Pandas前20题

## 导入相关库
import pandas as pd
import numpy as np

# 1.将下面的字典创建为DataFrame
data = {"grammer":["Python","C","Java","GO",np.nan,"SQL","PHP","Python"],
       "score":[1,2,np.nan,4,5,6,7,10]}

df = pd.DataFrame(data)
df

# 2.提取含有字符串"Python"的行

# 第一种方法
df[df['grammer'] == 'Python']

# 第二种方法
results = df['grammer'].str.contains("Python")
results.fillna(value=False,inplace = True)
df[results]

# 3.输出df的所有列名
df.columns

Index(['grammer', 'score'], dtype='object')

# 4.修改第二列列名为'popularity'
df.rename(columns={'score':'popularity'},inplace = True)
df

# 5.统计grammer列中每种编程语言出现的次数
df['grammer'].value_counts()

Python    2
SQL       1
Java      1
PHP       1
GO        1
C         1
Name: grammer, dtype: int64

# 6.将空值用上下值的平均值填充
df['popularity'] = df['popularity'].fillna(df['popularity'].interpolate())
df

# 7.提取popularity列中值大于3的行
df[df['popularity']>3]

# 8.按照grammer列进行去除重复值
df.drop_duplicates(['grammer'])

# 9.计算popularity列平均值
df['popularity'].mean()

4.75

# 10.将grammer列转换为list
df['grammer'].to_list()

['Python', 'C', 'Java', 'GO', nan, 'SQL', 'PHP', 'Python']

# 11.将DataFrame保存为EXCEL
df.to_excel('test.xlsx')

# 12.查看数据行列数
df.shape

(8, 2)

# 13.提取popularity列值大于3小于7的行
df[(df['popularity']>3) & (df['popularity']<7)]

# 14.交换两列位置
temp = df['popularity']
df.drop(labels=['popularity'], axis=1,inplace = True)
# insert中第一个参数是列的位置，第二参数是名称，第三个对象
df.insert(0, 'popularity', temp)
df

# 15.提取popularity列最大值所在行
df[df['popularity'] == df['popularity'].max()]

# 16.查看最后5行数据
df.tail()

# 17.删除最后一行数据

# 减1是因为是从第0行开始记数的
df.drop(len(df)-1,inplace = True)
df

# 18.添加一行数据['Perl',6.6]
row={'grammer':'Perl','popularity':6.6}
df = df.append(row,ignore_index=True)
df

# 19.对数据按照"popularity"列值的大小进行排序
df.sort_values('popularity',inplace = True)
df

# 20.统计grammer列每个字符串的长度
df['grammer'] = df['grammer'].fillna('R')
df['len_str'] = df['grammer'].map(lambda x: len(x))
df.loc[df[df['grammer']=='R'].index,'len_str'] = '未知'
df.loc[df[df['grammer']=='R'].index,'grammer'] = '未知'
df