import pandas as pd
df = pd.read_csv("sales_data.csv")  # 讀取CSV文件
print(df.head())  # 查看前5行數(shù)據(jù)
print(df.info())  # 獲取數(shù)據(jù)類型、缺失值等元信息

df = pd.read_excel("user_data.xlsx")
df.drop_duplicates(inplace=True)  # 刪除重復(fù)行
df.fillna({"age": df["age"].mean()}, inplace=True)  # 用均值填充缺失年齡

df = pd.read_sql("SELECT * FROM orders", conn)  # 從數(shù)據(jù)庫(kù)讀取訂單數(shù)據(jù)
monthly_sales = df.groupby(df["order_date"].dt.to_period("M"))["amount"].sum()  # 按月匯總銷售額

df = pd.read_csv("stock_prices.csv", parse_dates=["date"], index_col="date")  # 解析日期并設(shè)為索引
df["rolling_mean"] = df["close"].rolling(window=30).mean()  # 計(jì)算30天移動(dòng)平均

df = pd.read_csv("titanic.csv")
X = df[["Pclass", "Age", "Fare"]]  # 提取特征
y = df["Survived"]  # 提取標(biāo)簽
X = pd.get_dummies(X, columns=["Pclass"])  # 獨(dú)熱編碼分類特征

df = pd.read_json("api_response.json")  # 讀取API返回的JSON數(shù)據(jù)
summary = df.describe().T  # 生成統(tǒng)計(jì)摘要
summary.to_excel("analysis_report.xlsx")  # 導(dǎo)出為Excel報(bào)表

df1 = pd.read_csv("sales_2023.csv")
df2 = pd.read_excel("sales_2024.xlsx")
combined_df = pd.concat([df1, df2], ignore_index=True)  # 縱向合并兩年銷售數(shù)據(jù)

df = pd.read_csv("server_logs.csv", sep="|", header=None)  # 自定義分隔符讀取日志
df.columns = ["timestamp", "level", "message"]  # 手動(dòng)指定列名

df = pd.read_csv("experimental_results.csv")
correlation = df[["temperature", "yield"]].corr()  # 計(jì)算溫度與產(chǎn)量的相關(guān)性

df = pd.read_parquet("large_dataset.parquet")  # 高效讀取大數(shù)據(jù)文件
df_filtered = df[df["region"] == "North"]  # 按區(qū)域篩選數(shù)據(jù)
df_filtered.to_csv("north_region_data.csv")  # 輸出給BI工具