pandas读取数据集的实现示例

import pandas as pd
df = pd.read_csv("sales_data.csv")  # 读取CSV文件
print(df.head())  # 查看前5行数据
print(df.info())  # 获取数据类型、缺失值等元信息

df = pd.read_excel("user_data.xlsx")
df.drop_duplicates(inplace=True)  # 删除重复行
df.fillna({"age": df["age"].mean()}, inplace=True)  # 用均值填充缺失年龄

df = pd.read_sql("SELECT * FROM orders", conn)  # 从数据库读取订单数据
monthly_sales = df.groupby(df["order_date"].dt.to_period("M"))["amount"].sum()  # 按月汇总销售额

df = pd.read_csv("stock_prices.csv", parse_dates=["date"], index_col="date")  # 解析日期并设为索引
df["rolling_mean"] = df["close"].rolling(window=30).mean()  # 计算30天移动平均

df = pd.read_csv("titanic.csv")
X = df[["Pclass", "Age", "Fare"]]  # 提取特征
y = df["Survived"]  # 提取标签
X = pd.get_dummies(X, columns=["Pclass"])  # 独热编码分类特征

df = pd.read_json("api_response.json")  # 读取API返回的JSON数据
summary = df.describe().T  # 生成统计摘要
summary.to_excel("analysis_report.xlsx")  # 导出为Excel报表

df1 = pd.read_csv("sales_2023.csv")
df2 = pd.read_excel("sales_2024.xlsx")
combined_df = pd.concat([df1, df2], ignore_index=True)  # 纵向合并两年销售数据

df = pd.read_csv("server_logs.csv", sep="|", header=None)  # 自定义分隔符读取日志
df.columns = ["timestamp", "level", "message"]  # 手动指定列名

df = pd.read_csv("experimental_results.csv")
correlation = df[["temperature", "yield"]].corr()  # 计算温度与产量的相关性

df = pd.read_parquet("large_dataset.parquet")  # 高效读取大数据文件
df_filtered = df[df["region"] == "North"]  # 按区域筛选数据
df_filtered.to_csv("north_region_data.csv")  # 输出给BI工具