1.导入库 和数据表

#导入
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import re
import warnings
from pyecharts import options as opts
import numpy as np

#导入数据表
data=pd.read_excel('data.xlsx')

2.查看表数据是否导入成功和审核数据

#查看
print(data.head(10))

#审核数据类型
print(data.dtypes)

#分析数据分布趋势
print(data.describe(include='all').round(2))

3.查看重复值和去除重复值

#判断重复值
print(data[data.duplicated()])

#获取查看缺失值列
na_records = data.isnull().any(axis=1) # 获取每行是否包含NA判断结果
print(na_records.sum()) # NA记录的总数量
print(na_records[na_records]==True) # NA记录的行号

#清洗掉空格
raw_data=data.dropna(axis=0, how='any', thresh=None, subset=None, inplace=False)
print(raw_data.head(10))