Python处理数据利器 → Pandas
数据一般格式：csv/xlsx
如何用pandas读取数据
案例：用pandas处理商铺数据
用pandas处理
导入模块
import pandas as pd
# 导入pandas模块
import warnings
warnings.filterwarnings('ignore')
# 不发出警告
print('成功导入模块')# 如何用pandas读取数据 - csv
df = pd.read_csv('/home/kesci/商铺数据.csv')
print(type(df),df['name'].dtype) # 查看df类型，查看df中一列的数值类型
df.head()# 用pandas处理商铺数据 - comment字段清洗
df1 = df[df['comment'].str.contains('条')]
df1['comment'] = df1['comment'].str.split('条').str[0]
print(df1['comment'].dtype)
df1['comment'] = df1['comment'].astype('int')
print(df1['comment'].dtype) # 更改列数值类型
df1.head()# 用pandas处理商铺数据 - price字段清洗
df1 = df1[df1['price'].str.contains('￥')]
df1['price'] = df1['price'].str.split('￥').str[-1]
df1['price'] = df1['price'].astype('float')
print(df1['price'].dtype) # 更改列数值类型
df1.head()更多学习内容，请点击！