Pandas进阶修炼120题｜第五期

df = pd.read_csv('数据1.csv',encoding='gbk', usecols=['positionName', 'salary'],nrows = 10)

df = pd.read_csv('数据2.csv',converters={'薪资水平': lambda x: '高' if float(x) > 10000 else '低'} )

df.iloc[::20, :][['薪资水平']]

df = pd.DataFrame(np.random.random(10)**10, columns=['data'])

df.round(3)

df.style.format({'data': '{0:.2%}'.format})

df['data'].argsort()[::-1][7]

df.iloc[::-1, :]

df1= pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],
'key2': ['K0', 'K1', 'K0', 'K1'],
'A': ['A0', 'A1', 'A2', 'A3'],
'B': ['B0', 'B1', 'B2', 'B3']})

df2= pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
'key2': ['K0', 'K0', 'K0', 'K0'],
'C': ['C0', 'C1', 'C2', 'C3'],
'D': ['D0', 'D1', 'D2', 'D3']})

pd.merge(df1, df2, on=['key1', 'key2'])

pd.merge(df1, df2, how='left', on=['key1', 'key2'])

df = pd.read_csv('数据1.csv',encoding='gbk')
pd.set_option("display.max.columns", None)
df

np.where(df.secondType == df.thirdType)

np.argwhere(df['salary'] > df['salary'].mean())[2]

df[['salary']].apply(np.sqrt)

df['split'] = df['linestaion'].str.split('_')

df.shape[1]

df[df['industryField'].str.startswith('数据')]

pd.pivot_table(df,values=["salary","score"],index="positionId")

df[["salary","score"]].agg([np.sum,np.mean,np.min])

df.agg({"salary":np.sum,"score":np.mean})

df[['district','salary']].groupby(by='district').mean().sort_values('salary',ascending=False).head(1)