Pandas进阶修炼120题｜第二期

df = pd.read_excel('pandas120.xlsx')

df.head()

import re
for i in range(len(df)):
    str1 = df.ix[i,2]
    k = re.findall(r"\d+\.?\d*",str1)
    salary = ((int(k[0]) + int(k[1]))/2)*1000
    df.ix[i,2] = salary

education salary            
不限 19600.000000
大专 10000.000000
本科 19361.344538
硕士 20642.857143

df.groupby('education').mean()

for i in range(len(df)):
    df.ix[i,0] = df.ix[i,0].to_pydatetime().strftime("%m-%d")

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 135 entries, 0 to 134
Data columns (total 4 columns):
createTime 135 non-null object
education 135 non-null object
salary 135 non-null int64
categories 135 non-null category
dtypes: category(1), int64(1), object(2)
memory usage: 3.5+ KB

df.info()

df.describe()

bins = [0,5000, 20000, 50000]
group_names = ['低', '中', '高']
df['categories'] = pd.cut(df['salary'], bins, labels=group_names)

df.sort_values('salary', ascending=False)

df.loc[33]

np.median(df['salary'])

df.salary.plot(kind='hist')

df.salary.plot(kind='kde',xlim=(0,80000))

del df['categories']

df['test'] = df['education']+df['createTime']

df["test1"] = df["salary"].map(str) + df['education']

df[['salary']].apply(lambda x: x.max() - x.min())

pd.concat([df[:1], df[-2:-1]])

df.append(df.iloc[7])

createTime object
education object
salary int64
test object
test1 object
dtype: object

df.dtypes

df.set_index("createTime")

df1 = pd.DataFrame(pd.Series(np.random.randint(1, 10, 135)))

df= pd.concat([df,df1],axis=1)

df["new"] = df["salary"] - df[0]

df.isnull().values.any()

df['salary'].astype(np.float64)

len(df[df['salary']>10000])

本科 119
硕士 7
不限 5
大专 4
Name: education, dtype: int64

df.education.value_counts()

df['education'].nunique()

df1 = df[['salary','new']]
rowsums = df1.apply(np.sum, axis=1)
res = df.iloc[np.where(rowsums > 60000)[0][-3:], :]