF (zeros removed)")
fig.tight_layout()
fig.savefig("I_cdf_filtered.png", dpi=150)
plt.close(fig)

# =====================================================================
# Column P: Pac (AC power) -- also dominated by zeros (no generation at night)
# =====================================================================
pac = df["Pac"]
print("\n--- P: Pac ---")
report_percentiles("Pac (raw, incl. zeros)", pac)
pac_zeros = int((pac == 0).sum())
print("zeros in Pac:", pac_zeros, f"({pac_zeros/len(pac)*100:.1f}% of readings)")

fig, ax = plt.subplots(figsize=(6, 4.2))
xs, ys = cdf_xy(pac)
ax.plot(xs, ys, color="#2F3C7E")
ax.set_xlabel("Pac, W")
ax.set_ylabel("CDF")
ax.set_title("P -- Pac: CDF (raw, incl. zeros)")
fig.tight_layout()
fig.savefig("P_cdf_raw.png", dpi=150)
plt.close(fig)

pac_nz = pac[pac > 0]
report_percentiles("Pac (zeros removed)", pac_nz)

fig, ax = plt.subplots(figsize=(6, 4.2))
xs, ys = cdf_xy(pac_nz)
ax.plot(xs, ys, color="#2F3C7E")
ax.set_xlabel("Pac, W")
ax.set_ylabel("CDF")
ax.set_title("P -- Pac: CDF (zeros removed)")
fig.tight_layout()
fig.savefig("P_cdf_filtered.png", dpi=150)
plt.close(fig)

print("\nAll figures saved.")