数据可视化基础专题（十七）：Pandas120题（二）：1-20

import pandas as pd
import numpy as np

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

#方法一
df[df[‘grammer‘] == ‘Python‘]
#方法二
results = df[‘grammer‘].str.contains("Python")
results.fillna(value=False,inplace = True)
df[results]

print(df.columns

df.rename(columns={‘score‘:‘popularity‘}, inplace = True)
df

df[‘grammer‘].value_counts()

df[‘popularity‘] = df[‘popularity‘].fillna(df[‘popularity‘].interpolate())
df

df[df[‘popularity‘] > 3]

df.drop_duplicates([‘grammer‘])

df[‘popularity‘].mean()

df[‘grammer‘].to_list()

df.to_excel(‘test.xlsx‘)

df.shape

df[(df[‘popularity‘] > 3) & (df[‘popularity‘] < 7)]

‘‘‘
方法1
‘‘‘
temp = df[‘popularity‘]
df.drop(labels=[‘popularity‘], axis=1,inplace = True)
df.insert(0, ‘popularity‘, temp)
df
‘‘‘
方法2
cols = df.columns[[1,0]]
df = df[cols]
df
‘‘‘

df[df[‘popularity‘] == df[‘popularity‘].max()]

df.tail()

df.drop([len(df)-1],inplace=True)
df

row={‘grammer‘:‘Perl‘,‘popularity‘:6.6}
df = df.append(row,ignore_index=True)
df

df.sort_values("popularity",inplace=True)
df

df[‘grammer‘] = df[‘grammer‘].fillna(‘R‘)
df[‘len_str‘] = df[‘grammer‘].map(lambda x: len(x))
df