Pandas 02. 数据读取

Pandas需要先读取表格类型的数据，然后进行分析

示例：
 

import pandas as pd
import pymysql

# 读取csv文件
df = pd.read_csv("./ml-latest-small/ratings.csv",
                 encoding="utf-8",
                 sep=",",  # 分隔符，.csv文件默认为","
                 )
# print(df)
df1 = df.head(10)  # 读取前10行
print(df1)

df5 = df.tail(10)  # 读取后10行
print(df5)

df_shape = df.shape  # 返回DataFrame形状
print(df_shape)

df_col = df.columns  # 返回DataFrame的columns
print(df_col)

df_index = df.index  # 返回DataFrame的index
print(df_index)

df_dtype = df.dtypes  # 返回每列的数据类型组成的Series
print(df_dtype, type(df_dtype))

# 读取txt文件
df2 = pd.read_csv("./ml-latest-small/demo.txt",
                  sep="\t",  # 用制表符作为分隔符
                  header=None,  # 没有头
                  names=["pdata", "pv", "uv"])  # 指定列名
print(df2)

# 读取xlsx文件
df3 = pd.read_excel("./ml-latest-small/demo2.xlsx")
print(df3)

# 读取mysql
conn = pymysql.connect(host="qianshaoqing.mysql.rds.aliyuncs.com",
                       user="omron",
                       password="omron@2021",
                       database="officesystem")
df4 = pd.read_sql("select * from random_amount",  # 查询语句
                  con=conn)  # 传入连接
print(df4)