import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from datetime import datetime, timedelta
import seaborn as sns
import warnings

# 忽略字體警告
warnings.filterwarnings('ignore')

# 設(shè)置隨機(jī)種子
np.random.seed(42)

# ====== 關(guān)鍵修改：中文字體配置 ======
# Windows用戶使用以下配置
plt.rcParams['font.sans-serif'] = ['Microsoft YaHei', 'SimHei', 'Arial Unicode MS']
plt.rcParams['axes.unicode_minus'] = False

# 如果上述字體都不可用，可以嘗試：
# plt.rcParams['font.family'] = ['sans-serif']
# plt.rcParams['font.sans-serif'] = ['DejaVu Sans']
# 然后把中文換成英文標(biāo)簽

sns.set_style("whitegrid")

# 生成模擬銷售數(shù)據(jù)
def generate_sales_data(n_records=365):
    """生成一年的銷售數(shù)據(jù)"""
    start_date = datetime(2023, 1, 1)
    dates = [start_date + timedelta(days=x) for x in range(n_records)]
    
    categories = ['Electronics', 'Clothing', 'Food', 'Books', 'Home']  # 使用英文
    regions = ['East', 'North', 'South', 'Southwest', 'Northeast']
    
    data = {
        'Date': dates,
        'Sales': np.random.normal(50000, 15000, n_records).clip(min=10000),
        'Orders': np.random.poisson(100, n_records),
        'Category': np.random.choice(categories, n_records),
        'Region': np.random.choice(regions, n_records)
    }
    
    return pd.DataFrame(data)

# 生成數(shù)據(jù)
df = generate_sales_data()

# 創(chuàng)建圖形
fig = plt.figure(figsize=(16, 10))
fig.suptitle('Sales Data Dashboard', fontsize=20, fontweight='bold', y=0.995)

# 1. 月度銷售趨勢
ax1 = plt.subplot(2, 2, 1)
monthly_sales = df.groupby(df['Date'].dt.to_period('M'))['Sales'].sum()
monthly_sales.index = monthly_sales.index.to_timestamp()
ax1.plot(monthly_sales.index, monthly_sales.values, 
         marker='o', linewidth=2.5, markersize=8, color='#2E86AB')
ax1.fill_between(monthly_sales.index, monthly_sales.values, alpha=0.3, color='#2E86AB')
ax1.set_title('Monthly Sales Trend', fontsize=14, fontweight='bold', pad=15)
ax1.set_xlabel('Month', fontsize=11)
ax1.set_ylabel('Sales Amount', fontsize=11)
ax1.grid(True, alpha=0.3)

# 2. 產(chǎn)品類別銷售額
ax2 = plt.subplot(2, 2, 2)
category_sales = df.groupby('Category')['Sales'].sum().sort_values(ascending=False)
colors = sns.color_palette("husl", len(category_sales))
bars = ax2.bar(range(len(category_sales)), category_sales.values, color=colors, alpha=0.8)
ax2.set_title('Sales by Category', fontsize=14, fontweight='bold', pad=15)
ax2.set_xlabel('Category', fontsize=11)
ax2.set_ylabel('Total Sales', fontsize=11)
ax2.set_xticks(range(len(category_sales)))
ax2.set_xticklabels(category_sales.index, rotation=15)
ax2.grid(True, alpha=0.3, axis='y')

for bar in bars:
    height = bar.get_height()
    ax2.text(bar.get_x() + bar.get_width()/2., height,
             f'{int(height/10000)}w',
             ha='center', va='bottom', fontsize=9)

# 3. 地區(qū)銷售占比
ax3 = plt.subplot(2, 2, 3)
region_sales = df.groupby('Region')['Sales'].sum()
colors_pie = sns.color_palette("Set2", len(region_sales))
wedges, texts, autotexts = ax3.pie(region_sales.values, 
                                     labels=region_sales.index,
                                     autopct='%1.1f%%',
                                     colors=colors_pie,
                                     startangle=90,
                                     textprops={'fontsize': 10})
ax3.set_title('Sales by Region', fontsize=14, fontweight='bold', pad=15)
for autotext in autotexts:
    autotext.set_color('white')
    autotext.set_fontweight('bold')

# 4. 散點(diǎn)圖
ax4 = plt.subplot(2, 2, 4)
scatter = ax4.scatter(df['Orders'], df['Sales'], 
                     c=df['Sales'], cmap='viridis', 
                     alpha=0.6, s=50, edgecolors='black', linewidth=0.5)
ax4.set_title('Sales vs Orders', fontsize=14, fontweight='bold', pad=15)
ax4.set_xlabel('Order Count', fontsize=11)
ax4.set_ylabel('Sales Amount', fontsize=11)
ax4.grid(True, alpha=0.3)

z = np.polyfit(df['Orders'], df['Sales'], 1)
p = np.poly1d(z)
ax4.plot(df['Orders'].sort_values(), 
         p(df['Orders'].sort_values()),
         "r--", linewidth=2, alpha=0.8, label='Trend Line')
ax4.legend(fontsize=10)

cbar = plt.colorbar(scatter, ax=ax4)
cbar.set_label('Sales', fontsize=10)

plt.tight_layout()
plt.show()

print("=" * 50)
print("Data Summary")
print("=" * 50)
print(f"\nTotal Sales: {df['Sales'].sum():,.0f}")
print(f"Average Daily Sales: {df['Sales'].mean():,.0f}")
print(f"Total Orders: {df['Orders'].sum():,}")