Pandas进阶修炼120题｜完整版

data = {"grammer":["Python","C","Java","GO","R","SQL","PHP","Python"],
       "score":[1,2,np.nan,4,5,6,7,10]}

df = pd.DataFrame(data)

grammer  score
0 Python    1.0
7 Python   10.0

result=df[df['grammer'].str.contains("Python")]

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

df.columns

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

df['grammer'].value_counts()

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

df[df['popularity'] > 3]

df.drop_duplicates(['grammer'])

df['popularity'].mean()

df['grammer'].to_list()

df.to_excel('filename.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)

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

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

df['grammer'].map(lambda x: len(x))

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

df.head()

#备注，在某些版本pandas中.ix方法可能失效，可使用.iloc，参考https://mp.weixin.qq.com/s/5xJ-VLaHCV9qX2AMNOLRtw
#为什么不能直接使用max，min函数，因为我们的数据中是20k-35k这种字符串，所以需要先用正则表达式提取数字
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
df

education salary            
不限 19600.000000
大专 10000.000000
本科 19361.344538
硕士 20642.857143

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

#备注，在某些版本pandas中.ix方法可能失效，可使用.iloc，参考https://mp.weixin.qq.com/s/5xJ-VLaHCV9qX2AMNOLRtw
for i in range(len(df)):
    df.ix[i,0] = df.ix[i,0].to_pydatetime().strftime("%m-%d") 
df.head()

<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[32]

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:], :]

data = pd.read_excel('/Users/Desktop/600000.SH.xls')

data.head(3)

代码 1
简称 2
日期 2
前收盘价(元) 2
开盘价(元) 2
最高价(元) 2
最低价(元) 2
收盘价(元) 2
成交量(股) 2
成交金额(元) 2
.................

data.isnull().sum()

data[data['日期'].isnull()]

列名："代码", 第[327]行位置有缺失值
列名："简称", 第[327, 328]行位置有缺失值
列名："日期", 第[327, 328]行位置有缺失值
列名："前收盘价(元)", 第[327, 328]行位置有缺失值
列名："开盘价(元)", 第[327, 328]行位置有缺失值
列名："最高价(元)", 第[327, 328]行位置有缺失值
列名："最低价(元)", 第[327, 328]行位置有缺失值
列名："收盘价(元)", 第[327, 328]行位置有缺失值
................

for columname in data.columns:
    if data[columname].count() != len(data):
        loc = data[columname][data[columname].isnull().values==True].index.tolist()
        print('列名："{}", 第{}行位置有缺失值'.format(columname,loc))

data.dropna(axis=0, how='any', inplace=True)

axis：0-行操作（默认），1-列操作
how：any-只要有空值就删除（默认），all-全部为空值才删除
inplace：False-返回新的数据集（默认），True-在原数据集上操作

data['收盘价(元)'].plot()

data[['收盘价(元)','开盘价(元)']].plot()

data['涨跌幅(%)'].hist()

data['涨跌幅(%)'].hist(bins = 30)

temp = pd.DataFrame(columns = data.columns.to_list())

for i in range(len(data)):
    if type(data.iloc[i,13]) != float:
        temp = temp.append(data.loc[i])

temp

data[data['换手率(%)'].isin(['--'])]

data = data.reset_index()

k =[]
for i in range(len(data)):
    if type(data.iloc[i,13]) != float:
        k.append(i)
data.drop(labels=k,inplace=True)

data['换手率(%)'].plot(kind='kde')

data['收盘价(元)'].diff()

data['收盘价(元)'].pct_change()

data.set_index('日期')

data['收盘价(元)'].rolling(5).mean()

data['收盘价(元)'].rolling(5).sum()

data['收盘价(元)'].plot()
data['收盘价(元)'].rolling(5).mean().plot()
data['收盘价(元)'].rolling(20).mean().plot()

data['收盘价(元)'].resample('W').max()

data['收盘价(元)'].plot()
data['收盘价(元)'].resample('7D').max().plot()

data.shift(5)

data.shift(-5)

data['开盘价(元)'].expanding(min_periods=1).mean()

data[' expanding Open mean']=data['开盘价(元)'].expanding(min_periods=1).mean()
data[['开盘价(元)', 'expanding Open mean']].plot(figsize=(16, 6))

data['former 30 days rolling Close mean']=data['收盘价(元)'].rolling(20).mean()
data['upper bound']=data['former 30 days rolling Close mean']+2*data['收盘价(元)'].rolling(20).std()#在这里我们取20天内的标准差
data['lower bound']=data['former 30 days rolling Close mean']-2*data['收盘价(元)'].rolling(20).std()

data[['收盘价(元)', 'former 30 days rolling Close mean','upper bound','lower bound' ]].plot(figsize=(16, 6))

import pandas as pd
import numpy as np
print(np.__version__)
print(pd.__version__)

tem = np.random.randint(1,100,20)
df1 = pd.DataFrame(tem)

tem = np.arange(0,100,5)
df2 = pd.DataFrame(tem)

tem = np.random.normal(0, 1, 20)
df3 = pd.DataFrame(tem)

df = pd.concat([df1,df2,df3],axis=0,ignore_index=True)

0 1 2
0 95 0 0.022492
1 22 5 -1.209494
2 3 10 0.876127
3 21 15 -0.162149
4 51 20 -0.815424
5 30 25 -0.303792
...............

df = pd.concat([df1,df2,df3],axis=1,ignore_index=True)
df

print(np.percentile(df, q=[0, 25, 50, 75, 100]))

df.columns = ['col1','col2','col3']

df['col1'][~df['col1'].isin(df['col2'])]

temp = df['col1'].append(df['col2'])
temp.value_counts().index[:3]

np.argwhere(df['col1'] % 5==0)

df['col1'].diff().tolist()

df.ix[:, ::-1]

df['col1'].take([1,10,15])

tem = np.diff(np.sign(np.diff(df['col1'])))
np.where(tem == -2)[0] + 1

df[['col1','col2','col3']].mean(axis=1)

np.convolve(df['col2'], np.ones(3)/3, mode='valid')

df.sort_values("col3",inplace=True)

df.col1[df['col1'] > 50]= '高'

np.linalg.norm(df['col1']-df['col2'])

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)