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

# ----------------------------
# Team xG Data
# ----------------------------
teams = [
    "Spain", "Portugal", "Morocco", "Canada", "France", "Paraguay",
    "Brazil", "Norway", "Mexico", "England", "Argentina", "Egypt",
    "Switzerland", "Colombia", "Belgium", "USA", "Germany", "Netherlands"
]

xg_conceded = [
    0.30, 1.17, 1.29, 0.65, 1.04, 1.43,
    0.80, 1.52, 0.78, 1.17, 0.78, 1.65,
    1.05, 0.62, 1.35, 1.24, 0.81, 0.90
]

xg_created = [
    1.95, 1.40, 1.41, 1.94, 2.19, 0.32,
    2.46, 1.68, 1.33, 1.79, 1.82, 1.20,
    1.61, 1.48, 1.82, 1.23, 2.08, 1.37
]

# ----------------------------
# Create DataFrame
# ----------------------------
df = pd.DataFrame({
    "Team": teams,
    "xG Created": xg_created,
    "xG Conceded": xg_conceded
})

df["xG Difference"] = df["xG Created"] - df["xG Conceded"]
df["Attack/Defense Ratio"] = df["xG Created"] / df["xG Conceded"]

print("\nComplete Data")
print(df)

# ----------------------------
# Scatter Plot (Attack vs Defence)
# ----------------------------
plt.figure(figsize=(10, 8))

plt.scatter(df["xG Conceded"], df["xG Created"], s=90)

for _, row in df.iterrows():
    plt.text(row["xG Conceded"] + 0.02,
             row["xG Created"] + 0.02,
             row["Team"],
             fontsize=8)

plt.axvline(df["xG Conceded"].mean(),
            linestyle="--",
            linewidth=1,
            label="Average Defence")

plt.axhline(df["xG Created"].mean(),
            linestyle="--",
            linewidth=1,
            label="Average Attack")

plt.xlabel("xG Conceded per Match (Lower is Better)")
plt.ylabel("xG Created per Match (Higher is Better)")
plt.title("2026 FIFA World Cup: Attack vs Defence")
plt.grid(True, alpha=0.3)
plt.legend()

plt.tight_layout()
plt.show()

# ----------------------------
# xG Difference Ranking
# ----------------------------
ranking = df.sort_values("xG Difference", ascending=True)

plt.figure(figsize=(9, 8))

bars = plt.barh(ranking["Team"], ranking["xG Difference"])

for bar in bars:
    width = bar.get_width()
    plt.text(width + 0.02,
             bar.get_y() + bar.get_height()/2,
             f"{width:.2f}",
             va='center')

plt.xlabel("xG Difference")
plt.title("Net xG Difference per Match")
plt.grid(axis='x', linestyle='--', alpha=0.3)

plt.tight_layout()
plt.show()

# ----------------------------
# Attack vs Defence Comparison
# ----------------------------
plt.figure(figsize=(14, 7))

x = np.arange(len(df))
width = 0.38

plt.bar(x - width/2,
        df["xG Created"],
        width,
        label="xG Created")

plt.bar(x + width/2,
        df["xG Conceded"],
        width,
        label="xG Conceded")

# Add values above bars
for i in range(len(df)):
    plt.text(i - width/2,
             df["xG Created"][i] + 0.03,
             f'{df["xG Created"][i]:.2f}',
             ha='center',
             fontsize=8)

    plt.text(i + width/2,
             df["xG Conceded"][i] + 0.03,
             f'{df["xG Conceded"][i]:.2f}',
             ha='center',
             fontsize=8)

plt.xticks(x, df["Team"], rotation=45, ha='right')
plt.ylabel("xG per Match")
plt.title("Attack vs Defence Comparison")
plt.legend()
plt.grid(axis='y', linestyle='--', alpha=0.3)

plt.tight_layout()
plt.show()

# ----------------------------
# Top 5 Attack
# ----------------------------
print("\nTop 5 Attacking Teams")
print(df.nlargest(5, "xG Created")[["Team", "xG Created"]])

# ----------------------------
# Top 5 Defence
# ----------------------------
print("\nTop 5 Defensive Teams")
print(df.nsmallest(5, "xG Conceded")[["Team", "xG Conceded"]])

# ----------------------------
# Best Overall xG Difference
# ----------------------------
print("\nTop Teams by xG Difference")
print(df.sort_values("xG Difference", ascending=False)[
    ["Team", "xG Created", "xG Conceded", "xG Difference"]
])