pandas数据清洗实现删除的项目实践

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as  sns
sns.set_style("darkgrid")   

list_csv = ['Amazon_top_selling_book.csv','breast_cancer_wisconsin.csv','diamonds.csv','insurance.csv','netflix_titles.csv','penguins.csv',
           'titanic.csv','winequality-red.csv']
dic_path = r'C:\Users\pandas\Desktop\task\228datasets\datasets'
part_data = pd.read_csv(dic_path+'\\'+list_csv[4])
part_data

def missing_values_table(df):
        mis_val = df.isnull().sum()
        mis_val_percent = 100 * df.isnull().sum() / len(df)
        mis_val_table = pd.concat([mis_val, mis_val_percent], axis=1)
        mis_val_table_ren_columns = mis_val_table.rename(
        columns = {0 : 'Missing Values', 1 : '% of Total Values'})
        mis_val_table_ren_columns = mis_val_table_ren_columns[
            mis_val_table_ren_columns.iloc[:,1] != 0].sort_values(
        '% of Total Values', ascending=False).round(1)
        print ("Your selected dataframe has " + str(df.shape[1]) + " columns.\n"      
            "There are " + str(mis_val_table_ren_columns.shape[0]) +
              " columns that have missing values.")
        return mis_val_table_ren_columns

missing_values_table(part_data)

demo = part_data.drop(['director'], axis=1)
missing_values_table(demo)

# 删除release_year年份在2009年之前的行
demo = part_data.drop(part_data[part_data["release_year"]<2009].index)
demo.shape