import matplotlib.pyplot as plt
import pandas as pd
# 模擬數(shù)據(jù)：日期和銷售額
dates = pd.date_range(start='2023-01-01', periods=12, freq='M')
sales = [100, 120, 90, 150, 180, 200, 220, 190, 210, 230, 250, 280] # 假設(shè)的月度銷售額
plt.figure(figsize=(10, 6))
plt.plot(dates, sales, marker='o', linestyle='-', color='b')
plt.title('2023 年月度銷售趨勢(shì)')
plt.xlabel('月份')
plt.ylabel('銷售額 (萬(wàn)元)')
plt.grid(True)
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

import seaborn as sns
import pandas as pd
import numpy as np
# 模擬數(shù)據(jù)：不同產(chǎn)品類別的銷售額
np.random.seed(42)
categories = ['電子產(chǎn)品', '服裝', '家居', '食品']
data = {
    '類別': np.random.choice(categories, size=100),
    '銷售額': np.random.randint(50, 500, size=100) # 隨機(jī)銷售額
}
df = pd.DataFrame(data)
plt.figure(figsize=(8, 6))
sns.boxplot(x='類別', y='銷售額', data=df)
plt.title('不同產(chǎn)品類別銷售額分布')
plt.xlabel('產(chǎn)品類別')
plt.ylabel('銷售額 (元)')
plt.show()

import plotly.express as px
import pandas as pd
# 模擬數(shù)據(jù)：客戶城市、經(jīng)緯度、客戶規(guī)模
cities = ['北京', '上海', '廣州', '深圳', '杭州', '成都']
latitudes = [39.90, 31.22, 23.12, 22.54, 30.25, 30.67]
longitudes = [116.41, 121.48, 113.25, 114.05, 120.16, 104.06]
sizes = [500, 800, 300, 400, 350, 250] # 客戶數(shù)量或規(guī)模
df = pd.DataFrame({
    '城市': cities,
    '緯度': latitudes,
    '經(jīng)度': longitudes,
    '規(guī)模': sizes
})
fig = px.scatter_geo(df,
                    lat='緯度',
                    lon='經(jīng)度',
                    size='規(guī)模',
                    hover_name='城市',
                    projection="natural earth",
                    title='客戶地域分布')
fig.show()

import pandas as pd
import matplotlib.pyplot as plt
import openai  # 需要安裝 openai 庫(kù)并配置 API Key
# 1. 生成一個(gè)簡(jiǎn)單的銷售數(shù)據(jù)圖表
months = ['Jan', 'Feb', 'Mar', 'Apr']
sales = [100, 150, 120, 200]
plt.bar(months, sales)
plt.title('Monthly Sales')
plt.ylabel('Sales (k USD)')
plt.savefig('monthly_sales.png')  # 保存圖表
# 2. (模擬) 或者，我們直接提供數(shù)據(jù)描述給 LLM
data_description = f"Sales data for the first four months: January: $100k, February: $150k, March: $120k, April: $200k."
# 3. 調(diào)用 OpenAI API 生成分析描述 (需要有效的 API key)
openai.api_key = 'YOUR_OPENAI_API_KEY'  # 替換為你的實(shí)際 Key
response = openai.ChatCompletion.create(
    model="gpt-3.5-turbo",
    messages=[
        {"role": "system", "content": "You are a helpful data analyst assistant."},
        {"role": "user", "content": f"Analyze the following sales data and provide a brief summary of key trends and any potential anomalies. Data: {data_description}"}
    ]
)
ai_insight = response.choices[0].message['content']
print("AI Generated Insight:\n", ai_insight)

from fbprophet import Prophet  # 需要安裝 fbprophet
import pandas as pd
import matplotlib.pyplot as plt
# 準(zhǔn)備數(shù)據(jù) (Prophet 需要 ds 和 y 兩列)
df = pd.DataFrame({
    'ds': pd.date_range(start='2023-01-01', periods=12, freq='M'),
    'y': [100, 120, 90, 150, 180, 200, 220, 190, 210, 230, 250, 280]
})
# 創(chuàng)建并擬合模型
model = Prophet()
model.fit(df)
# 創(chuàng)建未來(lái)時(shí)間框架 (預(yù)測(cè)未來(lái) 6 個(gè)月)
future = model.make_future_dataframe(periods=6, freq='M')
forecast = model.predict(future)
# 可視化預(yù)測(cè)結(jié)果
fig = model.plot(forecast)
plt.title('銷售歷史數(shù)據(jù)與未來(lái)預(yù)測(cè)')
plt.xlabel('日期')
plt.ylabel('銷售額 (萬(wàn)元)')
plt.show()
# 可選：可視化預(yù)測(cè)組件 (趨勢(shì)、季節(jié)性)
fig_components = model.plot_components(forecast)
plt.show()

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.ensemble import IsolationForest
# 生成包含異常點(diǎn)的模擬數(shù)據(jù)
np.random.seed(42)
x = np.random.randn(100)
y = 2 * x + np.random.randn(100) * 0.5
# 添加幾個(gè)異常點(diǎn)
x = np.append(x, [3, -2, 4])
y = np.append(y, [10, -5, 0])
df = pd.DataFrame({'Feature1': x, 'Feature2': y})
# 使用 Isolation Forest 檢測(cè)異常
model_if = IsolationForest(contamination=0.05)  # 假設(shè)異常點(diǎn)占比約 5%
model_if.fit(df)
df['anomaly'] = model_if.predict(df)
# 預(yù)測(cè)值：-1 表示異常，1 表示正常
# 可視化，異常點(diǎn)用紅色高亮
plt.figure(figsize=(10, 6))
plt.scatter(df['Feature1'][df['anomaly'] == 1], df['Feature2'][df['anomaly'] == 1], c='blue', label='正常點(diǎn)')
plt.scatter(df['Feature1'][df['anomaly'] == -1], df['Feature2'][df['anomaly'] == -1], c='red', marker='X', s=100, label='異常點(diǎn)')
plt.title('特征散點(diǎn)圖（異常點(diǎn)高亮）')
plt.xlabel('Feature 1')
plt.ylabel('Feature 2')
plt.legend()
plt.grid(True)
plt.show()

import streamlit as st
import pandas as pd
import plotly.express as px
# 標(biāo)題
st.title('智能銷售數(shù)據(jù)分析儀表板')
# 加載數(shù)據(jù)
@st.cache_data
def load_data():
    # 這里替換為實(shí)際加載數(shù)據(jù)的代碼
    return pd.DataFrame({'Month': ['Jan', 'Feb', 'Mar'], 'Sales': [100, 150, 120]})
df = load_data()
# 顯示數(shù)據(jù)
st.subheader('原始數(shù)據(jù)')
st.dataframe(df)
# 繪制交互式圖表
st.subheader('月度銷售趨勢(shì)')
fig = px.line(df, x='Month', y='Sales', title='月度銷售')
st.plotly_chart(fig)
# (此處可加入前面提到的AI分析結(jié)果展示，例如預(yù)測(cè)、異常點(diǎn)、文本洞察等)